c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2025-01-27 18:34:22 +03:00
Code Issues Packages Projects Releases Wiki Activity
c7e47b3d9a
mirror_zfs/include/sys/fm/fs/zfs.h
Brian Atkinson b4e4cbeb20
Always validate checksums for Direct I/O reads 
This fixes an oversight in the Direct I/O PR. There is nothing that
stops a process from manipulating the contents of a buffer for a
Direct I/O read while the I/O is in flight. This can lead checksum
verify failures. However, the disk contents are still correct, and this
would lead to false reporting of checksum validation failures.

To remedy this, all Direct I/O reads that have a checksum verification
failure are treated as suspicious. In the event a checksum validation
failure occurs for a Direct I/O read, then the I/O request will be
reissued though the ARC. This allows for actual validation to happen and
removes any possibility of the buffer being manipulated after the I/O
has been issued.

Just as with Direct I/O write checksum validation failures, Direct I/O
read checksum validation failures are reported though zpool status -d in
the DIO column. Also the zevent has been updated to have both:
1. dio_verify_wr -> Checksum verification failure for writes
2. dio_verify_rd -> Checksum verification failure for reads.
This allows for determining what I/O operation was the culprit for the
checksum verification failure. All DIO errors are reported only on the
top-level VDEV.

Even though FreeBSD can write protect pages (stable pages) it still has
the same issue as Linux with Direct I/O reads.

This commit updates the following:
1. Propogates checksum failures for reads all the way up to the
   top-level VDEV.
2. Reports errors through zpool status -d as DIO.
3. Has two zevents for checksum verify errors with Direct I/O. One for
   read and one for write.
4. Updates FreeBSD ABD code to also check for ABD_FLAG_FROM_PAGES and
   handle ABD buffer contents validation the same as Linux.
5. Updated manipulate_user_buffer.c to also manipulate a buffer while a
   Direct I/O read is taking place.
6. Adds a new ZTS test case dio_read_verify that stress tests the new
   code.
7. Updated man pages.
8. Added an IMPLY statement to zio_checksum_verify() to make sure that
   Direct I/O reads are not issued as speculative.
9. Removed self healing through mirror, raidz, and dRAID VDEVs for
   Direct I/O reads.

This issue was first observed when installing a Windows 11 VM on a ZFS
dataset with the dataset property direct set to always. The zpool
devices would report checksum failures, but running a subsequent zpool
scrub would not repair any data and report no errors.

Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Signed-off-by: Brian Atkinson <batkinson@lanl.gov>
Closes #16598
2024-10-09 12:28:08 -07:00

141 lines
6.2 KiB
C
Raw Blame History

/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or https://opensource.org/licenses/CDDL-1.0.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright 2009 Sun Microsystems, Inc. All rights reserved.
* Use is subject to license terms.
*/
/*
* Copyright (c) 2020 by Delphix. All rights reserved.
*/
#ifndef _SYS_FM_FS_ZFS_H
#define _SYS_FM_FS_ZFS_H
#ifdef __cplusplus
extern "C" {
#endif
#define ZFS_ERROR_CLASS "fs.zfs"
#define FM_EREPORT_ZFS_CHECKSUM "checksum"
#define FM_EREPORT_ZFS_AUTHENTICATION "authentication"
#define FM_EREPORT_ZFS_IO "io"
#define FM_EREPORT_ZFS_DATA "data"
#define FM_EREPORT_ZFS_DELAY "delay"
#define FM_EREPORT_ZFS_DEADMAN "deadman"
#define FM_EREPORT_ZFS_DIO_VERIFY_WR "dio_verify_wr"
#define FM_EREPORT_ZFS_DIO_VERIFY_RD "dio_verify_rd"
#define FM_EREPORT_ZFS_POOL "zpool"
#define FM_EREPORT_ZFS_DEVICE_UNKNOWN "vdev.unknown"
#define FM_EREPORT_ZFS_DEVICE_OPEN_FAILED "vdev.open_failed"
#define FM_EREPORT_ZFS_DEVICE_CORRUPT_DATA "vdev.corrupt_data"
#define FM_EREPORT_ZFS_DEVICE_NO_REPLICAS "vdev.no_replicas"
#define FM_EREPORT_ZFS_DEVICE_BAD_GUID_SUM "vdev.bad_guid_sum"
#define FM_EREPORT_ZFS_DEVICE_TOO_SMALL "vdev.too_small"
#define FM_EREPORT_ZFS_DEVICE_BAD_LABEL "vdev.bad_label"
#define FM_EREPORT_ZFS_DEVICE_BAD_ASHIFT "vdev.bad_ashift"
#define FM_EREPORT_ZFS_IO_FAILURE "io_failure"
#define FM_EREPORT_ZFS_PROBE_FAILURE "probe_failure"
#define FM_EREPORT_ZFS_LOG_REPLAY "log_replay"
#define FM_EREPORT_ZFS_CONFIG_CACHE_WRITE "config_cache_write"
#define FM_EREPORT_PAYLOAD_ZFS_POOL "pool"
#define FM_EREPORT_PAYLOAD_ZFS_POOL_FAILMODE "pool_failmode"
#define FM_EREPORT_PAYLOAD_ZFS_POOL_GUID "pool_guid"
#define FM_EREPORT_PAYLOAD_ZFS_POOL_CONTEXT "pool_context"
#define FM_EREPORT_PAYLOAD_ZFS_POOL_STATE "pool_state"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_GUID "vdev_guid"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_TYPE "vdev_type"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_PATH "vdev_path"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_PHYSPATH "vdev_physpath"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_ENC_SYSFS_PATH "vdev_enc_sysfs_path"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_DEVID "vdev_devid"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_FRU "vdev_fru"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_STATE "vdev_state"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_LASTSTATE "vdev_laststate"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_ASHIFT "vdev_ashift"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_COMP_TS "vdev_complete_ts"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_DELTA_TS "vdev_delta_ts"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_SPARE_PATHS "vdev_spare_paths"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_SPARE_GUIDS "vdev_spare_guids"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_READ_ERRORS "vdev_read_errors"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_WRITE_ERRORS "vdev_write_errors"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_CKSUM_ERRORS "vdev_cksum_errors"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_CKSUM_N "vdev_cksum_n"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_CKSUM_T "vdev_cksum_t"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_IO_N "vdev_io_n"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_IO_T "vdev_io_t"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_SLOW_IO_N "vdev_slow_io_n"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_SLOW_IO_T "vdev_slow_io_t"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_DIO_VERIFY_ERRORS "dio_verify_errors"
#define FM_EREPORT_PAYLOAD_ZFS_VDEV_DELAYS "vdev_delays"
#define FM_EREPORT_PAYLOAD_ZFS_PARENT_GUID "parent_guid"
#define FM_EREPORT_PAYLOAD_ZFS_PARENT_TYPE "parent_type"
#define FM_EREPORT_PAYLOAD_ZFS_PARENT_PATH "parent_path"
#define FM_EREPORT_PAYLOAD_ZFS_PARENT_DEVID "parent_devid"
#define FM_EREPORT_PAYLOAD_ZFS_ZIO_OBJSET "zio_objset"
#define FM_EREPORT_PAYLOAD_ZFS_ZIO_OBJECT "zio_object"
#define FM_EREPORT_PAYLOAD_ZFS_ZIO_LEVEL "zio_level"
#define FM_EREPORT_PAYLOAD_ZFS_ZIO_BLKID "zio_blkid"
#define FM_EREPORT_PAYLOAD_ZFS_ZIO_ERR "zio_err"
#define FM_EREPORT_PAYLOAD_ZFS_ZIO_OFFSET "zio_offset"
#define FM_EREPORT_PAYLOAD_ZFS_ZIO_SIZE "zio_size"
#define FM_EREPORT_PAYLOAD_ZFS_ZIO_FLAGS "zio_flags"
#define FM_EREPORT_PAYLOAD_ZFS_ZIO_STAGE "zio_stage"
#define FM_EREPORT_PAYLOAD_ZFS_ZIO_PRIORITY "zio_priority"
#define FM_EREPORT_PAYLOAD_ZFS_ZIO_PIPELINE "zio_pipeline"
#define FM_EREPORT_PAYLOAD_ZFS_ZIO_DELAY "zio_delay"
#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_ALGO "cksum_algorithm"
#define FM_EREPORT_PAYLOAD_ZFS_CKSUM_BYTESWAP "cksum_byteswap"
#define FM_EREPORT_PAYLOAD_ZFS_BAD_OFFSET_RANGES "bad_ranges"
#define FM_EREPORT_PAYLOAD_ZFS_BAD_RANGE_MIN_GAP "bad_ranges_min_gap"
#define FM_EREPORT_PAYLOAD_ZFS_BAD_RANGE_SETS "bad_range_sets"
#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_SNAPSHOT_NAME "snapshot_name"
#define FM_EREPORT_PAYLOAD_ZFS_DEVICE_NAME "device_name"
#define FM_EREPORT_PAYLOAD_ZFS_RAW_DEVICE_NAME "raw_name"
#define FM_EREPORT_PAYLOAD_ZFS_VOLUME "volume"
#define FM_EREPORT_FAILMODE_WAIT "wait"
#define FM_EREPORT_FAILMODE_CONTINUE "continue"
#define FM_EREPORT_FAILMODE_PANIC "panic"
#define FM_RESOURCE_REMOVED "removed"
#define FM_RESOURCE_AUTOREPLACE "autoreplace"
#define FM_RESOURCE_STATECHANGE "statechange"
#define FM_RESOURCE_ZFS_SNAPSHOT_MOUNT "snapshot_mount"
#define FM_RESOURCE_ZFS_SNAPSHOT_UNMOUNT "snapshot_unmount"
#define FM_RESOURCE_ZVOL_CREATE_SYMLINK "zvol_create"
#define FM_RESOURCE_ZVOL_REMOVE_SYMLINK "zvol_remove"
#ifdef __cplusplus
}
#endif
#endif /* _SYS_FM_FS_ZFS_H */
Reference in New Issue View Git Blame Copy Permalink