config: make all settings commented

Drop the comment "This setting is no longer used." which
was printed just before the standard deprecation comment:
"This configuration option is deprecated."

.gitignore

@@ -30,7 +30,7 @@ make.tmpl
 /config.log
 /config.status
 /configure.scan
-/cscope.out
+/cscope.*
 /html/
 /reports/
 /tags
@@ -38,6 +38,10 @@ make.tmpl
 
 coverity/coverity_model.xml
 
+# gcov files:
+*.gcda
+*.gcno
+
 tools/man-generator
 tools/man-generator.c
 

README

@@ -1,7 +1,6 @@
 This tree contains the LVM2 and device-mapper tools and libraries.
 
-This is development branch, for stable 2.02 release see 2018-06-01-stable
-branch.
+This is development branch, for stable 2.02 release see stable-2.02 branch.
 
 For more information about LVM2 read the changelog in the WHATS_NEW file.
 Installation instructions are in INSTALL.
@@ -10,7 +9,6 @@ There is no warranty - see COPYING and COPYING.LIB.
 
 Tarballs are available from:
   ftp://sourceware.org/pub/lvm2/
-  ftp://sources.redhat.com/pub/lvm2/
   https://github.com/lvmteam/lvm2/releases
 
 The source code is stored in git:
@@ -45,6 +43,9 @@ Report upstream bugs at:
 or open issues at:
   https://github.com/lvmteam/lvm2/issues
 
-The source code repository used until 7th June 2012 is accessible here:
-  http://sources.redhat.com/cgi-bin/cvsweb.cgi/LVM2/?cvsroot=lvm2.
+The source code repository used until 7th June 2012 is accessible using CVS:
 
+  cvs -d :pserver:cvs@sourceware.org:/cvs/lvm2 login cvs
+  cvs -d :pserver:cvs@sourceware.org:/cvs/lvm2 checkout LVM2
+
+The password is cvs.

VERSION

@@ -1 +1 @@
-2.03.07(2)-git (2019-10-23)
+2.03.12(2)-git (2021-01-08)

VERSION_DM

@@ -1 +1 @@
-1.02.167-git (2019-10-23)
+1.02.177-git (2021-01-08)

WHATS_NEW

@@ -1,7 +1,110 @@
-Version 2.03.07 - 
+Version 2.03.12 - 
 ===================================
+  Add devices file feature, off by default for now.
+  Support extension of writecached volumes.
+  Fix problem with unbound variable usage within fsadm.
+  Check for presence of VDO target before starting any conversion.
+  Support metatadata profiles with volume VDO pool conversions.
+  Support -Zn for conversion of already formated VDO pools.
+  Avoid removing LVs on error path of lvconvert during creation volumes.
+  Fix crashing lvdisplay when thin volume was waiting for merge.
+  Support option --errorwhenfull when converting volume to thin-pool.
+  Improve thin-performance profile support conversion to thin-pool.
+  Add workaround to avoid read of internal 'converted' devices.
+  Prohibit merging snapshot into the read-only thick snapshot origin.
+  Restore support for flipping rw/r permissions for thin snapshot origin.
+  Support resize of cached volumes.
+  Disable autoactivation with global/event_activation=0.
+  Check if lvcreate passes read_only_volume_list with tags and skips zeroing.
+  Allocation prints better error when metadata cannot fit on a single PV.
+  Pvmove can better resolve full thin-pool tree move.
+  Limit pool metadata spare to 16GiB.
+  Improves convertsion and allocation of pool metadata.
+  Support thin pool metadata 15.88GiB, adds 64MiB, thin_pool_crop_metadata=0.
+  Enhance lvdisplay to report raid availiable/partial.
+  Support online rename of VDO pools.
+  Imporove removal of pmspare when last pool is removed.
+  Fix problem with wiping of converted LVs.
+  Fix memleak in scanning  (2.03.11).
+  Fix corner case allocation for thin-pools.
+
+Version 2.03.11 - 08th January 2021
+===================================
+  Fix pvck handling MDA at offset different from 4096.
+  Partial or degraded activation of writecache is not allowed.
+  Enhance error handling for fsadm and handle correct fsck result.
+  Dmeventd lvm plugin ignores higher reserved_stack lvm.conf values.
+  Support using BLKZEROOUT for clearing devices.
+  Support interruption when wipping LVs.
+  Support interruption for bcache waiting.
+  Fix bcache when device has too many failing writes.
+  Fix bcache waiting for IO completion with failing disks.
+  Configure use own python path name order to prefer using python3.
+  Add configure --enable-editline support as an alternative to readline.
+  Enhance reporting and error handling when creating thin volumes.
+  Enable vgsplit for VDO volumes.
+  Lvextend of vdo pool volumes ensure at least 1 new VDO slab is added.
+  Use revert_lv() on reload error path after vg_revert().
+  Configure --with-integrity enabled.
+  Restore lost signal blocking while VG lock is held.
+  Improve estimation of needed extents when creating thin-pool.
+  Use extra 1% when resizing thin-pool metadata LV with --use-policy.
+  Enhance --use-policy percentage rounding.
+  Configure --with-vdo and --with-writecache as internal segments.
+  Improving VDO man page examples.
+  Allow pvmove of writecache origin.
+  Report integrity fields.
+  Integrity volumes defaults to journal mode.
+  Switch code base to use flexible array syntax.
+  Fix 64bit math when calculation cachevol size.
+  Preserve uint32_t for seqno handling.
+  Switch from mmap to plain read when loading regular files.
+  Update lvmvdo man page and better explain DISCARD usage.
+
+Version 2.03.10 - 09th August 2020
+==================================
+  Add writecache and integrity support to lvmdbusd.
+  Generate unique cachevol name when default required from lvcreate.
+  Converting RAID1 volume to one with same number of legs now succeeds with a
+  warning.
+  Fix conversion to raid from striped lagging type.
+  Fix conversion to 'mirrored' mirror log with larger regionsize.
+  Zero pool metadata on allocation (disable with allocation/zero_metadata=0).
+  Failure in zeroing or wiping will fail command (bypass with -Zn, -Wn).
+  Add lvcreate of new cache or writecache lv with single command.
+  Fix running out of free buffers for async writing for larger writes.
+  Add integrity with raid capability.
+  Fix support for lvconvert --repair used by foreign apps (i.e. Docker).
+
+Version 2.03.09 - 26th March 2020
+=================================
+  Fix formating of vdopool (vdo_slab_size_mb was smaller by 2 bits).
+  Fix showing of a dm kernel error when uncaching a volume with cachevol.
+
+Version 2.03.08 - 11th February 2020
+====================================
+  Prevent problematic snapshots of writecache volumes.
+  Add error handling for failing allocation in _reserve_area().
+  Fix memleak in syncing of internal cache.
+  Fix pvck dump_current_text memleak.
+  Fix lvmlockd result code on error path for _query_lock_lv().
+  Update pvck man page and help output.
+  Reject invalid writecache high/low_watermark setting.
+  Report writecache status.
+  Accept more output lines from vdo_format.
+  Prohibit reshaping of stacked raid LVs.
+  Avoid running cache input arg validation when creating vdo pool.
+  Prevent raid reshaping of stacked volumes.
+  Added VDO lvmdbusd methods for enable/disable compression & dedupe.
+  Added VDO lvmdbusd method for converting LV to VDO pool.
+
+Version 2.03.07 - 30th November 2019
+====================================
+  Subcommand in vgck for repairing headers and metadata.
+  Ensure minimum required region size on striped RaidLV creation.
   Fix resize of thin-pool with data and metadata of different segtype.
   Improve mirror type leg splitting.
+  Improve error path handling in daemons on shutdown.
   Fix activation order when removing merged snapshot.
   Experimental VDO support for lvmdbusd.
 

WHATS_NEW_DM

@@ -1,5 +1,26 @@
-Version 1.02.167 - 
+Version 1.02.177 - 
 ====================================
+  Add dm_tree_node_add_thin_pool_target_v1 with crop_metadata support.
+
+Version 1.02.175 - 08th January 2021
+====================================
+
+Version 1.02.173 - 09th August 2020
+===================================
+  Add support for VDO in blkdeactivate script.
+
+Version 1.02.171 - 26th March 2020
+==================================
+  Try to remove all created devices on dm preload tree error path.
+  Fix dm_list interators with gcc 10 optimization (-ftree-pta).
+  Dmeventd handles timer without looping on short intervals.
+
+Version 1.02.169 - 11th February 2020
+=====================================
+  Enhance error messages for device creation.
+
+Version 1.02.167 - 30th November 2019
+=====================================
 
 Version 1.02.165 - 23rd October 2019
 ====================================

aclocal.m4

@@ -1,6 +1,6 @@
-# generated automatically by aclocal 1.15.1 -*- Autoconf -*-
+# generated automatically by aclocal 1.16.2 -*- Autoconf -*-
 
-# Copyright (C) 1996-2017 Free Software Foundation, Inc.
+# Copyright (C) 1996-2020 Free Software Foundation, Inc.
 
 # This file is free software; the Free Software Foundation
 # gives unlimited permission to copy and/or distribute it,
@@ -413,7 +413,7 @@ AS_IF([test "$AS_TR_SH([with_]m4_tolower([$1]))" = "yes"],
         [AC_DEFINE([HAVE_][$1], 1, [Enable ]m4_tolower([$1])[ support])])
 ])dnl PKG_HAVE_DEFINE_WITH_MODULES
 
-# Copyright (C) 1999-2017 Free Software Foundation, Inc.
+# Copyright (C) 1999-2020 Free Software Foundation, Inc.
 #
 # This file is free software; the Free Software Foundation
 # gives unlimited permission to copy and/or distribute it,
@@ -446,10 +446,12 @@ AC_DEFUN([AM_PATH_PYTHON],
  [
   dnl Find a Python interpreter.  Python versions prior to 2.0 are not
   dnl supported. (2.0 was released on October 16, 2000).
-  dnl FIXME: Remove the need to hard-code Python versions here.
   m4_define_default([_AM_PYTHON_INTERPRETER_LIST],
-[python python2 python3 python3.5 python3.4 python3.3 python3.2 python3.1 python3.0 python2.7 dnl
- python2.6 python2.5 python2.4 python2.3 python2.2 python2.1 python2.0])
+[python python2 python3 dnl
+ python3.9 python3.8 python3.7 python3.6 python3.5 python3.4 python3.3 dnl
+ python3.2 python3.1 python3.0 dnl
+ python2.7 python2.6 python2.5 python2.4 python2.3 python2.2 python2.1 dnl
+ python2.0])
 
   AC_ARG_VAR([PYTHON], [the Python interpreter])
 
@@ -494,12 +496,14 @@ AC_DEFUN([AM_PATH_PYTHON],
     m4_default([$3], [AC_MSG_ERROR([no suitable Python interpreter found])])
   else
 
-  dnl Query Python for its version number.  Getting [:3] seems to be
-  dnl the best way to do this; it's what "site.py" does in the standard
-  dnl library.
+  dnl Query Python for its version number.  Although site.py simply uses
+  dnl sys.version[:3], printing that failed with Python 3.10, since the
+  dnl trailing zero was eliminated. So now we output just the major
+  dnl and minor version numbers, as numbers. Apparently the tertiary
+  dnl version is not of interest.
 
   AC_CACHE_CHECK([for $am_display_PYTHON version], [am_cv_python_version],
-    [am_cv_python_version=`$PYTHON -c "import sys; sys.stdout.write(sys.version[[:3]])"`])
+    [am_cv_python_version=`$PYTHON -c "import sys; print('%u.%u' % sys.version_info[[:2]])"`])
   AC_SUBST([PYTHON_VERSION], [$am_cv_python_version])
 
   dnl Use the values of $prefix and $exec_prefix for the corresponding
@@ -649,7 +653,7 @@ for i in list(range(0, 4)): minverhex = (minverhex << 8) + minver[[i]]
 sys.exit(sys.hexversion < minverhex)"
   AS_IF([AM_RUN_LOG([$1 -c "$prog"])], [$3], [$4])])
 
-# Copyright (C) 2001-2017 Free Software Foundation, Inc.
+# Copyright (C) 2001-2020 Free Software Foundation, Inc.
 #
 # This file is free software; the Free Software Foundation
 # gives unlimited permission to copy and/or distribute it,

base/data-struct/hash.c

@@ -22,7 +22,7 @@ struct dm_hash_node {
 	void *data;
 	unsigned data_len;
 	unsigned keylen;
-	char key[0];
+	char key[];
 };
 
 struct dm_hash_table {
@@ -59,26 +59,27 @@ static unsigned char _nums[] = {
 	209
 };
 
-static struct dm_hash_node *_create_node(const char *str, unsigned len)
+static struct dm_hash_node *_create_node(const void *key, unsigned len)
 {
 	struct dm_hash_node *n = malloc(sizeof(*n) + len);
 
 	if (n) {
-		memcpy(n->key, str, len);
+		memcpy(n->key, key, len);
 		n->keylen = len;
 	}
 
 	return n;
 }
 
-static unsigned long _hash(const char *str, unsigned len)
+static unsigned long _hash(const void *key, unsigned len)
 {
+	const unsigned char *str = key;
 	unsigned long h = 0, g;
 	unsigned i;
 
 	for (i = 0; i < len; i++) {
 		h <<= 4;
-		h += _nums[(unsigned char) *str++];
+		h += _nums[*str++];
 		g = h & ((unsigned long) 0xf << 16u);
 		if (g) {
 			h ^= g >> 16u;

base/data-struct/list.h

@@ -1,6 +1,8 @@
 #ifndef BASE_DATA_STRUCT_LIST_H
 #define BASE_DATA_STRUCT_LIST_H
 
+#include "base/memory/container_of.h"
+
 //----------------------------------------------------------------
 
 /*
@@ -98,7 +100,7 @@ struct dm_list *dm_list_next(const struct dm_list *head, const struct dm_list *e
  * contained in a structure of type t, return the containing structure.
  */
 #define dm_list_struct_base(v, t, head) \
-    ((t *)((const char *)(v) - (const char *)&((t *) 0)->head))
+    container_of(v, t, head)
 
 /*
  * Given the address v of an instance of 'struct dm_list list' contained in
@@ -111,7 +113,7 @@ struct dm_list *dm_list_next(const struct dm_list *head, const struct dm_list *e
  * return another element f.
  */
 #define dm_struct_field(v, t, e, f) \
-    (((t *)((uintptr_t)(v) - (uintptr_t)&((t *) 0)->e))->f)
+    (((t *)((uintptr_t)(v) - offsetof(t, e)))->f)
 
 /*
  * Given the address v of a known element e in a known structure of type t,

base/data-struct/radix-tree-adaptive.c

@@ -47,7 +47,7 @@ struct value_chain {
 struct prefix_chain {
 	struct value child;
 	unsigned len;
-	uint8_t prefix[0];
+	uint8_t prefix[];
 };
 
 struct node4 {
@@ -1032,7 +1032,7 @@ void radix_tree_iterate(struct radix_tree *rt, uint8_t *kb, uint8_t *ke,
 {
 	struct lookup_result lr = _lookup_prefix(&rt->root, kb, ke);
 	if (lr.kb == ke || _prefix_chain_matches(&lr, ke))
-        	_iterate(lr.v, it);
+		(void) _iterate(lr.v, it);
 }
 
 //----------------------------------------------------------------

base/memory/container_of.h

@@ -1,4 +1,4 @@
-// Copyright (C) 2018 Red Hat, Inc. All rights reserved.
+// Copyright (C) 2018 - 2020 Red Hat, Inc. All rights reserved.
 // 
 // This file is part of LVM2.
 //
@@ -13,10 +13,12 @@
 #ifndef BASE_MEMORY_CONTAINER_OF_H
 #define BASE_MEMORY_CONTAINER_OF_H
 
+#include <stddef.h>  // offsetof
+
 //----------------------------------------------------------------
 
 #define container_of(v, t, head) \
-    ((t *)((const char *)(v) - (const char *)&((t *) 0)->head))
+    ((t *)((char *)(v) - offsetof(t, head)))
 
 //----------------------------------------------------------------
 

conf/example.conf.in

@@ -78,14 +78,14 @@ devices {
 	# routines to acquire this information. For example, this information
 	# is used to drive LVM filtering like MD component detection, multipath
 	# component detection, partition detection and others.
-	# 
+	#
 	# Accepted values:
 	#   none
 	#     No external device information source is used.
 	#   udev
 	#     Reuse existing udev database records. Applicable only if LVM is
 	#     compiled with udev support.
-	# 
+	#
 	external_device_info_source = "none"
 
 	# Configuration option devices/hints.
@@ -94,13 +94,13 @@ devices {
 	# scanning, and will only scan the listed PVs. Removing the hint file
 	# will cause lvm to generate a new one. Disable hints if PVs will
 	# be copied onto devices using non-lvm commands, like dd.
-	# 
+	#
 	# Accepted values:
 	#   all
 	#     Use all hints.
 	#   none
 	#     Use no hints.
-	# 
+	#
 	# This configuration option has an automatic default value.
 	# hints = "all"
 
@@ -118,10 +118,10 @@ devices {
 	# Prefer the name with the least number of slashes.
 	# Prefer a name that is a symlink.
 	# Prefer the path with least value in lexicographical order.
-	# 
+	#
 	# Example
 	# preferred_names = [ "^/dev/mpath/", "^/dev/mapper/mpath", "^/dev/[hs]d" ]
-	# 
+	#
 	# This configuration option does not have a default value defined.
 
 	# Configuration option devices/filter.
@@ -139,7 +139,7 @@ devices {
 	# then the device is accepted. Be careful mixing 'a' and 'r' patterns,
 	# as the combination might produce unexpected results (test changes.)
 	# Run vgscan after changing the filter to regenerate the cache.
-	# 
+	#
 	# Example
 	# Accept every block device:
 	# filter = [ "a|.*|" ]
@@ -151,7 +151,7 @@ devices {
 	# filter = [ "a|loop|", "r|/dev/hdc|", "a|/dev/ide|", "r|.*|" ]
 	# Use anchors to be very specific:
 	# filter = [ "a|^/dev/hda8$|", "r|.*|" ]
-	# 
+	#
 	# This configuration option has an automatic default value.
 	# filter = [ "a|.*|" ]
 
@@ -169,10 +169,10 @@ devices {
 	# List of additional acceptable block device types.
 	# These are of device type names from /proc/devices, followed by the
 	# maximum number of partitions.
-	# 
+	#
 	# Example
 	# types = [ "fd", 16 ]
-	# 
+	#
 	# This configuration option is advanced.
 	# This configuration option does not have a default value defined.
 
@@ -214,7 +214,7 @@ devices {
 	# Configuration option devices/md_component_checks.
 	# The checks LVM should use to detect MD component devices.
 	# MD component devices are block devices used by MD software RAID.
-	# 
+	#
 	# Accepted values:
 	#   auto
 	#     LVM will skip scanning the end of devices when it has other
@@ -225,7 +225,7 @@ devices {
 	#   full
 	#     LVM will scan the start and end of devices for MD superblocks.
 	#     This requires an extra read at the end of devices.
-	# 
+	#
 	# This configuration option has an automatic default value.
 	# md_component_checks = "auto"
 
@@ -367,7 +367,7 @@ allocation {
 	# defined here, it will check whether any of them are attached to the
 	# PVs concerned and then seek to match those PV tags between existing
 	# extents and new extents.
-	# 
+	#
 	# Example
 	# Use the special tag "@*" as a wildcard to match any PV tag:
 	# cling_tag_list = [ "@*" ]
@@ -375,7 +375,7 @@ allocation {
 	# PVs are tagged with either @site1 or @site2 to indicate where
 	# they are situated:
 	# cling_tag_list = [ "@site1", "@site2" ]
-	# 
+	#
 	# This configuration option does not have a default value defined.
 
 	# Configuration option allocation/maximise_cling.
@@ -429,29 +429,30 @@ allocation {
 
 	# Configuration option allocation/cache_pool_metadata_require_separate_pvs.
 	# Cache pool metadata and data will always use different PVs.
-	cache_pool_metadata_require_separate_pvs = 0
+	# This configuration option has an automatic default value.
+	# cache_pool_metadata_require_separate_pvs = 0
 
 	# Configuration option allocation/cache_metadata_format.
 	# Sets default metadata format for new cache.
-	# 
+	#
 	# Accepted values:
 	#   0  Automatically detected best available format
 	#   1  Original format
 	#   2  Improved 2nd. generation format
-	# 
+	#
 	# This configuration option has an automatic default value.
 	# cache_metadata_format = 0
 
 	# Configuration option allocation/cache_mode.
 	# The default cache mode used for new cache.
-	# 
+	#
 	# Accepted values:
 	#   writethrough
 	#     Data blocks are immediately written from the cache to disk.
 	#   writeback
 	#     Data blocks are written from the cache back to disk after some
 	#     delay to improve performance.
-	# 
+	#
 	# This setting replaces allocation/cache_pool_cachemode.
 	# This configuration option has an automatic default value.
 	# cache_mode = "writethrough"
@@ -488,8 +489,16 @@ allocation {
 	# This configuration option does not have a default value defined.
 
 	# Configuration option allocation/thin_pool_metadata_require_separate_pvs.
-	# Thin pool metdata and data will always use different PVs.
-	thin_pool_metadata_require_separate_pvs = 0
+	# Thin pool metadata and data will always use different PVs.
+	# This configuration option has an automatic default value.
+	# thin_pool_metadata_require_separate_pvs = 0
+
+	# Configuration option allocation/thin_pool_crop_metadata.
+	# Older version of lvm2 cropped pool's metadata size to 15.81 GiB.
+	# This is slightly less then the actual maximum 15.88 GiB.
+	# For compatibility with older version and use of cropped size set to 1.
+	# This configuration option has an automatic default value.
+	# thin_pool_crop_metadata = 0
 
 	# Configuration option allocation/thin_pool_zero.
 	# Thin pool data chunks are zeroed before they are first used.
@@ -499,18 +508,18 @@ allocation {
 
 	# Configuration option allocation/thin_pool_discards.
 	# The discards behaviour of thin pool volumes.
-	# 
+	#
 	# Accepted values:
 	#   ignore
 	#   nopassdown
 	#   passdown
-	# 
+	#
 	# This configuration option has an automatic default value.
 	# thin_pool_discards = "passdown"
 
 	# Configuration option allocation/thin_pool_chunk_size_policy.
 	# The chunk size calculation policy for thin pool volumes.
-	# 
+	#
 	# Accepted values:
 	#   generic
 	#     If thin_pool_chunk_size is defined, use it. Otherwise, calculate
@@ -522,10 +531,15 @@ allocation {
 	#     the chunk size for performance based on device hints exposed in
 	#     sysfs - the optimal_io_size. The chunk size is always at least
 	#     512KiB.
-	# 
+	#
 	# This configuration option has an automatic default value.
 	# thin_pool_chunk_size_policy = "generic"
 
+	# Configuration option allocation/zero_metadata.
+	# Zero whole metadata area before use with thin or cache pool.
+	# This configuration option has an automatic default value.
+	# zero_metadata = 1
+
 	# Configuration option allocation/thin_pool_chunk_size.
 	# The minimal chunk size in KiB for thin pool volumes.
 	# Larger chunk sizes may improve performance for plain thin volumes,
@@ -930,8 +944,7 @@ global {
 	# a volume group's metadata, instead of always granting the read-only
 	# requests immediately, delay them to allow the read-write requests to
 	# be serviced. Without this setting, write access may be stalled by a
-	# high volume of read-only requests. This option only affects
-	# locking_type 1 viz. local file-based locking.
+	# high volume of read-only requests. This option only affects file locks.
 	prioritise_write_locks = 1
 
 	# Configuration option global/library_dir.
@@ -955,7 +968,7 @@ global {
 	# Configuration option global/mirror_segtype_default.
 	# The segment type used by the short mirroring option -m.
 	# The --type mirror|raid1 option overrides this setting.
-	# 
+	#
 	# Accepted values:
 	#   mirror
 	#     The original RAID1 implementation from LVM/DM. It is
@@ -975,18 +988,19 @@ global {
 	#     handling a failure. This mirror implementation is not
 	#     cluster-aware and cannot be used in a shared (active/active)
 	#     fashion in a cluster.
-	# 
+	#
 	mirror_segtype_default = "@DEFAULT_MIRROR_SEGTYPE@"
 
 	# Configuration option global/support_mirrored_mirror_log.
 	# Enable mirrored 'mirror' log type for testing.
-	# 
+	#
 	# This type is deprecated to create or convert to but can
 	# be enabled to test that activation of existing mirrored
 	# logs and conversion to disk/core works.
-	# 
+	#
 	# Not supported for regular operation!
-	support_mirrored_mirror_log = 0
+	# This configuration option has an automatic default value.
+	# support_mirrored_mirror_log = 0
 
 	# Configuration option global/raid10_segtype_default.
 	# The segment type used by the -i -m combination.
@@ -994,7 +1008,7 @@ global {
 	# The --stripes/-i and --mirrors/-m options can both be specified
 	# during the creation of a logical volume to use both striping and
 	# mirroring for the LV. There are two different implementations.
-	# 
+	#
 	# Accepted values:
 	#   raid10
 	#     LVM uses MD's RAID10 personality through DM. This is the
@@ -1004,7 +1018,7 @@ global {
 	#     is done by creating a mirror LV on top of striped sub-LVs,
 	#     effectively creating a RAID 0+1 array. The layering is suboptimal
 	#     in terms of providing redundancy and performance.
-	# 
+	#
 	raid10_segtype_default = "@DEFAULT_RAID10_SEGTYPE@"
 
 	# Configuration option global/sparse_segtype_default.
@@ -1012,7 +1026,7 @@ global {
 	# The --type snapshot|thin option overrides this setting.
 	# The combination of -V and -L options creates a sparse LV. There are
 	# two different implementations.
-	# 
+	#
 	# Accepted values:
 	#   snapshot
 	#     The original snapshot implementation from LVM/DM. It uses an old
@@ -1024,7 +1038,7 @@ global {
 	#     bigger minimal chunk size (64KiB) and uses a separate volume for
 	#     metadata. It has better performance, especially when more data
 	#     is used. It also supports full snapshots.
-	# 
+	#
 	sparse_segtype_default = "@DEFAULT_SPARSE_SEGTYPE@"
 
 	# Configuration option global/lvdisplay_shows_full_device_path.
@@ -1044,7 +1058,8 @@ global {
 	# activated from these events (the default is all.)
 	# When event_activation is disabled, the system will generally run
 	# a direct activation command to activate LVs in complete VGs.
-	event_activation = 1
+	# This configuration option has an automatic default value.
+	# event_activation = 1
 
 	# Configuration option global/use_aio.
 	# Use async I/O when reading and writing devices.
@@ -1121,20 +1136,20 @@ global {
 	# causing problems. Features include: block_size, discards,
 	# discards_non_power_2, external_origin, metadata_resize,
 	# external_origin_extend, error_if_no_space.
-	# 
+	#
 	# Example
 	# thin_disabled_features = [ "discards", "block_size" ]
-	# 
+	#
 	# This configuration option does not have a default value defined.
 
 	# Configuration option global/cache_disabled_features.
 	# Features to not use in the cache driver.
 	# This can be helpful for testing, or to avoid using a feature that is
 	# causing problems. Features include: policy_mq, policy_smq, metadata2.
-	# 
+	#
 	# Example
 	# cache_disabled_features = [ "policy_smq" ]
-	# 
+	#
 	# This configuration option does not have a default value defined.
 
 	# Configuration option global/cache_check_executable.
@@ -1186,6 +1201,16 @@ global {
 	# This configuration option has an automatic default value.
 	# vdo_format_options = [ "" ]
 
+	# Configuration option global/vdo_disabled_features.
+	# Features to not use in the vdo driver.
+	# This can be helpful for testing, or to avoid using a feature that is
+	# causing problems. Features include: online_rename
+	#
+	# Example
+	# vdo_disabled_features = [ "online_rename" ]
+	#
+	# This configuration option does not have a default value defined.
+
 	# Configuration option global/fsadm_executable.
 	# The full path to the fsadm command.
 	# LVM uses this command to help with lvresize -r operations.
@@ -1198,7 +1223,7 @@ global {
 	# or vgimport.) A VG on shared storage devices is accessible only to
 	# the host with a matching system ID. See 'man lvmsystemid' for
 	# information on limitations and correct usage.
-	# 
+	#
 	# Accepted values:
 	#   none
 	#     The host has no system ID.
@@ -1215,7 +1240,7 @@ global {
 	#   file
 	#     Use the contents of another file (system_id_file) to set the
 	#     system ID.
-	# 
+	#
 	system_id_source = "none"
 
 	# Configuration option global/system_id_file.
@@ -1288,7 +1313,8 @@ activation {
 	# This enables additional checks (and if necessary, repairs) on entries
 	# in the device directory after udev has completed processing its
 	# events. Useful for diagnosing problems with LVM/udev interactions.
-	verify_udev_operations = 0
+	# This configuration option has an automatic default value.
+	# verify_udev_operations = 0
 
 	# Configuration option activation/retry_deactivation.
 	# Retry failed LV deactivation.
@@ -1313,30 +1339,34 @@ activation {
 	# When disabled, the striped target is used. The linear target is an
 	# optimised version of the striped target that only handles a single
 	# stripe.
-	use_linear_target = 1
+	# This configuration option has an automatic default value.
+	# use_linear_target = 1
 
 	# Configuration option activation/reserved_stack.
 	# Stack size in KiB to reserve for use while devices are suspended.
 	# Insufficent reserve risks I/O deadlock during device suspension.
-	reserved_stack = 64
+	# This configuration option has an automatic default value.
+	# reserved_stack = 64
 
 	# Configuration option activation/reserved_memory.
 	# Memory size in KiB to reserve for use while devices are suspended.
 	# Insufficent reserve risks I/O deadlock during device suspension.
-	reserved_memory = 8192
+	# This configuration option has an automatic default value.
+	# reserved_memory = 8192
 
 	# Configuration option activation/process_priority.
 	# Nice value used while devices are suspended.
 	# Use a high priority so that LVs are suspended
 	# for the shortest possible time.
-	process_priority = -18
+	# This configuration option has an automatic default value.
+	# process_priority = -18
 
 	# Configuration option activation/volume_list.
 	# Only LVs selected by this list are activated.
 	# If this list is defined, an LV is only activated if it matches an
 	# entry in this list. If this list is undefined, it imposes no limits
 	# on LV activation (all are allowed).
-	# 
+	#
 	# Accepted values:
 	#   vgname
 	#     The VG name is matched exactly and selects all LVs in the VG.
@@ -1350,10 +1380,10 @@ activation {
 	#     or VG. See tags/hosttags. If any host tags exist but volume_list
 	#     is not defined, a default single-entry list containing '@*'
 	#     is assumed.
-	# 
+	#
 	# Example
 	# volume_list = [ "vg1", "vg2/lvol1", "@tag1", "@*" ]
-	# 
+	#
 	# This configuration option does not have a default value defined.
 
 	# Configuration option activation/auto_activation_volume_list.
@@ -1373,7 +1403,7 @@ activation {
 	# commands run directly by a user. A user may also use the 'a' flag
 	# directly to perform auto-activation. Also see pvscan(8) for more
 	# information about auto-activation.
-	# 
+	#
 	# Accepted values:
 	#   vgname
 	#     The VG name is matched exactly and selects all LVs in the VG.
@@ -1387,10 +1417,10 @@ activation {
 	#     or VG. See tags/hosttags. If any host tags exist but volume_list
 	#     is not defined, a default single-entry list containing '@*'
 	#     is assumed.
-	# 
+	#
 	# Example
 	# auto_activation_volume_list = [ "vg1", "vg2/lvol1", "@tag1", "@*" ]
-	# 
+	#
 	# This configuration option does not have a default value defined.
 
 	# Configuration option activation/read_only_volume_list.
@@ -1399,7 +1429,7 @@ activation {
 	# against this list, and if it matches, it is activated in read-only
 	# mode. This overrides the permission setting stored in the metadata,
 	# e.g. from --permission rw.
-	# 
+	#
 	# Accepted values:
 	#   vgname
 	#     The VG name is matched exactly and selects all LVs in the VG.
@@ -1413,10 +1443,10 @@ activation {
 	#     or VG. See tags/hosttags. If any host tags exist but volume_list
 	#     is not defined, a default single-entry list containing '@*'
 	#     is assumed.
-	# 
+	#
 	# Example
 	# read_only_volume_list = [ "vg1", "vg2/lvol1", "@tag1", "@*" ]
-	# 
+	#
 	# This configuration option does not have a default value defined.
 
 	# Configuration option activation/raid_region_size.
@@ -1439,14 +1469,15 @@ activation {
 
 	# Configuration option activation/readahead.
 	# Setting to use when there is no readahead setting in metadata.
-	# 
+	#
 	# Accepted values:
 	#   none
 	#     Disable readahead.
 	#   auto
 	#     Use default value chosen by kernel.
-	# 
-	readahead = "auto"
+	#
+	# This configuration option has an automatic default value.
+	# readahead = "auto"
 
 	# Configuration option activation/raid_fault_policy.
 	# Defines how a device failure in a RAID LV is handled.
@@ -1456,7 +1487,7 @@ activation {
 	# performed by dmeventd automatically, and the steps perfomed by the
 	# manual command lvconvert --repair --use-policies.
 	# Automatic handling requires dmeventd to be monitoring the LV.
-	# 
+	#
 	# Accepted values:
 	#   warn
 	#     Use the system log to warn the user that a device in the RAID LV
@@ -1467,7 +1498,7 @@ activation {
 	#   allocate
 	#     Attempt to use any extra physical volumes in the VG as spares and
 	#     replace faulty devices.
-	# 
+	#
 	raid_fault_policy = "warn"
 
 	# Configuration option activation/mirror_image_fault_policy.
@@ -1479,7 +1510,7 @@ activation {
 	# determines the steps perfomed by dmeventd automatically, and the steps
 	# performed by the manual command lvconvert --repair --use-policies.
 	# Automatic handling requires dmeventd to be monitoring the LV.
-	# 
+	#
 	# Accepted values:
 	#   remove
 	#     Simply remove the faulty device and run without it. If the log
@@ -1504,7 +1535,7 @@ activation {
 	#     the redundant nature of the mirror. This policy acts like
 	#     'remove' if no suitable device and space can be allocated for the
 	#     replacement.
-	# 
+	#
 	mirror_image_fault_policy = "remove"
 
 	# Configuration option activation/mirror_log_fault_policy.
@@ -1519,26 +1550,26 @@ activation {
 	# The minimum value is 50 (a smaller value is treated as 50.)
 	# Also see snapshot_autoextend_percent.
 	# Automatic extension requires dmeventd to be monitoring the LV.
-	# 
+	#
 	# Example
 	# Using 70% autoextend threshold and 20% autoextend size, when a 1G
 	# snapshot exceeds 700M, it is extended to 1.2G, and when it exceeds
 	# 840M, it is extended to 1.44G:
 	# snapshot_autoextend_threshold = 70
-	# 
+	#
 	snapshot_autoextend_threshold = 100
 
 	# Configuration option activation/snapshot_autoextend_percent.
 	# Auto-extending a snapshot adds this percent extra space.
 	# The amount of additional space added to a snapshot is this
 	# percent of its current size.
-	# 
+	#
 	# Example
 	# Using 70% autoextend threshold and 20% autoextend size, when a 1G
 	# snapshot exceeds 700M, it is extended to 1.2G, and when it exceeds
 	# 840M, it is extended to 1.44G:
 	# snapshot_autoextend_percent = 20
-	# 
+	#
 	snapshot_autoextend_percent = 20
 
 	# Configuration option activation/thin_pool_autoextend_threshold.
@@ -1547,26 +1578,26 @@ activation {
 	# The minimum value is 50 (a smaller value is treated as 50.)
 	# Also see thin_pool_autoextend_percent.
 	# Automatic extension requires dmeventd to be monitoring the LV.
-	# 
+	#
 	# Example
 	# Using 70% autoextend threshold and 20% autoextend size, when a 1G
 	# thin pool exceeds 700M, it is extended to 1.2G, and when it exceeds
 	# 840M, it is extended to 1.44G:
 	# thin_pool_autoextend_threshold = 70
-	# 
+	#
 	thin_pool_autoextend_threshold = 100
 
 	# Configuration option activation/thin_pool_autoextend_percent.
 	# Auto-extending a thin pool adds this percent extra space.
 	# The amount of additional space added to a thin pool is this
 	# percent of its current size.
-	# 
+	#
 	# Example
 	# Using 70% autoextend threshold and 20% autoextend size, when a 1G
 	# thin pool exceeds 700M, it is extended to 1.2G, and when it exceeds
 	# 840M, it is extended to 1.44G:
 	# thin_pool_autoextend_percent = 20
-	# 
+	#
 	thin_pool_autoextend_percent = 20
 
 	# Configuration option activation/vdo_pool_autoextend_threshold.
@@ -1575,20 +1606,21 @@ activation {
 	# The minimum value is 50 (a smaller value is treated as 50.)
 	# Also see vdo_pool_autoextend_percent.
 	# Automatic extension requires dmeventd to be monitoring the LV.
-	# 
+	#
 	# Example
 	# Using 70% autoextend threshold and 20% autoextend size, when a 10G
 	# VDO pool exceeds 7G, it is extended to 12G, and when it exceeds
 	# 8.4G, it is extended to 14.4G:
 	# vdo_pool_autoextend_threshold = 70
-	# 
-	vdo_pool_autoextend_threshold = 100
+	#
+	# This configuration option has an automatic default value.
+	# vdo_pool_autoextend_threshold = 100
 
 	# Configuration option activation/vdo_pool_autoextend_percent.
 	# Auto-extending a VDO pool adds this percent extra space.
 	# The amount of additional space added to a VDO pool is this
 	# percent of its current size.
-	# 
+	#
 	# Example
 	# Using 70% autoextend threshold and 20% autoextend size, when a 10G
 	# VDO pool exceeds 7G, it is extended to 12G, and when it exceeds
@@ -1607,10 +1639,10 @@ activation {
 	# pages corresponding to lines that match are not pinned. On some
 	# systems, locale-archive was found to make up over 80% of the memory
 	# used by the process.
-	# 
+	#
 	# Example
 	# mlock_filter = [ "locale/locale-archive", "gconv/gconv-modules.cache" ]
-	# 
+	#
 	# This configuration option is advanced.
 	# This configuration option does not have a default value defined.
 
@@ -1618,7 +1650,8 @@ activation {
 	# Use the old behavior of mlockall to pin all memory.
 	# Prior to version 2.02.62, LVM used mlockall() to pin the whole
 	# process's memory while activating devices.
-	use_mlockall = 0
+	# This configuration option has an automatic default value.
+	# use_mlockall = 0
 
 	# Configuration option activation/monitoring.
 	# Monitor LVs that are activated.
@@ -1633,7 +1666,8 @@ activation {
 	# intervals of this number of seconds. If this is set to 0 and there
 	# is only one thing to wait for, there are no progress reports, but
 	# the process is awoken immediately once the operation is complete.
-	polling_interval = 15
+	# This configuration option has an automatic default value.
+	# polling_interval = 15
 
 	# Configuration option activation/auto_set_activation_skip.
 	# Set the activation skip flag on new thin snapshot LVs.
@@ -1649,7 +1683,7 @@ activation {
 	# Configuration option activation/activation_mode.
 	# How LVs with missing devices are activated.
 	# The --activationmode option overrides this setting.
-	# 
+	#
 	# Accepted values:
 	#   complete
 	#     Only allow activation of an LV if all of the Physical Volumes it
@@ -1664,7 +1698,7 @@ activation {
 	#     could cause data loss with a portion of the LV inaccessible.
 	#     This setting should not normally be used, but may sometimes
 	#     assist with data recovery.
-	# 
+	#
 	activation_mode = "degraded"
 
 	# Configuration option activation/lock_start_list.
@@ -1712,7 +1746,7 @@ activation {
 	# Configuration option metadata/pvmetadatacopies.
 	# Number of copies of metadata to store on each PV.
 	# The --pvmetadatacopies option overrides this setting.
-	# 
+	#
 	# Accepted values:
 	#   2
 	#     Two copies of the VG metadata are stored on the PV, one at the
@@ -1722,7 +1756,7 @@ activation {
 	#   0
 	#     No copies of VG metadata are stored on the PV. This may be
 	#     useful for VGs containing large numbers of PVs.
-	# 
+	#
 	# This configuration option is advanced.
 	# This configuration option has an automatic default value.
 	# pvmetadatacopies = 1
@@ -1872,7 +1906,7 @@ activation {
 	# sequences are copied verbatim. Each special character sequence is
 	# introduced by the '%' character and such sequence is then
 	# substituted with a value as described below.
-	# 
+	#
 	# Accepted values:
 	#   %a
 	#     The abbreviated name of the day of the week according to the
@@ -1995,7 +2029,7 @@ activation {
 	#     The timezone name or abbreviation.
 	#   %%
 	#     A literal '%' character.
-	# 
+	#
 	# This configuration option has an automatic default value.
 	# time_format = "%Y-%m-%d %T %z"
 
@@ -2189,7 +2223,8 @@ dmeventd {
 	# failures. It removes failed devices from a volume group and
 	# reconfigures a mirror as necessary. If no mirror library is
 	# provided, mirrors are not monitored through dmeventd.
-	mirror_library = "libdevmapper-event-lvm2mirror.so"
+	# This configuration option has an automatic default value.
+	# mirror_library = "libdevmapper-event-lvm2mirror.so"
 
 	# Configuration option dmeventd/raid_library.
 	# This configuration option has an automatic default value.
@@ -2200,14 +2235,16 @@ dmeventd {
 	# libdevmapper-event-lvm2snapshot.so monitors the filling of snapshots
 	# and emits a warning through syslog when the usage exceeds 80%. The
 	# warning is repeated when 85%, 90% and 95% of the snapshot is filled.
-	snapshot_library = "libdevmapper-event-lvm2snapshot.so"
+	# This configuration option has an automatic default value.
+	# snapshot_library = "libdevmapper-event-lvm2snapshot.so"
 
 	# Configuration option dmeventd/thin_library.
 	# The library dmeventd uses when monitoring a thin device.
 	# libdevmapper-event-lvm2thin.so monitors the filling of a pool
 	# and emits a warning through syslog when the usage exceeds 80%. The
 	# warning is repeated when 85%, 90% and 95% of the pool is filled.
-	thin_library = "libdevmapper-event-lvm2thin.so"
+	# This configuration option has an automatic default value.
+	# thin_library = "libdevmapper-event-lvm2thin.so"
 
 	# Configuration option dmeventd/thin_command.
 	# The plugin runs command with each 5% increment when thin-pool data volume
@@ -2261,12 +2298,12 @@ dmeventd {
 	# applied to the local machine as a 'host tag'. If this subsection is
 	# empty (has no host_list), then the subsection name is always applied
 	# as a 'host tag'.
-	# 
+	#
 	# Example
 	# The host tag foo is given to all hosts, and the host tag
 	# bar is given to the hosts named machine1 and machine2.
 	# tags { foo { } bar { host_list = [ "machine1", "machine2" ] } }
-	# 
+	#
 	# This configuration section has variable name.
 	# This configuration section has an automatic default value.
 	# tag {

conf/lvmlocal.conf.in

@@ -28,13 +28,13 @@ local {
 	# main configuration file, e.g. lvm.conf. When used, it must be set to
 	# a unique value among all hosts sharing access to the storage,
 	# e.g. a host name.
-	# 
+	#
 	# Example
 	# Set no system ID:
 	# system_id = ""
 	# Set the system_id to a specific name:
 	# system_id = "host1"
-	# 
+	#
 	# This configuration option has an automatic default value.
 	# system_id = ""
 

configure

@@ -753,6 +753,8 @@ BUILD_CMIRRORD
 BLKID_PC
 MODPROBE_CMD
 MSGFMT
+EDITLINE_LIBS
+EDITLINE_CFLAGS
 PYTHON3_CONFIG
 pkgpyexecdir
 pyexecdir
@@ -918,7 +920,9 @@ enable_cache_check_needs_check
 with_vdo
 with_vdo_format
 with_writecache
+with_integrity
 enable_readline
+enable_editline
 enable_realtime
 enable_ocf
 with_ocfdir
@@ -959,6 +963,7 @@ enable_fsadm
 enable_blkdeactivate
 enable_dmeventd
 enable_selinux
+enable_blkzeroout
 enable_nls
 with_localedir
 with_confdir
@@ -1014,7 +1019,9 @@ SYSTEMD_CFLAGS
 SYSTEMD_LIBS
 UDEV_CFLAGS
 UDEV_LIBS
-PYTHON'
+PYTHON
+EDITLINE_CFLAGS
+EDITLINE_LIBS'
 
 
 # Initialize some variables set by options.
@@ -1637,6 +1644,7 @@ Optional Features:
   --disable-cache_check_needs_check
                           required if cache_check version is < 0.5
   --disable-readline      disable readline support
+  --enable-editline       enable editline support
   --disable-realtime      disable realtime clock support
   --enable-ocf            enable Open Cluster Framework (OCF) compliant
                           resource agents
@@ -1677,6 +1685,7 @@ Optional Features:
   --disable-blkdeactivate disable blkdeactivate
   --enable-dmeventd       enable the device-mapper event daemon
   --disable-selinux       disable selinux support
+  --disable-blkzeroout    do not use BLKZEROOUT for device zeroing
   --enable-nls            enable Native Language Support
 
 Optional Packages:
@@ -1715,15 +1724,16 @@ Optional Packages:
                           cache_restore tool: [autodetect]
   --with-vdo=TYPE         vdo support: internal/none [internal]
   --with-vdo-format=PATH  vdoformat tool: [autodetect]
-  --with-writecache=TYPE  writecache support: internal/none [none]
+  --with-writecache=TYPE  writecache support: internal/none [internal]
+  --with-integrity=TYPE   integrity support: internal/none [internal]
   --with-ocfdir=DIR       install OCF files in
                           [PREFIX/lib/ocf/resource.d/lvm2]
   --with-default-pid-dir=PID_DIR
-                          Default directory to keep PID files in. [autodetect]
+                          default directory to keep PID files in [autodetect]
   --with-default-dm-run-dir=DM_RUN_DIR
-                          Default DM run directory. [autodetect]
+                          default DM run directory [autodetect]
   --with-default-run-dir=RUN_DIR
-                          Default LVM run directory. [autodetect_run_dir/lvm]
+                          default LVM run directory [autodetect_run_dir/lvm]
   --with-cmirrord-pidfile=PATH
                           cmirrord pidfile [PID_DIR/cmirrord.pid]
   --with-optimisation=OPT C optimisation flag [OPT=-O2]
@@ -1814,6 +1824,10 @@ Some influential environment variables:
   UDEV_CFLAGS C compiler flags for UDEV, overriding pkg-config
   UDEV_LIBS   linker flags for UDEV, overriding pkg-config
   PYTHON      the Python interpreter
+  EDITLINE_CFLAGS
+              C compiler flags for EDITLINE, overriding pkg-config
+  EDITLINE_LIBS
+              linker flags for EDITLINE, overriding pkg-config
 
 Use these variables to override the choices made by `configure' or to help
 it to find libraries and programs with nonstandard names/locations.
@@ -9584,7 +9598,7 @@ $as_echo_n "checking whether to include vdo... " >&6; }
 if test "${with_vdo+set}" = set; then :
   withval=$with_vdo; VDO=$withval
 else
-  VDO="none"
+  VDO="internal"
 fi
 
 
@@ -9744,7 +9758,7 @@ $as_echo_n "checking whether to include writecache... " >&6; }
 if test "${with_writecache+set}" = set; then :
   withval=$with_writecache; WRITECACHE=$withval
 else
-  WRITECACHE="none"
+  WRITECACHE="internal"
 fi
 
 
@@ -9761,6 +9775,31 @@ $as_echo "#define WRITECACHE_INTERNAL 1" >>confdefs.h
  *) as_fn_error $? "--with-writecache parameter invalid" "$LINENO" 5 ;;
 esac
 
+################################################################################
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to include integrity" >&5
+$as_echo_n "checking whether to include integrity... " >&6; }
+
+# Check whether --with-integrity was given.
+if test "${with_integrity+set}" = set; then :
+  withval=$with_integrity; INTEGRITY=$withval
+else
+  INTEGRITY="internal"
+fi
+
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $INTEGRITY" >&5
+$as_echo "$INTEGRITY" >&6; }
+
+case "$INTEGRITY" in
+ none) ;;
+ internal)
+
+$as_echo "#define INTEGRITY_INTERNAL 1" >>confdefs.h
+
+	;;
+ *) as_fn_error $? "--with-integrity parameter invalid" "$LINENO" 5 ;;
+esac
+
 ################################################################################
 # Check whether --enable-readline was given.
 if test "${enable_readline+set}" = set; then :
@@ -9770,6 +9809,15 @@ else
 fi
 
 
+################################################################################
+# Check whether --enable-editline was given.
+if test "${enable_editline+set}" = set; then :
+  enableval=$enable_editline; EDITLINE=$enableval
+else
+  EDITLINE=no
+fi
+
+
 ################################################################################
 { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to enable realtime support" >&5
 $as_echo_n "checking whether to enable realtime support... " >&6; }
@@ -11797,6 +11845,7 @@ if test "$BUILD_LVMDBUSD" = yes; then
 
 
 
+
         if test -n "$PYTHON"; then
       # If the user set $PYTHON, use it and don't search something else.
       { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether $PYTHON version is >= 3" >&5
@@ -11832,7 +11881,7 @@ if ${am_cv_pathless_PYTHON+:} false; then :
   $as_echo_n "(cached) " >&6
 else
 
-	for am_cv_pathless_PYTHON in python python2 python3 python3.5 python3.4 python3.3 python3.2 python3.1 python3.0 python2.7  python2.6 python2.5 python2.4 python2.3 python2.2 python2.1 python2.0 none; do
+	for am_cv_pathless_PYTHON in  python3 python2 python 	python3.9 python3.8 python3.7 python3.6 python3.5 python3.4 python3.3 python3.2 python3.1 python3.0 	python2.7 python2.6 python2.5 python2.4 python2.3 python2.2 python2.1 python2.0  none; do
 	  test "$am_cv_pathless_PYTHON" = none && break
 	  prog="import sys
 # split strings by '.' and convert to numeric.  Append some zeros
@@ -11913,7 +11962,7 @@ $as_echo_n "checking for $am_display_PYTHON version... " >&6; }
 if ${am_cv_python_version+:} false; then :
   $as_echo_n "(cached) " >&6
 else
-  am_cv_python_version=`$PYTHON -c "import sys; sys.stdout.write(sys.version[:3])"`
+  am_cv_python_version=`$PYTHON -c "import sys; print('%u.%u' % sys.version_info[:2])"`
 fi
 { $as_echo "$as_me:${as_lineno-$LINENO}: result: $am_cv_python_version" >&5
 $as_echo "$am_cv_python_version" >&6; }
@@ -12661,6 +12710,61 @@ fi
 
 fi
 
+################################################################################
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for BLKZEROOUT in sys/ioctl.h." >&5
+$as_echo_n "checking for BLKZEROOUT in sys/ioctl.h.... " >&6; }
+if ${ac_cv_have_blkzeroout+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <sys/ioctl.h>
+#include <linux/fs.h>
+int bar(void) { return ioctl(0, BLKZEROOUT, 0); }
+
+int
+main ()
+{
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+  ac_cv_have_blkzeroout=yes
+else
+  ac_cv_have_blkzeroout=no
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_have_blkzeroout" >&5
+$as_echo "$ac_cv_have_blkzeroout" >&6; }
+
+
+# Check whether --enable-blkzeroout was given.
+if test "${enable_blkzeroout+set}" = set; then :
+  enableval=$enable_blkzeroout; BLKZEROOUT=$enableval
+else
+  BLKZEROOUT=yes
+fi
+
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to use BLKZEROOUT for device zeroing" >&5
+$as_echo_n "checking whether to use BLKZEROOUT for device zeroing... " >&6; }
+if test "$BLKZEROOUT" = yes; then
+	if test $ac_cv_have_blkzeroout = yes; then :
+
+$as_echo "#define HAVE_BLKZEROOUT 1" >>confdefs.h
+
+else
+  BLKZEROOUT=no
+fi
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $BLKZEROOUT" >&5
+$as_echo "$BLKZEROOUT" >&6; }
+
+
 ################################################################################
 RT_LIBS=
 HAVE_REALTIME=no
@@ -12781,6 +12885,86 @@ fi
 done
 
 
+################################################################################
+if test "$EDITLINE" == yes; then
+
+pkg_failed=no
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for EDITLINE" >&5
+$as_echo_n "checking for EDITLINE... " >&6; }
+
+if test -n "$EDITLINE_CFLAGS"; then
+    pkg_cv_EDITLINE_CFLAGS="$EDITLINE_CFLAGS"
+ elif test -n "$PKG_CONFIG"; then
+    if test -n "$PKG_CONFIG" && \
+    { { $as_echo "$as_me:${as_lineno-$LINENO}: \$PKG_CONFIG --exists --print-errors \"libedit\""; } >&5
+  ($PKG_CONFIG --exists --print-errors "libedit") 2>&5
+  ac_status=$?
+  $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+  test $ac_status = 0; }; then
+  pkg_cv_EDITLINE_CFLAGS=`$PKG_CONFIG --cflags "libedit" 2>/dev/null`
+		      test "x$?" != "x0" && pkg_failed=yes
+else
+  pkg_failed=yes
+fi
+ else
+    pkg_failed=untried
+fi
+if test -n "$EDITLINE_LIBS"; then
+    pkg_cv_EDITLINE_LIBS="$EDITLINE_LIBS"
+ elif test -n "$PKG_CONFIG"; then
+    if test -n "$PKG_CONFIG" && \
+    { { $as_echo "$as_me:${as_lineno-$LINENO}: \$PKG_CONFIG --exists --print-errors \"libedit\""; } >&5
+  ($PKG_CONFIG --exists --print-errors "libedit") 2>&5
+  ac_status=$?
+  $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+  test $ac_status = 0; }; then
+  pkg_cv_EDITLINE_LIBS=`$PKG_CONFIG --libs "libedit" 2>/dev/null`
+		      test "x$?" != "x0" && pkg_failed=yes
+else
+  pkg_failed=yes
+fi
+ else
+    pkg_failed=untried
+fi
+
+
+
+if test $pkg_failed = yes; then
+   	{ $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+
+if $PKG_CONFIG --atleast-pkgconfig-version 0.20; then
+        _pkg_short_errors_supported=yes
+else
+        _pkg_short_errors_supported=no
+fi
+        if test $_pkg_short_errors_supported = yes; then
+	        EDITLINE_PKG_ERRORS=`$PKG_CONFIG --short-errors --print-errors --cflags --libs "libedit" 2>&1`
+        else
+	        EDITLINE_PKG_ERRORS=`$PKG_CONFIG --print-errors --cflags --libs "libedit" 2>&1`
+        fi
+	# Put the nasty error message in config.log where it belongs
+	echo "$EDITLINE_PKG_ERRORS" >&5
+
+	as_fn_error $? "libedit could not be found which is required for the --enable-readline option." "$LINENO" 5
+
+elif test $pkg_failed = untried; then
+     	{ $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+	as_fn_error $? "libedit could not be found which is required for the --enable-readline option." "$LINENO" 5
+
+else
+	EDITLINE_CFLAGS=$pkg_cv_EDITLINE_CFLAGS
+	EDITLINE_LIBS=$pkg_cv_EDITLINE_LIBS
+        { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5
+$as_echo "yes" >&6; }
+
+
+$as_echo "#define EDITLINE_SUPPORT 1" >>confdefs.h
+
+fi
+fi
+
 ################################################################################
 if test "$READLINE" != no; then
 	lvm_saved_libs=$LIBS
@@ -13219,6 +13403,28 @@ $as_echo_n "checking whether to enable readline... " >&6; }
 { $as_echo "$as_me:${as_lineno-$LINENO}: result: $READLINE" >&5
 $as_echo "$READLINE" >&6; }
 
+if test "$EDITLINE" = yes; then
+	for ac_header in editline/readline.h editline/history.h
+do :
+  as_ac_Header=`$as_echo "ac_cv_header_$ac_header" | $as_tr_sh`
+ac_fn_c_check_header_mongrel "$LINENO" "$ac_header" "$as_ac_Header" "$ac_includes_default"
+if eval test \"x\$"$as_ac_Header"\" = x"yes"; then :
+  cat >>confdefs.h <<_ACEOF
+#define `$as_echo "HAVE_$ac_header" | $as_tr_cpp` 1
+_ACEOF
+
+else
+  hard_bailout
+fi
+
+done
+
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to enable editline" >&5
+$as_echo_n "checking whether to enable editline... " >&6; }
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $EDITLINE" >&5
+$as_echo "$EDITLINE" >&6; }
+
 if test "$BUILD_CMIRRORD" = yes; then
 	for ac_func in atexit
 do :
@@ -13900,6 +14106,7 @@ _ACEOF
 
 
 
+
 
 
 ################################################################################
@@ -15272,8 +15479,8 @@ $as_echo "$as_me: WARNING: You should install latest cache_check vsn 0.7.0 to us
 fi
 
 if test -n "$VDO_CONFIGURE_WARN"; then :
-  { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: unrecognized 'vdoformat' tool is REQUIRED for VDO logical volume creation!" >&5
-$as_echo "$as_me: WARNING: unrecognized 'vdoformat' tool is REQUIRED for VDO logical volume creation!" >&2;}
+  { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: Unrecognized 'vdoformat' tool is REQUIRED for VDO logical volume creation!" >&5
+$as_echo "$as_me: WARNING: Unrecognized 'vdoformat' tool is REQUIRED for VDO logical volume creation!" >&2;}
 fi
 
 

configure.ac

@@ -607,7 +607,7 @@ AC_MSG_CHECKING(whether to include vdo)
 AC_ARG_WITH(vdo,
 	    AC_HELP_STRING([--with-vdo=TYPE],
 			   [vdo support: internal/none [internal]]),
-			   VDO=$withval, VDO="none")
+			   VDO=$withval, VDO="internal")
 
 AC_MSG_RESULT($VDO)
 
@@ -654,8 +654,8 @@ dnl -- writecache inclusion type
 AC_MSG_CHECKING(whether to include writecache)
 AC_ARG_WITH(writecache,
 	    AC_HELP_STRING([--with-writecache=TYPE],
-			   [writecache support: internal/none [none]]),
-			   WRITECACHE=$withval, WRITECACHE="none")
+			   [writecache support: internal/none [internal]]),
+			   WRITECACHE=$withval, WRITECACHE="internal")
 
 AC_MSG_RESULT($WRITECACHE)
 
@@ -667,12 +667,36 @@ case "$WRITECACHE" in
  *) AC_MSG_ERROR([--with-writecache parameter invalid]) ;;
 esac
 
+################################################################################
+dnl -- integrity inclusion type
+AC_MSG_CHECKING(whether to include integrity)
+AC_ARG_WITH(integrity,
+	    AC_HELP_STRING([--with-integrity=TYPE],
+			   [integrity support: internal/none [internal]]),
+			   INTEGRITY=$withval, INTEGRITY="internal")
+
+AC_MSG_RESULT($INTEGRITY)
+
+case "$INTEGRITY" in
+ none) ;;
+ internal)
+	AC_DEFINE([INTEGRITY_INTERNAL], 1, [Define to 1 to include built-in support for integrity.])
+	;;
+ *) AC_MSG_ERROR([--with-integrity parameter invalid]) ;;
+esac
+
 ################################################################################
 dnl -- Disable readline
 AC_ARG_ENABLE([readline],
 	      AC_HELP_STRING([--disable-readline], [disable readline support]),
 	      READLINE=$enableval, READLINE=maybe)
 
+################################################################################
+dnl -- Disable editline
+AC_ARG_ENABLE([editline],
+	      AC_HELP_STRING([--enable-editline], [enable editline support]),
+	      EDITLINE=$enableval, EDITLINE=no)
+
 ################################################################################
 dnl -- Disable realtime clock support
 AC_MSG_CHECKING(whether to enable realtime support)
@@ -716,7 +740,7 @@ dnl -- Set up pidfile and run directory
 AH_TEMPLATE(DEFAULT_PID_DIR)
 AC_ARG_WITH(default-pid-dir,
 	    AC_HELP_STRING([--with-default-pid-dir=PID_DIR],
-			   [Default directory to keep PID files in. [autodetect]]),
+			   [default directory to keep PID files in [autodetect]]),
 	    DEFAULT_PID_DIR="$withval", DEFAULT_PID_DIR=$RUN_DIR)
 AC_DEFINE_UNQUOTED(DEFAULT_PID_DIR, ["$DEFAULT_PID_DIR"],
 		   [Default directory to keep PID files in.])
@@ -724,7 +748,7 @@ AC_DEFINE_UNQUOTED(DEFAULT_PID_DIR, ["$DEFAULT_PID_DIR"],
 AH_TEMPLATE(DEFAULT_DM_RUN_DIR, [Name of default DM run directory.])
 AC_ARG_WITH(default-dm-run-dir,
 	    AC_HELP_STRING([--with-default-dm-run-dir=DM_RUN_DIR],
-			   [ Default DM run directory. [autodetect]]),
+			   [default DM run directory [autodetect]]),
 	    DEFAULT_DM_RUN_DIR="$withval", DEFAULT_DM_RUN_DIR=$RUN_DIR)
 AC_DEFINE_UNQUOTED(DEFAULT_DM_RUN_DIR, ["$DEFAULT_DM_RUN_DIR"],
 		   [Default DM run directory.])
@@ -732,7 +756,7 @@ AC_DEFINE_UNQUOTED(DEFAULT_DM_RUN_DIR, ["$DEFAULT_DM_RUN_DIR"],
 AH_TEMPLATE(DEFAULT_RUN_DIR, [Name of default LVM run directory.])
 AC_ARG_WITH(default-run-dir,
 	    AC_HELP_STRING([--with-default-run-dir=RUN_DIR],
-			   [Default LVM run directory. [autodetect_run_dir/lvm]]),
+			   [default LVM run directory [autodetect_run_dir/lvm]]),
 	    DEFAULT_RUN_DIR="$withval", DEFAULT_RUN_DIR="$RUN_DIR/lvm")
 AC_DEFINE_UNQUOTED(DEFAULT_RUN_DIR, ["$DEFAULT_RUN_DIR"],
 		   [Default LVM run directory.])
@@ -1200,6 +1224,9 @@ if test "$BUILD_LVMDBUSD" = yes; then
 	unset am_cv_pathless_PYTHON ac_cv_path_PYTHON am_cv_python_platform
 	unset am_cv_python_pythondir am_cv_python_version am_cv_python_pyexecdir
 	unset ac_cv_path_PYTHON_CONFIG ac_cv_path_ac_pt_PYTHON_CONFIG
+	m4_define_default([_AM_PYTHON_INTERPRETER_LIST],[ python3 python2 python dnl
+	python3.9 python3.8 python3.7 python3.6 python3.5 python3.4 python3.3 python3.2 python3.1 python3.0 dnl
+	python2.7 python2.6 python2.5 python2.4 python2.3 python2.2 python2.1 python2.0 ])
 	AM_PATH_PYTHON([3])
 	PYTHON3=$PYTHON
 	test -z "$PYTHON3" && AC_MSG_ERROR([python3 is required for --enable-python3_bindings or --enable-dbus-service but cannot be found])
@@ -1327,6 +1354,33 @@ if test "$SELINUX" = yes; then
 		HAVE_SELINUX=no ])
 fi
 
+################################################################################
+dnl -- Check BLKZEROOUT support
+
+AC_CACHE_CHECK([for BLKZEROOUT in sys/ioctl.h.],
+	[ac_cv_have_blkzeroout],
+	[AC_COMPILE_IFELSE([AC_LANG_PROGRAM(
+[#include <sys/ioctl.h>
+#include <linux/fs.h>
+int bar(void) { return ioctl(0, BLKZEROOUT, 0); }]
+	 )], [ac_cv_have_blkzeroout=yes], [ac_cv_have_blkzeroout=no])])
+
+
+AC_ARG_ENABLE(blkzeroout,
+	      AC_HELP_STRING([--disable-blkzeroout],
+			     [do not use BLKZEROOUT for device zeroing]),
+	      BLKZEROOUT=$enableval, BLKZEROOUT=yes)
+
+AC_MSG_CHECKING(whether to use BLKZEROOUT for device zeroing)
+if test "$BLKZEROOUT" = yes; then
+	AC_IF_YES(ac_cv_have_blkzeroout,
+		  AC_DEFINE(HAVE_BLKZEROOUT, 1,
+			    [Define if ioctl BLKZEROOUT can be used for device zeroing.]),
+		  BLKZEROOUT=no)
+fi
+AC_MSG_RESULT($BLKZEROOUT)
+
+
 ################################################################################
 dnl -- Check for realtime clock support
 RT_LIBS=
@@ -1360,6 +1414,16 @@ AC_IF_YES(ac_cv_stat_st_ctim,
 dnl -- Check for getopt
 AC_CHECK_HEADERS(getopt.h, AC_DEFINE([HAVE_GETOPTLONG], 1, [Define to 1 if getopt_long is available.]))
 
+################################################################################
+dnl -- Check for editline
+if test "$EDITLINE" == yes; then
+	PKG_CHECK_MODULES([EDITLINE], [libedit], [
+		AC_DEFINE([EDITLINE_SUPPORT], 1,
+			[Define to 1 to include the LVM editline shell.])], AC_MSG_ERROR(
+[libedit could not be found which is required for the --enable-readline option.])
+	)
+fi
+
 ################################################################################
 dnl -- Check for readline (Shamelessly copied from parted 1.4.17)
 if test "$READLINE" != no; then
@@ -1492,6 +1556,12 @@ fi
 AC_MSG_CHECKING(whether to enable readline)
 AC_MSG_RESULT($READLINE)
 
+if test "$EDITLINE" = yes; then
+	AC_CHECK_HEADERS(editline/readline.h editline/history.h,,hard_bailout)
+fi
+AC_MSG_CHECKING(whether to enable editline)
+AC_MSG_RESULT($EDITLINE)
+
 if test "$BUILD_CMIRRORD" = yes; then
 	AC_CHECK_FUNCS(atexit,,hard_bailout)
 fi
@@ -1747,6 +1817,7 @@ AC_SUBST(QUORUM_CFLAGS)
 AC_SUBST(QUORUM_LIBS)
 AC_SUBST(RT_LIBS)
 AC_SUBST(READLINE_LIBS)
+AC_SUBST(EDITLINE_LIBS)
 AC_SUBST(REPLICATORS)
 AC_SUBST(SACKPT_CFLAGS)
 AC_SUBST(SACKPT_LIBS)
@@ -1882,7 +1953,7 @@ AS_IF([test -n "$CACHE_CHECK_VERSION_WARN"],
       [AC_MSG_WARN([You should install latest cache_check vsn 0.7.0 to use lvm2 cache metadata format 2])])
 
 AS_IF([test -n "$VDO_CONFIGURE_WARN"],
-      [AC_MSG_WARN([unrecognized 'vdoformat' tool is REQUIRED for VDO logical volume creation!])])
+      [AC_MSG_WARN([Unrecognized 'vdoformat' tool is REQUIRED for VDO logical volume creation!])])
 
 
 AS_IF([test "$ODIRECT" != yes],

coverity/coverity_model.c

@@ -46,6 +46,7 @@ const char *find_config_tree_str(struct cmd_context *cmd, int id, struct profile
 	return "STRING";
 }
 
+/*
 struct logical_volume *origin_from_cow(const struct logical_volume *lv)
 {
 	if (lv)
@@ -53,6 +54,7 @@ struct logical_volume *origin_from_cow(const struct logical_volume *lv)
 
 	__coverity_panic__();
 }
+*/
 
 /* simple_memccpy() from glibc */
 void *memccpy(void *dest, const void *src, int c, size_t n)

daemons/dmeventd/dmeventd.c

@@ -752,7 +752,7 @@ static void _exit_timeout(void *unused __attribute__((unused)))
 static void *_timeout_thread(void *unused __attribute__((unused)))
 {
 	struct thread_status *thread;
-	struct timespec timeout;
+	struct timespec timeout, real_time;
 	time_t curr_time;
 	int ret;
 
@@ -763,7 +763,16 @@ static void *_timeout_thread(void *unused __attribute__((unused)))
 	while (!dm_list_empty(&_timeout_registry)) {
 		timeout.tv_sec = 0;
 		timeout.tv_nsec = 0;
+#ifndef HAVE_REALTIME
 		curr_time = time(NULL);
+#else
+		if (clock_gettime(CLOCK_REALTIME, &real_time)) {
+			log_error("Failed to read clock_gettime().");
+			break;
+		}
+		/* 10ms back to the future */
+		curr_time = real_time.tv_sec + ((real_time.tv_nsec > (1000000000 - 10000000)) ? 1 : 0);
+#endif
 
 		dm_list_iterate_items_gen(thread, &_timeout_registry, timeout_list) {
 			if (thread->next_time <= curr_time) {
@@ -1485,37 +1494,34 @@ static int _client_read(struct dm_event_fifos *fifos,
 		t.tv_usec = 0;
 		ret = select(fifos->client + 1, &fds, NULL, NULL, &t);
 
-		if (!ret && !bytes)	/* nothing to read */
-			return 0;
+		if (!ret && bytes)
+			continue; /* trying to finish read */
 
-		if (!ret)	/* trying to finish read */
-			continue;
-
-		if (ret < 0)	/* error */
-			return 0;
+		if (ret <= 0)	/* nothing to read */
+			goto bad;
 
 		ret = read(fifos->client, buf + bytes, size - bytes);
 		bytes += ret > 0 ? ret : 0;
-		if (header && (bytes == 2 * sizeof(uint32_t))) {
+		if (!msg->data && (bytes == 2 * sizeof(uint32_t))) {
 			msg->cmd = ntohl(header[0]);
-			size = msg->size = ntohl(header[1]);
 			bytes = 0;
-			if (!size)
-				break; /* No data -> error */
-			buf = msg->data = malloc(msg->size);
-			if (!buf)
-				break; /* No mem -> error */
-			header = 0;
+
+			if (!(size = msg->size = ntohl(header[1])))
+				break;
+
+			if (!(buf = msg->data = malloc(msg->size)))
+				goto bad;
 		}
 	}
 
-	if (bytes != size) {
-		free(msg->data);
-		msg->data = NULL;
-		return 0;
-	}
+	if (bytes == size)
+		return 1;
 
-	return 1;
+bad:
+	free(msg->data);
+	msg->data = NULL;
+
+	return 0;
 }
 
 /*
@@ -2022,8 +2028,8 @@ static int _reinstate_registrations(struct dm_event_fifos *fifos)
 static void _restart_dmeventd(void)
 {
 	struct dm_event_fifos fifos = {
-		.server = -1,
 		.client = -1,
+		.server = -1,
 		/* FIXME Make these either configurable or depend directly on dmeventd_path */
 		.client_path = DM_EVENT_FIFO_CLIENT,
 		.server_path = DM_EVENT_FIFO_SERVER
@@ -2237,7 +2243,8 @@ int main(int argc, char *argv[])
 
 	_init_thread_signals();
 
-	pthread_mutex_init(&_global_mutex, NULL);
+	if (pthread_mutex_init(&_global_mutex, NULL))
+		exit(EXIT_FAILURE);
 
 	if (!_systemd_activation && !_open_fifos(&fifos))
 		exit(EXIT_FIFO_FAILURE);

daemons/dmeventd/libdevmapper-event.c

@@ -237,16 +237,16 @@ static int _daemon_read(struct dm_event_fifos *fifos,
 			ret = select(fifos->server + 1, &fds, NULL, NULL, &tval);
 			if (ret < 0 && errno != EINTR) {
 				log_error("Unable to read from event server.");
-				return 0;
+				goto bad;
 			}
 			if ((ret == 0) && (i > 4) && !bytes) {
 				log_error("No input from event server.");
-				return 0;
+				goto bad;
 			}
 		}
 		if (ret < 1) {
 			log_error("Unable to read from event server.");
-			return 0;
+			goto bad;
 		}
 
 		ret = read(fifos->server, buf + bytes, size);
@@ -255,25 +255,32 @@ static int _daemon_read(struct dm_event_fifos *fifos,
 				continue;
 
 			log_error("Unable to read from event server.");
-			return 0;
+			goto bad;
 		}
 
 		bytes += ret;
-		if (header && (bytes == 2 * sizeof(uint32_t))) {
+		if (!msg->data && (bytes == 2 * sizeof(uint32_t))) {
 			msg->cmd = ntohl(header[0]);
-			msg->size = ntohl(header[1]);
-			buf = msg->data = malloc(msg->size);
-			size = msg->size;
 			bytes = 0;
-			header = 0;
+
+			if (!(size = msg->size = ntohl(header[1])))
+				break;
+
+			if (!(buf = msg->data = malloc(msg->size))) {
+				log_error("Unable to allocate message data.");
+				return 0;
+			}
 		}
 	}
 
-	if (bytes != size) {
-		free(msg->data);
-		msg->data = NULL;
-	}
-	return bytes == size;
+	if (bytes == size)
+		return 1;
+
+bad:
+	free(msg->data);
+	msg->data = NULL;
+
+	return 0;
 }
 
 /* Write message to daemon. */
@@ -608,8 +615,8 @@ static int _do_event(int cmd, char *dmeventd_path, struct dm_event_daemon_messag
 {
 	int ret;
 	struct dm_event_fifos fifos = {
-		.server = -1,
 		.client = -1,
+		.server = -1,
 		/* FIXME Make these either configurable or depend directly on dmeventd_path */
 		.client_path = DM_EVENT_FIFO_CLIENT,
 		.server_path = DM_EVENT_FIFO_SERVER

daemons/dmeventd/plugins/lvm2/dmeventd_lvm.c

@@ -71,7 +71,7 @@ int dmeventd_lvm2_init(void)
 	if (!_lvm_handle) {
 		lvm2_log_fn(_lvm2_print_log);
 
-		if (!(_lvm_handle = lvm2_init()))
+		if (!(_lvm_handle = lvm2_init_threaded()))
 			goto out;
 
 		/*

daemons/lvmdbusd/cmdhandler.py

@@ -398,6 +398,14 @@ def vg_create_vdo_pool_lv_and_lv(vg_name, pool_name, lv_name, data_size,
 	return call(cmd)
 
 
+def vg_create_vdo_pool(pool_full_name, lv_name, virtual_size, create_options):
+	cmd = ['lvconvert']
+	cmd.extend(options_to_cli_args(create_options))
+	cmd.extend(['--type', 'vdo-pool', '-n', lv_name, '--force', '-y',
+				'-V', '%dB' % virtual_size, pool_full_name])
+	return call(cmd)
+
+
 def lv_remove(lv_path, remove_options):
 	cmd = ['lvremove']
 	cmd.extend(options_to_cli_args(remove_options))
@@ -445,6 +453,15 @@ def lv_cache_lv(cache_pool_full_name, lv_full_name, cache_options):
 	return call(cmd)
 
 
+def lv_writecache_lv(cache_lv_full_name, lv_full_name, cache_options):
+	# lvconvert --type writecache --cachevol VG/CacheLV VG/OriginLV
+	cmd = ['lvconvert']
+	cmd.extend(options_to_cli_args(cache_options))
+	cmd.extend(['-y', '--type', 'writecache', '--cachevol',
+				cache_lv_full_name, lv_full_name])
+	return call(cmd)
+
+
 def lv_detach_cache(lv_full_name, detach_options, destroy_cache):
 	cmd = ['lvconvert']
 	if destroy_cache:
@@ -460,6 +477,28 @@ def lv_detach_cache(lv_full_name, detach_options, destroy_cache):
 	return call(cmd)
 
 
+def lv_vdo_compression(lv_path, enable, comp_options):
+	cmd = ['lvchange', '--compression']
+	if enable:
+		cmd.append('y')
+	else:
+		cmd.append('n')
+	cmd.extend(options_to_cli_args(comp_options))
+	cmd.append(lv_path)
+	return call(cmd)
+
+
+def lv_vdo_deduplication(lv_path, enable, dedup_options):
+	cmd = ['lvchange', '--deduplication']
+	if enable:
+		cmd.append('y')
+	else:
+		cmd.append('n')
+	cmd.extend(options_to_cli_args(dedup_options))
+	cmd.append(lv_path)
+	return call(cmd)
+
+
 def supports_json():
 	cmd = ['help']
 	rc, out, err = call(cmd)

daemons/lvmdbusd/lv.py

@@ -388,7 +388,7 @@ class LvCommon(AutomatedProperties):
 					'l': 'mirror log device', 'c': 'under conversion',
 					'V': 'thin Volume', 't': 'thin pool', 'T': 'Thin pool data',
 					'e': 'raid or pool metadata or pool metadata spare',
-					'd': 'vdo pool', 'D': 'vdo pool data',
+					'd': 'vdo pool', 'D': 'vdo pool data', 'g': 'integrity',
 					'-': 'Unspecified'}
 		return self.attr_struct(0, type_map)
 
@@ -743,6 +743,49 @@ class Lv(LvCommon):
 			cb, cbe, return_tuple=False)
 		cfg.worker_q.put(r)
 
+	@staticmethod
+	def _writecache_lv(lv_uuid, lv_name, lv_object_path, cache_options):
+		# Make sure we have a dbus object representing it
+		dbo = LvCommon.validate_dbus_object(lv_uuid, lv_name)
+
+		# Make sure we have dbus object representing lv to cache
+		lv_to_cache = cfg.om.get_object_by_path(lv_object_path)
+
+		if lv_to_cache:
+			fcn = lv_to_cache.lv_full_name()
+			rc, out, err = cmdhandler.lv_writecache_lv(
+				dbo.lv_full_name(), fcn, cache_options)
+			if rc == 0:
+				# When we cache an LV, the cache pool and the lv that is getting
+				# cached need to be removed from the object manager and
+				# re-created as their interfaces have changed!
+				mt_remove_dbus_objects((dbo, lv_to_cache))
+				cfg.load()
+
+				lv_converted = cfg.om.get_object_path_by_lvm_id(fcn)
+			else:
+				raise dbus.exceptions.DBusException(
+					LV_INTERFACE,
+					'Exit code %s, stderr = %s' % (str(rc), err))
+		else:
+			raise dbus.exceptions.DBusException(
+				LV_INTERFACE, 'LV to cache with object path %s not present!' %
+				lv_object_path)
+		return lv_converted
+
+	@dbus.service.method(
+		dbus_interface=LV_INTERFACE,
+		in_signature='oia{sv}',
+		out_signature='(oo)',
+		async_callbacks=('cb', 'cbe'))
+	def WriteCacheLv(self, lv_object, tmo, cache_options, cb, cbe):
+		r = RequestEntry(
+			tmo, Lv._writecache_lv,
+			(self.Uuid, self.lvm_id, lv_object,
+			cache_options), cb, cbe)
+		cfg.worker_q.put(r)
+
+
 # noinspection PyPep8Naming
 @utils.dbus_property(VDO_POOL_INTERFACE, 'OperatingMode', 's')
 @utils.dbus_property(VDO_POOL_INTERFACE, 'CompressionState', 's')
@@ -780,6 +823,72 @@ class LvVdoPool(Lv):
 	def DataLv(self):
 		return dbus.ObjectPath(self._data_lv)
 
+	@staticmethod
+	def _enable_disable_compression(pool_uuid, pool_name, enable, comp_options):
+		# Make sure we have a dbus object representing it
+		LvCommon.validate_dbus_object(pool_uuid, pool_name)
+		# Rename the logical volume
+		LvCommon.handle_execute(*cmdhandler.lv_vdo_compression(
+			pool_name, enable, comp_options))
+		return '/'
+
+	@dbus.service.method(
+		dbus_interface=VDO_POOL_INTERFACE,
+		in_signature='ia{sv}',
+		out_signature='o',
+		async_callbacks=('cb', 'cbe'))
+	def EnableCompression(self, tmo, comp_options, cb, cbe):
+		r = RequestEntry(
+			tmo, LvVdoPool._enable_disable_compression,
+			(self.Uuid, self.lvm_id, True, comp_options),
+			cb, cbe, False)
+		cfg.worker_q.put(r)
+
+	@dbus.service.method(
+	dbus_interface=VDO_POOL_INTERFACE,
+	in_signature='ia{sv}',
+	out_signature='o',
+	async_callbacks=('cb', 'cbe'))
+	def DisableCompression(self, tmo, comp_options, cb, cbe):
+		r = RequestEntry(
+			tmo, LvVdoPool._enable_disable_compression,
+			(self.Uuid, self.lvm_id, False, comp_options),
+			cb, cbe, False)
+		cfg.worker_q.put(r)
+
+	@staticmethod
+	def _enable_disable_deduplication(pool_uuid, pool_name, enable, dedup_options):
+		# Make sure we have a dbus object representing it
+		LvCommon.validate_dbus_object(pool_uuid, pool_name)
+		# Rename the logical volume
+		LvCommon.handle_execute(*cmdhandler.lv_vdo_deduplication(
+			pool_name, enable, dedup_options))
+		return '/'
+
+	@dbus.service.method(
+		dbus_interface=VDO_POOL_INTERFACE,
+		in_signature='ia{sv}',
+		out_signature='o',
+		async_callbacks=('cb', 'cbe'))
+	def EnableDeduplication(self, tmo, dedup_options, cb, cbe):
+		r = RequestEntry(
+			tmo, LvVdoPool._enable_disable_deduplication,
+			(self.Uuid, self.lvm_id, True, dedup_options),
+			cb, cbe, False)
+		cfg.worker_q.put(r)
+
+	@dbus.service.method(
+	dbus_interface=VDO_POOL_INTERFACE,
+	in_signature='ia{sv}',
+	out_signature='o',
+	async_callbacks=('cb', 'cbe'))
+	def DisableDeduplication(self, tmo, dedup_options, cb, cbe):
+		r = RequestEntry(
+			tmo, LvVdoPool._enable_disable_deduplication,
+			(self.Uuid, self.lvm_id, False, dedup_options),
+			cb, cbe, False)
+		cfg.worker_q.put(r)
+
 
 # noinspection PyPep8Naming
 class LvThinPool(Lv):

daemons/lvmdbusd/manager.py

@@ -27,7 +27,7 @@ class Manager(AutomatedProperties):
 
 	@property
 	def Version(self):
-		return dbus.String('1.0.0')
+		return dbus.String('1.1.0')
 
 	@staticmethod
 	def handle_execute(rc, out, err):

daemons/lvmdbusd/vg.py

@@ -813,3 +813,35 @@ class VgVdo(Vg):
 							round_size(virtual_size),
 							create_options), cb, cbe)
 		cfg.worker_q.put(r)
+
+	@staticmethod
+	def _vdo_pool_create(uuid, vg_name, pool_lv, name, virtual_size, create_options):
+		Vg.validate_dbus_object(uuid, vg_name)
+
+		# Retrieve the full name of the pool lv
+		pool = cfg.om.get_object_by_path(pool_lv)
+		if not pool:
+			msg = 'LV with object path %s not present!' % \
+					(pool_lv)
+			raise dbus.exceptions.DBusException(VG_VDO_INTERFACE, msg)
+
+		Vg.handle_execute(*cmdhandler.vg_create_vdo_pool(
+			pool.lv_full_name(), name, virtual_size,
+			create_options))
+		return Vg.fetch_new_lv(vg_name, pool.Name)
+
+	@dbus.service.method(
+		dbus_interface=VG_VDO_INTERFACE,
+		in_signature='ostia{sv}',
+		out_signature='(oo)',
+		async_callbacks=('cb', 'cbe'))
+	def CreateVdoPool(self, pool_lv, name, virtual_size,
+						tmo, create_options, cb, cbe):
+		utils.validate_lv_name(VG_VDO_INTERFACE, self.Name, name)
+
+		r = RequestEntry(tmo, VgVdo._vdo_pool_create,
+							(self.state.Uuid, self.state.lvm_id,
+							pool_lv, name,
+							round_size(virtual_size),
+							create_options), cb, cbe)
+		cfg.worker_q.put(r)

daemons/lvmlockd/lvmlockctl.c

@@ -280,13 +280,12 @@ static void format_info_line(char *line, char *r_name, char *r_type)
 
 static void format_info(void)
 {
-	char line[MAX_LINE];
-	char r_name[MAX_NAME+1];
-	char r_type[MAX_NAME+1];
+	char line[MAX_LINE] = { 0 };
+	char r_name[MAX_NAME+1] = { 0 };
+	char r_type[MAX_NAME+1] = { 0 };
 	int i, j;
 
 	j = 0;
-	memset(line, 0, sizeof(line));
 
 	for (i = 0; i < dump_len; i++) {
 		line[j++] = dump_buf[i];
@@ -326,6 +325,8 @@ static int _lvmlockd_result(daemon_reply reply, int *result)
 {
 	int reply_result;
 
+	*result = NO_LOCKD_RESULT;
+
 	if (reply.error) {
 		log_error("lvmlockd_result reply error %d", reply.error);
 		return 0;
@@ -337,7 +338,7 @@ static int _lvmlockd_result(daemon_reply reply, int *result)
 	}
 
 	reply_result = daemon_reply_int(reply, "op_result", NO_LOCKD_RESULT);
-	if (reply_result == -1000) {
+	if (reply_result == NO_LOCKD_RESULT) {
 		log_error("lvmlockd_result no op_result");
 		return 0;
 	}

daemons/lvmlockd/lvmlockd-client.h

@@ -14,6 +14,7 @@
 #include "libdaemon/client/daemon-client.h"
 
 #define LVMLOCKD_SOCKET DEFAULT_RUN_DIR "/lvmlockd.socket"
+#define LVMLOCKD_ADOPT_FILE DEFAULT_RUN_DIR "/lvmlockd.adopt"
 
 /* Wrappers to open/close connection */
 
@@ -22,9 +23,9 @@ static inline daemon_handle lvmlockd_open(const char *sock)
 	daemon_info lvmlockd_info = {
 		.path = "lvmlockd",
 		.socket = sock ?: LVMLOCKD_SOCKET,
+		.autostart = 0,
 		.protocol = "lvmlockd",
 		.protocol_version = 1,
-		.autostart = 0
 	};
 
 	return daemon_open(lvmlockd_info);
@@ -32,7 +33,7 @@ static inline daemon_handle lvmlockd_open(const char *sock)
 
 static inline void lvmlockd_close(daemon_handle h)
 {
-	return daemon_close(h);
+	daemon_close(h);
 }
 
 /*

daemons/lvmlockd/lvmlockd-core.c

@@ -38,6 +38,8 @@
 #define EXTERN
 #include "lvmlockd-internal.h"
 
+static int str_to_mode(const char *str);
+
 /*
  * Basic operation of lvmlockd
  *
@@ -142,6 +144,8 @@ static const char *lvmlockd_protocol = "lvmlockd";
 static const int lvmlockd_protocol_version = 1;
 static int daemon_quit;
 static int adopt_opt;
+static uint32_t adopt_update_count;
+static const char *adopt_file;
 
 /*
  * We use a separate socket for dumping daemon info.
@@ -811,6 +815,146 @@ int version_from_args(char *args, unsigned int *major, unsigned int *minor, unsi
 	return 0;
 }
 
+/*
+ * Write new info when a command exits if that command has acquired a new LV
+ * lock.  If the command has released an LV lock we don't bother updating the
+ * info.  When adopting, we eliminate any LV lock adoptions if there is no dm
+ * device for that LV.  If lvmlockd is terminated after acquiring but before
+ * writing this file, those LV locks would not be adopted on restart.
+ */
+
+#define ADOPT_VERSION_MAJOR 1
+#define ADOPT_VERSION_MINOR 0
+
+static void write_adopt_file(void)
+{
+	struct lockspace *ls;
+	struct resource *r;
+	struct lock *lk;
+	time_t t;
+	FILE *fp;
+
+	if (!(fp = fopen(adopt_file, "w")))
+		return;
+
+	adopt_update_count++;
+
+	t = time(NULL);
+	fprintf(fp, "lvmlockd adopt_version %u.%u pid %d updates %u %s",
+		ADOPT_VERSION_MAJOR, ADOPT_VERSION_MINOR, getpid(), adopt_update_count, ctime(&t));
+
+	pthread_mutex_lock(&lockspaces_mutex);
+	list_for_each_entry(ls, &lockspaces, list) {
+		if (ls->lm_type == LD_LM_DLM && !strcmp(ls->name, gl_lsname_dlm))
+			continue;
+		fprintf(fp, "VG: %38s %s %s %s\n",
+			ls->vg_uuid, ls->vg_name, lm_str(ls->lm_type), ls->vg_args);
+		list_for_each_entry(r, &ls->resources, list) {
+			if (r->type != LD_RT_LV)
+				continue;
+			if ((r->mode != LD_LK_EX) && (r->mode != LD_LK_SH))
+				continue;
+			list_for_each_entry(lk, &r->locks, list) {
+				fprintf(fp, "LV: %38s %s %s %s %u\n",
+					ls->vg_uuid, r->name, r->lv_args, mode_str(r->mode), r->version);
+			}
+		}
+	}
+	pthread_mutex_unlock(&lockspaces_mutex);
+
+	fflush(fp);
+	fclose(fp);
+}
+
+static int read_adopt_file(struct list_head *vg_lockd)
+{
+	char adopt_line[512];
+	char vg_uuid[72];
+	char lm_type_str[16];
+	char mode[8];
+	struct lockspace *ls = NULL, *ls2;
+	struct resource *r;
+	FILE *fp;
+
+	if (MAX_ARGS != 64 || MAX_NAME != 64)
+		return -1;
+
+	if (!(fp = fopen(adopt_file, "r")))
+		return 0;
+
+	while (fgets(adopt_line, sizeof(adopt_line), fp)) {
+		if (adopt_line[0] == '#')
+			continue;
+		else if (!strncmp(adopt_line, "lvmlockd", 8)) {
+			unsigned int v_major = 0, v_minor = 0;
+			if ((sscanf(adopt_line, "lvmlockd adopt_version %u.%u", &v_major, &v_minor) != 2) ||
+			    (v_major != ADOPT_VERSION_MAJOR))
+				goto fail;
+
+		} else if (!strncmp(adopt_line, "VG:", 3)) {
+			if (!(ls = alloc_lockspace()))
+				goto fail;
+
+			memset(vg_uuid, 0, sizeof(vg_uuid));
+			memset(lm_type_str, 0, sizeof(lm_type_str));
+
+			if (sscanf(adopt_line, "VG: %63s %64s %15s %64s",
+				   vg_uuid, ls->vg_name, lm_type_str, ls->vg_args) != 4) {
+				goto fail;
+			}
+
+			memcpy(ls->vg_uuid, vg_uuid, 64);
+
+			if ((ls->lm_type = str_to_lm(lm_type_str)) < 0)
+				goto fail;
+
+			list_add(&ls->list, vg_lockd);
+
+		} else if (!strncmp(adopt_line, "LV:", 3)) {
+			if (!(r = alloc_resource()))
+				goto fail;
+
+			r->type = LD_RT_LV;
+
+			memset(vg_uuid, 0, sizeof(vg_uuid));
+			memset(mode, 0, sizeof(mode));
+
+			if (sscanf(adopt_line, "LV: %64s %64s %s %7s %u",
+				   vg_uuid, r->name, r->lv_args, mode, &r->version) != 5) {
+				goto fail;
+			}
+
+			if ((r->adopt_mode = str_to_mode(mode)) == LD_LK_IV)
+				goto fail;
+
+			if (ls && !memcmp(ls->vg_uuid, vg_uuid, 64)) {
+				list_add(&r->list, &ls->resources);
+				r = NULL;
+			} else {
+				list_for_each_entry(ls2, vg_lockd, list) {
+					if (memcmp(ls2->vg_uuid, vg_uuid, 64))
+						continue;
+					list_add(&r->list, &ls2->resources);
+					r = NULL;
+					break;
+				}
+			}
+
+			if (r) {
+				log_error("No lockspace found for resource %s vg_uuid %s", r->name, vg_uuid);
+				goto fail;
+			}
+		}
+	}
+
+	fclose(fp);
+	return 0;
+
+fail:
+	fclose(fp);
+	return -1;
+}
+
 /*
  * These are few enough that arrays of function pointers can
  * be avoided.
@@ -4689,6 +4833,7 @@ static void *client_thread_main(void *arg_in)
 	struct client *cl;
 	struct action *act;
 	struct action *act_un;
+	uint32_t lock_acquire_count = 0, lock_acquire_written = 0;
 	int rv;
 
 	while (1) {
@@ -4720,6 +4865,9 @@ static void *client_thread_main(void *arg_in)
 				rv = -1;
 			}
 
+			if (act->flags & LD_AF_LV_LOCK)
+				lock_acquire_count++;
+
 			/*
 			 * The client failed after we acquired an LV lock for
 			 * it, but before getting this reply saying it's done.
@@ -4741,6 +4889,11 @@ static void *client_thread_main(void *arg_in)
 			continue;
 		}
 
+		if (adopt_opt && (lock_acquire_count > lock_acquire_written)) {
+			lock_acquire_written = lock_acquire_count;
+			write_adopt_file();
+		}
+
 		/*
 		 * Queue incoming actions for lockspace threads
 		 */
@@ -4814,6 +4967,8 @@ static void *client_thread_main(void *arg_in)
 			pthread_mutex_unlock(&client_mutex);
 	}
 out:
+	if (adopt_opt && lock_acquire_written)
+		unlink(adopt_file);
 	return NULL;
 }
 
@@ -4846,180 +5001,6 @@ static void close_client_thread(void)
 		log_error("pthread_join client_thread error %d", perrno);
 }
 
-/*
- * Get a list of all VGs with a lockd type (sanlock|dlm).
- * We'll match this list against a list of existing lockspaces that are
- * found in the lock manager.
- *
- * For each of these VGs, also create a struct resource on ls->resources to
- * represent each LV in the VG that uses a lock.  For each of these LVs
- * that are active, we'll attempt to adopt a lock.
- */
-
-static int get_lockd_vgs(struct list_head *vg_lockd)
-{
-	/* FIXME: get VGs some other way */
-	return -1;
-#if 0
-	struct list_head update_vgs;
-	daemon_reply reply;
-	struct dm_config_node *cn;
-	struct dm_config_node *metadata;
-	struct dm_config_node *md_cn;
-	struct dm_config_node *lv_cn;
-	struct lockspace *ls, *safe;
-	struct resource *r;
-	const char *vg_name;
-	const char *vg_uuid;
-	const char *lv_uuid;
-	const char *lock_type;
-	const char *lock_args;
-	char find_str_path[PATH_MAX];
-	int rv = 0;
-
-	INIT_LIST_HEAD(&update_vgs);
-
-	reply = send_lvmetad("vg_list", "token = %s", "skip", NULL);
-
-	if (reply.error || strcmp(daemon_reply_str(reply, "response", ""), "OK")) {
-		log_error("vg_list from lvmetad failed %d", reply.error);
-		rv = -EINVAL;
-		goto destroy;
-	}
-
-	if (!(cn = dm_config_find_node(reply.cft->root, "volume_groups"))) {
-		log_error("get_lockd_vgs no vgs");
-		rv = -EINVAL;
-		goto destroy;
-	}
-
-	/* create an update_vgs list of all vg uuids */
-
-	for (cn = cn->child; cn; cn = cn->sib) {
-		vg_uuid = cn->key;
-
-		if (!(ls = alloc_lockspace())) {
-			rv = -ENOMEM;
-			break;
-		}
-
-		strncpy(ls->vg_uuid, vg_uuid, 64);
-		list_add_tail(&ls->list, &update_vgs);
-		log_debug("get_lockd_vgs %s", vg_uuid);
-	}
- destroy:
-	daemon_reply_destroy(reply);
-
-	if (rv < 0)
-		goto out;
-
-	/* get vg_name and lock_type for each vg uuid entry in update_vgs */
-
-	list_for_each_entry(ls, &update_vgs, list) {
-		reply = send_lvmetad("vg_lookup",
-				     "token = %s", "skip",
-				     "uuid = %s", ls->vg_uuid,
-				     NULL);
-
-		if (reply.error || strcmp(daemon_reply_str(reply, "response", ""), "OK")) {
-			log_error("vg_lookup from lvmetad failed %d", reply.error);
-			rv = -EINVAL;
-			goto next;
-		}
-
-		vg_name = daemon_reply_str(reply, "name", NULL);
-		if (!vg_name) {
-			log_error("get_lockd_vgs %s no name", ls->vg_uuid);
-			rv = -EINVAL;
-			goto next;
-		}
-
-		strncpy(ls->vg_name, vg_name, MAX_NAME);
-
-		metadata = dm_config_find_node(reply.cft->root, "metadata");
-		if (!metadata) {
-			log_error("get_lockd_vgs %s name %s no metadata",
-				  ls->vg_uuid, ls->vg_name);
-			rv = -EINVAL;
-			goto next;
-		}
-
-		lock_type = dm_config_find_str(metadata, "metadata/lock_type", NULL);
-		ls->lm_type = str_to_lm(lock_type);
-
-		if ((ls->lm_type != LD_LM_SANLOCK) && (ls->lm_type != LD_LM_DLM)) {
-			log_debug("get_lockd_vgs %s not lockd type", ls->vg_name);
-			continue;
-		}
-
-		lock_args = dm_config_find_str(metadata, "metadata/lock_args", NULL);
-		if (lock_args)
-			strncpy(ls->vg_args, lock_args, MAX_ARGS);
-
-		log_debug("get_lockd_vgs %s lock_type %s lock_args %s",
-			  ls->vg_name, lock_type, lock_args ?: "none");
-
-		/*
-		 * Make a record (struct resource) of each lv that uses a lock.
-		 * For any lv that uses a lock, we'll check if the lv is active
-		 * and if so try to adopt a lock for it.
-		 */
-
-		for (md_cn = metadata->child; md_cn; md_cn = md_cn->sib) {
-			if (strcmp(md_cn->key, "logical_volumes"))
-				continue;
-
-			for (lv_cn = md_cn->child; lv_cn; lv_cn = lv_cn->sib) {
-				snprintf(find_str_path, PATH_MAX, "%s/lock_args", lv_cn->key);
-				lock_args = dm_config_find_str(lv_cn, find_str_path, NULL);
-				if (!lock_args)
-					continue;
-
-				snprintf(find_str_path, PATH_MAX, "%s/id", lv_cn->key);
-				lv_uuid = dm_config_find_str(lv_cn, find_str_path, NULL);
-
-				if (!lv_uuid) {
-					log_error("get_lock_vgs no lv id for name %s", lv_cn->key);
-					continue;
-				}
-
-				if (!(r = alloc_resource())) {
-					rv = -ENOMEM;
-					goto next;
-				}
-
-				r->use_vb = 0;
-				r->type = LD_RT_LV;
-				strncpy(r->name, lv_uuid, MAX_NAME);
-				if (lock_args)
-					strncpy(r->lv_args, lock_args, MAX_ARGS);
-				list_add_tail(&r->list, &ls->resources);
-				log_debug("get_lockd_vgs %s lv %s %s (name %s)",
-					  ls->vg_name, r->name, lock_args ? lock_args : "", lv_cn->key);
-			}
-		}
- next:
-		daemon_reply_destroy(reply);
-
-		if (rv < 0)
-			break;
-	}
-out:
-	/* Return lockd VG's on the vg_lockd list. */
-
-	list_for_each_entry_safe(ls, safe, &update_vgs, list) {
-		list_del(&ls->list);
-
-		if ((ls->lm_type == LD_LM_SANLOCK) || (ls->lm_type == LD_LM_DLM))
-			list_add_tail(&ls->list, vg_lockd);
-		else
-			free(ls);
-	}
-
-	return rv;
-#endif
-}
-
 static char _dm_uuid[DM_UUID_LEN];
 
 static char *get_dm_uuid(char *dm_name)
@@ -5236,9 +5217,9 @@ static void adopt_locks(void)
 	INIT_LIST_HEAD(&to_unlock);
 
 	/*
-	 * Get list of lockspaces from lock managers.
-	 * Get list of VGs from lvmetad with a lockd type.
-	 * Get list of active lockd type LVs from /dev.
+	 * Get list of lockspaces from currently running lock managers.
+	 * Get list of shared VGs from file written by prior lvmlockd.
+	 * Get list of active LVs (in the shared VGs) from the file.
 	 */
 
 	if (lm_support_dlm() && lm_is_running_dlm()) {
@@ -5262,12 +5243,17 @@ static void adopt_locks(void)
 	 * Adds a struct lockspace to vg_lockd for each lockd VG.
 	 * Adds a struct resource to ls->resources for each LV.
 	 */
-	rv = get_lockd_vgs(&vg_lockd);
+	rv = read_adopt_file(&vg_lockd);
 	if (rv < 0) {
-		log_error("adopt_locks get_lockd_vgs failed");
+		log_error("adopt_locks read_adopt_file failed");
 		goto fail;
 	}
 
+	if (list_empty(&vg_lockd)) {
+		log_debug("No lockspaces in adopt file");
+		return;
+	}
+
 	/*
 	 * For each resource on each lockspace, check if the
 	 * corresponding LV is active.  If so, leave the
@@ -5506,7 +5492,7 @@ static void adopt_locks(void)
 				goto fail;
 			act->op = LD_OP_LOCK;
 			act->rt = LD_RT_LV;
-			act->mode = LD_LK_EX;
+			act->mode = r->adopt_mode;
 			act->flags = (LD_AF_ADOPT | LD_AF_PERSISTENT);
 			act->client_id = INTERNAL_CLIENT_ID;
 			act->lm_type = ls->lm_type;
@@ -5604,8 +5590,9 @@ static void adopt_locks(void)
 			 * Adopt failed because the orphan has a different mode
 			 * than initially requested.  Repeat the lock-adopt operation
 			 * with the other mode.  N.B. this logic depends on first
-			 * trying sh then ex for GL/VG locks, and ex then sh for
-			 * LV locks.
+			 * trying sh then ex for GL/VG locks; for LV locks the mode
+			 * from the adopt file is tried first, the alternate
+			 * (if the mode in adopt file was wrong somehow.)
 			 */
 
 			if ((act->rt != LD_RT_LV) && (act->mode == LD_LK_SH)) {
@@ -5613,9 +5600,12 @@ static void adopt_locks(void)
 				act->mode = LD_LK_EX;
 				rv = add_lock_action(act);
 
-			} else if ((act->rt == LD_RT_LV) && (act->mode == LD_LK_EX)) {
-				/* LV locks: attempt to adopt sh after ex failed. */
-				act->mode = LD_LK_SH;
+			} else if (act->rt == LD_RT_LV) {
+				/* LV locks: attempt to adopt the other mode. */
+				if (act->mode == LD_LK_EX)
+					act->mode = LD_LK_SH;
+				else if (act->mode == LD_LK_SH)
+					act->mode = LD_LK_EX;
 				rv = add_lock_action(act);
 
 			} else {
@@ -5750,10 +5740,13 @@ static void adopt_locks(void)
 	if (count_start_fail || count_adopt_fail)
 		goto fail;
 
+	unlink(adopt_file);
+	write_adopt_file();
 	log_debug("adopt_locks done");
 	return;
 
 fail:
+	unlink(adopt_file);
 	log_error("adopt_locks failed, reset host");
 }
 
@@ -6028,6 +6021,8 @@ static void usage(char *prog, FILE *file)
 	fprintf(file, "        Set path to the pid file. [%s]\n", LVMLOCKD_PIDFILE);
 	fprintf(file, "  --socket-path | -s <path>\n");
 	fprintf(file, "        Set path to the socket to listen on. [%s]\n", LVMLOCKD_SOCKET);
+	fprintf(file, "  --adopt-file <path>\n");
+	fprintf(file, "        Set path to the adopt file. [%s]\n", LVMLOCKD_ADOPT_FILE);
 	fprintf(file, "  --syslog-priority | -S err|warning|debug\n");
 	fprintf(file, "        Write log messages from this level up to syslog. [%s]\n", _syslog_num_to_name(LOG_SYSLOG_PRIO));
 	fprintf(file, "  --gl-type | -g <str>\n");
@@ -6045,14 +6040,14 @@ static void usage(char *prog, FILE *file)
 int main(int argc, char *argv[])
 {
 	daemon_state ds = {
-		.daemon_main = main_loop,
-		.daemon_init = NULL,
-		.daemon_fini = NULL,
+		.name = "lvmlockd",
 		.pidfile = getenv("LVM_LVMLOCKD_PIDFILE"),
 		.socket_path = getenv("LVM_LVMLOCKD_SOCKET"),
 		.protocol = lvmlockd_protocol,
 		.protocol_version = lvmlockd_protocol_version,
-		.name = "lvmlockd",
+		.daemon_init = NULL,
+		.daemon_fini = NULL,
+		.daemon_main = main_loop,
 	};
 
 	static struct option long_options[] = {
@@ -6063,6 +6058,7 @@ int main(int argc, char *argv[])
 		{"daemon-debug",    no_argument,       0, 'D' },
 		{"pid-file",        required_argument, 0, 'p' },
 		{"socket-path",     required_argument, 0, 's' },
+		{"adopt-file",      required_argument, 0, 128 },
 		{"gl-type",         required_argument, 0, 'g' },
 		{"host-id",         required_argument, 0, 'i' },
 		{"host-id-file",    required_argument, 0, 'F' },
@@ -6085,6 +6081,9 @@ int main(int argc, char *argv[])
 		switch (c) {
 		case '0':
 			break;
+		case 128:
+			adopt_file = strdup(optarg);
+			break;
 		case 'h':
 			usage(argv[0], stdout);
 			exit(EXIT_SUCCESS);
@@ -6146,6 +6145,9 @@ int main(int argc, char *argv[])
 	if (!ds.socket_path)
 		ds.socket_path = LVMLOCKD_SOCKET;
 
+	if (!adopt_file)
+		adopt_file = LVMLOCKD_ADOPT_FILE;
+
 	/* runs daemon_main/main_loop */
 	daemon_start(ds);
 

daemons/lvmlockd/lvmlockd-dlm.c

@@ -398,12 +398,18 @@ static int lm_adopt_dlm(struct lockspace *ls, struct resource *r, int ld_mode,
 			  (void *)1, (void *)1, (void *)1,
 			  NULL, NULL);
 
-	if (rv == -1 && errno == -EAGAIN) {
+	if (rv == -1 && (errno == EAGAIN)) {
 		log_debug("S %s R %s adopt_dlm adopt mode %d try other mode",
 			  ls->name, r->name, ld_mode);
 		rv = -EUCLEAN;
 		goto fail;
 	}
+	if (rv == -1 && (errno == ENOENT)) {
+		log_debug("S %s R %s adopt_dlm adopt mode %d no lock",
+			  ls->name, r->name, ld_mode);
+		rv = -ENOENT;
+		goto fail;
+	}
 	if (rv < 0) {
 		log_debug("S %s R %s adopt_dlm mode %d flags %x error %d errno %d",
 			  ls->name, r->name, mode, flags, rv, errno);

daemons/lvmlockd/lvmlockd-internal.h

@@ -11,6 +11,8 @@
 #ifndef _LVM_LVMLOCKD_INTERNAL_H
 #define _LVM_LVMLOCKD_INTERNAL_H
 
+#include "base/memory/container_of.h"
+
 #define MAX_NAME 64
 #define MAX_ARGS 64
 
@@ -145,6 +147,7 @@ struct resource {
 	char name[MAX_NAME+1];		/* vg name or lv name */
 	int8_t type;			/* resource type LD_RT_ */
 	int8_t mode;
+	int8_t adopt_mode;
 	unsigned int sh_count;		/* number of sh locks on locks list */
 	uint32_t version;
 	uint32_t last_client_id;	/* last client_id to lock or unlock resource */
@@ -155,7 +158,7 @@ struct resource {
 	struct list_head locks;
 	struct list_head actions;
 	char lv_args[MAX_ARGS+1];
-	char lm_data[0];		/* lock manager specific data */
+	char lm_data[];			/* lock manager specific data */
 };
 
 #define LD_LF_PERSISTENT 0x00000001
@@ -216,10 +219,6 @@ struct val_blk {
 /* lm_unlock flags */
 #define LMUF_FREE_VG 0x00000001
 
-#define container_of(ptr, type, member) ({                      \
-	const typeof( ((type *)0)->member ) *__mptr = (ptr);    \
-	(type *)( (char *)__mptr - offsetof(type,member) );})
-
 static inline void INIT_LIST_HEAD(struct list_head *list)
 {
 	list->next = list;

daemons/lvmpolld/lvmpolld-cmd-utils.c

@@ -92,6 +92,12 @@ const char **cmdargv_ctr(const struct lvmpolld_lv *pdlv, const char *lvm_binary,
 	if (!add_to_cmd_arr(&cmd_argv, "-An", &i))
 		goto err;
 
+	if (pdlv->devicesfile) {
+		if (!add_to_cmd_arr(&cmd_argv, "--devicesfile", &i) ||
+		    !add_to_cmd_arr(&cmd_argv, pdlv->devicesfile, &i))
+			goto err;
+	}
+
 	/* terminating NULL */
 	if (!add_to_cmd_arr(&cmd_argv, NULL, &i))
 		goto err;

daemons/lvmpolld/lvmpolld-core.c

@@ -555,14 +555,15 @@ static struct lvmpolld_lv *construct_pdlv(request req, struct lvmpolld_state *ls
 				     const char *interval, const char *id,
 				     const char *vgname, const char *lvname,
 				     const char *sysdir, enum poll_type type,
-				     unsigned abort_polling, unsigned uinterval)
+				     unsigned abort_polling, unsigned uinterval,
+				     const char *devicesfile)
 {
 	const char **cmdargv, **cmdenvp;
 	struct lvmpolld_lv *pdlv;
 	unsigned handle_missing_pvs = daemon_request_int(req, LVMPD_PARM_HANDLE_MISSING_PVS, 0);
 
 	pdlv = pdlv_create(ls, id, vgname, lvname, sysdir, type,
-			   interval, uinterval, pdst);
+			   interval, uinterval, pdst, devicesfile);
 
 	if (!pdlv) {
 		ERROR(ls, "%s: %s", PD_LOG_PREFIX, "failed to create internal LV data structure.");
@@ -621,6 +622,7 @@ static response poll_init(client_handle h, struct lvmpolld_state *ls, request re
 	const char *lvname = daemon_request_str(req, LVMPD_PARM_LVNAME, NULL);
 	const char *vgname = daemon_request_str(req, LVMPD_PARM_VGNAME, NULL);
 	const char *sysdir = daemon_request_str(req, LVMPD_PARM_SYSDIR, NULL);
+	const char *devicesfile = daemon_request_str(req, LVMPD_PARM_DEVICESFILE, NULL);
 	unsigned abort_polling = daemon_request_int(req, LVMPD_PARM_ABORT, 0);
 
 	assert(type < POLL_TYPE_MAX);
@@ -680,7 +682,7 @@ static response poll_init(client_handle h, struct lvmpolld_state *ls, request re
 		pdlv->init_rq_count++; /* safe. protected by store lock */
 	} else {
 		pdlv = construct_pdlv(req, ls, pdst, interval, id, vgname,
-				      lvname, sysdir, type, abort_polling, 2 * uinterval);
+				      lvname, sysdir, type, abort_polling, 2 * uinterval, devicesfile);
 		if (!pdlv) {
 			pdst_unlock(pdst);
 			free(id);

daemons/lvmpolld/lvmpolld-data-utils.c

@@ -93,11 +93,13 @@ struct lvmpolld_lv *pdlv_create(struct lvmpolld_state *ls, const char *id,
 			   const char *vgname, const char *lvname,
 			   const char *sysdir, enum poll_type type,
 			   const char *sinterval, unsigned pdtimeout,
-			   struct lvmpolld_store *pdst)
+			   struct lvmpolld_store *pdst,
+			   const char *devicesfile)
 {
 	char *lvmpolld_id = strdup(id), /* copy */
 	     *full_lvname = _construct_full_lvname(vgname, lvname), /* copy */
 	     *lvm_system_dir_env = _construct_lvm_system_dir_env(sysdir); /* copy */
+	char *devicesfile_dup = devicesfile ? strdup(devicesfile) : NULL;
 
 	struct lvmpolld_lv tmp = {
 		.ls = ls,
@@ -105,6 +107,7 @@ struct lvmpolld_lv *pdlv_create(struct lvmpolld_state *ls, const char *id,
 		.lvmpolld_id = lvmpolld_id,
 		.lvid = _get_lvid(lvmpolld_id, sysdir),
 		.lvname = full_lvname,
+		.devicesfile = devicesfile_dup,
 		.lvm_system_dir_env = lvm_system_dir_env,
 		.sinterval = strdup(sinterval), /* copy */
 		.pdtimeout = pdtimeout < MIN_POLLING_TIMEOUT ? MIN_POLLING_TIMEOUT : pdtimeout,
@@ -124,6 +127,7 @@ struct lvmpolld_lv *pdlv_create(struct lvmpolld_state *ls, const char *id,
 	return pdlv;
 
 err:
+	free((void *)devicesfile_dup);
 	free((void *)full_lvname);
 	free((void *)lvmpolld_id);
 	free((void *)lvm_system_dir_env);
@@ -136,6 +140,7 @@ err:
 void pdlv_destroy(struct lvmpolld_lv *pdlv)
 {
 	free((void *)pdlv->lvmpolld_id);
+	free((void *)pdlv->devicesfile);
 	free((void *)pdlv->lvname);
 	free((void *)pdlv->sinterval);
 	free((void *)pdlv->lvm_system_dir_env);

daemons/lvmpolld/lvmpolld-data-utils.h

@@ -49,6 +49,7 @@ struct lvmpolld_lv {
 	const enum poll_type type;
 	const char *const lvid;
 	const char *const lvmpolld_id;
+	const char *const devicesfile;
 	const char *const lvname; /* full vg/lv name */
 	const unsigned pdtimeout; /* in seconds */
 	const char *const sinterval;
@@ -101,7 +102,8 @@ struct lvmpolld_lv *pdlv_create(struct lvmpolld_state *ls, const char *id,
 			   const char *vgname, const char *lvname,
 			   const char *sysdir, enum poll_type type,
 			   const char *sinterval, unsigned pdtimeout,
-			   struct lvmpolld_store *pdst);
+			   struct lvmpolld_store *pdst,
+			   const char *devicesfile);
 
 /* only call with appropriate struct lvmpolld_store lock held */
 void pdlv_destroy(struct lvmpolld_lv *pdlv);

daemons/lvmpolld/lvmpolld-protocol.h

@@ -35,6 +35,7 @@
 #define LVMPD_PARM_SYSDIR		"sysdir"
 #define LVMPD_PARM_VALUE		"value" /* either retcode or signal value */
 #define LVMPD_PARM_VGNAME		"vgname"
+#define LVMPD_PARM_DEVICESFILE		"devicesfile"
 
 #define LVMPD_RESP_FAILED	"failed"
 #define LVMPD_RESP_FINISHED	"finished"

device_mapper/all.h

@@ -164,20 +164,20 @@ struct dm_info {
 struct dm_deps {
 	uint32_t count;
 	uint32_t filler;
-	uint64_t device[0];
+	uint64_t device[];
 };
 
 struct dm_names {
 	uint64_t dev;
 	uint32_t next;		/* Offset to next struct from start of this struct */
-	char name[0];
+	char name[];
 };
 
 struct dm_versions {
 	uint32_t next;		/* Offset to next struct from start of this struct */
 	uint32_t version[3];
 
-	char name[0];
+	char name[];
 };
 
 int dm_get_library_version(char *version, size_t size);
@@ -234,6 +234,7 @@ int dm_task_suppress_identical_reload(struct dm_task *dmt);
 int dm_task_secure_data(struct dm_task *dmt);
 int dm_task_retry_remove(struct dm_task *dmt);
 int dm_task_deferred_remove(struct dm_task *dmt);
+void dm_task_skip_reload_params_compare(struct dm_task *dmt);
 
 /*
  * Record timestamp immediately after the ioctl returns.
@@ -383,7 +384,7 @@ int dm_get_status_cache(struct dm_pool *mem, const char *params,
 			struct dm_status_cache **status);
 
 struct dm_status_writecache {
-	uint32_t error;
+	uint64_t error;
 	uint64_t total_blocks;
 	uint64_t free_blocks;
 	uint64_t writeback_blocks;
@@ -950,6 +951,8 @@ struct writecache_settings {
 	uint64_t autocommit_time; /* in milliseconds */
 	uint32_t fua;
 	uint32_t nofua;
+	uint32_t cleaner;
+	uint32_t max_age;
 
 	/*
 	 * Allow an unrecognized key and its val to be passed to the kernel for
@@ -969,6 +972,8 @@ struct writecache_settings {
 	unsigned autocommit_time_set:1;
 	unsigned fua_set:1;
 	unsigned nofua_set:1;
+	unsigned cleaner_set:1;
+	unsigned max_age_set:1;
 };
 
 int dm_tree_node_add_writecache_target(struct dm_tree_node *node,
@@ -982,14 +987,14 @@ int dm_tree_node_add_writecache_target(struct dm_tree_node *node,
 struct integrity_settings {
 	char mode[8];
 	uint32_t tag_size;
-	const char *internal_hash;
+	uint32_t block_size;       /* optional table param always set by lvm */
+	const char *internal_hash; /* optional table param always set by lvm */
 
 	uint32_t journal_sectors;
 	uint32_t interleave_sectors;
 	uint32_t buffer_sectors;
 	uint32_t journal_watermark;
 	uint32_t commit_time;
-	uint32_t block_size;
 	uint32_t bitmap_flush_interval;
 	uint64_t sectors_per_bit;
 
@@ -998,7 +1003,6 @@ struct integrity_settings {
 	unsigned buffer_sectors_set:1;
 	unsigned journal_watermark_set:1;
 	unsigned commit_time_set:1;
-	unsigned block_size_set:1;
 	unsigned bitmap_flush_interval_set:1;
 	unsigned sectors_per_bit_set:1;
 };
@@ -1007,13 +1011,15 @@ int dm_tree_node_add_integrity_target(struct dm_tree_node *node,
 				uint64_t size,
 				const char *origin_uuid,
 				const char *meta_uuid,
-				struct integrity_settings *settings);
+				struct integrity_settings *settings,
+				int recalculate);
 
 /*
  * VDO target
  */
 int dm_tree_node_add_vdo_target(struct dm_tree_node *node,
 				uint64_t size,
+				const char *vdo_pool_name,
 				const char *data_uuid,
 				uint64_t data_size,
 				const struct dm_vdo_target_params *param);
@@ -1066,10 +1072,10 @@ int dm_tree_node_add_replicator_dev_target(struct dm_tree_node *node,
 #define DM_THIN_MIN_DATA_BLOCK_SIZE (UINT32_C(128))
 #define DM_THIN_MAX_DATA_BLOCK_SIZE (UINT32_C(2097152))
 /*
- * Max supported size for thin pool  metadata device (17112760320 bytes)
- * Limitation is hardcoded into the kernel and bigger device size
- * is not accepted.
+ * Max supported size for thin pool metadata device (17045913600 bytes)
  * drivers/md/dm-thin-metadata.h THIN_METADATA_MAX_SECTORS
+ * But here DM_THIN_MAX_METADATA_SIZE got defined incorrectly
+ * Correct size is (UINT64_C(255) * ((1 << 14) - 64) * (4096 / (1 << 9)))
  */
 #define DM_THIN_MAX_METADATA_SIZE   (UINT64_C(255) * (1 << 14) * (4096 / (1 << 9)) - 256 * 1024)
 
@@ -1082,6 +1088,16 @@ int dm_tree_node_add_thin_pool_target(struct dm_tree_node *node,
 				      uint64_t low_water_mark,
 				      unsigned skip_block_zeroing);
 
+int dm_tree_node_add_thin_pool_target_v1(struct dm_tree_node *node,
+					 uint64_t size,
+					 uint64_t transaction_id,
+					 const char *metadata_uuid,
+					 const char *pool_uuid,
+					 uint32_t data_block_size,
+					 uint64_t low_water_mark,
+					 unsigned skip_block_zeroing,
+					 unsigned crop_metadata);
+
 /* Supported messages for thin provision target */
 typedef enum {
 	DM_THIN_MESSAGE_CREATE_SNAP,		/* device_id, origin_id */
@@ -1312,7 +1328,7 @@ int dm_bit_get_next(dm_bitset_t bs, int last_bit);
 int dm_bit_get_last(dm_bitset_t bs);
 int dm_bit_get_prev(dm_bitset_t bs, int last_bit);
 
-#define DM_BITS_PER_INT (sizeof(int) * CHAR_BIT)
+#define DM_BITS_PER_INT ((unsigned)sizeof(int) * CHAR_BIT)
 
 #define dm_bit(bs, i) \
    ((bs)[((i) / DM_BITS_PER_INT) + 1] & (0x1 << ((i) & (DM_BITS_PER_INT - 1))))

device_mapper/ioctl/libdm-iface.c

@@ -205,7 +205,7 @@ static int _get_proc_number(const char *file, const char *name,
 	}
 
 	while (getline(&line, &len, fl) != -1) {
-		if (sscanf(line, "%d %255s\n", &num, &nm[0]) == 2) {
+		if (sscanf(line, "%u %255s\n", &num, &nm[0]) == 2) {
 			if (!strcmp(name, nm)) {
 				if (number) {
 					*number = num;
@@ -805,6 +805,11 @@ int dm_task_suppress_identical_reload(struct dm_task *dmt)
 	return 1;
 }
 
+void dm_task_skip_reload_params_compare(struct dm_task *dmt)
+{
+	dmt->skip_reload_params_compare = 1;
+}
+
 int dm_task_set_add_node(struct dm_task *dmt, dm_add_node_t add_node)
 {
 	switch (add_node) {
@@ -1575,11 +1580,36 @@ static int _reload_with_suppression_v4(struct dm_task *dmt)
 		len = strlen(t2->params);
 		while (len-- > 0 && t2->params[len] == ' ')
 			t2->params[len] = '\0';
-		if ((t1->start != t2->start) ||
-		    (t1->length != t2->length) ||
-		    (strcmp(t1->type, t2->type)) ||
-		    (strcmp(t1->params, t2->params)))
+
+		if (t1->start != t2->start) {
+			log_debug("reload %u:%u diff start %llu %llu type %s %s", task->major, task->minor,
+				   (unsigned long long)t1->start, (unsigned long long)t2->start, t1->type, t2->type);
 			goto no_match;
+		}
+		if (t1->length != t2->length) {
+			log_debug("reload %u:%u diff length %llu %llu type %s %s", task->major, task->minor,
+				  (unsigned long long)t1->length, (unsigned long long)t2->length, t1->type, t2->type);
+			goto no_match;
+		}
+		if (strcmp(t1->type, t2->type)) {
+			log_debug("reload %u:%u diff type %s %s", task->major, task->minor, t1->type, t2->type);
+			goto no_match;
+		}
+		if (strcmp(t1->params, t2->params)) {
+			if (dmt->skip_reload_params_compare) {
+				log_debug("reload %u:%u diff params ignore for type %s",
+					  task->major, task->minor, t1->type);
+				log_debug("reload params1 %s", t1->params);
+				log_debug("reload params2 %s", t2->params);
+			} else {
+				log_debug("reload %u:%u diff params for type %s",
+					  task->major, task->minor, t1->type);
+				log_debug("reload params1 %s", t1->params);
+				log_debug("reload params2 %s", t2->params);
+				goto no_match;
+			}
+		}
+
 		t1 = t1->next;
 		t2 = t2->next;
 	}

device_mapper/ioctl/libdm-targets.h

@@ -59,6 +59,7 @@ struct dm_task {
 	int skip_lockfs;
 	int query_inactive_table;
 	int suppress_identical_reload;
+	int skip_reload_params_compare;
 	dm_add_node_t add_node;
 	uint64_t existing_table_size;
 	int cookie_set;

device_mapper/libdm-common.c

@@ -512,7 +512,7 @@ int unmangle_string(const char *str, const char *str_name, size_t len,
 	int strict = mode != DM_STRING_MANGLING_NONE;
 	char str_rest[DM_NAME_LEN];
 	size_t i, j;
-	int code;
+	unsigned int code;
 	int r = 0;
 
 	if (!str || !buf)
@@ -1445,7 +1445,7 @@ struct node_op_parms {
 	char *old_name;
 	int warn_if_udev_failed;
 	unsigned rely_on_udev;
-	char names[0];
+	char names[];
 };
 
 static void _store_str(char **pos, char **ptr, const char *str)

device_mapper/libdm-deptree.c

@@ -227,6 +227,7 @@ struct load_segment {
 	uint64_t integrity_data_sectors;		/* integrity (provided_data_sectors) */
 	struct dm_tree_node *integrity_meta_node;	/* integrity */
 	struct integrity_settings integrity_settings;	/* integrity */
+	int integrity_recalculate;			/* integrity */
 };
 
 /* Per-device properties */
@@ -273,6 +274,16 @@ struct load_properties {
 	 */
 	unsigned delay_resume_if_extended;
 
+	/*
+	 * When comparing table lines to decide if a reload is
+	 * needed, ignore any differences betwen the lvm device
+	 * params and the kernel-reported device params.
+	 * dm-integrity reports many internal parameters on the
+	 * table line when lvm does not explicitly set them,
+	 * causing lvm and the kernel to have differing params.
+	 */
+	unsigned skip_reload_params_compare;
+
 	/*
 	 * Call node_send_messages(), set to 2 if there are messages
 	 * When != 0, it validates matching transaction id, thus thin-pools
@@ -1578,8 +1589,37 @@ static int _thin_pool_node_message(struct dm_tree_node *dnode, struct thin_messa
 	}
 
 	if (!_node_message(dnode->info.major, dnode->info.minor,
-			   tm->expected_errno, buf))
-		return_0;
+			   tm->expected_errno, buf)) {
+		switch (m->type) {
+		case DM_THIN_MESSAGE_CREATE_SNAP:
+		case DM_THIN_MESSAGE_CREATE_THIN:
+			if (errno == EEXIST) {
+				/*
+				 * ATM errno from ioctl() is preserved through code error path chain
+				 * If this would ever change, another way need to be used to
+				 * obtain result from failed DM message
+				 */
+				log_error("Thin pool %s already contain thin device with device_id %u.",
+					  _node_name(dnode), m->u.m_create_snap.device_id);
+				/*
+				 * TODO:
+				 *
+				 * Give some useful advice how to solve this problem,
+				 * until lvconvert --repair can handle this automatically
+				 */
+				log_error("Manual intervention may be required to remove device dev_id=%u in thin pool metadata.",
+					  m->u.m_create_snap.device_id);
+				log_error("Optionally new thin volume with device_id=%u can be manually added into a volume group.",
+					  m->u.m_create_snap.device_id);
+				log_warn("WARNING: When uncertain how to do this, contact support!");
+				return 0;
+			}
+			/* fall through */
+		default:
+			return_0;
+		}
+
+	}
 
 	return 1;
 }
@@ -1626,6 +1666,15 @@ static int _thin_pool_node_send_messages(struct dm_tree_node *dnode,
 	if (!have_messages || !send)
 		return 1; /* transaction_id is matching */
 
+	if (stp.fail || stp.read_only || stp.needs_check) {
+		log_error("Cannot send messages to thin pool %s%s%s%s.",
+			  _node_name(dnode),
+			  stp.fail ? " in failed state" : "",
+			  stp.read_only ? " with read only metadata" : "",
+			  stp.needs_check ? " which needs check first" : "");
+		return 0;
+	}
+
 	dm_list_iterate_items(tmsg, &seg->thin_messages) {
 		if (!(_thin_pool_node_message(dnode, tmsg)))
 			return_0;
@@ -2087,7 +2136,7 @@ int dm_tree_activate_children(struct dm_tree_node *dnode,
 	return r;
 }
 
-static int _create_node(struct dm_tree_node *dnode)
+static int _create_node(struct dm_tree_node *dnode, struct dm_tree_node *parent)
 {
 	int r = 0;
 	struct dm_task *dmt;
@@ -2136,38 +2185,15 @@ static int _create_node(struct dm_tree_node *dnode)
 				  "Unable to get DM task info for %s.",
 				  dnode->name);
 	}
+
+	if (r)
+		dm_list_add_h(&parent->activated, &dnode->activated_list);
 out:
 	dm_task_destroy(dmt);
 
 	return r;
 }
 
-/*
- * _remove_node
- *
- * This function is only used to remove a DM device that has failed
- * to load any table.
- */
-static int _remove_node(struct dm_tree_node *dnode)
-{
-	if (!dnode->info.exists)
-		return 1;
-
-	if (dnode->info.live_table || dnode->info.inactive_table) {
-		log_error(INTERNAL_ERROR
-			  "_remove_node called on device with loaded table(s).");
-		return 0;
-	}
-
-	if (!_deactivate_node(dnode->name, dnode->info.major, dnode->info.minor,
-			      &dnode->dtree->cookie, dnode->udev_flags, 0)) {
-		log_error("Failed to clean-up device with no table: %s.",
-			  _node_name(dnode));
-		return 0;
-	}
-	return 1;
-}
-
 static int _build_dev_string(char *devbuf, size_t bufsize, struct dm_tree_node *node)
 {
 	if (!dm_format_dev(devbuf, bufsize, node->info.major, node->info.minor)) {
@@ -2356,7 +2382,7 @@ static int _mirror_emit_segment_line(struct dm_task *dmt, struct load_segment *s
 
 	EMIT_PARAMS(pos, " %u ", seg->mirror_area_count);
 
-	if (_emit_areas_line(dmt, seg, params, paramsize, &pos) <= 0)
+	if (!_emit_areas_line(dmt, seg, params, paramsize, &pos))
 		return_0;
 
 	if (handle_errors)
@@ -2558,7 +2584,7 @@ static int _raid_emit_segment_line(struct dm_task *dmt, uint32_t major,
 	/* Print number of metadata/data device pairs */
 	EMIT_PARAMS(pos, " %u", area_count);
 
-	if (_emit_areas_line(dmt, seg, params, paramsize, &pos) <= 0)
+	if (!_emit_areas_line(dmt, seg, params, paramsize, &pos))
 		return_0;
 
 	return 1;
@@ -2659,6 +2685,10 @@ static int _writecache_emit_segment_line(struct dm_task *dmt,
 		count += 1;
 	if (seg->writecache_settings.nofua_set)
 		count += 1;
+	if (seg->writecache_settings.cleaner_set && seg->writecache_settings.cleaner)
+		count += 1;
+	if (seg->writecache_settings.max_age_set)
+		count += 2;
 	if (seg->writecache_settings.new_key)
 		count += 2;
 
@@ -2702,6 +2732,14 @@ static int _writecache_emit_segment_line(struct dm_task *dmt,
 		EMIT_PARAMS(pos, " nofua");
 	}
 
+	if (seg->writecache_settings.cleaner_set && seg->writecache_settings.cleaner) {
+		EMIT_PARAMS(pos, " cleaner");
+	}
+
+	if (seg->writecache_settings.max_age_set) {
+		EMIT_PARAMS(pos, " max_age %u", seg->writecache_settings.max_age);
+	}
+
 	if (seg->writecache_settings.new_key) {
 		EMIT_PARAMS(pos, " %s %s",
 			seg->writecache_settings.new_key,
@@ -2728,11 +2766,14 @@ static int _integrity_emit_segment_line(struct dm_task *dmt,
 	    !_build_dev_string(meta_dev, sizeof(meta_dev), seg->integrity_meta_node))
 		return_0;
 
-	count = 1; /* for internal_hash which we always pass in */
+	count = 3; /* block_size, internal_hash, fix_padding options are always passed */
 
 	if (seg->integrity_meta_node)
 		count++;
 
+	if (seg->integrity_recalculate)
+		count++;
+
 	if (set->journal_sectors_set)
 		count++;
 	if (set->interleave_sectors_set)
@@ -2743,23 +2784,25 @@ static int _integrity_emit_segment_line(struct dm_task *dmt,
 		count++;
 	if (set->commit_time_set)
 		count++;
-	if (set->block_size_set)
-		count++;
 	if (set->bitmap_flush_interval_set)
 		count++;
 	if (set->sectors_per_bit_set)
 		count++;
 
-	EMIT_PARAMS(pos, "%s 0 %u %s %d internal_hash:%s",
+	EMIT_PARAMS(pos, "%s 0 %u %s %d fix_padding block_size:%u internal_hash:%s",
 		    origin_dev,
 		    set->tag_size,
 		    set->mode,
 		    count,
+		    set->block_size,
 		    set->internal_hash);
 
 	if (seg->integrity_meta_node)
 		EMIT_PARAMS(pos, " meta_device:%s", meta_dev);
 
+	if (seg->integrity_recalculate)
+		EMIT_PARAMS(pos, " recalculate");
+
 	if (set->journal_sectors_set)
 		EMIT_PARAMS(pos, " journal_sectors:%u", set->journal_sectors);
 
@@ -2775,9 +2818,6 @@ static int _integrity_emit_segment_line(struct dm_task *dmt,
 	if (set->commit_time_set)
 		EMIT_PARAMS(pos, " commit_time:%u", set->commit_time);
 
-	if (set->block_size_set)
-		EMIT_PARAMS(pos, " block_size:%u", set->block_size);
-
 	if (set->bitmap_flush_interval_set)
 		EMIT_PARAMS(pos, " bitmap_flush_interval:%u", set->bitmap_flush_interval);
 
@@ -2887,7 +2927,6 @@ static int _emit_segment_line(struct dm_task *dmt, uint32_t major,
 			      size_t paramsize)
 {
 	int pos = 0;
-	int r;
 	int target_type_is_raid = 0;
 	char originbuf[DM_FORMAT_DEV_BUFSIZE], cowbuf[DM_FORMAT_DEV_BUFSIZE];
 
@@ -2898,8 +2937,7 @@ static int _emit_segment_line(struct dm_task *dmt, uint32_t major,
 		break;
 	case SEG_MIRRORED:
 		/* Mirrors are pretty complicated - now in separate function */
-		r = _mirror_emit_segment_line(dmt, seg, params, paramsize);
-		if (!r)
+		if (!_mirror_emit_segment_line(dmt, seg, params, paramsize))
 			return_0;
 		break;
 	case SEG_SNAPSHOT:
@@ -2920,7 +2958,7 @@ static int _emit_segment_line(struct dm_task *dmt, uint32_t major,
 		EMIT_PARAMS(pos, "%u %u ", seg->area_count, seg->stripe_size);
 		break;
 	case SEG_VDO:
-		if (!(r = _vdo_emit_segment_line(dmt, seg, params, paramsize)))
+		if (!_vdo_emit_segment_line(dmt, seg, params, paramsize))
 		      return_0;
 		break;
 	case SEG_CRYPT:
@@ -2949,9 +2987,8 @@ static int _emit_segment_line(struct dm_task *dmt, uint32_t major,
 	case SEG_RAID6_LA_6:
 	case SEG_RAID6_RA_6:
 		target_type_is_raid = 1;
-		r = _raid_emit_segment_line(dmt, major, minor, seg, seg_start,
-					    params, paramsize);
-		if (!r)
+		if (!_raid_emit_segment_line(dmt, major, minor, seg, seg_start,
+					     params, paramsize))
 			return_0;
 
 		break;
@@ -2992,10 +3029,9 @@ static int _emit_segment_line(struct dm_task *dmt, uint32_t major,
 	case SEG_CRYPT:
 	case SEG_LINEAR:
 	case SEG_STRIPED:
-		if ((r = _emit_areas_line(dmt, seg, params, paramsize, &pos)) <= 0) {
-			stack;
-			return r;
-		}
+		if (!_emit_areas_line(dmt, seg, params, paramsize, &pos))
+			return_0;
+
 		if (!params[0]) {
 			log_error("No parameters supplied for %s target "
 				  "%u:%u.", _dm_segtypes[seg->type].target,
@@ -3092,6 +3128,9 @@ static int _load_node(struct dm_tree_node *dnode)
 	if (!dm_task_suppress_identical_reload(dmt))
 		log_warn("WARNING: Failed to suppress reload of identical tables.");
 
+	if (dnode->props.skip_reload_params_compare)
+		dm_task_skip_reload_params_compare(dmt);
+
 	if ((r = dm_task_run(dmt))) {
 		r = dm_task_get_info(dmt, &dnode->info);
 		if (r && !dnode->info.inactive_table)
@@ -3110,8 +3149,8 @@ static int _load_node(struct dm_tree_node *dnode)
 			if (!existing_table_size && dnode->props.delay_resume_if_new)
 				dnode->props.size_changed = 0;
 
-			log_debug_activation("Table size changed from %" PRIu64 " to %"
-					     PRIu64 " for %s.%s", existing_table_size,
+			log_debug_activation("Table size changed from %" PRIu64 " to %" PRIu64 " for %s.%s",
+					     existing_table_size,
 					     seg_start, _node_name(dnode),
 					     dnode->props.size_changed ? "" : " (Ignoring.)");
 
@@ -3163,6 +3202,16 @@ static int _dm_tree_revert_activated(struct dm_tree_node *parent)
 	return 1;
 }
 
+static int _dm_tree_wait_and_revert_activated(struct dm_tree_node *dnode)
+{
+	if (!dm_udev_wait(dm_tree_get_cookie(dnode)))
+		stack;
+
+	dm_tree_set_cookie(dnode, 0);
+
+	return _dm_tree_revert_activated(dnode);
+}
+
 int dm_tree_preload_children(struct dm_tree_node *dnode,
 			     const char *uuid_prefix,
 			     size_t uuid_prefix_len)
@@ -3192,7 +3241,7 @@ int dm_tree_preload_children(struct dm_tree_node *dnode,
 				return_0;
 
 		/* FIXME Cope if name exists with no uuid? */
-		if (!child->info.exists && !(node_created = _create_node(child)))
+		if (!child->info.exists && !(node_created = _create_node(child, dnode)))
 			return_0;
 
 		/* Propagate delayed resume from exteded child node */
@@ -3202,28 +3251,22 @@ int dm_tree_preload_children(struct dm_tree_node *dnode,
 		if (!child->info.inactive_table &&
 		    child->props.segment_count &&
 		    !_load_node(child)) {
+			stack;
 			/*
-			 * If the table load does not succeed, we remove the
-			 * device in the kernel that would otherwise have an
-			 * empty table.  This makes the create + load of the
-			 * device atomic.  However, if other dependencies have
-			 * already been created and loaded; this code is
-			 * insufficient to remove those - only the node
-			 * encountering the table load failure is removed.
+			 * If the table load fails, try to device in the kernel
+			 * together with other created and preloaded devices.
 			 */
-			if (node_created) {
-				if (!_remove_node(child))
-					return_0;
-				if (!dm_udev_wait(dm_tree_get_cookie(dnode)))
-					stack;
-				dm_tree_set_cookie(dnode, 0);
-				(void) _dm_tree_revert_activated(child);
-			}
-			return_0;
+			if (!_dm_tree_wait_and_revert_activated(dnode))
+				stack;
+			r = 0;
+			continue;
 		}
 
 		/* No resume for a device without parents or with unchanged or smaller size */
-		if (!dm_tree_node_num_children(child, 1) || (child->props.size_changed <= 0))
+		if (!dm_tree_node_num_children(child, 1))
+			continue;
+
+		if (child->props.size_changed <= 0)
 			continue;
 
 		if (!child->info.inactive_table && !child->info.suspended)
@@ -3234,28 +3277,19 @@ int dm_tree_preload_children(struct dm_tree_node *dnode,
 				  &child->info, &child->dtree->cookie, child->udev_flags,
 				  child->info.suspended)) {
 			log_error("Unable to resume %s.", _node_name(child));
-			/* If the device was not previously active, we might as well remove this node. */
-			if (!child->info.live_table &&
-			    !_deactivate_node(child->name, child->info.major, child->info.minor,
-					      &child->dtree->cookie, child->udev_flags, 0))
-				log_error("Unable to deactivate %s.", _node_name(child));
+			if (!_dm_tree_wait_and_revert_activated(dnode))
+				stack;
 			r = 0;
-			/* Each child is handled independently */
 			continue;
 		}
 
 		if (node_created) {
-			/* Collect newly introduced devices for revert */
-			dm_list_add_h(&dnode->activated, &child->activated_list);
-
 			/* When creating new node also check transaction_id. */
 			if (child->props.send_messages &&
 			    !_node_send_messages(child, uuid_prefix, uuid_prefix_len, 0)) {
 				stack;
-				if (!dm_udev_wait(dm_tree_get_cookie(dnode)))
+				if (!_dm_tree_wait_and_revert_activated(dnode))
 					stack;
-				dm_tree_set_cookie(dnode, 0);
-				(void) _dm_tree_revert_activated(dnode);
 				r = 0;
 				continue;
 			}
@@ -3829,32 +3863,41 @@ int dm_tree_node_add_integrity_target(struct dm_tree_node *node,
 				  uint64_t size,
 				  const char *origin_uuid,
 				  const char *meta_uuid,
-				  struct integrity_settings *settings)
+				  struct integrity_settings *settings,
+				  int recalculate)
 {
 	struct load_segment *seg;
 
 	if (!(seg = _add_segment(node, SEG_INTEGRITY, size)))
 		return_0;
 
-	if (meta_uuid) {
-		if (!(seg->integrity_meta_node = dm_tree_find_node_by_uuid(node->dtree, meta_uuid))) {
-			log_error("Missing integrity's meta uuid %s.", meta_uuid);
-			return 0;
-		}
-
-		if (!_link_tree_nodes(node, seg->integrity_meta_node))
-			return_0;
+	if (!meta_uuid) {
+		log_error("No integrity meta uuid.");
+		return 0;
 	}
 
+	if (!(seg->integrity_meta_node = dm_tree_find_node_by_uuid(node->dtree, meta_uuid))) {
+		log_error("Missing integrity's meta uuid %s.", meta_uuid);
+		return 0;
+	}
+
+	if (!_link_tree_nodes(node, seg->integrity_meta_node))
+		return_0;
+
 	if (!(seg->origin = dm_tree_find_node_by_uuid(node->dtree, origin_uuid))) {
 		log_error("Missing integrity's origin uuid %s.", origin_uuid);
 		return 0;
 	}
+
 	if (!_link_tree_nodes(node, seg->origin))
 		return_0;
 
 	memcpy(&seg->integrity_settings, settings, sizeof(struct integrity_settings));
 
+	seg->integrity_recalculate = recalculate;
+
+	node->props.skip_reload_params_compare = 1;
+
 	return 1;
 }
 
@@ -3931,6 +3974,24 @@ int dm_tree_node_add_thin_pool_target(struct dm_tree_node *node,
 				      uint32_t data_block_size,
 				      uint64_t low_water_mark,
 				      unsigned skip_block_zeroing)
+{
+	return dm_tree_node_add_thin_pool_target_v1(node, size, transaction_id,
+						    metadata_uuid, pool_uuid,
+						    data_block_size,
+						    low_water_mark,
+						    skip_block_zeroing,
+						    1);
+}
+
+int dm_tree_node_add_thin_pool_target_v1(struct dm_tree_node *node,
+					 uint64_t size,
+					 uint64_t transaction_id,
+					 const char *metadata_uuid,
+					 const char *pool_uuid,
+					 uint32_t data_block_size,
+					 uint64_t low_water_mark,
+					 unsigned skip_block_zeroing,
+					 unsigned crop_metadata)
 {
 	struct load_segment *seg, *mseg;
 	uint64_t devsize = 0;
@@ -3958,17 +4019,18 @@ int dm_tree_node_add_thin_pool_target(struct dm_tree_node *node,
 	if (!_link_tree_nodes(node, seg->metadata))
 		return_0;
 
-	/* FIXME: more complex target may need more tweaks */
-	dm_list_iterate_items(mseg, &seg->metadata->props.segs) {
-		devsize += mseg->size;
-		if (devsize > DM_THIN_MAX_METADATA_SIZE) {
-			log_debug_activation("Ignoring %" PRIu64 " of device.",
-					     devsize - DM_THIN_MAX_METADATA_SIZE);
-			mseg->size -= (devsize - DM_THIN_MAX_METADATA_SIZE);
-			devsize = DM_THIN_MAX_METADATA_SIZE;
-			/* FIXME: drop remaining segs */
+	if (crop_metadata)
+		/* FIXME: more complex target may need more tweaks */
+		dm_list_iterate_items(mseg, &seg->metadata->props.segs) {
+			devsize += mseg->size;
+			if (devsize > DM_THIN_MAX_METADATA_SIZE) {
+				log_debug_activation("Ignoring %" PRIu64 " of device.",
+						     devsize - DM_THIN_MAX_METADATA_SIZE);
+				mseg->size -= (devsize - DM_THIN_MAX_METADATA_SIZE);
+				devsize = DM_THIN_MAX_METADATA_SIZE;
+				/* FIXME: drop remaining segs */
+			}
 		}
-	}
 
 	if (!(seg->pool = dm_tree_find_node_by_uuid(node->dtree, pool_uuid))) {
 		log_error("Missing pool uuid %s.", pool_uuid);
@@ -4320,6 +4382,7 @@ int dm_tree_node_add_cache_target_base(struct dm_tree_node *node,
 
 int dm_tree_node_add_vdo_target(struct dm_tree_node *node,
 				uint64_t size,
+				const char *vdo_pool_name,
 				const char *data_uuid,
 				uint64_t data_size,
 				const struct dm_vdo_target_params *vtp)
@@ -4341,7 +4404,7 @@ int dm_tree_node_add_vdo_target(struct dm_tree_node *node,
 		return_0;
 
 	seg->vdo_params = *vtp;
-	seg->vdo_name = node->name;
+	seg->vdo_name = vdo_pool_name;
 	seg->vdo_data_size = data_size;
 
 	node->props.send_messages = 2;

device_mapper/libdm-report.c

@@ -492,7 +492,7 @@ static int _report_field_string_list(struct dm_report *rh,
 		delimiter = ",";
 	delimiter_len = strlen(delimiter);
 
-	i = pos = len = 0;
+	i = pos = 0;
 	dm_list_iterate_items(sl, data) {
 		arr[i].str = sl->str;
 		if (!sort) {
@@ -749,10 +749,11 @@ static void _display_fields_more(struct dm_report *rh,
 			id_len = strlen(type->prefix) + 3;
 
 	for (f = 0; fields[f].report_fn; f++) {
-		if ((type = _find_type(rh, fields[f].type)) && type->desc)
-			desc = type->desc;
-		else
-			desc = " ";
+		if (!(type = _find_type(rh, fields[f].type))) {
+			log_debug(INTERNAL_ERROR "Field type undefined.");
+			continue;
+		}
+		desc = (type->desc) ? : " ";
 		if (desc != last_desc) {
 			if (*last_desc)
 				log_warn(" ");

device_mapper/libdm-targets.c

@@ -366,8 +366,8 @@ int dm_get_status_writecache(struct dm_pool *mem, const char *params,
 	if (!(s = dm_pool_zalloc(mem, sizeof(struct dm_status_writecache))))
 		return_0;
 
-	if (sscanf(params, "%u %llu %llu %llu",
-		   &s->error,
+	if (sscanf(params, "%llu %llu %llu %llu",
+		   (unsigned long long *)&s->error,
 		   (unsigned long long *)&s->total_blocks,
 		   (unsigned long long *)&s->free_blocks,
 		   (unsigned long long *)&s->writeback_blocks) != 4) {
@@ -384,13 +384,11 @@ int dm_get_status_integrity(struct dm_pool *mem, const char *params,
 			     struct dm_status_integrity **status)
 {
 	struct dm_status_integrity *s;
-	char recalc_str[8];
+	char recalc_str[16] = "\0";
 
-	if (!(s = dm_pool_zalloc(mem, sizeof(struct dm_status_integrity))))
+	if (!(s = dm_pool_zalloc(mem, sizeof(*s))))
 		return_0;
 
-	memset(recalc_str, 0, sizeof(recalc_str));
-
 	if (sscanf(params, "%llu %llu %s",
 		   (unsigned long long *)&s->number_of_mismatches,
 		   (unsigned long long *)&s->provided_data_sectors,

device_mapper/misc/dm-ioctl.h

@@ -183,7 +183,7 @@ struct dm_target_spec {
 struct dm_target_deps {
 	uint32_t count;	/* Array size */
 	uint32_t padding;	/* unused */
-	uint64_t dev[0];	/* out */
+	uint64_t dev[];		/* out */
 };
 
 /*
@@ -193,7 +193,7 @@ struct dm_name_list {
 	uint64_t dev;
 	uint32_t next;		/* offset to the next record from
 				   the _start_ of this */
-	char name[0];
+	char name[];
 };
 
 /*
@@ -203,7 +203,7 @@ struct dm_target_versions {
         uint32_t next;
         uint32_t version[3];
 
-        char name[0];
+        char name[];
 };
 
 /*
@@ -212,7 +212,7 @@ struct dm_target_versions {
 struct dm_target_msg {
 	uint64_t sector;	/* Device sector */
 
-	char message[0];
+	char message[];
 };
 
 /*

device_mapper/mm/pool.c

@@ -98,7 +98,7 @@ void dm_pools_check_leaks(void)
 			  p->orig_pool,
 			  p->name, p->stats.bytes);
 #else
-		log_error(" [%p] %s", p, p->name);
+		log_error(" [%p] %s", (void *)p, p->name);
 #endif
 	}
 	pthread_mutex_unlock(&_dm_pools_mutex);

include/configure.h.in

@@ -126,6 +126,9 @@
 /* Library version */
 #undef DM_LIB_VERSION
 
+/* Define to 1 to include the LVM editline shell. */
+#undef EDITLINE_SUPPORT
+
 /* Path to fsadm binary. */
 #undef FSADM_PATH
 
@@ -151,6 +154,9 @@
 /* Define to 1 if you have the `atexit' function. */
 #undef HAVE_ATEXIT
 
+/* Define if ioctl BLKZEROOUT can be used for device zeroing. */
+#undef HAVE_BLKZEROOUT
+
 /* Define to 1 if canonicalize_file_name is available. */
 #undef HAVE_CANONICALIZE_FILE_NAME
 
@@ -176,6 +182,12 @@
 /* Define to 1 if you don't have `vprintf' but do have `_doprnt.' */
 #undef HAVE_DOPRNT
 
+/* Define to 1 if you have the <editline/history.h> header file. */
+#undef HAVE_EDITLINE_HISTORY_H
+
+/* Define to 1 if you have the <editline/readline.h> header file. */
+#undef HAVE_EDITLINE_READLINE_H
+
 /* Define to 1 if you have the <errno.h> header file. */
 #undef HAVE_ERRNO_H
 
@@ -531,6 +543,9 @@
 /* Define to 1 if the system has the `__builtin_clzll' built-in function */
 #undef HAVE___BUILTIN_CLZLL
 
+/* Define to 1 to include built-in support for integrity. */
+#undef INTEGRITY_INTERNAL
+
 /* Internalization package */
 #undef INTL_PACKAGE
 

lib/Makefile.in

@@ -29,6 +29,7 @@ SOURCES =\
 	device/bcache.c \
 	device/bcache-utils.c \
 	device/dev-cache.c \
+	device/device_id.c \
 	device/dev-ext.c \
 	device/dev-io.c \
 	device/dev-md.c \
@@ -52,6 +53,7 @@ SOURCES =\
 	filters/filter-usable.c \
 	filters/filter-internal.c \
 	filters/filter-signature.c \
+	filters/filter-deviceid.c \
 	format_text/archive.c \
 	format_text/archiver.c \
 	format_text/export.c \
@@ -76,6 +78,7 @@ SOURCES =\
 	metadata/mirror.c \
 	metadata/pool_manip.c \
 	metadata/pv.c \
+	metadata/pv_list.c \
 	metadata/pv_manip.c \
 	metadata/pv_map.c \
 	metadata/raid_manip.c \

lib/activate/activate.c

@@ -185,8 +185,8 @@ void set_activation(int act, int silent)
 	if (warned || !act)
 		return;
 
-	log_error("Compiled without libdevmapper support. "
-		  "Can't enable activation.");
+	log_warn("WARNING: Compiled without libdevmapper support. "
+		 "Can't enable activation.");
 
 	warned = 1;
 }
@@ -221,23 +221,13 @@ int lv_info(struct cmd_context *cmd, const struct logical_volume *lv, int use_la
 {
 	return 0;
 }
-int lv_info_by_lvid(struct cmd_context *cmd, const char *lvid_s, int use_layer,
-		    struct lvinfo *info, int with_open_count, int with_read_ahead)
-{
-	return 0;
-}
-int lv_info_with_seg_status(struct cmd_context *cmd, const struct logical_volume *lv,
-			    const struct lv_segment *lv_seg, int use_layer,
+int lv_info_with_seg_status(struct cmd_context *cmd,
+			    const struct lv_segment *lv_seg,
 			    struct lv_with_info_and_seg_status *status,
 			    int with_open_count, int with_read_ahead)
 {
 	return 0;
 }
-int lv_status(struct cmd_context *cmd, const struct lv_segment *lv_seg,
-	      int use_layer, struct lv_seg_status *lv_seg_status)
-{
-	return 0;
-}
 int lv_cache_status(const struct logical_volume *cache_lv,
 		    struct lv_status_cache **status)
 {
@@ -284,18 +274,17 @@ int lv_raid_message(const struct logical_volume *lv, const char *msg)
 {
 	return 0;
 }
-int lv_thin_pool_percent(const struct logical_volume *lv, int metadata,
-			 dm_percent_t *percent)
+int lv_writecache_message(const struct logical_volume *lv, const char *msg)
 {
 	return 0;
 }
-int lv_thin_percent(const struct logical_volume *lv, int mapped,
-		    dm_percent_t *percent)
+int lv_thin_pool_status(const struct logical_volume *lv, int flush,
+			struct lv_status_thin_pool **thin_pool_status)
 {
 	return 0;
 }
-int lv_thin_pool_transaction_id(const struct logical_volume *lv,
-				uint64_t *transaction_id)
+int lv_thin_status(const struct logical_volume *lv, int flush,
+		   struct lv_status_thin **thin_status)
 {
 	return 0;
 }
@@ -303,6 +292,15 @@ int lv_thin_device_id(const struct logical_volume *lv, uint32_t *device_id)
 {
 	return 0;
 }
+int lv_vdo_pool_status(const struct logical_volume *lv, int flush,
+		       struct lv_status_vdo **vdo_status)
+{
+	return 0;
+}
+int lv_vdo_pool_percent(const struct logical_volume *lv, dm_percent_t *percent)
+{
+	return 0;
+}
 int lvs_in_vg_activated(const struct volume_group *vg)
 {
 	return 0;
@@ -468,6 +466,11 @@ static int _passes_readonly_filter(struct cmd_context *cmd,
 	return _lv_passes_volumes_filter(cmd, lv, cn, activation_read_only_volume_list_CFG);
 }
 
+int lv_passes_readonly_filter(const struct logical_volume *lv)
+{
+	return _passes_readonly_filter(lv->vg->cmd, lv);
+}
+
 int library_version(char *version, size_t size)
 {
 	if (!activation())
@@ -1248,86 +1251,52 @@ int lv_cache_status(const struct logical_volume *cache_lv,
 	return 1;
 }
 
-/*
- * Returns data or metadata percent usage, depends on metadata 0/1.
- * Returns 1 if percent set, else 0 on failure.
- */
-int lv_thin_pool_percent(const struct logical_volume *lv, int metadata,
-			 dm_percent_t *percent)
+int lv_thin_pool_status(const struct logical_volume *lv, int flush,
+			struct lv_status_thin_pool **thin_pool_status)
 {
-	int r;
 	struct dev_manager *dm;
 
 	if (!lv_info(lv->vg->cmd, lv, 1, NULL, 0, 0))
 		return 0;
 
-	log_debug_activation("Checking thin %sdata percent for LV %s.",
-			     (metadata) ? "meta" : "", display_lvname(lv));
+	log_debug_activation("Checking thin pool status for LV %s.",
+			     display_lvname(lv));
 
 	if (!(dm = dev_manager_create(lv->vg->cmd, lv->vg->name, 1)))
 		return_0;
 
-	if (!(r = dev_manager_thin_pool_percent(dm, lv, metadata, percent)))
-		stack;
+	if (!dev_manager_thin_pool_status(dm, lv, flush, thin_pool_status)) {
+		dev_manager_destroy(dm);
+		return_0;
+	}
 
-	dev_manager_destroy(dm);
+	/* User has to call dm_pool_destroy(thin_pool_status->mem)! */
 
-	return r;
+	return 1;
 }
 
-/*
- * Returns 1 if percent set, else 0 on failure.
- */
-int lv_thin_percent(const struct logical_volume *lv,
-		    int mapped, dm_percent_t *percent)
+int lv_thin_status(const struct logical_volume *lv, int flush,
+		   struct lv_status_thin **thin_status)
 {
-	int r;
 	struct dev_manager *dm;
 
 	if (!lv_info(lv->vg->cmd, lv, 0, NULL, 0, 0))
 		return 0;
 
-	log_debug_activation("Checking thin percent for LV %s.",
+	log_debug_activation("Checking thin status for LV %s.",
 			     display_lvname(lv));
 
 	if (!(dm = dev_manager_create(lv->vg->cmd, lv->vg->name, 1)))
 		return_0;
 
-	if (!(r = dev_manager_thin_percent(dm, lv, mapped, percent)))
-		stack;
-
-	dev_manager_destroy(dm);
-
-	return r;
-}
-
-/*
- * Returns 1 if transaction_id set, else 0 on failure.
- */
-int lv_thin_pool_transaction_id(const struct logical_volume *lv,
-				uint64_t *transaction_id)
-{
-	int r;
-	struct dev_manager *dm;
-	struct dm_status_thin_pool *status;
-
-	if (!lv_info(lv->vg->cmd, lv, 1, NULL, 0, 0))
-		return 0;
-
-	log_debug_activation("Checking thin-pool transaction id for LV %s.",
-			     display_lvname(lv));
-
-	if (!(dm = dev_manager_create(lv->vg->cmd, lv->vg->name, 1)))
+	if (!dev_manager_thin_status(dm, lv, flush, thin_status)) {
+		dev_manager_destroy(dm);
 		return_0;
+	}
 
-	if (!(r = dev_manager_thin_pool_status(dm, lv, &status, 0)))
-		stack;
-	else
-		*transaction_id = status->transaction_id;
+	/* User has to call dm_pool_destroy(thin_status->mem)! */
 
-	dev_manager_destroy(dm);
-
-	return r;
+	return 1;
 }
 
 int lv_thin_device_id(const struct logical_volume *lv, uint32_t *device_id)
@@ -2197,8 +2166,6 @@ static int _lv_suspend(struct cmd_context *cmd, const char *lvid_s,
 	if (laopts->origin_only && lv_is_thin_volume(lv) && lv_is_thin_volume(lv_pre))
 		lockfs = 1;
 
-	critical_section_inc(cmd, "suspending");
-
 	if (!lv_is_locked(lv) && lv_is_locked(lv_pre) &&
 	    (pvmove_lv = find_pvmove_lv_in_lv(lv_pre))) {
 		/*
@@ -2240,16 +2207,23 @@ static int _lv_suspend(struct cmd_context *cmd, const char *lvid_s,
 			}
 			dm_list_add(&suspend_lvs, &lvl->list);
 		}
+
+		critical_section_inc(cmd, "suspending");
+
 		dm_list_iterate_items(lvl, &suspend_lvs)
 			if (!_lv_suspend_lv(lvl->lv, laopts, lockfs, 1)) {
 				critical_section_dec(cmd, "failed suspend");
 				goto_out; /* FIXME: resume on recovery path? */
 			}
-	} else  /* Standard suspend */
+
+	} else { /* Standard suspend */
+		critical_section_inc(cmd, "suspending");
+
 		if (!_lv_suspend_lv(lv, laopts, lockfs, flush_required)) {
 			critical_section_dec(cmd, "failed suspend");
 			goto_out;
 		}
+	}
 
 	r = 1;
 out:
@@ -2269,8 +2243,8 @@ int lv_suspend_if_active(struct cmd_context *cmd, const char *lvid_s, unsigned o
 			 const struct logical_volume *lv, const struct logical_volume *lv_pre)
 {
 	struct lv_activate_opts laopts = {
-		.origin_only = origin_only,
-		.exclusive = exclusive
+		.exclusive = exclusive,
+		.origin_only = origin_only
 	};
 
 	return _lv_suspend(cmd, lvid_s, &laopts, 0, lv, lv_pre);
@@ -2322,6 +2296,9 @@ static int _lv_resume(struct cmd_context *cmd, const char *lvid_s,
 			      lv_is_thin_volume(lv) ? " thin only" : " without snapshots") : "",
 			     laopts->revert ? " (reverting)" : "");
 
+	if (laopts->revert)
+		goto needs_resume;
+
 	if (!lv_info(cmd, lv, laopts->origin_only, &info, 0, 0))
 		goto_out;
 
@@ -2381,8 +2358,8 @@ int lv_resume_if_active(struct cmd_context *cmd, const char *lvid_s,
 			unsigned revert, const struct logical_volume *lv)
 {
 	struct lv_activate_opts laopts = {
-		.origin_only = origin_only,
 		.exclusive = exclusive,
+		.origin_only = origin_only,
 		.revert = revert
 	};
 
@@ -2535,6 +2512,13 @@ static int _lv_activate(struct cmd_context *cmd, const char *lvid_s,
 		goto out;
 	}
 
+	if ((cmd->partial_activation || cmd->degraded_activation) &&
+	    lv_is_partial(lv) && lv_is_raid(lv) && lv_raid_has_integrity((struct logical_volume *)lv)) {
+		cmd->partial_activation = 0;
+		cmd->degraded_activation = 0;
+		log_print("No degraded or partial activation for raid with integrity.");
+	}
+
 	if ((!lv->vg->cmd->partial_activation) && lv_is_partial(lv)) {
 		if (!lv_is_raid_type(lv) || !partial_raid_lv_supports_degraded_activation(lv)) {
 			log_error("Refusing activation of partial LV %s.  "
@@ -2551,6 +2535,14 @@ static int _lv_activate(struct cmd_context *cmd, const char *lvid_s,
 		}
 	}
 
+	if ((cmd->partial_activation || cmd->degraded_activation) && lv_is_writecache(lv)) {
+		struct logical_volume *lv_fast = first_seg(lv)->writecache;
+		if (lv_is_partial(lv) || (lv_fast && lv_is_partial(lv_fast))) {
+			log_error("Cannot use partial or degraded activation with writecache.");
+			goto out;
+		}
+	}
+
 	if (lv_has_unknown_segments(lv)) {
 		log_error("Refusing activation of LV %s containing "
 			  "an unrecognised segment.", display_lvname(lv));
@@ -2870,7 +2862,6 @@ int deactivate_lv_with_sub_lv(const struct logical_volume *lv)
 int activate_lv(struct cmd_context *cmd, const struct logical_volume *lv)
 {
 	const struct logical_volume *active_lv;
-	const struct logical_volume *lv_use;
 	int ret;
 
 	/*
@@ -2889,30 +2880,19 @@ int activate_lv(struct cmd_context *cmd, const struct logical_volume *lv)
 		goto out;
 	}
 
-	if (lv->status & LV_UNCOMMITTED)
-		lv_use = lv;
-	else
-		lv_use = lv_committed(lv);
-
 	ret = lv_activate_with_filter(cmd, NULL, 0,
 				      (lv->status & LV_NOSCAN) ? 1 : 0,
 				      (lv->status & LV_TEMPORARY) ? 1 : 0,
-				      lv_use);
+				      lv_committed(lv));
 out:
 	return ret;
 }
 
 int deactivate_lv(struct cmd_context *cmd, const struct logical_volume *lv)
 {
-	const struct logical_volume *lv_use;
 	int ret;
 
-	if (lv->status & LV_UNCOMMITTED)
-		lv_use = lv;
-	else
-		lv_use = lv_committed(lv);
-
-	ret = lv_deactivate(cmd, NULL, lv_use);
+	ret = lv_deactivate(cmd, NULL, lv_committed(lv));
 
 	return ret;
 }
@@ -2967,8 +2947,7 @@ int revert_lv(struct cmd_context *cmd, const struct logical_volume *lv)
 
 	ret = lv_resume_if_active(cmd, NULL, 0, 0, 1, lv_committed(lv));
 
-	critical_section_dec(cmd, "unlocking on resume");
+	critical_section_dec(cmd, "unlocking on revert");
 
 	return ret;
 }
-

lib/activate/activate.h

@@ -191,13 +191,11 @@ int lv_raid_message(const struct logical_volume *lv, const char *msg);
 int lv_writecache_message(const struct logical_volume *lv, const char *msg);
 int lv_cache_status(const struct logical_volume *cache_lv,
 		    struct lv_status_cache **status);
-int lv_thin_pool_percent(const struct logical_volume *lv, int metadata,
-			 dm_percent_t *percent);
-int lv_thin_percent(const struct logical_volume *lv, int mapped,
-		    dm_percent_t *percent);
-int lv_thin_pool_transaction_id(const struct logical_volume *lv,
-				uint64_t *transaction_id);
 int lv_thin_device_id(const struct logical_volume *lv, uint32_t *device_id);
+int lv_thin_status(const struct logical_volume *lv, int flush,
+		   struct lv_status_thin **status);
+int lv_thin_pool_status(const struct logical_volume *lv, int flush,
+			struct lv_status_thin_pool **status);
 int lv_vdo_pool_status(const struct logical_volume *lv, int flush,
 		       struct lv_status_vdo **status);
 int lv_vdo_pool_percent(const struct logical_volume *lv, dm_percent_t *percent);
@@ -210,6 +208,8 @@ int lvs_in_vg_opened(const struct volume_group *vg);
 
 int lv_is_active(const struct logical_volume *lv);
 
+int lv_passes_readonly_filter(const struct logical_volume *lv);
+
 /* Check is any component LV is active */
 const struct logical_volume *lv_component_is_active(const struct logical_volume *lv);
 const struct logical_volume *lv_holder_is_active(const struct logical_volume *lv);

lib/activate/dev_manager.c

@@ -46,7 +46,7 @@ typedef enum {
 } action_t;
 
 /* This list must match lib/misc/lvm-string.c:build_dm_uuid(). */
-const char *uuid_suffix_list[] = { "pool", "cdata", "cmeta", "cvol", "tdata", "tmeta", "vdata", "vpool", NULL};
+const char *uuid_suffix_list[] = { "pool", "cdata", "cmeta", "cvol", "tdata", "tmeta", "vdata", "vpool", "imeta", NULL};
 
 struct dlid_list {
 	struct dm_list list;
@@ -86,7 +86,7 @@ int read_only_lv(const struct logical_volume *lv, const struct lv_activate_opts
 		return 0; /* Keep RAID SubLvs writable */
 
 	if (!layer) {
-		if (lv_is_thin_pool(lv))
+		if (lv_is_thin_pool(lv) || lv_is_vdo_pool(lv))
 			return 1;
 	}
 
@@ -261,7 +261,7 @@ static int _info_run(const char *dlid, struct dm_info *dminfo,
 	int dmtask;
 	int with_flush; /* TODO: arg for _info_run */
 	void *target = NULL;
-	uint64_t target_start, target_length, start, length;
+	uint64_t target_start, target_length, start, length, length_crop = 0;
 	char *target_name, *target_params;
 	const char *devname;
 
@@ -297,7 +297,7 @@ static int _info_run(const char *dlid, struct dm_info *dminfo,
 		/* Uses max DM_THIN_MAX_METADATA_SIZE sectors for metadata device */
 		if (lv_is_thin_pool_metadata(seg_status->seg->lv) &&
 		    (length > DM_THIN_MAX_METADATA_SIZE))
-			length = DM_THIN_MAX_METADATA_SIZE;
+			length_crop = DM_THIN_MAX_METADATA_SIZE;
 
 		/* Uses virtual size with headers for VDO pool device */
 		if (lv_is_vdo_pool(seg_status->seg->lv))
@@ -310,7 +310,9 @@ static int _info_run(const char *dlid, struct dm_info *dminfo,
 			target = dm_get_next_target(dmt, target, &target_start,
 						    &target_length, &target_name, &target_params);
 
-			if ((start == target_start) && (length == target_length))
+			if ((start == target_start) &&
+			    ((length == target_length) ||
+			     (length_crop && (length_crop == target_length))))
 				break; /* Keep target_params when matching segment is found */
 
 			target_params = NULL; /* Marking this target_params unusable */
@@ -1564,9 +1566,6 @@ int dev_manager_cache_status(struct dev_manager *dm,
 	if (!(dlid = build_dm_uuid(dm->mem, lv, lv_layer(lv))))
 		return_0;
 
-	if (!(*status = dm_pool_zalloc(dm->mem, sizeof(struct lv_status_cache))))
-		return_0;
-
 	if (!(dmt = _setup_task_run(DM_DEVICE_STATUS, &info, NULL, dlid, 0, 0, 0, 0, 0, 0)))
 		return_0;
 
@@ -1589,8 +1588,11 @@ int dev_manager_cache_status(struct dev_manager *dm,
 	if (!dm_get_status_cache(dm->mem, params, &c))
 		goto_out;
 
-	(*status)->cache = c;
+	if (!(*status = dm_pool_zalloc(dm->mem, sizeof(struct lv_status_cache))))
+		goto_out;
+
 	(*status)->mem = dm->mem; /* User has to destroy this mem pool later */
+	(*status)->cache = c;
 	if (c->fail || c->error) {
 		(*status)->data_usage =
 			(*status)->metadata_usage =
@@ -1612,10 +1614,10 @@ out:
 }
 
 int dev_manager_thin_pool_status(struct dev_manager *dm,
-				 const struct logical_volume *lv,
-				 struct dm_status_thin_pool **status,
-				 int flush)
+				 const struct logical_volume *lv, int flush,
+				 struct lv_status_thin_pool **status)
 {
+	struct dm_status_thin_pool *dm_status;
 	const char *dlid;
 	struct dm_task *dmt;
 	struct dm_info info;
@@ -1636,11 +1638,31 @@ int dev_manager_thin_pool_status(struct dev_manager *dm,
 
 	dm_get_next_target(dmt, NULL, &start, &length, &type, &params);
 
-	/* FIXME Check for thin and check there's exactly one target */
+	if (!type || strcmp(type, TARGET_NAME_THIN_POOL)) {
+		log_error("Expected %s segment type but got %s instead.",
+			  TARGET_NAME_THIN_POOL, type ? type : "NULL");
+		goto out;
+	}
 
-	if (!dm_get_status_thin_pool(dm->mem, params, status))
+	if (!dm_get_status_thin_pool(dm->mem, params, &dm_status))
 		goto_out;
 
+	if (!(*status = dm_pool_zalloc(dm->mem, sizeof(struct lv_status_thin_pool))))
+		goto_out;
+
+	(*status)->mem = dm->mem;
+	(*status)->thin_pool = dm_status;
+
+	if (dm_status->fail || dm_status->error) {
+		(*status)->data_usage =
+			(*status)->metadata_usage = DM_PERCENT_INVALID;
+	} else {
+		(*status)->data_usage = dm_make_percent(dm_status->used_data_blocks,
+							dm_status->total_data_blocks);
+		(*status)->metadata_usage = dm_make_percent(dm_status->used_metadata_blocks,
+							    dm_status->total_metadata_blocks);
+	}
+
 	r = 1;
 out:
 	dm_task_destroy(dmt);
@@ -1648,52 +1670,68 @@ out:
 	return r;
 }
 
-int dev_manager_thin_pool_percent(struct dev_manager *dm,
-				  const struct logical_volume *lv,
-				  int metadata, dm_percent_t *percent)
+int dev_manager_thin_status(struct dev_manager *dm,
+			    const struct logical_volume *lv, int flush,
+			    struct lv_status_thin **status)
 {
-	char *name;
+	struct dm_status_thin *dm_status;
 	const char *dlid;
-	const char *layer = lv_layer(lv);
+	struct dm_task *dmt;
+	struct dm_info info;
+	uint64_t start, length;
+	char *type = NULL;
+	char *params = NULL;
+	uint64_t csize;
+	int r = 0;
 
-	/* Build a name for the top layer */
-	if (!(name = dm_build_dm_name(dm->mem, lv->vg->name, lv->name, layer)))
+	if (!(dlid = build_dm_uuid(dm->mem, lv, lv_layer(lv))))
 		return_0;
 
-	if (!(dlid = build_dm_uuid(dm->mem, lv, layer)))
+	if (!(dmt = _setup_task_run(DM_DEVICE_STATUS, &info, NULL, dlid, 0, 0, 0, 0, flush, 0)))
 		return_0;
 
-	log_debug_activation("Getting device status percentage for %s.", name);
+	if (!info.exists)
+		goto_out;
 
-	if (!(_percent(dm, name, dlid, TARGET_NAME_THIN_POOL, 0,
-		       (metadata) ? lv : NULL, percent, NULL, 1)))
-		return_0;
+	dm_get_next_target(dmt, NULL, &start, &length, &type, &params);
 
-	return 1;
-}
+	if (!type || strcmp(type, TARGET_NAME_THIN)) {
+		log_error("Expected %s segment type but got %s instead.",
+			  TARGET_NAME_THIN, type ? type : "NULL");
+		goto out;
+	}
 
-int dev_manager_thin_percent(struct dev_manager *dm,
-			     const struct logical_volume *lv,
-			     int mapped, dm_percent_t *percent)
-{
-	char *name;
-	const char *dlid;
-	const char *layer = lv_layer(lv);
+	if (!dm_get_status_thin(dm->mem, params, &dm_status))
+		goto_out;
 
-	/* Build a name for the top layer */
-	if (!(name = dm_build_dm_name(dm->mem, lv->vg->name, lv->name, layer)))
-		return_0;
+	if (!(*status = dm_pool_zalloc(dm->mem, sizeof(struct lv_status_thin))))
+		goto_out;
 
-	if (!(dlid = build_dm_uuid(dm->mem, lv, layer)))
-		return_0;
+	(*status)->mem = dm->mem;
+	(*status)->thin = dm_status;
 
-	log_debug_activation("Getting device status percentage for %s", name);
+	if (dm_status->fail)
+		(*status)->usage = DM_PERCENT_INVALID;
+	else {
+		/* Pool allocates whole chunk so round-up to nearest one */
+		csize = first_seg(first_seg(lv)->pool_lv)->chunk_size;
+		csize = ((lv->size + csize - 1) / csize) * csize;
+		if (dm_status->mapped_sectors > csize) {
+			log_warn("WARNING: LV %s maps %s while the size is only %s.",
+				 display_lvname(lv),
+				 display_size(dm->cmd, dm_status->mapped_sectors),
+				 display_size(dm->cmd, csize));
+			/* Don't show nonsense numbers like i.e. 1000% full */
+			dm_status->mapped_sectors = csize;
+		}
+		(*status)->usage = dm_make_percent(dm_status->mapped_sectors, csize);
+	}
 
-	if (!(_percent(dm, name, dlid, TARGET_NAME_THIN, 0,
-		       (mapped) ? NULL : lv, percent, NULL, 1)))
-		return_0;
+	r = 1;
+out:
+	dm_task_destroy(dmt);
 
-	return 1;
+	return r;
 }
 
 /*
@@ -2234,21 +2272,31 @@ static int _pool_callback(struct dm_tree_node *node,
 	const struct pool_cb_data *data = cb_data;
 	const struct logical_volume *pool_lv = data->pool_lv;
 	const struct logical_volume *mlv = first_seg(pool_lv)->metadata_lv;
+	struct cmd_context *cmd = pool_lv->vg->cmd;
 	long buf[64 / sizeof(long)]; /* buffer for short disk header (64B) */
 	int args = 0;
 	char *mpath;
 	const char *argv[19] = { /* Max supported 15 args */
-		find_config_tree_str_allow_empty(pool_lv->vg->cmd, data->exec, NULL)
+		find_config_tree_str_allow_empty(cmd, data->exec, NULL)
 	};
 
 	if (!*argv[0]) /* *_check tool is unconfigured/disabled with "" setting */
 		return 1;
 
-	if (!(mpath = lv_dmpath_dup(data->dm->mem, mlv))) {
-		log_error("Failed to build device path for checking pool metadata %s.",
-			  display_lvname(mlv));
-		return 0;
+	if (lv_is_cache_vol(pool_lv)) {
+		if (!(mpath = lv_dmpath_suffix_dup(data->dm->mem, pool_lv, "-cmeta"))) {
+			log_error("Failed to build device path for checking cachevol metadata %s.",
+			  	 display_lvname(pool_lv));
+			return 0;
+		}
+	} else {
+		if (!(mpath = lv_dmpath_dup(data->dm->mem, mlv))) {
+			log_error("Failed to build device path for checking pool metadata %s.",
+			  	 display_lvname(mlv));
+			return 0;
+		}
 	}
+	log_debug("Running check command on %s", mpath);
 
 	if (data->skip_zero) {
 		if ((fd = open(mpath, O_RDONLY)) < 0) {
@@ -2276,7 +2324,7 @@ static int _pool_callback(struct dm_tree_node *node,
 		}
 	}
 
-	if (!(cn = find_config_tree_array(mlv->vg->cmd, data->opts, NULL))) {
+	if (!(cn = find_config_tree_array(cmd, data->opts, NULL))) {
 		log_error(INTERNAL_ERROR "Unable to find configuration for pool check options.");
 		return 0;
 	}
@@ -2298,7 +2346,7 @@ static int _pool_callback(struct dm_tree_node *node,
 
 	argv[++args] = mpath;
 
-	if (!(ret = exec_cmd(pool_lv->vg->cmd, (const char * const *)argv,
+	if (!(ret = exec_cmd(cmd, (const char * const *)argv,
 			     &status, 0))) {
 		if (status == ENOENT) {
 			log_warn("WARNING: Check is skipped, please install recommended missing binary %s!",
@@ -2307,7 +2355,7 @@ static int _pool_callback(struct dm_tree_node *node,
 		}
 
 		if ((data->version.maj || data->version.min || data->version.patch) &&
-		    !_check_tool_version(pool_lv->vg->cmd, argv[0],
+		    !_check_tool_version(cmd, argv[0],
 					 data->version.maj, data->version.min, data->version.patch)) {
 			log_warn("WARNING: Check is skipped, please upgrade installed version of %s!",
 				 argv[0]);
@@ -2351,10 +2399,6 @@ static int _pool_register_callback(struct dev_manager *dm,
 		return 1;
 #endif
 
-	/* Skip for single-device cache pool */
-	if (lv_is_cache(lv) && lv_is_cache_vol(first_seg(lv)->pool_lv))
-		return 1;
-
 	if (!(data = dm_pool_zalloc(dm->mem, sizeof(*data)))) {
 		log_error("Failed to allocated path for callback.");
 		return 0;
@@ -3177,8 +3221,8 @@ static int _add_new_lv_to_dtree(struct dev_manager *dm, struct dm_tree *dtree,
 		char *dlid_meta;
 		char *dlid_data;
 		char *dlid_pool;
-		uint64_t meta_len = first_seg(lv)->metadata_len;
-		uint64_t data_len = first_seg(lv)->data_len;
+		uint64_t meta_size = first_seg(lv)->metadata_len;
+		uint64_t data_size = first_seg(lv)->data_len;
 		uint16_t udev_flags = _get_udev_flags(dm, lv, layer,
 					     laopts->noscan, laopts->temporary,
 					     0);
@@ -3226,12 +3270,12 @@ static int _add_new_lv_to_dtree(struct dev_manager *dm, struct dm_tree *dtree,
 
 		if (dm->track_pending_delete) {
 			log_debug_activation("Using error for pending meta delete %s.", display_lvname(lv));
-			if (!dm_tree_node_add_error_target(dnode_meta, (uint64_t)lv->vg->extent_size * meta_len))
+			if (!dm_tree_node_add_error_target(dnode_meta, meta_size))
 				return_0;
 		} else {
 			/* add load_segment to meta dnode: linear, size of meta area */
 			if (!add_linear_area_to_dtree(dnode_meta,
-						      meta_len,
+						      meta_size,
 						      lv->vg->extent_size,
 						      lv->vg->cmd->use_linear_target,
 						      lv->vg->name, lv->name))
@@ -3255,19 +3299,19 @@ static int _add_new_lv_to_dtree(struct dev_manager *dm, struct dm_tree *dtree,
 
 		if (dm->track_pending_delete) {
 			log_debug_activation("Using error for pending data delete %s.", display_lvname(lv));
-			if (!dm_tree_node_add_error_target(dnode_data, (uint64_t)lv->vg->extent_size * data_len))
+			if (!dm_tree_node_add_error_target(dnode_data, data_size))
 				return_0;
 		} else {
 			/* add load_segment to data dnode: linear, size of data area */
 			if (!add_linear_area_to_dtree(dnode_data,
-						      data_len,
+						      data_size,
 						      lv->vg->extent_size,
 						      lv->vg->cmd->use_linear_target,
 						      lv->vg->name, lv->name))
 				return_0;
 
 			/* add seg_area to prev load_seg: offset 0 maps to cachepool lv after meta */
-			if (!dm_tree_node_add_target_area(dnode_data, NULL, dlid_pool, meta_len))
+			if (!dm_tree_node_add_target_area(dnode_data, NULL, dlid_pool, meta_size))
 				return_0;
 		}
 	}
@@ -3332,6 +3376,10 @@ static int _add_new_lv_to_dtree(struct dev_manager *dm, struct dm_tree *dtree,
 	if (!layer && lv_is_new_thin_pool(lv))
 		layer = lv_layer(lv);
 
+	/* Adds -real to the dm uuid of wcorig LV. */
+	if (!layer && lv_is_writecache_origin(lv))
+		layer = lv_layer(lv); /* "real" */
+
 	if (!(dlid = build_dm_uuid(dm->mem, lv, layer)))
 		return_0;
 
@@ -3443,6 +3491,12 @@ static int _add_new_lv_to_dtree(struct dev_manager *dm, struct dm_tree *dtree,
 	    !_pool_register_callback(dm, dnode, lv))
 		return_0;
 
+	if (lv_is_cache(lv) && lv_is_cache_vol(first_seg(lv)->pool_lv) &&
+	    /* Register callback only for layer activation or non-layered cache LV */
+	    (layer || !lv_layer(lv)) &&
+	    !_pool_register_callback(dm, dnode, lv))
+		return_0;
+
 	/*
 	 * Update tables for ANY PVMOVE holders for active LV where the name starts with 'pvmove',
 	 * but it's not anymore PVMOVE LV and also it's not a PVMOVE _mimage LV.

lib/activate/dev_manager.h

@@ -69,19 +69,15 @@ int dev_manager_writecache_message(struct dev_manager *dm,
 int dev_manager_cache_status(struct dev_manager *dm,
 			     const struct logical_volume *lv,
 			     struct lv_status_cache **status);
-int dev_manager_thin_pool_status(struct dev_manager *dm,
-				 const struct logical_volume *lv,
-				 struct dm_status_thin_pool **status,
-				 int flush);
-int dev_manager_thin_pool_percent(struct dev_manager *dm,
-				  const struct logical_volume *lv,
-				  int metadata, dm_percent_t *percent);
-int dev_manager_thin_percent(struct dev_manager *dm,
-			     const struct logical_volume *lv,
-			     int mapped, dm_percent_t *percent);
+int dev_manager_thin_status(struct dev_manager *dm,
+			    const struct logical_volume *lv, int flush,
+			    struct lv_status_thin **status);
 int dev_manager_thin_device_id(struct dev_manager *dm,
 			       const struct logical_volume *lv,
 			       uint32_t *device_id);
+int dev_manager_thin_pool_status(struct dev_manager *dm,
+				 const struct logical_volume *lv, int flush,
+				 struct lv_status_thin_pool **status);
 int dev_manager_vdo_pool_status(struct dev_manager *dm,
 				const struct logical_volume *lv,
 				struct lv_status_vdo **vdo_status,

lib/activate/fs.c

@@ -313,7 +313,7 @@ struct fs_op_parms {
 	char *lv_name;
 	char *dev;
 	char *old_lv_name;
-	char names[0];
+	char names[];
 };
 
 static void _store_str(char **pos, char **ptr, const char *str)

lib/cache/lvmcache.h

@@ -69,18 +69,19 @@ void lvmcache_destroy(struct cmd_context *cmd, int retain_orphans, int reset);
 int lvmcache_label_scan(struct cmd_context *cmd);
 int lvmcache_label_rescan_vg(struct cmd_context *cmd, const char *vgname, const char *vgid);
 int lvmcache_label_rescan_vg_rw(struct cmd_context *cmd, const char *vgname, const char *vgid);
+int lvmcache_label_reopen_vg_rw(struct cmd_context *cmd, const char *vgname, const char *vgid);
 
 /* Add/delete a device */
-struct lvmcache_info *lvmcache_add(struct labeller *labeller, const char *pvid,
+struct lvmcache_info *lvmcache_add(struct cmd_context *cmd, struct labeller *labeller, const char *pvid,
                                    struct device *dev, uint64_t label_sector,
                                    const char *vgname, const char *vgid,
                                    uint32_t vgstatus, int *is_duplicate);
-int lvmcache_add_orphan_vginfo(const char *vgname, struct format_type *fmt);
+int lvmcache_add_orphan_vginfo(struct cmd_context *cmd, const char *vgname, struct format_type *fmt);
 void lvmcache_del(struct lvmcache_info *info);
 void lvmcache_del_dev(struct device *dev);
 
 /* Update things */
-int lvmcache_update_vgname_and_id(struct lvmcache_info *info,
+int lvmcache_update_vgname_and_id(struct cmd_context *cmd, struct lvmcache_info *info,
 				  struct lvmcache_vgsummary *vgsummary);
 int lvmcache_update_vg_from_read(struct volume_group *vg, unsigned precommitted);
 int lvmcache_update_vg_from_write(struct volume_group *vg);
@@ -161,11 +162,6 @@ struct device *lvmcache_device(struct lvmcache_info *info);
 unsigned lvmcache_mda_count(struct lvmcache_info *info);
 uint64_t lvmcache_smallest_mda_size(struct lvmcache_info *info);
 
-struct metadata_area *lvmcache_get_mda(struct cmd_context *cmd,
-                                      const char *vgname,
-                                      struct device *dev,
-                                      int use_mda_num);
-
 bool lvmcache_has_duplicate_devs(void);
 void lvmcache_del_dev_from_duplicates(struct device *dev);
 bool lvmcache_dev_is_unused_duplicate(struct device *dev);
@@ -174,6 +170,7 @@ int lvmcache_get_unused_duplicates(struct cmd_context *cmd, struct dm_list *head
 int vg_has_duplicate_pvs(struct volume_group *vg);
 
 int lvmcache_found_duplicate_vgnames(void);
+bool lvmcache_has_duplicate_local_vgname(const char *vgid, const char *vgname);
 
 int lvmcache_contains_lock_type_sanlock(struct cmd_context *cmd);
 
@@ -216,4 +213,17 @@ void lvmcache_get_bad_mdas(struct cmd_context *cmd,
                            const char *vgname, const char *vgid,
                            struct dm_list *bad_mda_list);
 
+void lvmcache_get_mdas(struct cmd_context *cmd,
+                       const char *vgname, const char *vgid,
+                       struct dm_list *mda_list);
+
+const char *dev_filtered_reason(struct device *dev);
+const char *devname_error_reason(const char *devname);
+
+struct metadata_area *lvmcache_get_dev_mda(struct device *dev, int mda_num);
+
+void lvmcache_extra_md_component_checks(struct cmd_context *cmd);
+
+unsigned int lvmcache_vg_info_count(void);
+
 #endif

lib/commands/toolcontext.c

@@ -32,6 +32,7 @@
 #include "lib/cache/lvmcache.h"
 #include "lib/format_text/archiver.h"
 #include "lib/lvmpolld/lvmpolld-client.h"
+#include "lib/device/device_id.h"
 
 #include <locale.h>
 #include <sys/stat.h>
@@ -1066,7 +1067,7 @@ static int _init_dev_cache(struct cmd_context *cmd)
 	return 1;
 }
 
-#define MAX_FILTERS 10
+#define MAX_FILTERS 11
 
 static struct dev_filter *_init_filter_chain(struct cmd_context *cmd)
 {
@@ -1085,6 +1086,9 @@ static struct dev_filter *_init_filter_chain(struct cmd_context *cmd)
 	 * sysfs filter. Only available on 2.6 kernels.  Non-critical.
 	 * Listed first because it's very efficient at eliminating
 	 * unavailable devices.
+	 *
+	 * TODO: I suspect that using the lvm_type and device_id
+	 * filters before this one may be more efficient.
 	 */
 	if (find_config_tree_bool(cmd, devices_sysfs_scan_CFG, NULL)) {
 		if ((filters[nr_filt] = sysfs_filter_create()))
@@ -1123,6 +1127,13 @@ static struct dev_filter *_init_filter_chain(struct cmd_context *cmd)
 	}
 	nr_filt++;
 
+	/* filter based on the device_ids saved in the devices file */
+	if (!(filters[nr_filt] = deviceid_filter_create(cmd))) {
+		log_error("Failed to create deviceid device filter");
+		goto bad;
+	}
+	nr_filt++;
+
 	/* usable device filter. Required. */
 	if (!(filters[nr_filt] = usable_filter_create(cmd, cmd->dev_types, FILTER_MODE_NO_LVMETAD))) {
 		log_error("Failed to create usabled device filter");
@@ -1276,7 +1287,7 @@ int init_lvmcache_orphans(struct cmd_context *cmd)
 	struct format_type *fmt;
 
 	dm_list_iterate_items(fmt, &cmd->formats)
-		if (!lvmcache_add_orphan_vginfo(fmt->orphan_vg_name, fmt))
+		if (!lvmcache_add_orphan_vginfo(cmd, fmt->orphan_vg_name, fmt))
 			return_0;
 
 	return 1;
@@ -1362,8 +1373,10 @@ static int _init_segtypes(struct cmd_context *cmd)
 		return 0;
 #endif
 
+#ifdef INTEGRITY_INTERNAL
 	if (!init_integrity_segtypes(cmd, &seglib))
 		return 0;
+#endif
 
 	return 1;
 }
@@ -1483,6 +1496,7 @@ int init_run_by_dmeventd(struct cmd_context *cmd)
 	init_dmeventd_monitor(DMEVENTD_MONITOR_IGNORE);
 	init_ignore_suspended_devices(1);
 	init_disable_dmeventd_monitoring(1); /* Lock settings */
+	cmd->run_by_dmeventd = 1;
 
 	return 0;
 }
@@ -1596,6 +1610,7 @@ struct cmd_context *create_toolcontext(unsigned is_clvmd,
 	dm_list_init(&cmd->formats);
 	dm_list_init(&cmd->segtypes);
 	dm_list_init(&cmd->tags);
+	dm_list_init(&cmd->hints);
 	dm_list_init(&cmd->config_files);
 	label_init();
 
@@ -1714,6 +1729,8 @@ struct cmd_context *create_toolcontext(unsigned is_clvmd,
 	if (!_init_dev_cache(cmd))
 		goto_out;
 
+	devices_file_init(cmd);
+
 	memlock_init(cmd);
 
 	if (!_init_formats(cmd))
@@ -1839,6 +1856,7 @@ int refresh_toolcontext(struct cmd_context *cmd)
 	_destroy_segtypes(&cmd->segtypes);
 	_destroy_formats(cmd, &cmd->formats);
 
+	devices_file_exit(cmd);
 	if (!dev_cache_exit())
 		stack;
 	_destroy_dev_types(cmd);
@@ -1918,6 +1936,8 @@ int refresh_toolcontext(struct cmd_context *cmd)
 	if (!_init_dev_cache(cmd))
 		return_0;
 
+	devices_file_init(cmd);
+
 	if (!_init_formats(cmd))
 		return_0;
 
@@ -1967,6 +1987,7 @@ void destroy_toolcontext(struct cmd_context *cmd)
 	_destroy_filters(cmd);
 	if (cmd->mem)
 		dm_pool_destroy(cmd->mem);
+	devices_file_exit(cmd);
 	dev_cache_exit();
 	_destroy_dev_types(cmd);
 	_destroy_tags(cmd);

lib/commands/toolcontext.h

@@ -182,13 +182,27 @@ struct cmd_context {
 	unsigned pvscan_recreate_hints:1;	/* enable special case hint handling for pvscan --cache */
 	unsigned scan_lvs:1;
 	unsigned wipe_outdated_pvs:1;
+	unsigned enable_devices_list:1;		/* command is using --devices option */
+	unsigned enable_devices_file:1;		/* command is using devices file */
+	unsigned pending_devices_file:1;	/* command may create and enable devices file */
+	unsigned create_edit_devices_file:1;	/* command expects to create and/or edit devices file */
+	unsigned edit_devices_file:1;		/* command expects to edit devices file */
+	unsigned filter_deviceid_skip:1;	/* don't use filter-deviceid */
+	unsigned filter_regex_with_devices_file:1; /* use filter-regex even when devices file is enabled */
+	unsigned filter_nodata_only:1;          /* only use filters that do not require data from the dev */
+	unsigned run_by_dmeventd:1;		/* command is being run by dmeventd */
+	unsigned sysinit:1;			/* --sysinit is used */
 
 	/*
 	 * Devices and filtering.
 	 */
 	struct dev_filter *filter;
 	struct dm_list hints;
+	struct dm_list use_devices;		/* struct dev_use for each entry in devices file */
 	const char *md_component_checks;
+	const char *search_for_devnames;	/* config file setting */
+	const char *devicesfile;                /* from --devicesfile option */
+	struct dm_list deviceslist;             /* from --devices option, struct dm_str_list */
 
 	/*
 	 * Configuration.
@@ -220,6 +234,7 @@ struct cmd_context {
 	char system_dir[PATH_MAX];
 	char dev_dir[PATH_MAX];
 	char proc_dir[PATH_MAX];
+	char devices_file_path[PATH_MAX];
 
 	/*
 	 * Reporting.

lib/config/config.c

@@ -503,10 +503,10 @@ int config_file_read_fd(struct dm_config_tree *cft, struct device *dev, dev_io_r
 {
 	char *fb, *fe;
 	int r = 0;
-	int use_mmap = 1;
-	off_t mmap_offset = 0;
+	int sz, use_plain_read = 1;
 	char *buf = NULL;
 	struct config_source *cs = dm_config_get_custom(cft);
+	size_t rsize;
 
 	if (!_is_file_based_config_source(cs->type)) {
 		log_error(INTERNAL_ERROR "config_file_read_fd: expected file, special file "
@@ -515,26 +515,28 @@ int config_file_read_fd(struct dm_config_tree *cft, struct device *dev, dev_io_r
 		return 0;
 	}
 
-	/* Only use mmap with regular files */
+	/* Only use plain read with regular files */
 	if (!(dev->flags & DEV_REGULAR) || size2)
-		use_mmap = 0;
+		use_plain_read = 0;
 
-	if (use_mmap) {
-		mmap_offset = offset % lvm_getpagesize();
-		/* memory map the file */
-		fb = mmap((caddr_t) 0, size + mmap_offset, PROT_READ,
-			  MAP_PRIVATE, dev_fd(dev), offset - mmap_offset);
-		if (fb == (caddr_t) (-1)) {
-			log_sys_error("mmap", dev_name(dev));
-			goto out;
+	if (!(buf = malloc(size + size2))) {
+		log_error("Failed to allocate circular buffer.");
+		return 0;
+	}
+
+	if (use_plain_read) {
+		/* Note: also used for lvm.conf to read all settings */
+		for (rsize = 0; rsize < size; rsize += sz) {
+			do {
+				sz = read(dev_fd(dev), buf + rsize, size - rsize);
+			} while ((sz < 0) && ((errno == EINTR) || (errno == EAGAIN)));
+
+			if (sz < 0) {
+				log_sys_error("read", dev_name(dev));
+				goto out;
+			}
 		}
-		fb = fb + mmap_offset;
 	} else {
-		if (!(buf = malloc(size + size2))) {
-			log_error("Failed to allocate circular buffer.");
-			return 0;
-		}
-
 		if (!dev_read_bytes(dev, offset, size, buf))
 			goto out;
 
@@ -542,10 +544,10 @@ int config_file_read_fd(struct dm_config_tree *cft, struct device *dev, dev_io_r
 			if (!dev_read_bytes(dev, offset2, size2, buf + size))
 				goto out;
 		}
-
-		fb = buf;
 	}
 
+	fb = buf;
+
 	/*
 	 * The checksum passed in is the checksum from the mda_header
 	 * preceding this metadata.  They should always match.
@@ -573,15 +575,7 @@ int config_file_read_fd(struct dm_config_tree *cft, struct device *dev, dev_io_r
 	r = 1;
 
       out:
-	if (!use_mmap)
-		free(buf);
-	else {
-		/* unmap the file */
-		if (munmap(fb - mmap_offset, size + mmap_offset)) {
-			log_sys_error("munmap", dev_name(dev));
-			r = 0;
-		}
-	}
+	free(buf);
 
 	return r;
 }
@@ -716,7 +710,7 @@ static struct dm_config_value *_get_def_array_values(struct cmd_context *cmd,
 		return array;
 	}
 
-	if (!(p = token = enc_value = strdup(def_enc_value))) {
+	if (!(token = enc_value = strdup(def_enc_value))) {
 		log_error("_get_def_array_values: strdup failed");
 		return NULL;
 	}
@@ -1714,6 +1708,7 @@ static int _out_prefix_fn(const struct dm_config_node *cn, const char *line, voi
 	const char *node_type_name = cn->v ? "option" : "section";
 	char path[CFG_PATH_MAX_LEN];
 	char commentline[MAX_COMMENT_LINE+1];
+	int is_deprecated = 0;
 
 	if (cn->id <= 0)
 		return 1;
@@ -1727,13 +1722,14 @@ static int _out_prefix_fn(const struct dm_config_node *cn, const char *line, voi
 
 	cfg_def = cfg_def_get_item_p(cn->id);
 
+	is_deprecated = _def_node_is_deprecated(cfg_def, out->tree_spec);
+
 	if (out->tree_spec->withsummary || out->tree_spec->withcomments) {
 		_cfg_def_make_path(path, sizeof(path), cfg_def->id, cfg_def, 1);
 		fprintf(out->fp, "\n");
 		fprintf(out->fp, "%s# Configuration %s %s.\n", line, node_type_name, path);
 
-		if (out->tree_spec->withcomments &&
-		    _def_node_is_deprecated(cfg_def, out->tree_spec))
+		if (out->tree_spec->withcomments && is_deprecated && cfg_def->deprecation_comment)
 			fprintf(out->fp, "%s# %s", line, cfg_def->deprecation_comment);
 
 		if (cfg_def->comment) {
@@ -1744,14 +1740,14 @@ static int _out_prefix_fn(const struct dm_config_node *cn, const char *line, voi
 						continue;
 					commentline[0] = '\0';
 				}
-				fprintf(out->fp, "%s# %s\n", line, commentline);
+				fprintf(out->fp, "%s#%s%s\n", line, commentline[0] ? " " : "", commentline);
 				/* withsummary prints only the first comment line. */
 				if (!out->tree_spec->withcomments)
 					break;
 			}
 		}
 
-		if (_def_node_is_deprecated(cfg_def, out->tree_spec))
+		if (is_deprecated)
 			fprintf(out->fp, "%s# This configuration %s is deprecated.\n", line, node_type_name);
 
 		if (cfg_def->flags & CFG_ADVANCED)
@@ -1779,7 +1775,7 @@ static int _out_prefix_fn(const struct dm_config_node *cn, const char *line, voi
 			return_0;
 		fprintf(out->fp, "%s# Available since version %s.\n", line, version);
 
-		if (_def_node_is_deprecated(cfg_def, out->tree_spec)) {
+		if (is_deprecated) {
 			if (!_get_config_node_version(cfg_def->deprecated_since_version, version))
 				return_0;
 			fprintf(out->fp, "%s# Deprecated since version %s.\n", line, version);

lib/config/config_settings.h

@@ -205,7 +205,7 @@ cfg_section(local_CFG_SECTION, "local", root_CFG_SECTION, 0, vsn(2, 2, 117), 0,
 	"# Please take care that each setting only appears once if uncommenting\n" \
 	"# example settings in this file and never copy this file between hosts.\n\n"
 
-cfg(config_checks_CFG, "checks", config_CFG_SECTION, 0, CFG_TYPE_BOOL, 1, vsn(2, 2, 99), NULL, 0, NULL,
+cfg(config_checks_CFG, "checks", config_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, 1, vsn(2, 2, 99), NULL, 0, NULL,
 	"If enabled, any LVM configuration mismatch is reported.\n"
 	"This implies checking that the configuration key is understood by\n"
 	"LVM and that the value of the key is the proper type. If disabled,\n"
@@ -213,22 +213,22 @@ cfg(config_checks_CFG, "checks", config_CFG_SECTION, 0, CFG_TYPE_BOOL, 1, vsn(2,
 	"without any warning (a message about the configuration key not being\n"
 	"found is issued in verbose mode only).\n")
 
-cfg(config_abort_on_errors_CFG, "abort_on_errors", config_CFG_SECTION, 0, CFG_TYPE_BOOL, 0, vsn(2,2,99), NULL, 0, NULL,
+cfg(config_abort_on_errors_CFG, "abort_on_errors", config_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, 0, vsn(2,2,99), NULL, 0, NULL,
 	"Abort the LVM process if a configuration mismatch is found.\n")
 
-cfg_runtime(config_profile_dir_CFG, "profile_dir", config_CFG_SECTION, CFG_DISALLOW_INTERACTIVE, CFG_TYPE_STRING, vsn(2, 2, 99), 0, NULL,
+cfg_runtime(config_profile_dir_CFG, "profile_dir", config_CFG_SECTION, CFG_DEFAULT_COMMENTED | CFG_DISALLOW_INTERACTIVE, CFG_TYPE_STRING, vsn(2, 2, 99), 0, NULL,
 	"Directory where LVM looks for configuration profiles.\n")
 
-cfg(devices_dir_CFG, "dir", devices_CFG_SECTION, CFG_ADVANCED, CFG_TYPE_STRING, DEFAULT_DEV_DIR, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(devices_dir_CFG, "dir", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED | CFG_ADVANCED, CFG_TYPE_STRING, DEFAULT_DEV_DIR, vsn(1, 0, 0), NULL, 0, NULL,
 	"Directory in which to create volume group device nodes.\n"
 	"Commands also accept this as a prefix on volume group names.\n")
 
-cfg_array(devices_scan_CFG, "scan", devices_CFG_SECTION, CFG_ADVANCED, CFG_TYPE_STRING, "#S/dev", vsn(1, 0, 0), NULL, 0, NULL,
+cfg_array(devices_scan_CFG, "scan", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED | CFG_ADVANCED, CFG_TYPE_STRING, "#S/dev", vsn(1, 0, 0), NULL, 0, NULL,
 	"Directories containing device nodes to use with LVM.\n")
 
 cfg_array(devices_loopfiles_CFG, "loopfiles", devices_CFG_SECTION, CFG_DEFAULT_UNDEFINED | CFG_UNSUPPORTED, CFG_TYPE_STRING, NULL, vsn(1, 2, 0), NULL, vsn(2, 3, 0), NULL, NULL)
 
-cfg(devices_obtain_device_list_from_udev_CFG, "obtain_device_list_from_udev", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_OBTAIN_DEVICE_LIST_FROM_UDEV, vsn(2, 2, 85), NULL, 0, NULL,
+cfg(devices_obtain_device_list_from_udev_CFG, "obtain_device_list_from_udev", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_OBTAIN_DEVICE_LIST_FROM_UDEV, vsn(2, 2, 85), NULL, 0, NULL,
 	"Obtain the list of available devices from udev.\n"
 	"This avoids opening or using any inapplicable non-block devices or\n"
 	"subdirectories found in the udev directory. Any device node or\n"
@@ -237,7 +237,7 @@ cfg(devices_obtain_device_list_from_udev_CFG, "obtain_device_list_from_udev", de
 	"directories will be scanned fully. LVM needs to be compiled with\n"
 	"udev support for this setting to apply.\n")
 
-cfg(devices_external_device_info_source_CFG, "external_device_info_source", devices_CFG_SECTION, 0, CFG_TYPE_STRING, DEFAULT_EXTERNAL_DEVICE_INFO_SOURCE, vsn(2, 2, 116), NULL, 0, NULL,
+cfg(devices_external_device_info_source_CFG, "external_device_info_source", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_EXTERNAL_DEVICE_INFO_SOURCE, vsn(2, 2, 116), NULL, 0, NULL,
 	"Select an external device information source.\n"
 	"Some information may already be available in the system and LVM can\n"
 	"use this information to determine the exact type or use of devices it\n"
@@ -288,6 +288,32 @@ cfg_array(devices_preferred_names_CFG, "preferred_names", devices_CFG_SECTION, C
 	"preferred_names = [ \"^/dev/mpath/\", \"^/dev/mapper/mpath\", \"^/dev/[hs]d\" ]\n"
 	"#\n")
 
+cfg(devices_use_devicesfile_CFG, "use_devicesfile", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_USE_DEVICES_FILE, vsn(2, 3, 12), NULL, 0, NULL,
+	"Enable or disable the use of a devices file.\n"
+	"When enabled, lvm will only use devices that\n"
+	"are lised in the devices file. A devices file will\n"
+	"be used, regardless of this setting, when the --devicesfile\n"
+	"option is set to a specific file name.\n")
+
+cfg(devices_devicesfile_CFG, "devicesfile", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_DEVICES_FILE, vsn(2, 3, 12), NULL, 0, NULL,
+	"The name of the system devices file, listing devices that LVM should use.\n"
+	"This should not be used to select a non-system devices file.\n"
+	"The --devicesfile option is intended for alternative devices files.\n")
+
+cfg(devices_search_for_devnames_CFG, "search_for_devnames", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_SEARCH_FOR_DEVNAMES, vsn(2, 3, 12), NULL, 0, NULL,
+	"Look outside of the devices file for missing devname entries.\n"
+	"A devname entry is used for a device that does not have a stable\n"
+	"device id, e.g. wwid, so the unstable device name is used as\n"
+	"the device id. After reboot, or if the device is reattached,\n"
+	"the device name may change, in which case lvm will not find\n"
+	"the expected PV on the device listed in the devices file.\n"
+	"This setting controls whether lvm will search other devices,\n"
+	"outside the devices file, to look for the missing PV on a\n"
+	"renamed device. If \"none\", lvm will not look at other devices,\n"
+	"and the PV may appear to be missing. If \"auto\", lvm will look\n"
+	"at other devices, but only those that are likely to have the PV.\n"
+	"If \"all\", lvm will look at all devices on the system.\n")
+
 cfg_array(devices_filter_CFG, "filter", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, "#Sa|.*|", vsn(1, 0, 0), NULL, 0, NULL,
 	"Limit the block devices that are used by LVM commands.\n"
 	"This is a list of regular expressions used to accept or reject block\n"
@@ -326,16 +352,16 @@ cfg_array(devices_global_filter_CFG, "global_filter", devices_CFG_SECTION, CFG_D
 	"global_filter are not opened by LVM.\n")
 
 cfg_runtime(devices_cache_CFG, "cache", devices_CFG_SECTION, 0, CFG_TYPE_STRING, vsn(1, 0, 0), vsn(1, 2, 19), NULL,
-	"This setting is no longer used.\n")
+	NULL)
 
 cfg_runtime(devices_cache_dir_CFG, "cache_dir", devices_CFG_SECTION, 0, CFG_TYPE_STRING, vsn(1, 2, 19), vsn(2, 3, 0), NULL,
-	"This setting is no longer used.\n")
+	NULL)
 
 cfg(devices_cache_file_prefix_CFG, "cache_file_prefix", devices_CFG_SECTION, CFG_ALLOW_EMPTY, CFG_TYPE_STRING, DEFAULT_CACHE_FILE_PREFIX, vsn(1, 2, 19), NULL, vsn(2, 3, 0), NULL,
-	"This setting is no longer used.\n")
+	NULL)
 
 cfg(devices_write_cache_state_CFG, "write_cache_state", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, 1, vsn(1, 0, 0), NULL, vsn(2, 3, 0), NULL,
-	"This setting is no longer used.\n")
+	NULL)
 
 cfg_array(devices_types_CFG, "types", devices_CFG_SECTION, CFG_DEFAULT_UNDEFINED | CFG_ADVANCED, CFG_TYPE_INT | CFG_TYPE_STRING, NULL, vsn(1, 0, 0), NULL, 0, NULL,
 	"List of additional acceptable block device types.\n"
@@ -346,12 +372,12 @@ cfg_array(devices_types_CFG, "types", devices_CFG_SECTION, CFG_DEFAULT_UNDEFINED
 	"types = [ \"fd\", 16 ]\n"
 	"#\n")
 
-cfg(devices_sysfs_scan_CFG, "sysfs_scan", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_SYSFS_SCAN, vsn(1, 0, 8), NULL, 0, NULL,
+cfg(devices_sysfs_scan_CFG, "sysfs_scan", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_SYSFS_SCAN, vsn(1, 0, 8), NULL, 0, NULL,
 	"Restrict device scanning to block devices appearing in sysfs.\n"
 	"This is a quick way of filtering out block devices that are not\n"
 	"present on the system. sysfs must be part of the kernel and mounted.)\n")
 
-cfg(devices_scan_lvs_CFG, "scan_lvs", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_SCAN_LVS, vsn(2, 2, 182), NULL, 0, NULL,
+cfg(devices_scan_lvs_CFG, "scan_lvs", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_SCAN_LVS, vsn(2, 2, 182), NULL, 0, NULL,
 	"Scan LVM LVs for layered PVs, allowing LVs to be used as PVs.\n"
 	"When 1, LVM will detect PVs layered on LVs, and caution must be\n"
 	"taken to avoid a host accessing a layered VG that may not belong\n"
@@ -364,10 +390,10 @@ cfg(devices_scan_lvs_CFG, "scan_lvs", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, DEF
 	"an LV. The LVs are ignored using a built in device filter that\n"
 	"identifies and excludes LVs.\n")
 
-cfg(devices_multipath_component_detection_CFG, "multipath_component_detection", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_MULTIPATH_COMPONENT_DETECTION, vsn(2, 2, 89), NULL, 0, NULL,
+cfg(devices_multipath_component_detection_CFG, "multipath_component_detection", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_MULTIPATH_COMPONENT_DETECTION, vsn(2, 2, 89), NULL, 0, NULL,
 	"Ignore devices that are components of DM multipath devices.\n")
 
-cfg(devices_md_component_detection_CFG, "md_component_detection", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_MD_COMPONENT_DETECTION, vsn(1, 0, 18), NULL, 0, NULL,
+cfg(devices_md_component_detection_CFG, "md_component_detection", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_MD_COMPONENT_DETECTION, vsn(1, 0, 18), NULL, 0, NULL,
 	"Enable detection and exclusion of MD component devices.\n"
 	"An MD component device is a block device that MD uses as part\n"
 	"of a software RAID virtual device. When an LVM PV is created\n"
@@ -393,12 +419,12 @@ cfg(devices_md_component_checks_CFG, "md_component_checks", devices_CFG_SECTION,
 	"    This requires an extra read at the end of devices.\n"
 	"#\n")
 
-cfg(devices_fw_raid_component_detection_CFG, "fw_raid_component_detection", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_FW_RAID_COMPONENT_DETECTION, vsn(2, 2, 112), NULL, 0, NULL,
+cfg(devices_fw_raid_component_detection_CFG, "fw_raid_component_detection", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_FW_RAID_COMPONENT_DETECTION, vsn(2, 2, 112), NULL, 0, NULL,
 	"Ignore devices that are components of firmware RAID devices.\n"
 	"LVM must use an external_device_info_source other than none for this\n"
 	"detection to execute.\n")
 
-cfg(devices_md_chunk_alignment_CFG, "md_chunk_alignment", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_MD_CHUNK_ALIGNMENT, vsn(2, 2, 48), NULL, 0, NULL,
+cfg(devices_md_chunk_alignment_CFG, "md_chunk_alignment", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_MD_CHUNK_ALIGNMENT, vsn(2, 2, 48), NULL, 0, NULL,
 	"Align the start of a PV data area with md device's stripe-width.\n"
 	"This applies if a PV is placed directly on an md device.\n"
 	"default_data_alignment will be overriden if it is not aligned\n"
@@ -412,7 +438,7 @@ cfg(devices_default_data_alignment_CFG, "default_data_alignment", devices_CFG_SE
 	"This setting is overriden by data_alignment and the --dataalignment\n"
 	"option.\n")
 
-cfg(devices_data_alignment_detection_CFG, "data_alignment_detection", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_DATA_ALIGNMENT_DETECTION, vsn(2, 2, 51), NULL, 0, NULL,
+cfg(devices_data_alignment_detection_CFG, "data_alignment_detection", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_DATA_ALIGNMENT_DETECTION, vsn(2, 2, 51), NULL, 0, NULL,
 	"Align the start of a PV data area with sysfs io properties.\n"
 	"The start of a PV data area will be a multiple of minimum_io_size or\n"
 	"optimal_io_size exposed in sysfs. minimum_io_size is the smallest\n"
@@ -426,14 +452,14 @@ cfg(devices_data_alignment_detection_CFG, "data_alignment_detection", devices_CF
 	"This setting is overriden by data_alignment and the --dataalignment\n"
 	"option.\n")
 
-cfg(devices_data_alignment_CFG, "data_alignment", devices_CFG_SECTION, 0, CFG_TYPE_INT, 0, vsn(2, 2, 45), NULL, 0, NULL,
+cfg(devices_data_alignment_CFG, "data_alignment", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, 0, vsn(2, 2, 45), NULL, 0, NULL,
 	"Align the start of a PV data area with this number of KiB.\n"
 	"When non-zero, this setting overrides default_data_alignment.\n"
 	"Set to 0 to disable, in which case default_data_alignment\n"
 	"is used to align the first PE in units of MiB.\n"
 	"This setting is overriden by the --dataalignment option.\n")
 
-cfg(devices_data_alignment_offset_detection_CFG, "data_alignment_offset_detection", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_DATA_ALIGNMENT_OFFSET_DETECTION, vsn(2, 2, 50), NULL, 0, NULL,
+cfg(devices_data_alignment_offset_detection_CFG, "data_alignment_offset_detection", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_DATA_ALIGNMENT_OFFSET_DETECTION, vsn(2, 2, 50), NULL, 0, NULL,
 	"Shift the start of an aligned PV data area based on sysfs information.\n"
 	"After a PV data area is aligned, it will be shifted by the\n"
 	"alignment_offset exposed in sysfs. This offset is often 0, but may\n"
@@ -443,12 +469,12 @@ cfg(devices_data_alignment_offset_detection_CFG, "data_alignment_offset_detectio
 	"LBA -1, and consequently sector 63 is aligned on a 4KiB boundary).\n"
 	"This setting is overriden by the --dataalignmentoffset option.\n")
 
-cfg(devices_ignore_suspended_devices_CFG, "ignore_suspended_devices", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_IGNORE_SUSPENDED_DEVICES, vsn(1, 2, 19), NULL, 0, NULL,
+cfg(devices_ignore_suspended_devices_CFG, "ignore_suspended_devices", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_IGNORE_SUSPENDED_DEVICES, vsn(1, 2, 19), NULL, 0, NULL,
 	"Ignore DM devices that have I/O suspended while scanning devices.\n"
 	"Otherwise, LVM waits for a suspended device to become accessible.\n"
 	"This should only be needed in recovery situations.\n")
 
-cfg(devices_ignore_lvm_mirrors_CFG, "ignore_lvm_mirrors", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_IGNORE_LVM_MIRRORS, vsn(2, 2, 104), NULL, 0, NULL,
+cfg(devices_ignore_lvm_mirrors_CFG, "ignore_lvm_mirrors", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_IGNORE_LVM_MIRRORS, vsn(2, 2, 104), NULL, 0, NULL,
 	"Do not scan 'mirror' LVs to avoid possible deadlocks.\n"
 	"This avoids possible deadlocks when using the 'mirror' segment type.\n"
 	"This setting determines whether LVs using the 'mirror' segment type\n"
@@ -466,19 +492,19 @@ cfg(devices_ignore_lvm_mirrors_CFG, "ignore_lvm_mirrors", devices_CFG_SECTION, 0
 	"apply to LVM RAID types like 'raid1' which handle failures in a\n"
 	"different way, making them a better choice for VG stacking.\n")
 
-cfg(devices_disable_after_error_count_CFG, "disable_after_error_count", devices_CFG_SECTION, 0, CFG_TYPE_INT, 0, vsn(2, 2, 75), NULL, vsn(2, 3, 0), NULL,
-	"This setting is no longer used.\n")
+cfg(devices_disable_after_error_count_CFG, "disable_after_error_count", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, 0, vsn(2, 2, 75), NULL, vsn(2, 3, 0), NULL,
+	NULL)
 
-cfg(devices_require_restorefile_with_uuid_CFG, "require_restorefile_with_uuid", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_REQUIRE_RESTOREFILE_WITH_UUID, vsn(2, 2, 73), NULL, 0, NULL,
+cfg(devices_require_restorefile_with_uuid_CFG, "require_restorefile_with_uuid", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_REQUIRE_RESTOREFILE_WITH_UUID, vsn(2, 2, 73), NULL, 0, NULL,
 	"Allow use of pvcreate --uuid without requiring --restorefile.\n")
 
-cfg(devices_pv_min_size_CFG, "pv_min_size", devices_CFG_SECTION, 0, CFG_TYPE_INT, DEFAULT_PV_MIN_SIZE_KB, vsn(2, 2, 85), NULL, 0, NULL,
+cfg(devices_pv_min_size_CFG, "pv_min_size", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, DEFAULT_PV_MIN_SIZE_KB, vsn(2, 2, 85), NULL, 0, NULL,
 	"Minimum size in KiB of block devices which can be used as PVs.\n"
 	"In a clustered environment all nodes must use the same value.\n"
 	"Any value smaller than 512KiB is ignored. The previous built-in\n"
 	"value was 512.\n")
 
-cfg(devices_issue_discards_CFG, "issue_discards", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_ISSUE_DISCARDS, vsn(2, 2, 85), NULL, 0, NULL,
+cfg(devices_issue_discards_CFG, "issue_discards", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_ISSUE_DISCARDS, vsn(2, 2, 85), NULL, 0, NULL,
 	"Issue discards to PVs that are no longer used by an LV.\n"
 	"Discards are sent to an LV's underlying physical volumes when the LV\n"
 	"is no longer using the physical volumes' space, e.g. lvremove,\n"
@@ -490,7 +516,7 @@ cfg(devices_issue_discards_CFG, "issue_discards", devices_CFG_SECTION, 0, CFG_TY
 	"generally do. If enabled, discards will only be issued if both the\n"
 	"storage and kernel provide support.\n")
 
-cfg(devices_allow_changes_with_duplicate_pvs_CFG, "allow_changes_with_duplicate_pvs", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_ALLOW_CHANGES_WITH_DUPLICATE_PVS, vsn(2, 2, 153), NULL, 0, NULL,
+cfg(devices_allow_changes_with_duplicate_pvs_CFG, "allow_changes_with_duplicate_pvs", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_ALLOW_CHANGES_WITH_DUPLICATE_PVS, vsn(2, 2, 153), NULL, 0, NULL,
 	"Allow VG modification while a PV appears on multiple devices.\n"
 	"When a PV appears on multiple devices, LVM attempts to choose the\n"
 	"best device to use for the PV. If the devices represent the same\n"
@@ -502,7 +528,7 @@ cfg(devices_allow_changes_with_duplicate_pvs_CFG, "allow_changes_with_duplicate_
 	"Enabling this setting allows the VG to be used as usual even with\n"
 	"uncertain devices.\n")
 
-cfg(devices_allow_mixed_block_sizes_CFG, "allow_mixed_block_sizes", devices_CFG_SECTION, 0, CFG_TYPE_BOOL, 0, vsn(2, 3, 6), NULL, 0, NULL,
+cfg(devices_allow_mixed_block_sizes_CFG, "allow_mixed_block_sizes", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, 0, vsn(2, 3, 6), NULL, 0, NULL,
 	"Allow PVs in the same VG with different logical block sizes.\n"
 	"When allowed, the user is responsible to ensure that an LV is\n"
 	"using PVs with matching block sizes when necessary.\n")
@@ -525,14 +551,14 @@ cfg_array(allocation_cling_tag_list_CFG, "cling_tag_list", allocation_CFG_SECTIO
 	"cling_tag_list = [ \"@site1\", \"@site2\" ]\n"
 	"#\n")
 
-cfg(allocation_maximise_cling_CFG, "maximise_cling", allocation_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_MAXIMISE_CLING, vsn(2, 2, 85), NULL, 0, NULL,
+cfg(allocation_maximise_cling_CFG, "maximise_cling", allocation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_MAXIMISE_CLING, vsn(2, 2, 85), NULL, 0, NULL,
 	"Use a previous allocation algorithm.\n"
 	"Changes made in version 2.02.85 extended the reach of the 'cling'\n"
 	"policies to detect more situations where data can be grouped onto\n"
 	"the same disks. This setting can be used to disable the changes\n"
 	"and revert to the previous algorithm.\n")
 
-cfg(allocation_use_blkid_wiping_CFG, "use_blkid_wiping", allocation_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_USE_BLKID_WIPING, vsn(2, 2, 105), "@DEFAULT_USE_BLKID_WIPING@", 0, NULL,
+cfg(allocation_use_blkid_wiping_CFG, "use_blkid_wiping", allocation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_USE_BLKID_WIPING, vsn(2, 2, 105), "@DEFAULT_USE_BLKID_WIPING@", 0, NULL,
 	"Use blkid to detect and erase existing signatures on new PVs and LVs.\n"
 	"The blkid library can detect more signatures than the native LVM\n"
 	"detection code, but may take longer. LVM needs to be compiled with\n"
@@ -541,7 +567,7 @@ cfg(allocation_use_blkid_wiping_CFG, "use_blkid_wiping", allocation_CFG_SECTION,
 	"swap signature, and LUKS signatures. To see the list of signatures\n"
 	"recognized by blkid, check the output of the 'blkid -k' command.\n")
 
-cfg(allocation_wipe_signatures_when_zeroing_new_lvs_CFG, "wipe_signatures_when_zeroing_new_lvs", allocation_CFG_SECTION, 0, CFG_TYPE_BOOL, 1, vsn(2, 2, 105), NULL, 0, NULL,
+cfg(allocation_wipe_signatures_when_zeroing_new_lvs_CFG, "wipe_signatures_when_zeroing_new_lvs", allocation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, 1, vsn(2, 2, 105), NULL, 0, NULL,
 	"Look for and erase any signatures while zeroing a new LV.\n"
 	"The --wipesignatures option overrides this setting.\n"
 	"Zeroing is controlled by the -Z/--zero option, and if not specified,\n"
@@ -557,7 +583,7 @@ cfg(allocation_wipe_signatures_when_zeroing_new_lvs_CFG, "wipe_signatures_when_z
 	"When this setting is disabled, signatures on new LVs are not detected\n"
 	"or erased unless the --wipesignatures option is used directly.\n")
 
-cfg(allocation_mirror_logs_require_separate_pvs_CFG, "mirror_logs_require_separate_pvs", allocation_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_MIRROR_LOGS_REQUIRE_SEPARATE_PVS, vsn(2, 2, 85), NULL, 0, NULL,
+cfg(allocation_mirror_logs_require_separate_pvs_CFG, "mirror_logs_require_separate_pvs", allocation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_MIRROR_LOGS_REQUIRE_SEPARATE_PVS, vsn(2, 2, 85), NULL, 0, NULL,
 	"Mirror logs and images will always use different PVs.\n"
 	"The default setting changed in version 2.02.85.\n")
 
@@ -568,7 +594,7 @@ cfg(allocation_raid_stripe_all_devices_CFG, "raid_stripe_all_devices", allocatio
 	"stripes to use.\n"
 	"This was the default behaviour until release 2.02.162.\n")
 
-cfg(allocation_cache_pool_metadata_require_separate_pvs_CFG, "cache_pool_metadata_require_separate_pvs", allocation_CFG_SECTION, CFG_PROFILABLE | CFG_PROFILABLE_METADATA, CFG_TYPE_BOOL, DEFAULT_CACHE_POOL_METADATA_REQUIRE_SEPARATE_PVS, vsn(2, 2, 106), NULL, 0, NULL,
+cfg(allocation_cache_pool_metadata_require_separate_pvs_CFG, "cache_pool_metadata_require_separate_pvs", allocation_CFG_SECTION, CFG_PROFILABLE | CFG_PROFILABLE_METADATA | CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_CACHE_POOL_METADATA_REQUIRE_SEPARATE_PVS, vsn(2, 2, 106), NULL, 0, NULL,
 	"Cache pool metadata and data will always use different PVs.\n")
 
 cfg(allocation_cache_pool_cachemode_CFG, "cache_pool_cachemode", allocation_CFG_SECTION, CFG_PROFILABLE | CFG_PROFILABLE_METADATA | CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_CACHE_MODE, vsn(2, 2, 113), NULL, vsn(2, 2, 128),
@@ -625,8 +651,13 @@ cfg(allocation_cache_pool_max_chunks_CFG, "cache_pool_max_chunks", allocation_CF
 	"For cache target v1.9 the recommended maximumm is 1000000 chunks.\n"
 	"Using cache pool with more chunks may degrade cache performance.\n")
 
-cfg(allocation_thin_pool_metadata_require_separate_pvs_CFG, "thin_pool_metadata_require_separate_pvs", allocation_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_THIN_POOL_METADATA_REQUIRE_SEPARATE_PVS, vsn(2, 2, 89), NULL, 0, NULL,
-	"Thin pool metdata and data will always use different PVs.\n")
+cfg(allocation_thin_pool_metadata_require_separate_pvs_CFG, "thin_pool_metadata_require_separate_pvs", allocation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_THIN_POOL_METADATA_REQUIRE_SEPARATE_PVS, vsn(2, 2, 89), NULL, 0, NULL,
+	"Thin pool metadata and data will always use different PVs.\n")
+
+cfg(allocation_thin_pool_crop_metadata_CFG, "thin_pool_crop_metadata", allocation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_THIN_POOL_CROP_METADATA, vsn(2, 3, 12), NULL, 0, NULL,
+	"Older version of lvm2 cropped pool's metadata size to 15.81 GiB.\n"
+	"This is slightly less then the actual maximum 15.88 GiB.\n"
+	"For compatibility with older version and use of cropped size set to 1.\n")
 
 cfg(allocation_thin_pool_zero_CFG, "thin_pool_zero", allocation_CFG_SECTION, CFG_PROFILABLE | CFG_PROFILABLE_METADATA | CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_THIN_POOL_ZERO, vsn(2, 2, 99), NULL, 0, NULL,
 	"Thin pool data chunks are zeroed before they are first used.\n"
@@ -657,6 +688,9 @@ cfg(allocation_thin_pool_chunk_size_policy_CFG, "thin_pool_chunk_size_policy", a
 	"    512KiB.\n"
 	"#\n")
 
+cfg(allocation_zero_metadata_CFG, "zero_metadata", allocation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_ZERO_METADATA, vsn(2, 3, 10), NULL, 0, NULL,
+	"Zero whole metadata area before use with thin or cache pool.\n")
+
 cfg_runtime(allocation_thin_pool_chunk_size_CFG, "thin_pool_chunk_size", allocation_CFG_SECTION, CFG_PROFILABLE | CFG_PROFILABLE_METADATA | CFG_DEFAULT_UNDEFINED, CFG_TYPE_INT, vsn(2, 2, 99), 0, NULL,
 	"The minimal chunk size in KiB for thin pool volumes.\n"
 	"Larger chunk sizes may improve performance for plain thin volumes,\n"
@@ -823,10 +857,10 @@ cfg(log_command_log_selection_CFG, "command_log_selection", log_CFG_SECTION, CFG
 	"For more information about selection criteria in general, see\n"
 	"lvm(8) man page.\n")
 
-cfg(log_verbose_CFG, "verbose", log_CFG_SECTION, 0, CFG_TYPE_INT, DEFAULT_VERBOSE, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(log_verbose_CFG, "verbose", log_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, DEFAULT_VERBOSE, vsn(1, 0, 0), NULL, 0, NULL,
 	"Controls the messages sent to stdout or stderr.\n")
 
-cfg(log_silent_CFG, "silent", log_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_SILENT, vsn(2, 2, 98), NULL, 0, NULL,
+cfg(log_silent_CFG, "silent", log_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_SILENT, vsn(2, 2, 98), NULL, 0, NULL,
 	"Suppress all non-essential messages from stdout.\n"
 	"This has the same effect as -qq. When enabled, the following commands\n"
 	"still produce output: dumpconfig, lvdisplay, lvmdiskscan, lvs, pvck,\n"
@@ -836,16 +870,16 @@ cfg(log_silent_CFG, "silent", log_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_SILENT,
 	"Any 'yes' or 'no' questions not overridden by other arguments are\n"
 	"suppressed and default to 'no'.\n")
 
-cfg(log_syslog_CFG, "syslog", log_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_SYSLOG, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(log_syslog_CFG, "syslog", log_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_SYSLOG, vsn(1, 0, 0), NULL, 0, NULL,
 	"Send log messages through syslog.\n")
 
 cfg(log_file_CFG, "file", log_CFG_SECTION, CFG_DEFAULT_UNDEFINED, CFG_TYPE_STRING, NULL, vsn(1, 0, 0), NULL, 0, NULL,
 	"Write error and debug log messages to a file specified here.\n")
 
-cfg(log_overwrite_CFG, "overwrite", log_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_OVERWRITE, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(log_overwrite_CFG, "overwrite", log_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_OVERWRITE, vsn(1, 0, 0), NULL, 0, NULL,
 	"Overwrite the log file each time the program is run.\n")
 
-cfg(log_level_CFG, "level", log_CFG_SECTION, 0, CFG_TYPE_INT, DEFAULT_LOGLEVEL, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(log_level_CFG, "level", log_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, DEFAULT_LOGLEVEL, vsn(1, 0, 0), NULL, 0, NULL,
 	"The level of log messages that are sent to the log file or syslog.\n"
 	"There are 6 syslog-like log levels currently in use: 2 to 7 inclusive.\n"
 	"7 is the most verbose (LOG_DEBUG).\n")
@@ -853,23 +887,23 @@ cfg(log_level_CFG, "level", log_CFG_SECTION, 0, CFG_TYPE_INT, DEFAULT_LOGLEVEL,
 cfg(log_indent_CFG, "indent", log_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_INDENT, vsn(1, 0, 0), NULL, 0, NULL,
 	"Indent messages according to their severity.\n")
 
-cfg(log_command_names_CFG, "command_names", log_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_CMD_NAME, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(log_command_names_CFG, "command_names", log_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_CMD_NAME, vsn(1, 0, 0), NULL, 0, NULL,
 	"Display the command name on each line of output.\n")
 
-cfg(log_prefix_CFG, "prefix", log_CFG_SECTION, CFG_ALLOW_EMPTY, CFG_TYPE_STRING, DEFAULT_MSG_PREFIX, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(log_prefix_CFG, "prefix", log_CFG_SECTION, CFG_DEFAULT_COMMENTED | CFG_ALLOW_EMPTY, CFG_TYPE_STRING, DEFAULT_MSG_PREFIX, vsn(1, 0, 0), NULL, 0, NULL,
 	"A prefix to use before the log message text.\n"
 	"(After the command name, if selected).\n"
 	"Two spaces allows you to see/grep the severity of each message.\n"
 	"To make the messages look similar to the original LVM tools use:\n"
 	"indent = 0, command_names = 1, prefix = \" -- \"\n")
 
-cfg(log_activation_CFG, "activation", log_CFG_SECTION, 0, CFG_TYPE_BOOL, 0, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(log_activation_CFG, "activation", log_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, 0, vsn(1, 0, 0), NULL, 0, NULL,
 	"Log messages during activation.\n"
 	"Don't use this in low memory situations (can deadlock).\n")
 
 cfg(log_activate_file_CFG, "activate_file", log_CFG_SECTION, CFG_DEFAULT_UNDEFINED | CFG_UNSUPPORTED, CFG_TYPE_STRING, NULL, vsn(1, 0, 0), NULL, 0, NULL, NULL)
 
-cfg_array(log_debug_classes_CFG, "debug_classes", log_CFG_SECTION, CFG_ALLOW_EMPTY, CFG_TYPE_STRING, "#Smemory#Sdevices#Sio#Sactivation#Sallocation#Smetadata#Scache#Slocking#Slvmpolld#Sdbus", vsn(2, 2, 99), NULL, 0, NULL,
+cfg_array(log_debug_classes_CFG, "debug_classes", log_CFG_SECTION, CFG_DEFAULT_COMMENTED | CFG_ALLOW_EMPTY, CFG_TYPE_STRING, "#Smemory#Sdevices#Sio#Sactivation#Sallocation#Smetadata#Scache#Slocking#Slvmpolld#Sdbus", vsn(2, 2, 99), NULL, 0, NULL,
 	"Select log messages by class.\n"
 	"Some debugging messages are assigned to a class and only appear in\n"
 	"debug output if the class is listed here. Classes currently\n"
@@ -884,55 +918,55 @@ cfg_array(log_debug_output_fields_CFG, "debug_output_fields", log_CFG_SECTION, C
 	  "The fields included in debug output written to stderr.\n"
 	  "Use \"all\" to include everything (the default).\n")
 
-cfg(backup_backup_CFG, "backup", backup_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_BACKUP_ENABLED, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(backup_backup_CFG, "backup", backup_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_BACKUP_ENABLED, vsn(1, 0, 0), NULL, 0, NULL,
 	"Maintain a backup of the current metadata configuration.\n"
 	"Think very hard before turning this off!\n")
 
-cfg_runtime(backup_backup_dir_CFG, "backup_dir", backup_CFG_SECTION, 0, CFG_TYPE_STRING, vsn(1, 0, 0), 0, NULL,
+cfg_runtime(backup_backup_dir_CFG, "backup_dir", backup_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, vsn(1, 0, 0), 0, NULL,
 	"Location of the metadata backup files.\n"
 	"Remember to back up this directory regularly!\n")
 
-cfg(backup_archive_CFG, "archive", backup_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_ARCHIVE_ENABLED, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(backup_archive_CFG, "archive", backup_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_ARCHIVE_ENABLED, vsn(1, 0, 0), NULL, 0, NULL,
 	"Maintain an archive of old metadata configurations.\n"
 	"Think very hard before turning this off.\n")
 
-cfg_runtime(backup_archive_dir_CFG, "archive_dir", backup_CFG_SECTION, 0, CFG_TYPE_STRING, vsn(1, 0, 0), 0, NULL,
+cfg_runtime(backup_archive_dir_CFG, "archive_dir", backup_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, vsn(1, 0, 0), 0, NULL,
 	"Location of the metdata archive files.\n"
 	"Remember to back up this directory regularly!\n")
 
-cfg(backup_retain_min_CFG, "retain_min", backup_CFG_SECTION, 0, CFG_TYPE_INT, DEFAULT_ARCHIVE_NUMBER, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(backup_retain_min_CFG, "retain_min", backup_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, DEFAULT_ARCHIVE_NUMBER, vsn(1, 0, 0), NULL, 0, NULL,
 	"Minimum number of archives to keep.\n")
 
-cfg(backup_retain_days_CFG, "retain_days", backup_CFG_SECTION, 0, CFG_TYPE_INT, DEFAULT_ARCHIVE_DAYS, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(backup_retain_days_CFG, "retain_days", backup_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, DEFAULT_ARCHIVE_DAYS, vsn(1, 0, 0), NULL, 0, NULL,
 	"Minimum number of days to keep archive files.\n")
 
-cfg(shell_history_size_CFG, "history_size", shell_CFG_SECTION, 0, CFG_TYPE_INT, DEFAULT_MAX_HISTORY, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(shell_history_size_CFG, "history_size", shell_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, DEFAULT_MAX_HISTORY, vsn(1, 0, 0), NULL, 0, NULL,
 	"Number of lines of history to store in ~/.lvm_history.\n")
 
-cfg(global_umask_CFG, "umask", global_CFG_SECTION, CFG_FORMAT_INT_OCTAL, CFG_TYPE_INT, DEFAULT_UMASK, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(global_umask_CFG, "umask", global_CFG_SECTION, CFG_DEFAULT_COMMENTED | CFG_FORMAT_INT_OCTAL, CFG_TYPE_INT, DEFAULT_UMASK, vsn(1, 0, 0), NULL, 0, NULL,
 	"The file creation mask for any files and directories created.\n"
 	"Interpreted as octal if the first digit is zero.\n")
 
-cfg(global_test_CFG, "test", global_CFG_SECTION, 0, CFG_TYPE_BOOL, 0, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(global_test_CFG, "test", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, 0, vsn(1, 0, 0), NULL, 0, NULL,
 	"No on-disk metadata changes will be made in test mode.\n"
 	"Equivalent to having the -t option on every command.\n")
 
-cfg(global_units_CFG, "units", global_CFG_SECTION, CFG_PROFILABLE, CFG_TYPE_STRING, DEFAULT_UNITS, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(global_units_CFG, "units", global_CFG_SECTION, CFG_DEFAULT_COMMENTED | CFG_PROFILABLE, CFG_TYPE_STRING, DEFAULT_UNITS, vsn(1, 0, 0), NULL, 0, NULL,
 	"Default value for --units argument.\n")
 
-cfg(global_si_unit_consistency_CFG, "si_unit_consistency", global_CFG_SECTION, CFG_PROFILABLE, CFG_TYPE_BOOL, DEFAULT_SI_UNIT_CONSISTENCY,  vsn(2, 2, 54), NULL, 0, NULL,
+cfg(global_si_unit_consistency_CFG, "si_unit_consistency", global_CFG_SECTION, CFG_DEFAULT_COMMENTED | CFG_PROFILABLE, CFG_TYPE_BOOL, DEFAULT_SI_UNIT_CONSISTENCY,  vsn(2, 2, 54), NULL, 0, NULL,
 	"Distinguish between powers of 1024 and 1000 bytes.\n"
 	"The LVM commands distinguish between powers of 1024 bytes,\n"
 	"e.g. KiB, MiB, GiB, and powers of 1000 bytes, e.g. KB, MB, GB.\n"
 	"If scripts depend on the old behaviour, disable this setting\n"
 	"temporarily until they are updated.\n")
 
-cfg(global_suffix_CFG, "suffix", global_CFG_SECTION, CFG_PROFILABLE, CFG_TYPE_BOOL, DEFAULT_SUFFIX, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(global_suffix_CFG, "suffix", global_CFG_SECTION, CFG_DEFAULT_COMMENTED | CFG_PROFILABLE, CFG_TYPE_BOOL, DEFAULT_SUFFIX, vsn(1, 0, 0), NULL, 0, NULL,
 	"Display unit suffix for sizes.\n"
 	"This setting has no effect if the units are in human-readable form\n"
 	"(global/units = \"h\") in which case the suffix is always displayed.\n")
 
-cfg(global_activation_CFG, "activation", global_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_ACTIVATION, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(global_activation_CFG, "activation", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_ACTIVATION, vsn(1, 0, 0), NULL, 0, NULL,
 	"Enable/disable communication with the kernel device-mapper.\n"
 	"Disable to use the tools to manipulate LVM metadata without\n"
 	"activating any logical volumes. If the device-mapper driver\n"
@@ -940,70 +974,69 @@ cfg(global_activation_CFG, "activation", global_CFG_SECTION, 0, CFG_TYPE_BOOL, D
 	"the error messages.\n")
 
 cfg(global_fallback_to_lvm1_CFG, "fallback_to_lvm1", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, 0, vsn(1, 0, 18), NULL, vsn(2, 3, 0), NULL,
-	"This setting is no longer used.\n")
+	NULL)
 
 cfg(global_format_CFG, "format", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_FORMAT, vsn(1, 0, 0), NULL, vsn(2, 3, 0), NULL,
-	"This setting is no longer used.\n")
+	NULL)
 
 cfg_array(global_format_libraries_CFG, "format_libraries", global_CFG_SECTION, CFG_DEFAULT_UNDEFINED, CFG_TYPE_STRING, NULL, vsn(1, 0, 0), NULL, vsn(2, 3, 0), NULL,
-	"This setting is no longer used.")
+	  NULL)
 
 cfg_array(global_segment_libraries_CFG, "segment_libraries", global_CFG_SECTION, CFG_DEFAULT_UNDEFINED, CFG_TYPE_STRING, NULL, vsn(1, 0, 18), NULL, vsn(2, 3, 3), NULL, NULL)
 
-cfg(global_proc_CFG, "proc", global_CFG_SECTION, CFG_ADVANCED, CFG_TYPE_STRING, DEFAULT_PROC_DIR, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(global_proc_CFG, "proc", global_CFG_SECTION, CFG_DEFAULT_COMMENTED | CFG_ADVANCED, CFG_TYPE_STRING, DEFAULT_PROC_DIR, vsn(1, 0, 0), NULL, 0, NULL,
 	"Location of proc filesystem.\n")
 
-cfg(global_etc_CFG, "etc", global_CFG_SECTION, 0, CFG_TYPE_STRING, DEFAULT_ETC_DIR, vsn(2, 2, 117), "@CONFDIR@", 0, NULL,
+cfg(global_etc_CFG, "etc", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_ETC_DIR, vsn(2, 2, 117), "@CONFDIR@", 0, NULL,
 	"Location of /etc system configuration directory.\n")
 
-cfg(global_locking_type_CFG, "locking_type", global_CFG_SECTION, 0, CFG_TYPE_INT, 1, vsn(1, 0, 0), NULL, vsn(2, 3, 0), NULL,
-	"This setting is no longer used.")
+cfg(global_locking_type_CFG, "locking_type", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, 1, vsn(1, 0, 0), NULL, vsn(2, 3, 0), NULL,
+    NULL)
 
-cfg(global_wait_for_locks_CFG, "wait_for_locks", global_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_WAIT_FOR_LOCKS, vsn(2, 2, 50), NULL, 0, NULL,
+cfg(global_wait_for_locks_CFG, "wait_for_locks", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_WAIT_FOR_LOCKS, vsn(2, 2, 50), NULL, 0, NULL,
 	"When disabled, fail if a lock request would block.\n")
 
-cfg(global_fallback_to_clustered_locking_CFG, "fallback_to_clustered_locking", global_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_FALLBACK_TO_CLUSTERED_LOCKING, vsn(2, 2, 42), NULL, vsn(2, 3, 0), NULL,
-	"This setting is no longer used.\n")
+cfg(global_fallback_to_clustered_locking_CFG, "fallback_to_clustered_locking", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_FALLBACK_TO_CLUSTERED_LOCKING, vsn(2, 2, 42), NULL, vsn(2, 3, 0), NULL,
+	NULL)
 
-cfg(global_fallback_to_local_locking_CFG, "fallback_to_local_locking", global_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_FALLBACK_TO_LOCAL_LOCKING, vsn(2, 2, 42), NULL, vsn(2, 3, 0), NULL,
-	"This setting is no longer used.\n")
+cfg(global_fallback_to_local_locking_CFG, "fallback_to_local_locking", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_FALLBACK_TO_LOCAL_LOCKING, vsn(2, 2, 42), NULL, vsn(2, 3, 0), NULL,
+	NULL)
 
-cfg(global_locking_dir_CFG, "locking_dir", global_CFG_SECTION, 0, CFG_TYPE_STRING, DEFAULT_LOCK_DIR, vsn(1, 0, 0), "@DEFAULT_LOCK_DIR@", 0, NULL,
+cfg(global_locking_dir_CFG, "locking_dir", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_LOCK_DIR, vsn(1, 0, 0), "@DEFAULT_LOCK_DIR@", 0, NULL,
 	"Directory to use for LVM command file locks.\n"
 	"Local non-LV directory that holds file-based locks while commands are\n"
 	"in progress. A directory like /tmp that may get wiped on reboot is OK.\n")
 
-cfg(global_prioritise_write_locks_CFG, "prioritise_write_locks", global_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_PRIORITISE_WRITE_LOCKS, vsn(2, 2, 52), NULL, 0, NULL,
+cfg(global_prioritise_write_locks_CFG, "prioritise_write_locks", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_PRIORITISE_WRITE_LOCKS, vsn(2, 2, 52), NULL, 0, NULL,
 	"Allow quicker VG write access during high volume read access.\n"
 	"When there are competing read-only and read-write access requests for\n"
 	"a volume group's metadata, instead of always granting the read-only\n"
 	"requests immediately, delay them to allow the read-write requests to\n"
 	"be serviced. Without this setting, write access may be stalled by a\n"
-	"high volume of read-only requests. This option only affects\n"
-	"locking_type 1 viz. local file-based locking.\n")
+	"high volume of read-only requests. This option only affects file locks.\n")
 
 cfg(global_library_dir_CFG, "library_dir", global_CFG_SECTION, CFG_DEFAULT_UNDEFINED, CFG_TYPE_STRING, NULL, vsn(1, 0, 0), NULL, 0, NULL,
 	"Search this directory first for shared libraries.\n")
 
 cfg(global_locking_library_CFG, "locking_library", global_CFG_SECTION, CFG_ALLOW_EMPTY | CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_LOCKING_LIB, vsn(1, 0, 0), NULL, vsn(2, 3, 0), NULL,
-	"This setting is no longer used.\n")
+	NULL)
 
-cfg(global_abort_on_internal_errors_CFG, "abort_on_internal_errors", global_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_ABORT_ON_INTERNAL_ERRORS, vsn(2, 2, 57), NULL, 0, NULL,
+cfg(global_abort_on_internal_errors_CFG, "abort_on_internal_errors", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_ABORT_ON_INTERNAL_ERRORS, vsn(2, 2, 57), NULL, 0, NULL,
 	"Abort a command that encounters an internal error.\n"
 	"Treat any internal errors as fatal errors, aborting the process that\n"
 	"encountered the internal error. Please only enable for debugging.\n")
 
-cfg(global_detect_internal_vg_cache_corruption_CFG, "detect_internal_vg_cache_corruption", global_CFG_SECTION, 0, CFG_TYPE_BOOL, 0, vsn(2, 2, 96), NULL, vsn(2, 2, 174), NULL,
-	"No longer used.\n")
+cfg(global_detect_internal_vg_cache_corruption_CFG, "detect_internal_vg_cache_corruption", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, 0, vsn(2, 2, 96), NULL, vsn(2, 2, 174), NULL,
+	NULL)
 
-cfg(global_metadata_read_only_CFG, "metadata_read_only", global_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_METADATA_READ_ONLY, vsn(2, 2, 75), NULL, 0, NULL,
+cfg(global_metadata_read_only_CFG, "metadata_read_only", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_METADATA_READ_ONLY, vsn(2, 2, 75), NULL, 0, NULL,
 	"No operations that change on-disk metadata are permitted.\n"
 	"Additionally, read-only commands that encounter metadata in need of\n"
 	"repair will still be allowed to proceed exactly as if the repair had\n"
 	"been performed (except for the unchanged vg_seqno). Inappropriate\n"
 	"use could mess up your system, so seek advice first!\n")
 
-cfg(global_mirror_segtype_default_CFG, "mirror_segtype_default", global_CFG_SECTION, 0, CFG_TYPE_STRING, DEFAULT_MIRROR_SEGTYPE, vsn(2, 2, 87), "@DEFAULT_MIRROR_SEGTYPE@", 0, NULL,
+cfg(global_mirror_segtype_default_CFG, "mirror_segtype_default", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_MIRROR_SEGTYPE, vsn(2, 2, 87), "@DEFAULT_MIRROR_SEGTYPE@", 0, NULL,
 	"The segment type used by the short mirroring option -m.\n"
 	"The --type mirror|raid1 option overrides this setting.\n"
 	"#\n"
@@ -1028,7 +1061,7 @@ cfg(global_mirror_segtype_default_CFG, "mirror_segtype_default", global_CFG_SECT
 	"    fashion in a cluster.\n"
 	"#\n")
 
-cfg(global_support_mirrored_mirror_log_CFG, "support_mirrored_mirror_log", global_CFG_SECTION, 0, CFG_TYPE_BOOL, 0, vsn(2, 3, 2), NULL, 0, NULL,
+cfg(global_support_mirrored_mirror_log_CFG, "support_mirrored_mirror_log", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, 0, vsn(2, 3, 2), NULL, 0, NULL,
 	"Enable mirrored 'mirror' log type for testing.\n"
 	"#\n"
 	"This type is deprecated to create or convert to but can\n"
@@ -1038,7 +1071,7 @@ cfg(global_support_mirrored_mirror_log_CFG, "support_mirrored_mirror_log", globa
 	"Not supported for regular operation!\n"
 	"\n")
 
-cfg(global_raid10_segtype_default_CFG, "raid10_segtype_default", global_CFG_SECTION, 0, CFG_TYPE_STRING, DEFAULT_RAID10_SEGTYPE, vsn(2, 2, 99), "@DEFAULT_RAID10_SEGTYPE@", 0, NULL,
+cfg(global_raid10_segtype_default_CFG, "raid10_segtype_default", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_RAID10_SEGTYPE, vsn(2, 2, 99), "@DEFAULT_RAID10_SEGTYPE@", 0, NULL,
 	"The segment type used by the -i -m combination.\n"
 	"The --type raid10|mirror option overrides this setting.\n"
 	"The --stripes/-i and --mirrors/-m options can both be specified\n"
@@ -1056,7 +1089,7 @@ cfg(global_raid10_segtype_default_CFG, "raid10_segtype_default", global_CFG_SECT
 	"    in terms of providing redundancy and performance.\n"
 	"#\n")
 
-cfg(global_sparse_segtype_default_CFG, "sparse_segtype_default", global_CFG_SECTION, 0, CFG_TYPE_STRING, DEFAULT_SPARSE_SEGTYPE, vsn(2, 2, 112), "@DEFAULT_SPARSE_SEGTYPE@", 0, NULL,
+cfg(global_sparse_segtype_default_CFG, "sparse_segtype_default", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_SPARSE_SEGTYPE, vsn(2, 2, 112), "@DEFAULT_SPARSE_SEGTYPE@", 0, NULL,
 	"The segment type used by the -V -L combination.\n"
 	"The --type snapshot|thin option overrides this setting.\n"
 	"The combination of -V and -L options creates a sparse LV. There are\n"
@@ -1082,7 +1115,7 @@ cfg(global_lvdisplay_shows_full_device_path_CFG, "lvdisplay_shows_full_device_pa
 	"Previously this was always shown as /dev/vgname/lvname even when that\n"
 	"was never a valid path in the /dev filesystem.\n")
 
-cfg(global_event_activation_CFG, "event_activation", global_CFG_SECTION, 0, CFG_TYPE_BOOL, 1, vsn(2, 3, 1), 0, 0, NULL,
+cfg(global_event_activation_CFG, "event_activation", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, 1, vsn(2, 3, 1), 0, 0, NULL,
 	"Activate LVs based on system-generated device events.\n"
 	"When a device appears on the system, a system-generated event runs\n"
 	"the pvscan command to activate LVs if the new PV completes the VG.\n"
@@ -1091,16 +1124,16 @@ cfg(global_event_activation_CFG, "event_activation", global_CFG_SECTION, 0, CFG_
 	"When event_activation is disabled, the system will generally run\n"
 	"a direct activation command to activate LVs in complete VGs.\n")
 
-cfg(global_use_lvmetad_CFG, "use_lvmetad", global_CFG_SECTION, 0, CFG_TYPE_BOOL, 0, vsn(2, 2, 93), 0, vsn(2, 3, 0), NULL,
-	"This setting is no longer used.\n")
+cfg(global_use_lvmetad_CFG, "use_lvmetad", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, 0, vsn(2, 2, 93), 0, vsn(2, 3, 0), NULL,
+	NULL)
 
 cfg(global_lvmetad_update_wait_time_CFG, "lvmetad_update_wait_time", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, 0, vsn(2, 2, 151), NULL, vsn(2, 3, 0), NULL,
-	"This setting is no longer used.\n")
+	NULL)
 
 cfg(global_use_aio_CFG, "use_aio", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_USE_AIO, vsn(2, 2, 183), NULL, 0, NULL,
 	"Use async I/O when reading and writing devices.\n")
 
-cfg(global_use_lvmlockd_CFG, "use_lvmlockd", global_CFG_SECTION, 0, CFG_TYPE_BOOL, 0, vsn(2, 2, 124), NULL, 0, NULL,
+cfg(global_use_lvmlockd_CFG, "use_lvmlockd", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, 0, vsn(2, 2, 124), NULL, 0, NULL,
 	"Use lvmlockd for locking among hosts using LVM on shared storage.\n"
 	"Applicable only if LVM is compiled with lockd support in which\n"
 	"case there is also lvmlockd(8) man page available for more\n"
@@ -1204,11 +1237,20 @@ cfg(global_vdo_format_executable_CFG, "vdo_format_executable", global_CFG_SECTIO
 cfg_array(global_vdo_format_options_CFG, "vdo_format_options", global_CFG_SECTION, CFG_ALLOW_EMPTY | CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_VDO_FORMAT_OPTIONS_CONFIG, VDO_1ST_VSN, NULL, 0, NULL,
 	"List of options passed added to standard vdoformat command.\n")
 
+cfg_array(global_vdo_disabled_features_CFG, "vdo_disabled_features", global_CFG_SECTION, CFG_ALLOW_EMPTY | CFG_DEFAULT_UNDEFINED, CFG_TYPE_STRING, NULL, vsn(2, 3, 11), NULL, 0, NULL,
+	"Features to not use in the vdo driver.\n"
+	"This can be helpful for testing, or to avoid using a feature that is\n"
+	"causing problems. Features include: online_rename\n"
+	"#\n"
+	"Example\n"
+	"vdo_disabled_features = [ \"online_rename\" ]\n"
+	"#\n")
+
 cfg(global_fsadm_executable_CFG, "fsadm_executable", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_FSADM_PATH, vsn(2, 2, 170), "@FSADM_PATH@", 0, NULL,
 	"The full path to the fsadm command.\n"
 	"LVM uses this command to help with lvresize -r operations.\n")
 
-cfg(global_system_id_source_CFG, "system_id_source", global_CFG_SECTION, 0, CFG_TYPE_STRING, DEFAULT_SYSTEM_ID_SOURCE, vsn(2, 2, 117), NULL, 0, NULL,
+cfg(global_system_id_source_CFG, "system_id_source", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_SYSTEM_ID_SOURCE, vsn(2, 2, 117), NULL, 0, NULL,
 	"The method LVM uses to set the local system ID.\n"
 	"Volume Groups can also be given a system ID (by vgcreate, vgchange,\n"
 	"or vgimport.) A VG on shared storage devices is accessible only to\n"
@@ -1238,13 +1280,13 @@ cfg(global_system_id_file_CFG, "system_id_file", global_CFG_SECTION, CFG_DEFAULT
 	"This is used when system_id_source is set to 'file'.\n"
 	"Comments starting with the character # are ignored.\n")
 
-cfg(activation_checks_CFG, "checks", activation_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_ACTIVATION_CHECKS, vsn(2, 2, 86), NULL, 0, NULL,
+cfg(activation_checks_CFG, "checks", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_ACTIVATION_CHECKS, vsn(2, 2, 86), NULL, 0, NULL,
 	"Perform internal checks of libdevmapper operations.\n"
 	"Useful for debugging problems with activation. Some of the checks may\n"
 	"be expensive, so it's best to use this only when there seems to be a\n"
 	"problem.\n")
 
-cfg(global_use_lvmpolld_CFG, "use_lvmpolld", global_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_USE_LVMPOLLD, vsn(2, 2, 120), "@DEFAULT_USE_LVMPOLLD@", 0, NULL,
+cfg(global_use_lvmpolld_CFG, "use_lvmpolld", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_USE_LVMPOLLD, vsn(2, 2, 120), "@DEFAULT_USE_LVMPOLLD@", 0, NULL,
 	"Use lvmpolld to supervise long running LVM commands.\n"
 	"When enabled, control of long running LVM commands is transferred\n"
 	"from the original LVM command to the lvmpolld daemon. This allows\n"
@@ -1257,7 +1299,7 @@ cfg(global_use_lvmpolld_CFG, "use_lvmpolld", global_CFG_SECTION, 0, CFG_TYPE_BOO
 	"commands will supervise long running operations by forking themselves.\n"
 	"Applicable only if LVM is compiled with lvmpolld support.\n")
 
-cfg(global_notify_dbus_CFG, "notify_dbus", global_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_NOTIFY_DBUS, vsn(2, 2, 145), NULL, 0, NULL,
+cfg(global_notify_dbus_CFG, "notify_dbus", global_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_NOTIFY_DBUS, vsn(2, 2, 145), NULL, 0, NULL,
 	"Enable D-Bus notification from LVM commands.\n"
 	"When enabled, an LVM command that changes PVs, changes VG metadata,\n"
 	"or changes the activation state of an LV will send a notification.\n")
@@ -1270,7 +1312,7 @@ cfg(global_io_memory_size_CFG, "io_memory_size", global_CFG_SECTION, CFG_DEFAULT
 	"This value should usually not be decreased from the default; setting\n"
 	"it too low can result in lvm failing to read VGs.\n")
 
-cfg(activation_udev_sync_CFG, "udev_sync", activation_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_UDEV_SYNC, vsn(2, 2, 51), NULL, 0, NULL,
+cfg(activation_udev_sync_CFG, "udev_sync", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_UDEV_SYNC, vsn(2, 2, 51), NULL, 0, NULL,
 	"Use udev notifications to synchronize udev and LVM.\n"
 	"The --nodevsync option overrides this setting.\n"
 	"When disabled, LVM commands will not wait for notifications from\n"
@@ -1280,25 +1322,25 @@ cfg(activation_udev_sync_CFG, "udev_sync", activation_CFG_SECTION, 0, CFG_TYPE_B
 	"running, and LVM processes are waiting for udev, run the command\n"
 	"'dmsetup udevcomplete_all' to wake them up.\n")
 
-cfg(activation_udev_rules_CFG, "udev_rules", activation_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_UDEV_RULES, vsn(2, 2, 57), NULL, 0, NULL,
+cfg(activation_udev_rules_CFG, "udev_rules", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_UDEV_RULES, vsn(2, 2, 57), NULL, 0, NULL,
 	"Use udev rules to manage LV device nodes and symlinks.\n"
 	"When disabled, LVM will manage the device nodes and symlinks for\n"
 	"active LVs itself. Manual intervention may be required if this\n"
 	"setting is changed while LVs are active.\n")
 
-cfg(activation_verify_udev_operations_CFG, "verify_udev_operations", activation_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_VERIFY_UDEV_OPERATIONS, vsn(2, 2, 86), NULL, 0, NULL,
+cfg(activation_verify_udev_operations_CFG, "verify_udev_operations", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_VERIFY_UDEV_OPERATIONS, vsn(2, 2, 86), NULL, 0, NULL,
 	"Use extra checks in LVM to verify udev operations.\n"
 	"This enables additional checks (and if necessary, repairs) on entries\n"
 	"in the device directory after udev has completed processing its\n"
 	"events. Useful for diagnosing problems with LVM/udev interactions.\n")
 
-cfg(activation_retry_deactivation_CFG, "retry_deactivation", activation_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_RETRY_DEACTIVATION, vsn(2, 2, 89), NULL, 0, NULL,
+cfg(activation_retry_deactivation_CFG, "retry_deactivation", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_RETRY_DEACTIVATION, vsn(2, 2, 89), NULL, 0, NULL,
 	"Retry failed LV deactivation.\n"
 	"If LV deactivation fails, LVM will retry for a few seconds before\n"
 	"failing. This may happen because a process run from a quick udev rule\n"
 	"temporarily opened the device.\n")
 
-cfg(activation_missing_stripe_filler_CFG, "missing_stripe_filler", activation_CFG_SECTION, CFG_ADVANCED, CFG_TYPE_STRING, DEFAULT_STRIPE_FILLER, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(activation_missing_stripe_filler_CFG, "missing_stripe_filler", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED | CFG_ADVANCED, CFG_TYPE_STRING, DEFAULT_STRIPE_FILLER, vsn(1, 0, 0), NULL, 0, NULL,
 	"Method to fill missing stripes when activating an incomplete LV.\n"
 	"Using 'error' will make inaccessible parts of the device return I/O\n"
 	"errors on access. Using 'zero' will return success (and zero) on I/O\n"
@@ -1307,21 +1349,21 @@ cfg(activation_missing_stripe_filler_CFG, "missing_stripe_filler", activation_CF
 	"other than 'error' with mirrored or snapshotted volumes is likely to\n"
 	"result in data corruption.\n")
 
-cfg(activation_use_linear_target_CFG, "use_linear_target", activation_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_USE_LINEAR_TARGET, vsn(2, 2, 89), NULL, 0, NULL,
+cfg(activation_use_linear_target_CFG, "use_linear_target", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_USE_LINEAR_TARGET, vsn(2, 2, 89), NULL, 0, NULL,
 	"Use the linear target to optimize single stripe LVs.\n"
 	"When disabled, the striped target is used. The linear target is an\n"
 	"optimised version of the striped target that only handles a single\n"
 	"stripe.\n")
 
-cfg(activation_reserved_stack_CFG, "reserved_stack", activation_CFG_SECTION, 0, CFG_TYPE_INT, DEFAULT_RESERVED_STACK, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(activation_reserved_stack_CFG, "reserved_stack", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, DEFAULT_RESERVED_STACK, vsn(1, 0, 0), NULL, 0, NULL,
 	"Stack size in KiB to reserve for use while devices are suspended.\n"
 	"Insufficent reserve risks I/O deadlock during device suspension.\n")
 
-cfg(activation_reserved_memory_CFG, "reserved_memory", activation_CFG_SECTION, 0, CFG_TYPE_INT, DEFAULT_RESERVED_MEMORY, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(activation_reserved_memory_CFG, "reserved_memory", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, DEFAULT_RESERVED_MEMORY, vsn(1, 0, 0), NULL, 0, NULL,
 	"Memory size in KiB to reserve for use while devices are suspended.\n"
 	"Insufficent reserve risks I/O deadlock during device suspension.\n")
 
-cfg(activation_process_priority_CFG, "process_priority", activation_CFG_SECTION, 0, CFG_TYPE_INT, DEFAULT_PROCESS_PRIORITY, vsn(1, 0, 0), NULL, 0, NULL,
+cfg(activation_process_priority_CFG, "process_priority", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, DEFAULT_PROCESS_PRIORITY, vsn(1, 0, 0), NULL, 0, NULL,
 	"Nice value used while devices are suspended.\n"
 	"Use a high priority so that LVs are suspended\n"
 	"for the shortest possible time.\n")
@@ -1411,11 +1453,11 @@ cfg_array(activation_read_only_volume_list_CFG, "read_only_volume_list", activat
 	"read_only_volume_list = [ \"vg1\", \"vg2/lvol1\", \"@tag1\", \"@*\" ]\n"
 	"#\n")
 
- cfg(activation_mirror_region_size_CFG, "mirror_region_size", activation_CFG_SECTION, 0, CFG_TYPE_INT, DEFAULT_RAID_REGION_SIZE, vsn(1, 0, 0), NULL, vsn(2, 2, 99),
+ cfg(activation_mirror_region_size_CFG, "mirror_region_size", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, DEFAULT_RAID_REGION_SIZE, vsn(1, 0, 0), NULL, vsn(2, 2, 99),
 	"This has been replaced by the activation/raid_region_size setting.\n",
 	"Size in KiB of each raid or mirror synchronization region.\n")
 
-cfg(activation_raid_region_size_CFG, "raid_region_size", activation_CFG_SECTION, 0, CFG_TYPE_INT, DEFAULT_RAID_REGION_SIZE, vsn(2, 2, 99), NULL, 0, NULL,
+cfg(activation_raid_region_size_CFG, "raid_region_size", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, DEFAULT_RAID_REGION_SIZE, vsn(2, 2, 99), NULL, 0, NULL,
 	"Size in KiB of each raid or mirror synchronization region.\n"
 	"The clean/dirty state of data is tracked for each region.\n"
 	"The value is rounded down to a power of two if necessary, and\n"
@@ -1430,7 +1472,7 @@ cfg(activation_error_when_full_CFG, "error_when_full", activation_CFG_SECTION, C
 	"thin pool data space is extended. New thin pools are assigned the\n"
 	"behavior defined here.\n")
 
-cfg(activation_readahead_CFG, "readahead", activation_CFG_SECTION, 0, CFG_TYPE_STRING, DEFAULT_READ_AHEAD, vsn(1, 0, 23), NULL, 0, NULL,
+cfg(activation_readahead_CFG, "readahead", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_READ_AHEAD, vsn(1, 0, 23), NULL, 0, NULL,
 	"Setting to use when there is no readahead setting in metadata.\n"
 	"#\n"
 	"Accepted values:\n"
@@ -1440,7 +1482,7 @@ cfg(activation_readahead_CFG, "readahead", activation_CFG_SECTION, 0, CFG_TYPE_S
 	"    Use default value chosen by kernel.\n"
 	"#\n")
 
-cfg(activation_raid_fault_policy_CFG, "raid_fault_policy", activation_CFG_SECTION, 0, CFG_TYPE_STRING, DEFAULT_RAID_FAULT_POLICY, vsn(2, 2, 89), NULL, 0, NULL,
+cfg(activation_raid_fault_policy_CFG, "raid_fault_policy", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_RAID_FAULT_POLICY, vsn(2, 2, 89), NULL, 0, NULL,
 	"Defines how a device failure in a RAID LV is handled.\n"
 	"This includes LVs that have the following segment types:\n"
 	"raid1, raid4, raid5*, and raid6*.\n"
@@ -1461,7 +1503,7 @@ cfg(activation_raid_fault_policy_CFG, "raid_fault_policy", activation_CFG_SECTIO
 	"    replace faulty devices.\n"
 	"#\n")
 
-cfg_runtime(activation_mirror_image_fault_policy_CFG, "mirror_image_fault_policy", activation_CFG_SECTION, 0, CFG_TYPE_STRING, vsn(2, 2, 57), 0, NULL,
+cfg_runtime(activation_mirror_image_fault_policy_CFG, "mirror_image_fault_policy", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, vsn(2, 2, 57), 0, NULL,
 	"Defines how a device failure in a 'mirror' LV is handled.\n"
 	"An LV with the 'mirror' segment type is composed of mirror images\n"
 	"(copies) and a mirror log. A disk log ensures that a mirror LV does\n"
@@ -1497,16 +1539,16 @@ cfg_runtime(activation_mirror_image_fault_policy_CFG, "mirror_image_fault_policy
 	"    replacement.\n"
 	"#\n")
 
-cfg(activation_mirror_log_fault_policy_CFG, "mirror_log_fault_policy", activation_CFG_SECTION, 0, CFG_TYPE_STRING, DEFAULT_MIRROR_LOG_FAULT_POLICY, vsn(1, 2, 18), NULL, 0, NULL,
+cfg(activation_mirror_log_fault_policy_CFG, "mirror_log_fault_policy", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_MIRROR_LOG_FAULT_POLICY, vsn(1, 2, 18), NULL, 0, NULL,
 	"Defines how a device failure in a 'mirror' log LV is handled.\n"
 	"The mirror_image_fault_policy description for mirrored LVs also\n"
 	"applies to mirrored log LVs.\n")
 
-cfg(activation_mirror_device_fault_policy_CFG, "mirror_device_fault_policy", activation_CFG_SECTION, 0, CFG_TYPE_STRING, DEFAULT_MIRROR_DEVICE_FAULT_POLICY, vsn(1, 2, 10), NULL, vsn(2, 2, 57),
+cfg(activation_mirror_device_fault_policy_CFG, "mirror_device_fault_policy", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_MIRROR_DEVICE_FAULT_POLICY, vsn(1, 2, 10), NULL, vsn(2, 2, 57),
 	"This has been replaced by the activation/mirror_image_fault_policy setting.\n",
 	"Define how a device failure affecting a mirror is handled.\n")
 
-cfg(activation_snapshot_autoextend_threshold_CFG, "snapshot_autoextend_threshold", activation_CFG_SECTION, 0, CFG_TYPE_INT, DEFAULT_SNAPSHOT_AUTOEXTEND_THRESHOLD, vsn(2, 2, 75), NULL, 0, NULL,
+cfg(activation_snapshot_autoextend_threshold_CFG, "snapshot_autoextend_threshold", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, DEFAULT_SNAPSHOT_AUTOEXTEND_THRESHOLD, vsn(2, 2, 75), NULL, 0, NULL,
 	"Auto-extend a snapshot when its usage exceeds this percent.\n"
 	"Setting this to 100 disables automatic extension.\n"
 	"The minimum value is 50 (a smaller value is treated as 50.)\n"
@@ -1520,7 +1562,7 @@ cfg(activation_snapshot_autoextend_threshold_CFG, "snapshot_autoextend_threshold
 	"snapshot_autoextend_threshold = 70\n"
 	"#\n")
 
-cfg(activation_snapshot_autoextend_percent_CFG, "snapshot_autoextend_percent", activation_CFG_SECTION, 0, CFG_TYPE_INT, DEFAULT_SNAPSHOT_AUTOEXTEND_PERCENT, vsn(2, 2, 75), NULL, 0, NULL,
+cfg(activation_snapshot_autoextend_percent_CFG, "snapshot_autoextend_percent", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, DEFAULT_SNAPSHOT_AUTOEXTEND_PERCENT, vsn(2, 2, 75), NULL, 0, NULL,
 	"Auto-extending a snapshot adds this percent extra space.\n"
 	"The amount of additional space added to a snapshot is this\n"
 	"percent of its current size.\n"
@@ -1532,7 +1574,7 @@ cfg(activation_snapshot_autoextend_percent_CFG, "snapshot_autoextend_percent", a
 	"snapshot_autoextend_percent = 20\n"
 	"#\n")
 
-cfg(activation_thin_pool_autoextend_threshold_CFG, "thin_pool_autoextend_threshold", activation_CFG_SECTION, CFG_PROFILABLE | CFG_PROFILABLE_METADATA, CFG_TYPE_INT, DEFAULT_THIN_POOL_AUTOEXTEND_THRESHOLD, vsn(2, 2, 89), NULL, 0, NULL,
+cfg(activation_thin_pool_autoextend_threshold_CFG, "thin_pool_autoextend_threshold", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED | CFG_PROFILABLE | CFG_PROFILABLE_METADATA, CFG_TYPE_INT, DEFAULT_THIN_POOL_AUTOEXTEND_THRESHOLD, vsn(2, 2, 89), NULL, 0, NULL,
 	"Auto-extend a thin pool when its usage exceeds this percent.\n"
 	"Setting this to 100 disables automatic extension.\n"
 	"The minimum value is 50 (a smaller value is treated as 50.)\n"
@@ -1546,7 +1588,7 @@ cfg(activation_thin_pool_autoextend_threshold_CFG, "thin_pool_autoextend_thresho
 	"thin_pool_autoextend_threshold = 70\n"
 	"#\n")
 
-cfg(activation_thin_pool_autoextend_percent_CFG, "thin_pool_autoextend_percent", activation_CFG_SECTION, CFG_PROFILABLE | CFG_PROFILABLE_METADATA, CFG_TYPE_INT, DEFAULT_THIN_POOL_AUTOEXTEND_PERCENT, vsn(2, 2, 89), NULL, 0, NULL,
+cfg(activation_thin_pool_autoextend_percent_CFG, "thin_pool_autoextend_percent", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED | CFG_PROFILABLE | CFG_PROFILABLE_METADATA, CFG_TYPE_INT, DEFAULT_THIN_POOL_AUTOEXTEND_PERCENT, vsn(2, 2, 89), NULL, 0, NULL,
 	"Auto-extending a thin pool adds this percent extra space.\n"
 	"The amount of additional space added to a thin pool is this\n"
 	"percent of its current size.\n"
@@ -1558,7 +1600,7 @@ cfg(activation_thin_pool_autoextend_percent_CFG, "thin_pool_autoextend_percent",
 	"thin_pool_autoextend_percent = 20\n"
 	"#\n")
 
-cfg(activation_vdo_pool_autoextend_threshold_CFG, "vdo_pool_autoextend_threshold", activation_CFG_SECTION, CFG_PROFILABLE | CFG_PROFILABLE_METADATA, CFG_TYPE_INT, DEFAULT_VDO_POOL_AUTOEXTEND_THRESHOLD, VDO_1ST_VSN, NULL, 0, NULL,
+cfg(activation_vdo_pool_autoextend_threshold_CFG, "vdo_pool_autoextend_threshold", activation_CFG_SECTION, CFG_PROFILABLE | CFG_PROFILABLE_METADATA | CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, DEFAULT_VDO_POOL_AUTOEXTEND_THRESHOLD, VDO_1ST_VSN, NULL, 0, NULL,
 	"Auto-extend a VDO pool when its usage exceeds this percent.\n"
 	"Setting this to 100 disables automatic extension.\n"
 	"The minimum value is 50 (a smaller value is treated as 50.)\n"
@@ -1598,17 +1640,17 @@ cfg_array(activation_mlock_filter_CFG, "mlock_filter", activation_CFG_SECTION, C
 	"mlock_filter = [ \"locale/locale-archive\", \"gconv/gconv-modules.cache\" ]\n"
 	"#\n")
 
-cfg(activation_use_mlockall_CFG, "use_mlockall", activation_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_USE_MLOCKALL, vsn(2, 2, 62), NULL, 0, NULL,
+cfg(activation_use_mlockall_CFG, "use_mlockall", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_USE_MLOCKALL, vsn(2, 2, 62), NULL, 0, NULL,
 	"Use the old behavior of mlockall to pin all memory.\n"
 	"Prior to version 2.02.62, LVM used mlockall() to pin the whole\n"
 	"process's memory while activating devices.\n")
 
-cfg(activation_monitoring_CFG, "monitoring", activation_CFG_SECTION, 0, CFG_TYPE_BOOL, DEFAULT_DMEVENTD_MONITOR, vsn(2, 2, 63), NULL, 0, NULL,
+cfg(activation_monitoring_CFG, "monitoring", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_BOOL, DEFAULT_DMEVENTD_MONITOR, vsn(2, 2, 63), NULL, 0, NULL,
 	"Monitor LVs that are activated.\n"
 	"The --ignoremonitoring option overrides this setting.\n"
 	"When enabled, LVM will ask dmeventd to monitor activated LVs.\n")
 
-cfg(activation_polling_interval_CFG, "polling_interval", activation_CFG_SECTION, 0, CFG_TYPE_INT, DEFAULT_INTERVAL, vsn(2, 2, 63), NULL, 0, NULL,
+cfg(activation_polling_interval_CFG, "polling_interval", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, DEFAULT_INTERVAL, vsn(2, 2, 63), NULL, 0, NULL,
 	"Check pvmove or lvconvert progress at this interval (seconds).\n"
 	"When pvmove or lvconvert must wait for the kernel to finish\n"
 	"synchronising or merging data, they check and report progress at\n"
@@ -1625,7 +1667,7 @@ cfg(activation_auto_set_activation_skip_CFG, "auto_set_activation_skip", activat
 	"flag set. When this setting is enabled, the activation skip flag is\n"
 	"set on new thin snapshot LVs.\n")
 
-cfg(activation_mode_CFG, "activation_mode", activation_CFG_SECTION, 0, CFG_TYPE_STRING, DEFAULT_ACTIVATION_MODE, vsn(2,2,108), NULL, 0, NULL,
+cfg(activation_mode_CFG, "activation_mode", activation_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_ACTIVATION_MODE, vsn(2,2,108), NULL, 0, NULL,
 	"How LVs with missing devices are activated.\n"
 	"The --activationmode option overrides this setting.\n"
 	"#\n"
@@ -1722,7 +1764,7 @@ cfg(metadata_pvmetadataignore_CFG, "pvmetadataignore", metadata_CFG_SECTION, CFG
 cfg(metadata_stripesize_CFG, "stripesize", metadata_CFG_SECTION, CFG_ADVANCED | CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, DEFAULT_STRIPESIZE, vsn(1, 0, 0), NULL, 0, NULL, NULL)
 
 cfg_array(metadata_dirs_CFG, "dirs", metadata_CFG_SECTION, CFG_ADVANCED | CFG_DEFAULT_UNDEFINED, CFG_TYPE_STRING, NULL, vsn(1, 0, 0), NULL, vsn(2, 3, 0), NULL,
-	  "This setting is no longer used.\n")
+	  NULL)
 
 cfg_section(metadata_disk_areas_CFG_SUBSECTION, "disk_areas", metadata_CFG_SECTION, CFG_UNSUPPORTED | CFG_DEFAULT_COMMENTED, vsn(1, 0, 0), vsn(2, 3, 0), NULL, NULL)
 cfg_section(disk_area_CFG_SUBSECTION, "disk_area", metadata_disk_areas_CFG_SUBSECTION, CFG_NAME_VARIABLE | CFG_UNSUPPORTED | CFG_DEFAULT_COMMENTED, vsn(1, 0, 0), vsn(2, 3, 0), NULL, NULL)
@@ -2047,7 +2089,7 @@ cfg(report_two_word_unknown_device_CFG, "two_word_unknown_device", report_CFG_SE
 	"Use the two words 'unknown device' in place of '[unknown]'.\n"
 	"This is displayed when the device for a PV is not known.\n")
 
-cfg(dmeventd_mirror_library_CFG, "mirror_library", dmeventd_CFG_SECTION, 0, CFG_TYPE_STRING, DEFAULT_DMEVENTD_MIRROR_LIB, vsn(1, 2, 3), NULL, 0, NULL,
+cfg(dmeventd_mirror_library_CFG, "mirror_library", dmeventd_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_DMEVENTD_MIRROR_LIB, vsn(1, 2, 3), NULL, 0, NULL,
 	"The library dmeventd uses when monitoring a mirror device.\n"
 	"libdevmapper-event-lvm2mirror.so attempts to recover from\n"
 	"failures. It removes failed devices from a volume group and\n"
@@ -2056,13 +2098,13 @@ cfg(dmeventd_mirror_library_CFG, "mirror_library", dmeventd_CFG_SECTION, 0, CFG_
 
 cfg(dmeventd_raid_library_CFG, "raid_library", dmeventd_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_DMEVENTD_RAID_LIB, vsn(2, 2, 87), NULL, 0, NULL, NULL)
 
-cfg(dmeventd_snapshot_library_CFG, "snapshot_library", dmeventd_CFG_SECTION, 0, CFG_TYPE_STRING, DEFAULT_DMEVENTD_SNAPSHOT_LIB, vsn(1, 2, 26), NULL, 0, NULL,
+cfg(dmeventd_snapshot_library_CFG, "snapshot_library", dmeventd_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_DMEVENTD_SNAPSHOT_LIB, vsn(1, 2, 26), NULL, 0, NULL,
 	"The library dmeventd uses when monitoring a snapshot device.\n"
 	"libdevmapper-event-lvm2snapshot.so monitors the filling of snapshots\n"
 	"and emits a warning through syslog when the usage exceeds 80%. The\n"
 	"warning is repeated when 85%, 90% and 95% of the snapshot is filled.\n")
 
-cfg(dmeventd_thin_library_CFG, "thin_library", dmeventd_CFG_SECTION, 0, CFG_TYPE_STRING, DEFAULT_DMEVENTD_THIN_LIB, vsn(2, 2, 89), NULL, 0, NULL,
+cfg(dmeventd_thin_library_CFG, "thin_library", dmeventd_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, DEFAULT_DMEVENTD_THIN_LIB, vsn(2, 2, 89), NULL, 0, NULL,
 	"The library dmeventd uses when monitoring a thin device.\n"
 	"libdevmapper-event-lvm2thin.so monitors the filling of a pool\n"
 	"and emits a warning through syslog when the usage exceeds 80%. The\n"
@@ -2148,4 +2190,4 @@ cfg(local_host_id_CFG, "host_id", local_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_
 	"This must be unique among all hosts, and must be between 1 and 2000.\n"
 	"Applicable only if LVM is compiled with lockd support\n")
 
-cfg(CFG_COUNT, NULL, root_CFG_SECTION, 0, CFG_TYPE_INT, 0, vsn(0, 0, 0), NULL, 0, NULL, NULL)
+cfg(CFG_COUNT, NULL, root_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, 0, vsn(0, 0, 0), NULL, 0, NULL, NULL)

lib/config/defaults.h

@@ -118,6 +118,8 @@
 #define DEFAULT_THIN_REPAIR_OPTION1 ""
 #define DEFAULT_THIN_REPAIR_OPTIONS_CONFIG "#S" DEFAULT_THIN_REPAIR_OPTION1
 #define DEFAULT_THIN_POOL_METADATA_REQUIRE_SEPARATE_PVS 0
+#define DEFAULT_THIN_POOL_CROP_METADATA 0
+#define DEFAULT_THIN_POOL_MAX_METADATA_SIZE_V1_KB (UINT64_C(255) * ((1 << 14) - 64) * 4)  /* KB */ /* 0x3f8040 blocks */
 #define DEFAULT_THIN_POOL_MAX_METADATA_SIZE (DM_THIN_MAX_METADATA_SIZE / 2)  /* KB */
 #define DEFAULT_THIN_POOL_MIN_METADATA_SIZE 2048  /* KB */
 #define DEFAULT_THIN_POOL_OPTIMAL_METADATA_SIZE (128 * 1024) /* KB */
@@ -129,6 +131,7 @@
 #define DEFAULT_THIN_POOL_DISCARDS "passdown"
 #define DEFAULT_THIN_POOL_ZERO 1
 #define DEFAULT_POOL_METADATA_SPARE 1 /* thin + cache */
+#define DEFAULT_ZERO_METADATA 1		/* thin + cache */
 
 #ifdef CACHE_CHECK_NEEDS_CHECK
 #  define DEFAULT_CACHE_CHECK_OPTION1 "-q"
@@ -320,4 +323,9 @@
 
 #define DEFAULT_MD_COMPONENT_CHECKS "auto"
 
+#define DEFAULT_USE_DEVICES_FILE 0
+#define DEFAULT_DEVICES_FILE "system.devices"
+
+#define DEFAULT_SEARCH_FOR_DEVNAMES "auto"
+
 #endif				/* _LVM_DEFAULTS_H */

lib/device/bcache-utils.c

@@ -39,32 +39,32 @@ static uint64_t _min(uint64_t lhs, uint64_t rhs)
 
 //----------------------------------------------------------------
 
-void bcache_prefetch_bytes(struct bcache *cache, int fd, uint64_t start, size_t len)
+void bcache_prefetch_bytes(struct bcache *cache, int di, uint64_t start, size_t len)
 {
 	block_address bb, be;
 
 	byte_range_to_block_range(cache, start, len, &bb, &be);
 	while (bb < be) {
-		bcache_prefetch(cache, fd, bb);
+		bcache_prefetch(cache, di, bb);
 		bb++;
 	}
 }
 
 //----------------------------------------------------------------
 
-bool bcache_read_bytes(struct bcache *cache, int fd, uint64_t start, size_t len, void *data)
+bool bcache_read_bytes(struct bcache *cache, int di, uint64_t start, size_t len, void *data)
 {
 	struct block *b;
 	block_address bb, be;
 	uint64_t block_size = bcache_block_sectors(cache) << SECTOR_SHIFT;
 	uint64_t block_offset = start % block_size;
 
-	bcache_prefetch_bytes(cache, fd, start, len);
+	bcache_prefetch_bytes(cache, di, start, len);
 
 	byte_range_to_block_range(cache, start, len, &bb, &be);
 
 	for (; bb != be; bb++) {
-        	if (!bcache_get(cache, fd, bb, 0, &b))
+        	if (!bcache_get(cache, di, bb, 0, &b))
 			return false;
 
 		size_t blen = _min(block_size - block_offset, len);
@@ -79,6 +79,21 @@ bool bcache_read_bytes(struct bcache *cache, int fd, uint64_t start, size_t len,
 	return true;
 }
 
+bool bcache_invalidate_bytes(struct bcache *cache, int di, uint64_t start, size_t len)
+{
+	block_address bb, be;
+	bool result = true;
+
+	byte_range_to_block_range(cache, start, len, &bb, &be);
+
+	for (; bb != be; bb++) {
+		if (!bcache_invalidate(cache, di, bb))
+			result = false;
+	}
+
+	return result;
+}
+
 //----------------------------------------------------------------
 
 // Writing bytes and zeroing bytes are very similar, so we factor out
@@ -86,8 +101,8 @@ bool bcache_read_bytes(struct bcache *cache, int fd, uint64_t start, size_t len,
  
 struct updater;
 
-typedef bool (*partial_update_fn)(struct updater *u, int fd, block_address bb, uint64_t offset, size_t len);
-typedef bool (*whole_update_fn)(struct updater *u, int fd, block_address bb, block_address be);
+typedef bool (*partial_update_fn)(struct updater *u, int di, block_address bb, uint64_t offset, size_t len);
+typedef bool (*whole_update_fn)(struct updater *u, int di, block_address bb, block_address be);
 
 struct updater {
 	struct bcache *cache;
@@ -96,7 +111,7 @@ struct updater {
 	void *data;
 };
 
-static bool _update_bytes(struct updater *u, int fd, uint64_t start, size_t len)
+static bool _update_bytes(struct updater *u, int di, uint64_t start, size_t len)
 {
         struct bcache *cache = u->cache;
 	block_address bb, be;
@@ -109,12 +124,12 @@ static bool _update_bytes(struct updater *u, int fd, uint64_t start, size_t len)
 	// If the last block is partial, we will require a read, so let's 
 	// prefetch it.
 	if ((start + len) % block_size)
-        	bcache_prefetch(cache, fd, (start + len) / block_size);
+        	bcache_prefetch(cache, di, (start + len) / block_size);
 
 	// First block may be partial
 	if (block_offset) {
         	size_t blen = _min(block_size - block_offset, len);
-		if (!u->partial_fn(u, fd, bb, block_offset, blen))
+		if (!u->partial_fn(u, di, bb, block_offset, blen))
         		return false;
 
 		len -= blen;
@@ -126,7 +141,7 @@ static bool _update_bytes(struct updater *u, int fd, uint64_t start, size_t len)
 
         // Now we write out a set of whole blocks
         nr_whole = len / block_size;
-        if (!u->whole_fn(u, fd, bb, bb + nr_whole))
+        if (!u->whole_fn(u, di, bb, bb + nr_whole))
                 return false;
 
 	bb += nr_whole;
@@ -136,17 +151,17 @@ static bool _update_bytes(struct updater *u, int fd, uint64_t start, size_t len)
         	return true;
 
         // Finally we write a partial end block
-        return u->partial_fn(u, fd, bb, 0, len);
+        return u->partial_fn(u, di, bb, 0, len);
 }
 
 //----------------------------------------------------------------
 
-static bool _write_partial(struct updater *u, int fd, block_address bb,
+static bool _write_partial(struct updater *u, int di, block_address bb,
                            uint64_t offset, size_t len)
 {
 	struct block *b;
 
-	if (!bcache_get(u->cache, fd, bb, GF_DIRTY, &b))
+	if (!bcache_get(u->cache, di, bb, GF_DIRTY, &b))
 		return false;
 
 	memcpy(((unsigned char *) b->data) + offset, u->data, len);
@@ -156,7 +171,7 @@ static bool _write_partial(struct updater *u, int fd, block_address bb,
 	return true;
 }
 
-static bool _write_whole(struct updater *u, int fd, block_address bb, block_address be)
+static bool _write_whole(struct updater *u, int di, block_address bb, block_address be)
 {
 	struct block *b;
 	uint64_t block_size = bcache_block_sectors(u->cache) << SECTOR_SHIFT;
@@ -164,7 +179,7 @@ static bool _write_whole(struct updater *u, int fd, block_address bb, block_addr
 	for (; bb != be; bb++) {
         	// We don't need to read the block since we are overwriting
         	// it completely.
-		if (!bcache_get(u->cache, fd, bb, GF_ZERO, &b))
+		if (!bcache_get(u->cache, di, bb, GF_ZERO, &b))
         		return false;
 		memcpy(b->data, u->data, block_size);
 		u->data = ((unsigned char *) u->data) + block_size;
@@ -174,7 +189,7 @@ static bool _write_whole(struct updater *u, int fd, block_address bb, block_addr
 	return true;
 }
 
-bool bcache_write_bytes(struct bcache *cache, int fd, uint64_t start, size_t len, void *data)
+bool bcache_write_bytes(struct bcache *cache, int di, uint64_t start, size_t len, void *data)
 {
         struct updater u;
 
@@ -183,16 +198,16 @@ bool bcache_write_bytes(struct bcache *cache, int fd, uint64_t start, size_t len
         u.whole_fn = _write_whole;
         u.data = data;
 
-	return _update_bytes(&u, fd, start, len);
+	return _update_bytes(&u, di, start, len);
 }
 
 //----------------------------------------------------------------
 
-static bool _zero_partial(struct updater *u, int fd, block_address bb, uint64_t offset, size_t len)
+static bool _zero_partial(struct updater *u, int di, block_address bb, uint64_t offset, size_t len)
 {
 	struct block *b;
 
-	if (!bcache_get(u->cache, fd, bb, GF_DIRTY, &b))
+	if (!bcache_get(u->cache, di, bb, GF_DIRTY, &b))
 		return false;
 
 	memset(((unsigned char *) b->data) + offset, 0, len);
@@ -201,12 +216,12 @@ static bool _zero_partial(struct updater *u, int fd, block_address bb, uint64_t
 	return true;
 }
 
-static bool _zero_whole(struct updater *u, int fd, block_address bb, block_address be)
+static bool _zero_whole(struct updater *u, int di, block_address bb, block_address be)
 {
 	struct block *b;
 
 	for (; bb != be; bb++) {
-		if (!bcache_get(u->cache, fd, bb, GF_ZERO, &b))
+		if (!bcache_get(u->cache, di, bb, GF_ZERO, &b))
         		return false;
         	bcache_put(b);
 	}
@@ -214,7 +229,7 @@ static bool _zero_whole(struct updater *u, int fd, block_address bb, block_addre
 	return true;
 }
 
-bool bcache_zero_bytes(struct bcache *cache, int fd, uint64_t start, size_t len)
+bool bcache_zero_bytes(struct bcache *cache, int di, uint64_t start, size_t len)
 {
         struct updater u;
 
@@ -223,17 +238,17 @@ bool bcache_zero_bytes(struct bcache *cache, int fd, uint64_t start, size_t len)
         u.whole_fn = _zero_whole;
         u.data = NULL;
 
-	return _update_bytes(&u, fd, start, len);
+	return _update_bytes(&u, di, start, len);
 }
 
 //----------------------------------------------------------------
 
-static bool _set_partial(struct updater *u, int fd, block_address bb, uint64_t offset, size_t len)
+static bool _set_partial(struct updater *u, int di, block_address bb, uint64_t offset, size_t len)
 {
 	struct block *b;
 	uint8_t val = *((uint8_t *) u->data);
 
-	if (!bcache_get(u->cache, fd, bb, GF_DIRTY, &b))
+	if (!bcache_get(u->cache, di, bb, GF_DIRTY, &b))
 		return false;
 
 	memset(((unsigned char *) b->data) + offset, val, len);
@@ -242,14 +257,14 @@ static bool _set_partial(struct updater *u, int fd, block_address bb, uint64_t o
 	return true;
 }
 
-static bool _set_whole(struct updater *u, int fd, block_address bb, block_address be)
+static bool _set_whole(struct updater *u, int di, block_address bb, block_address be)
 {
 	struct block *b;
 	uint8_t val = *((uint8_t *) u->data);
         uint64_t len = bcache_block_sectors(u->cache) * 512;
 
 	for (; bb != be; bb++) {
-		if (!bcache_get(u->cache, fd, bb, GF_ZERO, &b))
+		if (!bcache_get(u->cache, di, bb, GF_ZERO, &b))
         		return false;
         	memset((unsigned char *) b->data, val, len);
         	bcache_put(b);
@@ -258,7 +273,7 @@ static bool _set_whole(struct updater *u, int fd, block_address bb, block_addres
 	return true;
 }
 
-bool bcache_set_bytes(struct bcache *cache, int fd, uint64_t start, size_t len, uint8_t val)
+bool bcache_set_bytes(struct bcache *cache, int di, uint64_t start, size_t len, uint8_t val)
 {
         struct updater u;
 
@@ -267,6 +282,6 @@ bool bcache_set_bytes(struct bcache *cache, int fd, uint64_t start, size_t len,
         u.whole_fn = _set_whole;
         u.data = &val;
 
-	return _update_bytes(&u, fd, start, len);
+	return _update_bytes(&u, di, start, len);
 }
 

lib/device/bcache.c

@@ -33,11 +33,16 @@
 
 #define SECTOR_SHIFT 9L
 
+#define FD_TABLE_INC 1024
+static int _fd_table_size;
+static int *_fd_table;
+
+
 //----------------------------------------------------------------
 
 static void log_sys_warn(const char *call)
 {
-	log_warn("%s failed: %s", call, strerror(errno));
+	log_warn("WARNING: %s failed: %s.", call, strerror(errno));
 }
 
 // Assumes the list is not empty.
@@ -61,23 +66,17 @@ struct control_block {
 struct cb_set {
 	struct dm_list free;
 	struct dm_list allocated;
-	struct control_block *vec;
+	struct control_block vec[];
 } control_block_set;
 
 static struct cb_set *_cb_set_create(unsigned nr)
 {
-	int i;
-	struct cb_set *cbs = malloc(sizeof(*cbs));
+	unsigned i;
+	struct cb_set *cbs = malloc(sizeof(*cbs) + nr * sizeof(*cbs->vec));
 
-	if (!cbs)
+	if (!cbs->vec)
 		return NULL;
 
-	cbs->vec = malloc(nr * sizeof(*cbs->vec));
-	if (!cbs->vec) {
-		free(cbs);
-		return NULL;
-	}
-
 	dm_list_init(&cbs->free);
 	dm_list_init(&cbs->allocated);
 
@@ -93,11 +92,10 @@ static void _cb_set_destroy(struct cb_set *cbs)
 	// never be in flight IO.
 	if (!dm_list_empty(&cbs->allocated)) {
 		// bail out
-		log_error("async io still in flight");
+		log_warn("WARNING: async io still in flight.");
 		return;
 	}
 
-	free(cbs->vec);
 	free(cbs);
 }
 
@@ -155,11 +153,11 @@ static void _async_destroy(struct io_engine *ioe)
 	free(e);
 }
 
-static int _last_byte_fd;
+static int _last_byte_di;
 static uint64_t _last_byte_offset;
 static int _last_byte_sector_size;
 
-static bool _async_issue(struct io_engine *ioe, enum dir d, int fd,
+static bool _async_issue(struct io_engine *ioe, enum dir d, int di,
 			 sector_t sb, sector_t se, void *data, void *context)
 {
 	int r;
@@ -183,7 +181,7 @@ static bool _async_issue(struct io_engine *ioe, enum dir d, int fd,
 	/*
 	 * If bcache block goes past where lvm wants to write, then clamp it.
 	 */
-	if ((d == DIR_WRITE) && _last_byte_offset && (fd == _last_byte_fd)) {
+	if ((d == DIR_WRITE) && _last_byte_offset && (di == _last_byte_di)) {
 		if (offset > _last_byte_offset) {
 			log_error("Limit write at %llu len %llu beyond last byte %llu",
 				  (unsigned long long)offset,
@@ -268,7 +266,7 @@ static bool _async_issue(struct io_engine *ioe, enum dir d, int fd,
 
 	memset(&cb->cb, 0, sizeof(cb->cb));
 
-	cb->cb.aio_fildes = (int) fd;
+	cb->cb.aio_fildes = (int) _fd_table[di];
 	cb->cb.u.c.buf = data;
 	cb->cb.u.c.offset = offset;
 	cb->cb.u.c.nbytes = nbytes;
@@ -276,13 +274,15 @@ static bool _async_issue(struct io_engine *ioe, enum dir d, int fd,
 
 #if 0
 	if (d == DIR_READ) {
-		log_debug("io R off %llu bytes %llu",
+		log_debug("io R off %llu bytes %llu di %d fd %d",
 			  (unsigned long long)cb->cb.u.c.offset,
-			  (unsigned long long)cb->cb.u.c.nbytes);
+			  (unsigned long long)cb->cb.u.c.nbytes,
+			  di, _fd_table[di]);
 	} else {
-		log_debug("io W off %llu bytes %llu",
+		log_debug("io W off %llu bytes %llu di %d fd %d",
 			  (unsigned long long)cb->cb.u.c.offset,
-			  (unsigned long long)cb->cb.u.c.nbytes);
+			  (unsigned long long)cb->cb.u.c.nbytes,
+			  di, _fd_table[di]);
 	}
 #endif
 
@@ -318,9 +318,7 @@ static bool _async_wait(struct io_engine *ioe, io_complete_fn fn)
 	struct async_engine *e = _to_async(ioe);
 
 	memset(&event, 0, sizeof(event));
-	do {
-		r = io_getevents(e->aio_context, 1, MAX_EVENT, event, NULL);
-	} while (r == -EINTR);
+	r = io_getevents(e->aio_context, 1, MAX_EVENT, event, NULL);
 
 	if (r < 0) {
 		log_sys_warn("io_getevents");
@@ -414,7 +412,7 @@ static void _sync_destroy(struct io_engine *ioe)
         free(e);
 }
 
-static bool _sync_issue(struct io_engine *ioe, enum dir d, int fd,
+static bool _sync_issue(struct io_engine *ioe, enum dir d, int di,
                         sector_t sb, sector_t se, void *data, void *context)
 {
 	int rv;
@@ -430,7 +428,7 @@ static bool _sync_issue(struct io_engine *ioe, enum dir d, int fd,
 	}
 
 	where = sb * 512;
-	off = lseek(fd, where, SEEK_SET);
+	off = lseek(_fd_table[di], where, SEEK_SET);
 	if (off == (off_t) -1) {
 		log_warn("Device seek error %d for offset %llu", errno, (unsigned long long)where);
 		free(io);
@@ -445,7 +443,7 @@ static bool _sync_issue(struct io_engine *ioe, enum dir d, int fd,
 	/*
 	 * If bcache block goes past where lvm wants to write, then clamp it.
 	 */
-	if ((d == DIR_WRITE) && _last_byte_offset && (fd == _last_byte_fd)) {
+	if ((d == DIR_WRITE) && _last_byte_offset && (di == _last_byte_di)) {
 		uint64_t offset = where;
 		uint64_t nbytes = len;
 		sector_t limit_nbytes = 0;
@@ -515,6 +513,7 @@ static bool _sync_issue(struct io_engine *ioe, enum dir d, int fd,
 					  (unsigned long long)limit_nbytes,
 					  (unsigned long long)extra_nbytes,
 					  (unsigned long long)_last_byte_sector_size);
+				free(io);
 				return false;
 			}
 		}
@@ -525,9 +524,9 @@ static bool _sync_issue(struct io_engine *ioe, enum dir d, int fd,
 
 	while (pos < len) {
 		if (d == DIR_READ)
-			rv = read(fd, (char *)data + pos, len - pos);
+			rv = read(_fd_table[di], (char *)data + pos, len - pos);
 		else
-			rv = write(fd, (char *)data + pos, len - pos);
+			rv = write(_fd_table[di], (char *)data + pos, len - pos);
 
 		if (rv == -1 && errno == EINTR)
 			continue;
@@ -687,7 +686,7 @@ struct bcache {
 //----------------------------------------------------------------
 
 struct key_parts {
-	uint32_t fd;
+	uint32_t di;
 	uint64_t b;
 } __attribute__ ((packed));
 
@@ -696,12 +695,12 @@ union key {
         uint8_t bytes[12];
 };
 
-static struct block *_block_lookup(struct bcache *cache, int fd, uint64_t i)
+static struct block *_block_lookup(struct bcache *cache, int di, uint64_t i)
 {
 	union key k;
 	union radix_value v;
 
-	k.parts.fd = fd;
+	k.parts.di = di;
 	k.parts.b = i;
 
 	if (radix_tree_lookup(cache->rtree, k.bytes, k.bytes + sizeof(k.bytes), &v))
@@ -715,7 +714,7 @@ static bool _block_insert(struct block *b)
         union key k;
         union radix_value v;
 
-        k.parts.fd = b->fd;
+        k.parts.di = b->di;
         k.parts.b = b->index;
         v.ptr = b;
 
@@ -726,7 +725,7 @@ static void _block_remove(struct block *b)
 {
         union key k;
 
-        k.parts.fd = b->fd;
+        k.parts.di = b->di;
         k.parts.b = b->index;
 
 	radix_tree_remove(b->cache->rtree, k.bytes, k.bytes + sizeof(k.bytes));
@@ -868,7 +867,7 @@ static void _issue_low_level(struct block *b, enum dir d)
 
 	dm_list_move(&cache->io_pending, &b->list);
 
-	if (!cache->engine->issue(cache->engine, d, b->fd, sb, se, b->data, b)) {
+	if (!cache->engine->issue(cache->engine, d, b->di, sb, se, b->data, b)) {
 		/* FIXME: if io_submit() set an errno, return that instead of EIO? */
 		_complete_io(b, -EIO);
 		return;
@@ -944,21 +943,26 @@ static struct block *_find_unused_clean_block(struct bcache *cache)
 	return NULL;
 }
 
-static struct block *_new_block(struct bcache *cache, int fd, block_address i, bool can_wait)
+static struct block *_new_block(struct bcache *cache, int di, block_address i, bool can_wait)
 {
 	struct block *b;
 
 	b = _alloc_block(cache);
-	while (!b && !dm_list_empty(&cache->clean)) {
+	while (!b) {
 		b = _find_unused_clean_block(cache);
 		if (!b) {
 			if (can_wait) {
 				if (dm_list_empty(&cache->io_pending))
 					_writeback(cache, 16);  // FIXME: magic number
-				_wait_io(cache);
+				_wait_all(cache);
+				if (dm_list_size(&cache->errored) >= cache->max_io) {
+					log_debug("bcache no new blocks for di %d index %u with >%d errors.",
+						  di, (uint32_t) i, cache->max_io);
+					return NULL;
+				}
 			} else {
-				log_debug("bcache no new blocks for fd %d index %u",
-					  fd, (uint32_t) i);
+				log_debug("bcache no new blocks for di %d index %u",
+					  di, (uint32_t) i);
 				return NULL;
 			}
 		}
@@ -967,7 +971,7 @@ static struct block *_new_block(struct bcache *cache, int fd, block_address i, b
 	if (b) {
 		dm_list_init(&b->list);
 		b->flags = 0;
-		b->fd = fd;
+		b->di = di;
 		b->index = i;
 		b->ref_count = 0;
 		b->error = 0;
@@ -1013,10 +1017,10 @@ static void _miss(struct bcache *cache, unsigned flags)
 }
 
 static struct block *_lookup_or_read_block(struct bcache *cache,
-				  	   int fd, block_address i,
+				  	   int di, block_address i,
 					   unsigned flags)
 {
-	struct block *b = _block_lookup(cache, fd, i);
+	struct block *b = _block_lookup(cache, di, i);
 
 	if (b) {
 		// FIXME: this is insufficient.  We need to also catch a read
@@ -1041,7 +1045,7 @@ static struct block *_lookup_or_read_block(struct bcache *cache,
 	} else {
 		_miss(cache, flags);
 
-		b = _new_block(cache, fd, i, true);
+		b = _new_block(cache, di, i, true);
 		if (b) {
 			if (flags & GF_ZERO)
 				_zero_block(b);
@@ -1086,6 +1090,7 @@ struct bcache *bcache_create(sector_t block_sectors, unsigned nr_cache_blocks,
 	struct bcache *cache;
 	unsigned max_io = engine->max_io(engine);
 	long pgsize = sysconf(_SC_PAGESIZE);
+	int i;
 
 	if (pgsize < 0) {
 		log_warn("WARNING: _SC_PAGESIZE returns negative value.");
@@ -1146,6 +1151,18 @@ struct bcache *bcache_create(sector_t block_sectors, unsigned nr_cache_blocks,
 		return NULL;
 	}
 
+	_fd_table_size = FD_TABLE_INC;
+
+	if (!(_fd_table = malloc(sizeof(int) * _fd_table_size))) {
+		cache->engine->destroy(cache->engine);
+		radix_tree_destroy(cache->rtree);
+		free(cache);
+		return NULL;
+	}
+
+	for (i = 0; i < _fd_table_size; i++)
+		_fd_table[i] = -1;
+
 	return cache;
 }
 
@@ -1161,6 +1178,9 @@ void bcache_destroy(struct bcache *cache)
 	radix_tree_destroy(cache->rtree);
 	cache->engine->destroy(cache->engine);
 	free(cache);
+	free(_fd_table);
+	_fd_table = NULL;
+	_fd_table_size = 0;
 }
 
 sector_t bcache_block_sectors(struct bcache *cache)
@@ -1178,13 +1198,13 @@ unsigned bcache_max_prefetches(struct bcache *cache)
 	return cache->max_io;
 }
 
-void bcache_prefetch(struct bcache *cache, int fd, block_address i)
+void bcache_prefetch(struct bcache *cache, int di, block_address i)
 {
-	struct block *b = _block_lookup(cache, fd, i);
+	struct block *b = _block_lookup(cache, di, i);
 
 	if (!b) {
 		if (cache->nr_io_pending < cache->max_io) {
-			b = _new_block(cache, fd, i, false);
+			b = _new_block(cache, di, i, false);
 			if (b) {
 				cache->prefetches++;
 				_issue_read(b);
@@ -1202,12 +1222,15 @@ static void _recycle_block(struct bcache *cache, struct block *b)
 	_free_block(b);
 }
 
-bool bcache_get(struct bcache *cache, int fd, block_address i,
+bool bcache_get(struct bcache *cache, int di, block_address i,
 	        unsigned flags, struct block **result)
 {
 	struct block *b;
 
-	b = _lookup_or_read_block(cache, fd, i, flags);
+	if (di >= _fd_table_size)
+		goto bad;
+
+	b = _lookup_or_read_block(cache, di, i, flags);
 	if (b) {
 		if (b->error) {
 			if (b->io_dir == DIR_READ) {
@@ -1226,10 +1249,10 @@ bool bcache_get(struct bcache *cache, int fd, block_address i,
 		*result = b;
 		return true;
 	}
-
+bad:
 	*result = NULL;
 
-	log_error("bcache failed to get block %u fd %d", (uint32_t) i, fd);
+	log_error("bcache failed to get block %u di %d", (uint32_t) i, di);
 	return false;
 }
 
@@ -1293,7 +1316,7 @@ static bool _invalidate_block(struct bcache *cache, struct block *b)
 
 	if (b->ref_count) {
 		log_warn("bcache_invalidate: block (%d, %llu) still held",
-			 b->fd, (unsigned long long) b->index);
+			 b->di, (unsigned long long) b->index);
 		return false;
 	}
 
@@ -1310,9 +1333,9 @@ static bool _invalidate_block(struct bcache *cache, struct block *b)
 	return true;
 }
 
-bool bcache_invalidate(struct bcache *cache, int fd, block_address i)
+bool bcache_invalidate(struct bcache *cache, int di, block_address i)
 {
-	return _invalidate_block(cache, _block_lookup(cache, fd, i));
+	return _invalidate_block(cache, _block_lookup(cache, di, i));
 }
 
 //----------------------------------------------------------------
@@ -1328,27 +1351,27 @@ static bool _writeback_v(struct radix_tree_iterator *it,
 	struct block *b = v.ptr;
 
 	if (_test_flags(b, BF_DIRTY))
-        	_issue_write(b);
+		_issue_write(b);
 
-        return true;
+	return true;
 }
 
 static bool _invalidate_v(struct radix_tree_iterator *it,
                           uint8_t *kb, uint8_t *ke, union radix_value v)
 {
 	struct block *b = v.ptr;
-        struct invalidate_iterator *iit = container_of(it, struct invalidate_iterator, it);
+	struct invalidate_iterator *iit = container_of(it, struct invalidate_iterator, it);
 
 	if (b->error || _test_flags(b, BF_DIRTY)) {
-        	log_warn("bcache_invalidate: block (%d, %llu) still dirty",
-                         b->fd, (unsigned long long) b->index);
-        	iit->success = false;
-        	return true;
+		log_warn("WARNING: bcache_invalidate: block (%d, %llu) still dirty.",
+			 b->di, (unsigned long long) b->index);
+		iit->success = false;
+		return true;
 	}
 
 	if (b->ref_count) {
-		log_warn("bcache_invalidate: block (%d, %llu) still held",
-			 b->fd, (unsigned long long) b->index);
+		log_warn("WARNING: bcache_invalidate: block (%d, %llu) still held.",
+			 b->di, (unsigned long long) b->index);
 		iit->success = false;
 		return true;
 	}
@@ -1361,24 +1384,24 @@ static bool _invalidate_v(struct radix_tree_iterator *it,
 	return true;
 }
 
-bool bcache_invalidate_fd(struct bcache *cache, int fd)
+bool bcache_invalidate_di(struct bcache *cache, int di)
 {
-        union key k;
+	union key k;
 	struct invalidate_iterator it;
 
-	k.parts.fd = fd;
+	k.parts.di = di;
 
 	it.it.visit = _writeback_v;
-	radix_tree_iterate(cache->rtree, k.bytes, k.bytes + sizeof(k.parts.fd), &it.it);
+	radix_tree_iterate(cache->rtree, k.bytes, k.bytes + sizeof(k.parts.di), &it.it);
 
 	_wait_all(cache);
 
 	it.success = true;
 	it.it.visit = _invalidate_v;
-	radix_tree_iterate(cache->rtree, k.bytes, k.bytes + sizeof(k.parts.fd), &it.it);
+	radix_tree_iterate(cache->rtree, k.bytes, k.bytes + sizeof(k.parts.di), &it.it);
 
 	if (it.success)
-		radix_tree_remove_prefix(cache->rtree, k.bytes, k.bytes + sizeof(k.parts.fd));
+		radix_tree_remove_prefix(cache->rtree, k.bytes, k.bytes + sizeof(k.parts.di));
 
 	return it.success;
 }
@@ -1392,7 +1415,7 @@ static bool _abort_v(struct radix_tree_iterator *it,
 
 	if (b->ref_count) {
 		log_fatal("bcache_abort: block (%d, %llu) still held",
-			 b->fd, (unsigned long long) b->index);
+			 b->di, (unsigned long long) b->index);
 		return true;
 	}
 
@@ -1404,35 +1427,94 @@ static bool _abort_v(struct radix_tree_iterator *it,
 	return true;
 }
 
-void bcache_abort_fd(struct bcache *cache, int fd)
+void bcache_abort_di(struct bcache *cache, int di)
 {
-        union key k;
+	union key k;
 	struct radix_tree_iterator it;
 
-	k.parts.fd = fd;
+	k.parts.di = di;
 
 	it.visit = _abort_v;
-	radix_tree_iterate(cache->rtree, k.bytes, k.bytes + sizeof(k.parts.fd), &it);
-	radix_tree_remove_prefix(cache->rtree, k.bytes, k.bytes + sizeof(k.parts.fd));
+	radix_tree_iterate(cache->rtree, k.bytes, k.bytes + sizeof(k.parts.di), &it);
+	radix_tree_remove_prefix(cache->rtree, k.bytes, k.bytes + sizeof(k.parts.di));
 }
 
 //----------------------------------------------------------------
 
-void bcache_set_last_byte(struct bcache *cache, int fd, uint64_t offset, int sector_size)
+void bcache_set_last_byte(struct bcache *cache, int di, uint64_t offset, int sector_size)
 {
-	_last_byte_fd = fd;
+	_last_byte_di = di;
 	_last_byte_offset = offset;
 	_last_byte_sector_size = sector_size;
 	if (!sector_size)
 		_last_byte_sector_size = 512;
 }
 
-void bcache_unset_last_byte(struct bcache *cache, int fd)
+void bcache_unset_last_byte(struct bcache *cache, int di)
 {
-	if (_last_byte_fd == fd) {
-		_last_byte_fd = 0;
+	if (_last_byte_di == di) {
+		_last_byte_di = 0;
 		_last_byte_offset = 0;
 		_last_byte_sector_size = 0;
 	}
 }
 
+int bcache_set_fd(int fd)
+{
+	int *new_table = NULL;
+	int new_size = 0;
+	int i;
+
+ retry:
+	for (i = 0; i < _fd_table_size; i++) {
+		if (_fd_table[i] == -1) {
+			_fd_table[i] = fd;
+			return i;
+		}
+	}
+
+	/* already tried once, shouldn't happen */
+	if (new_size)
+		return -1;
+
+	new_size = _fd_table_size + FD_TABLE_INC;
+
+	new_table = realloc(_fd_table, sizeof(int) * new_size);
+	if (!new_table) {
+		log_error("Cannot extend bcache fd table");
+		return -1;
+	}
+
+	for (i = _fd_table_size; i < new_size; i++)
+		new_table[i] = -1;
+
+	_fd_table = new_table;
+	_fd_table_size = new_size;
+
+	goto retry;
+}
+
+/*
+ * Should we check for unflushed or inprogress io on an fd
+ * prior to doing clear_fd or change_fd?  (To catch mistakes;
+ * the caller should be smart enough to not do that.)
+ */
+
+void bcache_clear_fd(int di)
+{
+	if (di >= _fd_table_size)
+		return;
+	_fd_table[di] = -1;
+}
+
+int bcache_change_fd(int di, int fd)
+{
+	if (di >= _fd_table_size)
+		return 0;
+	if (di < 0) {
+		log_error(INTERNAL_ERROR "Cannot change not opened DI with FD:%d", fd);
+		return 0;
+	}
+	_fd_table[di] = fd;
+	return 1;
+}

lib/device/bcache.h

@@ -16,19 +16,12 @@
 #define BCACHE_H
 
 #include "device_mapper/all.h"
+#include "base/memory/container_of.h"
 
 #include <linux/fs.h>
 #include <stdint.h>
 #include <stdbool.h>
 
-/*----------------------------------------------------------------*/
-
-// FIXME: move somewhere more sensible
-#define container_of(v, t, head) \
-    ((t *)((const char *)(v) - (const char *)&((t *) 0)->head))
-
-/*----------------------------------------------------------------*/
-
 enum dir {
 	DIR_READ,
 	DIR_WRITE
@@ -41,7 +34,7 @@ typedef void io_complete_fn(void *context, int io_error);
 
 struct io_engine {
 	void (*destroy)(struct io_engine *e);
-	bool (*issue)(struct io_engine *e, enum dir d, int fd,
+	bool (*issue)(struct io_engine *e, enum dir d, int di,
 		      sector_t sb, sector_t se, void *data, void *context);
 	bool (*wait)(struct io_engine *e, io_complete_fn fn);
 	unsigned (*max_io)(struct io_engine *e);
@@ -55,7 +48,7 @@ struct io_engine *create_sync_io_engine(void);
 struct bcache;
 struct block {
 	/* clients may only access these three fields */
-	int fd;
+	int di;
 	uint64_t index;
 	void *data;
 
@@ -113,12 +106,12 @@ unsigned bcache_max_prefetches(struct bcache *cache);
  * they complete.  But we're talking a very small difference, and it's worth it
  * to keep callbacks out of this interface.
  */
-void bcache_prefetch(struct bcache *cache, int fd, block_address index);
+void bcache_prefetch(struct bcache *cache, int di, block_address index);
 
 /*
  * Returns true on success.
  */
-bool bcache_get(struct bcache *cache, int fd, block_address index,
+bool bcache_get(struct bcache *cache, int di, block_address index,
 	        unsigned flags, struct block **result);
 void bcache_put(struct block *b);
 
@@ -136,37 +129,42 @@ bool bcache_flush(struct bcache *cache);
  * 
  * If the block is currently held false will be returned.
  */
-bool bcache_invalidate(struct bcache *cache, int fd, block_address index);
+bool bcache_invalidate(struct bcache *cache, int di, block_address index);
 
 /*
  * Invalidates all blocks on the given descriptor.  Call this before closing
  * the descriptor to make sure everything is written back.
  */
-bool bcache_invalidate_fd(struct bcache *cache, int fd);
+bool bcache_invalidate_di(struct bcache *cache, int di);
 
 /*
  * Call this function if flush, or invalidate fail and you do not
  * wish to retry the writes.  This will throw away any dirty data
- * not written.  If any blocks for fd are held, then it will call
+ * not written.  If any blocks for di are held, then it will call
  * abort().
  */
-void bcache_abort_fd(struct bcache *cache, int fd);
+void bcache_abort_di(struct bcache *cache, int di);
 
 //----------------------------------------------------------------
 // The next four functions are utilities written in terms of the above api.
  
 // Prefetches the blocks neccessary to satisfy a byte range.
-void bcache_prefetch_bytes(struct bcache *cache, int fd, uint64_t start, size_t len);
+void bcache_prefetch_bytes(struct bcache *cache, int di, uint64_t start, size_t len);
 
 // Reads, writes and zeroes bytes.  Returns false if errors occur.
-bool bcache_read_bytes(struct bcache *cache, int fd, uint64_t start, size_t len, void *data);
-bool bcache_write_bytes(struct bcache *cache, int fd, uint64_t start, size_t len, void *data);
-bool bcache_zero_bytes(struct bcache *cache, int fd, uint64_t start, size_t len);
-bool bcache_set_bytes(struct bcache *cache, int fd, uint64_t start, size_t len, uint8_t val);
+bool bcache_read_bytes(struct bcache *cache, int di, uint64_t start, size_t len, void *data);
+bool bcache_write_bytes(struct bcache *cache, int di, uint64_t start, size_t len, void *data);
+bool bcache_zero_bytes(struct bcache *cache, int di, uint64_t start, size_t len);
+bool bcache_set_bytes(struct bcache *cache, int di, uint64_t start, size_t len, uint8_t val);
+bool bcache_invalidate_bytes(struct bcache *cache, int di, uint64_t start, size_t len);
 
-void bcache_set_last_byte(struct bcache *cache, int fd, uint64_t offset, int sector_size);
-void bcache_unset_last_byte(struct bcache *cache, int fd);
+void bcache_set_last_byte(struct bcache *cache, int di, uint64_t offset, int sector_size);
+void bcache_unset_last_byte(struct bcache *cache, int di);
 
 //----------------------------------------------------------------
 
+int bcache_set_fd(int fd); /* returns di */
+void bcache_clear_fd(int di);
+int bcache_change_fd(int di, int fd);
+
 #endif

lib/device/dev-cache.c

@@ -16,6 +16,7 @@
 #include "base/memory/zalloc.h"
 #include "lib/misc/lib.h"
 #include "lib/device/dev-type.h"
+#include "lib/device/device_id.h"
 #include "lib/datastruct/btree.h"
 #include "lib/config/config.h"
 #include "lib/commands/toolcontext.h"
@@ -35,7 +36,7 @@ struct dev_iter {
 
 struct dir_list {
 	struct dm_list list;
-	char dir[0];
+	char dir[];
 };
 
 static struct {
@@ -65,12 +66,16 @@ static int _insert(const char *path, const struct stat *info,
 static void _dev_init(struct device *dev)
 {
 	dev->fd = -1;
+	dev->bcache_fd = -1;
+	dev->bcache_di = -1;
 	dev->read_ahead = -1;
+	dev->part = -1;
 
 	dev->ext.enabled = 0;
 	dev->ext.src = DEV_EXT_NONE;
 
 	dm_list_init(&dev->aliases);
+	dm_list_init(&dev->ids);
 }
 
 void dev_destroy_file(struct device *dev)
@@ -319,20 +324,38 @@ static int _compare_paths(const char *path0, const char *path1)
 	return 1;
 }
 
-static int _add_alias(struct device *dev, const char *path)
+enum add_hash {
+	NO_HASH,
+	HASH,
+	REHASH
+};
+
+static int _add_alias(struct device *dev, const char *path, enum add_hash hash)
 {
-	struct dm_str_list *sl = _zalloc(sizeof(*sl));
+	struct dm_str_list *sl;
 	struct dm_str_list *strl;
 	const char *oldpath;
 	int prefer_old = 1;
 
-	if (!sl)
-		return_0;
+	if (hash == REHASH)
+		dm_hash_remove(_cache.names, path);
 
 	/* Is name already there? */
-	dm_list_iterate_items(strl, &dev->aliases) {
-		if (!strcmp(strl->str, path))
-			return 1;
+	dm_list_iterate_items(strl, &dev->aliases)
+		if (!strcmp(strl->str, path)) {
+			path = strl->str;
+			goto out;
+		}
+
+	if (!(path = dm_pool_strdup(_cache.mem, path)) ||
+	    !(sl = _zalloc(sizeof(*sl)))) {
+		log_error("Failed to add allias to dev cache.");
+		return 0;
+	}
+
+	if (!strncmp(path, "/dev/nvme", 9)) {
+		log_debug("Found nvme device %s", dev_name(dev));
+		dev->flags |= DEV_IS_NVME;
 	}
 
 	sl->str = path;
@@ -346,23 +369,31 @@ static int _add_alias(struct device *dev, const char *path)
 		dm_list_add(&dev->aliases, &sl->list);
 	else
 		dm_list_add_h(&dev->aliases, &sl->list);
+out:
+	if ((hash != NO_HASH) &&
+	    !dm_hash_insert(_cache.names, path, dev)) {
+		log_error("Couldn't add name to hash in dev cache.");
+		return 0;
+	}
 
 	return 1;
 }
 
-static int _get_sysfs_value(const char *path, char *buf, size_t buf_size, int error_if_no_value)
+int get_sysfs_value(const char *path, char *buf, size_t buf_size, int error_if_no_value)
 {
 	FILE *fp;
 	size_t len;
 	int r = 0;
 
 	if (!(fp = fopen(path, "r"))) {
-		log_sys_error("fopen", path);
+		if (error_if_no_value)
+			log_sys_error("fopen", path);
 		return 0;
 	}
 
 	if (!fgets(buf, buf_size, fp)) {
-		log_sys_error("fgets", path);
+		if (error_if_no_value)
+			log_sys_error("fgets", path);
 		goto out;
 	}
 
@@ -375,7 +406,7 @@ static int _get_sysfs_value(const char *path, char *buf, size_t buf_size, int er
 		r = 1;
 out:
 	if (fclose(fp))
-		log_sys_error("fclose", path);
+		log_sys_debug("fclose", path);
 
 	return r;
 }
@@ -389,7 +420,7 @@ static int _get_dm_uuid_from_sysfs(char *buf, size_t buf_size, int major, int mi
 		return 0;
 	}
 
-	return _get_sysfs_value(path, buf, buf_size, 0);
+	return get_sysfs_value(path, buf, buf_size, 0);
 }
 
 static struct dm_list *_get_or_add_list_by_index_key(struct dm_hash_table *idx, const char *key)
@@ -419,7 +450,6 @@ static struct device *_insert_sysfs_dev(dev_t devno, const char *devname)
 	static struct device _fake_dev = { .flags = DEV_USED_FOR_LV };
 	struct stat stat0;
 	char path[PATH_MAX];
-	char *path_copy;
 	struct device *dev;
 
 	if (dm_snprintf(path, sizeof(path), "%s%s", _cache.dev_dir, devname) < 0) {
@@ -437,15 +467,9 @@ static struct device *_insert_sysfs_dev(dev_t devno, const char *devname)
 	if (!(dev = _dev_create(devno)))
 		return_NULL;
 
-	if (!(path_copy = dm_pool_strdup(_cache.mem, path))) {
-		log_error("_insert_sysfs_dev: %s: dm_pool_strdup failed", devname);
-		return NULL;
-	}
-
-	if (!_add_alias(dev, path_copy)) {
-		log_error("Couldn't add alias to dev cache.");
+	if (!_add_alias(dev, path, NO_HASH)) {
 		_free(dev);
-		return NULL;
+		return_NULL;
 	}
 
 	if (!btree_insert(_cache.sysfs_only_devices, (uint32_t) devno, dev)) {
@@ -470,7 +494,7 @@ static struct device *_get_device_for_sysfs_dev_name_using_devno(const char *dev
 		return NULL;
 	}
 
-	if (!_get_sysfs_value(path, buf, sizeof(buf), 1))
+	if (!get_sysfs_value(path, buf, sizeof(buf), 1))
 		return_NULL;
 
 	if (sscanf(buf, "%d:%d", &major, &minor) != 2) {
@@ -687,7 +711,6 @@ static int _insert_dev(const char *path, dev_t d)
 	struct device *dev;
 	struct device *dev_by_devt;
 	struct device *dev_by_path;
-	char *path_copy;
 
 	dev_by_devt = (struct device *) btree_lookup(_cache.devices, (uint32_t) d);
 	dev_by_path = (struct device *) dm_hash_lookup(_cache.names, path);
@@ -721,20 +744,8 @@ static int _insert_dev(const char *path, dev_t d)
 			return 0;
 		}
 
-		if (!(path_copy = dm_pool_strdup(_cache.mem, path))) {
-			log_error("Failed to duplicate path string.");
-			return 0;
-		}
-
-		if (!_add_alias(dev, path_copy)) {
-			log_error("Couldn't add alias to dev cache.");
-			return 0;
-		}
-
-		if (!dm_hash_insert(_cache.names, path_copy, dev)) {
-			log_error("Couldn't add name to hash in dev cache.");
-			return 0;
-		}
+		if (!_add_alias(dev, path, HASH))
+			return_0;
 
 		return 1;
 	}
@@ -746,20 +757,8 @@ static int _insert_dev(const char *path, dev_t d)
 		log_debug_devs("Found dev %d:%d %s - new alias.",
 			       (int)MAJOR(d), (int)MINOR(d), path);
 
-		if (!(path_copy = dm_pool_strdup(_cache.mem, path))) {
-			log_error("Failed to duplicate path string.");
-			return 0;
-		}
-
-		if (!_add_alias(dev, path_copy)) {
-			log_error("Couldn't add alias to dev cache.");
-			return 0;
-		}
-
-		if (!dm_hash_insert(_cache.names, path_copy, dev)) {
-			log_error("Couldn't add name to hash in dev cache.");
-			return 0;
-		}
+		if (!_add_alias(dev, path, HASH))
+			return_0;
 
 		return 1;
 	}
@@ -785,25 +784,10 @@ static int _insert_dev(const char *path, dev_t d)
 			return 0;
 		}
 
-		if (!(path_copy = dm_pool_strdup(_cache.mem, path))) {
-			log_error("Failed to duplicate path string.");
-			return 0;
-		}
-
-		if (!_add_alias(dev, path_copy)) {
-			log_error("Couldn't add alias to dev cache.");
-			return 0;
-		}
-
-		dm_hash_remove(_cache.names, path);
-
-		if (!dm_hash_insert(_cache.names, path_copy, dev)) {
-			log_error("Couldn't add name to hash in dev cache.");
-			return 0;
-		}
+		if (!_add_alias(dev, path, REHASH))
+			return_0;
 
 		return 1;
-
 	}
 
 	/*
@@ -815,22 +799,8 @@ static int _insert_dev(const char *path, dev_t d)
 			       (int)MAJOR(d), (int)MINOR(d), path,
 			       (int)MAJOR(dev_by_path->dev), (int)MINOR(dev_by_path->dev));
 
-		if (!(path_copy = dm_pool_strdup(_cache.mem, path))) {
-			log_error("Failed to duplicate path string.");
-			return 0;
-		}
-
-		if (!_add_alias(dev, path_copy)) {
-			log_error("Couldn't add alias to dev cache.");
-			return 0;
-		}
-
-		dm_hash_remove(_cache.names, path);
-
-		if (!dm_hash_insert(_cache.names, path_copy, dev)) {
-			log_error("Couldn't add name to hash in dev cache.");
-			return 0;
-		}
+		if (!_add_alias(dev, path, REHASH))
+			return_0;
 
 		return 1;
 	}
@@ -963,12 +933,12 @@ static int _dev_cache_iterate_sysfs_for_index(const char *path)
 	r = !partial_failure;
 
 	if (closedir(d))
-		log_sys_error("closedir", path);
+		log_sys_debug("closedir", path);
 
 	return r;
 }
 
-int dev_cache_index_devs(void)
+static int dev_cache_index_devs(void)
 {
 	static int sysfs_has_dev_block = -1;
 	char path[PATH_MAX];
@@ -989,7 +959,7 @@ int dev_cache_index_devs(void)
 				return 1;
 			}
 
-			log_sys_error("stat", path);
+			log_sys_debug("stat", path);
 			return 0;
 		}
 	} else if (!sysfs_has_dev_block)
@@ -1154,13 +1124,13 @@ static int _insert(const char *path, const struct stat *info,
 		}
 
 		if (rec && !_insert_dir(path))
-			return_0;
+			return 0;
 	} else {		/* add a device */
 		if (!S_ISBLK(info->st_mode))
 			return 1;
 
 		if (!_insert_dev(path, info->st_rdev))
-			return_0;
+			return 0;
 	}
 
 	return 1;
@@ -1317,12 +1287,20 @@ int dev_cache_check_for_open_devices(void)
 
 int dev_cache_exit(void)
 {
+	struct device *dev;
+	struct dm_hash_node *n;
 	int num_open = 0;
 
-	if (_cache.names)
+	if (_cache.names) {
 		if ((num_open = _check_for_open_devices(1)) > 0)
 			log_error(INTERNAL_ERROR "%d device(s) were left open and have been closed.", num_open);
 
+		dm_hash_iterate(n, _cache.names) {
+			dev = (struct device *) dm_hash_get_data(_cache.names, n);
+			free_dids(&dev->ids);
+		}
+	}
+
 	if (_cache.mem)
 		dm_pool_destroy(_cache.mem);
 
@@ -1419,72 +1397,156 @@ const char *dev_name_confirmed(struct device *dev, int quiet)
 	return dev_name(dev);
 }
 
-/* Provide a custom reason when a device is ignored */
-const char *dev_cache_filtered_reason(const char *name)
+struct device *dev_hash_get(const char *name)
 {
-	const char *reason = "not found";
-	struct device *d = (struct device *) dm_hash_lookup(_cache.names, name);
+	return (struct device *) dm_hash_lookup(_cache.names, name);
+}
 
-	if (d)
-		/* FIXME Record which filter caused the exclusion */
-		reason = "excluded by a filter";
+static void _remove_alias(struct device *dev, const char *name)
+{
+	struct dm_str_list *strl;
 
-	return reason;
+	dm_list_iterate_items(strl, &dev->aliases) {
+		if (!strcmp(strl->str, name)) {
+			dm_list_del(&strl->list);
+			return;
+		}
+	}
+}
+
+/*
+ * Check that paths for this dev still refer to the same dev_t.  This is known
+ * to drop invalid paths in the case where lvm deactivates an LV, which causes
+ * that LV path to go away, but that LV path is not removed from dev-cache (it
+ * probably should be).  Later a new path to a different LV is added to
+ * dev-cache, where the new LV has the same major:minor as the previously
+ * deactivated LV.  The new LV will find the existing struct dev, and that
+ * struct dev will have dev->aliases entries that refer to the name of the old
+ * deactivated LV.  Those old paths are all invalid and are dropped here.
+ */
+
+static void _verify_aliases(struct device *dev, const char *newname)
+{
+	struct dm_str_list *strl, *strl2;
+	struct stat st;
+
+	dm_list_iterate_items_safe(strl, strl2, &dev->aliases) {
+		/* newname was just stat'd and added by caller */
+		if (newname && !strcmp(strl->str, newname))
+			continue;
+
+		if (stat(strl->str, &st) || (st.st_rdev != dev->dev)) {
+			log_debug("Drop invalid path %s for %d:%d (new path %s).",
+				  strl->str, (int)MAJOR(dev->dev), (int)MINOR(dev->dev), newname ?: "");
+			dm_hash_remove(_cache.names, strl->str);
+			dm_list_del(&strl->list);
+		}
+	}
 }
 
 struct device *dev_cache_get(struct cmd_context *cmd, const char *name, struct dev_filter *f)
 {
-	struct stat buf;
-	struct device *d = (struct device *) dm_hash_lookup(_cache.names, name);
-	int info_available = 0;
-	int ret = 1;
+	struct device *dev = (struct device *) dm_hash_lookup(_cache.names, name);
+	struct stat st;
+	int ret;
 
-	if (d && (d->flags & DEV_REGULAR))
-		return d;
+	/*
+	 * DEV_REGULAR means that is "dev" is actually a file, not a device.
+	 * FIXME: I don't think dev-cache is used for files any more and this
+	 * can be dropped?
+	 */
+	if (dev && (dev->flags & DEV_REGULAR))
+		return dev;
+
+	/*
+	 * The requested path is invalid, remove any dev-cache
+	 * info for it.
+	 */
+	if (stat(name, &st)) {
+		if (dev) {
+			log_print("Device path %s is invalid for %d:%d %s.",
+				  name, (int)MAJOR(dev->dev), (int)MINOR(dev->dev), dev_name(dev));
 
-	/* If the entry's wrong, remove it */
-	if (stat(name, &buf) < 0) {
-		if (d)
 			dm_hash_remove(_cache.names, name);
-		log_sys_very_verbose("stat", name);
-		d = NULL;
-	} else
-		info_available = 1;
 
-	if (d && (buf.st_rdev != d->dev)) {
+			_remove_alias(dev, name);
+
+			/* Remove any other names in dev->aliases that are incorrect. */
+			_verify_aliases(dev, NULL);
+		}
+		return NULL;
+	}
+
+	if (!S_ISBLK(st.st_mode)) {
+		log_debug("Not a block device %s.", name);
+		return NULL;
+	}
+
+	/*
+	 * dev-cache has incorrect info for the requested path.
+	 * Remove incorrect info and then add new dev-cache entry.
+	 */
+	if (dev && (st.st_rdev != dev->dev)) {
+		log_print("Device path %s does not match %d:%d %s.",
+			  name, (int)MAJOR(dev->dev), (int)MINOR(dev->dev), dev_name(dev));
+
 		dm_hash_remove(_cache.names, name);
-		d = NULL;
+
+		_remove_alias(dev, name);
+
+		/* Remove any other names in dev->aliases that are incorrect. */
+		_verify_aliases(dev, NULL);
+
+		/* Add new dev-cache entry next. */
+		dev = NULL;
 	}
 
-	if (!d) {
-		_insert(name, info_available ? &buf : NULL, 0, obtain_device_list_from_udev());
-		d = (struct device *) dm_hash_lookup(_cache.names, name);
-		if (!d) {
-			dev_cache_scan();
-			d = (struct device *) dm_hash_lookup(_cache.names, name);
+	/*
+	 * Either add a new struct dev for st_rdev and name,
+	 * or add name as a new alias for an existing struct dev
+	 * for st_rdev.
+	 */
+	if (!dev) {
+		_insert_dev(name, st.st_rdev);
+
+		/* Get the struct dev that was just added. */
+		dev = (struct device *) dm_hash_lookup(_cache.names, name);
+
+		if (!dev) {
+			log_error("Failed to get device %s", name);
+			return NULL;
 		}
+
+		_verify_aliases(dev, name);
 	}
 
-	if (!d)
-		return NULL;
+	/*
+	 * The caller passed a filter if they only want the dev if it
+	 * passes filters.
+	 */
 
-	if (d && (d->flags & DEV_REGULAR))
-		return d;
+	if (!f)
+		return dev;
 
-	if (f && !(d->flags & DEV_REGULAR)) {
-		ret = f->passes_filter(cmd, f, d, NULL);
+	ret = f->passes_filter(cmd, f, dev, NULL);
 
-		if (ret == -EAGAIN) {
-			log_debug_devs("get device by name defer filter %s", dev_name(d));
-			d->flags |= DEV_FILTER_AFTER_SCAN;
-			ret = 1;
-		}
+	/*
+	 * This might happen if this function is called before
+	 * filters can do i/o.  I don't think this will happen
+	 * any longer and this EAGAIN case can be removed.
+	 */
+	if (ret == -EAGAIN) {
+		log_debug_devs("dev_cache_get filter deferred %s", dev_name(dev));
+		dev->flags |= DEV_FILTER_AFTER_SCAN;
+		ret = 1;
 	}
 
-	if (f && !(d->flags & DEV_REGULAR) && !ret)
+	if (!ret) {
+		log_debug_devs("dev_cache_get filter excludes %s", dev_name(dev));
 		return NULL;
+	}
 
-	return d;
+	return dev;
 }
 
 static struct device *_dev_cache_seek_devt(dev_t dev)
@@ -1522,7 +1584,7 @@ struct device *dev_cache_get_by_devt(struct cmd_context *cmd, dev_t dev, struct
 		sysfs_dir = dm_sysfs_dir();
 		if (sysfs_dir && *sysfs_dir) {
 			/* First check if dev is sysfs to avoid useless scan */
-			if (dm_snprintf(path, sizeof(path), "%s/dev/block/%d:%d",
+			if (dm_snprintf(path, sizeof(path), "%sdev/block/%d:%d",
 					sysfs_dir, (int)MAJOR(dev), (int)MINOR(dev)) < 0) {
 				log_error("dm_snprintf partition failed.");
 				return NULL;
@@ -1535,6 +1597,8 @@ struct device *dev_cache_get_by_devt(struct cmd_context *cmd, dev_t dev, struct
 			}
 		}
 
+		log_debug_devs("Device num not found in dev_cache repeat dev_cache_scan for %d:%d",
+				(int)MAJOR(dev), (int)MINOR(dev));
 		dev_cache_scan();
 		d = _dev_cache_seek_devt(dev);
 	}
@@ -1651,3 +1715,334 @@ bool dev_cache_has_md_with_end_superblock(struct dev_types *dt)
 	return false;
 }
 
+static int _setup_devices_list(struct cmd_context *cmd)
+{
+	struct dm_str_list *strl;
+	struct dev_use *du;
+
+	/*
+	 * For each --devices arg, add a du to cmd->use_devices.
+	 * The du has devname is the devices arg value.
+	 */
+
+	dm_list_iterate_items(strl, &cmd->deviceslist) {
+		if (!(du = zalloc(sizeof(struct dev_use))))
+			return_0;
+
+		if (!(du->devname = strdup(strl->str)))
+			return_0;
+
+		dm_list_add(&cmd->use_devices, &du->list);
+	}
+
+	return 1;
+}
+
+static int _setup_devices_file_dmeventd(struct cmd_context *cmd)
+{
+	char path[PATH_MAX];
+	struct stat st;
+
+	/*
+	 * When command is run by dmeventd there is no --devicesfile
+	 * option that can enable/disable the use of a devices file.
+	 */
+	if (!find_config_tree_bool(cmd, devices_use_devicesfile_CFG, NULL)) {
+		cmd->enable_devices_file = 0;
+		return 1;
+	}
+
+	/*
+	 * If /etc/lvm/devices/dmeventd.devices exists, then use that.
+	 * The optional dmeventd.devices allows the user to control
+	 * which devices dmeventd will look at and use.
+	 * Otherwise, disable the devices file because dmeventd should
+	 * be able to manage LVs in any VG (i.e. LVs in a non-system
+	 * devices file.)
+	 */
+	if (dm_snprintf(path, sizeof(path), "%s/devices/dmeventd.devices", cmd->system_dir) < 0) {
+		log_warn("Failed to copy devices path");
+		cmd->enable_devices_file = 0;
+		return 1;
+	}
+
+	if (stat(path, &st)) {
+		/* No dmeventd.devices, so do not use a devices file. */
+		cmd->enable_devices_file = 0;
+		return 1;
+	}
+
+	cmd->enable_devices_file = 1;
+	(void) dm_strncpy(cmd->devices_file_path, path, sizeof(cmd->devices_file_path));
+	return 1;
+}
+	
+int setup_devices_file(struct cmd_context *cmd)
+{
+	char dirpath[PATH_MAX];
+	const char *filename = NULL;
+	struct stat st;
+	int rv;
+
+	if (cmd->run_by_dmeventd)
+		return _setup_devices_file_dmeventd(cmd);
+
+	if (cmd->devicesfile) {
+		/* --devicesfile <filename> or "" has been set which overrides
+		   lvm.conf settings use_devicesfile and devicesfile. */
+		if (!strlen(cmd->devicesfile))
+			cmd->enable_devices_file = 0;
+		else {
+			cmd->enable_devices_file = 1;
+			filename = cmd->devicesfile;
+		}
+		/* TODO: print a warning if --devicesfile system.devices
+		   while lvm.conf use_devicesfile=0. */
+	} else {
+		if (!find_config_tree_bool(cmd, devices_use_devicesfile_CFG, NULL))
+			cmd->enable_devices_file = 0;
+		else {
+			cmd->enable_devices_file = 1;
+			filename = find_config_tree_str(cmd, devices_devicesfile_CFG, NULL);
+			if (!validate_name(filename)) {
+				log_error("Invalid devices file name from config setting \"%s\".", filename);
+				return 0;
+			}
+		}
+	}
+
+	if (!cmd->enable_devices_file)
+		return 1;
+
+	if (dm_snprintf(dirpath, sizeof(dirpath), "%s/devices", cmd->system_dir) < 0) {
+		log_error("Failed to copy devices dir path");
+		return 0;
+	}
+
+	if (stat(dirpath, &st)) {
+		log_debug("Creating %s.", dirpath);
+		dm_prepare_selinux_context(dirpath, S_IFDIR);
+		rv = mkdir(dirpath, 0755);
+		dm_prepare_selinux_context(NULL, 0);
+
+		if ((rv < 0) && stat(dirpath, &st)) {
+			log_error("Failed to create %s %d", dirpath, errno);
+			return 0;
+		}
+	}
+	
+	if (dm_snprintf(cmd->devices_file_path, sizeof(cmd->devices_file_path),
+			"%s/devices/%s", cmd->system_dir, filename) < 0) {
+		log_error("Failed to copy devices file path");
+		return 0;
+	}
+	return 1;
+}
+
+/*
+ * Add all system devices to dev-cache, and attempt to
+ * match all devices_file entries to dev-cache entries.
+ */
+int setup_devices(struct cmd_context *cmd)
+{
+	int file_exists;
+	int lock_mode = 0;
+
+	if (cmd->enable_devices_list) {
+		if (!_setup_devices_list(cmd))
+			return_0;
+		goto scan;
+	}
+
+	if (!setup_devices_file(cmd))
+		return_0;
+
+	if (!cmd->enable_devices_file)
+		goto scan;
+
+	file_exists = devices_file_exists(cmd);
+
+	/*
+	 * Removing the devices file is another way of disabling the use of
+	 * a devices file, unless the command creates the devices file.
+	 */
+	if (!file_exists && !cmd->create_edit_devices_file) {
+		log_debug("Devices file not found, ignoring.");
+		cmd->enable_devices_file = 0;
+		goto scan;
+	}
+
+	/*
+	 * Don't let pvcreate or vgcreate create a new system devices file
+	 * unless it's specified explicitly with --devicesfile.  This avoids
+	 * a problem where a system is running with existing PVs, and is
+	 * not using a devices file based on the fact that the system
+	 * devices file doesn't exist.  If the user simply uses pvcreate
+	 * to create a new PV, they almost certainly do not want that to
+	 * create a new system devices file containing the new PV and none
+	 * of the existing PVs that the system is already using.
+	 * However, if they use the vgimportdevices or lvmdevices command
+	 * then they are clearly intending to use the devices file, so we
+	 * can create it.  Or, if they specify a non-system devices file
+	 * with pvcreate/vgcreate, then they clearly want to use a devices
+	 * file and we can create it (and creating a non-system devices file 
+	 * would not cause existing PVs to disappear from the main system.)
+	 *
+	 * An exception is if pvcreate/vgcreate get to device_id_write and
+	 * did not see any existing VGs during label scan.  In that case
+	 * they will create a new system devices file, since there will be
+	 * no VGs that the new file would hide.
+	 */
+	if (cmd->create_edit_devices_file && !cmd->devicesfile && !file_exists &&
+	    (!strncmp(cmd->name, "pvcreate", 8) || !strncmp(cmd->name, "vgcreate", 8))) {
+		/* The command will decide in device_ids_write whether to create
+		   a new system devices file. */
+		cmd->enable_devices_file = 0;
+		cmd->pending_devices_file = 1;
+		goto scan;
+	}
+
+	if (!file_exists && cmd->sysinit) {
+		cmd->enable_devices_file = 0;
+		goto scan;
+	}
+
+	if (!file_exists) {
+		/*
+		 * pvcreate/vgcreate/vgimportdevices/lvmdevices-add create
+		 * a new devices file here if it doesn't exist.
+		 * They have the create_edit_devices_file flag set.
+		 * First they create/lock-ex the devices file lockfile.
+		 * Other commands will not use a devices file if none exists.
+		 */
+		lock_mode = LOCK_EX;
+
+		if (!lock_devices_file(cmd, lock_mode)) {
+			log_error("Failed to lock the devices file to create.");
+			return 0;
+		}
+
+		/* The file will be created in device_ids_write() */
+		if (!devices_file_exists(cmd))
+			goto scan;
+	} else {
+		/*
+		 * Commands that intend to edit the devices file have
+		 * edit_devices_file or create_edit_devices_file set (create if
+		 * they can also create a new devices file) and lock it ex
+		 * here prior to reading.  Other commands that intend to just
+		 * read the devices file lock sh.
+		 */
+		lock_mode = (cmd->create_edit_devices_file || cmd->edit_devices_file) ? LOCK_EX : LOCK_SH;
+
+		if (!lock_devices_file(cmd, lock_mode)) {
+			log_error("Failed to lock the devices file.");
+			return 0;
+		}
+	}
+
+	/*
+	 * Read the list of device ids that lvm can use.
+	 * Adds a struct dev_id to cmd->use_devices for each one.
+	 */
+	if (!device_ids_read(cmd)) {
+		log_error("Failed to read the devices file.");
+		unlock_devices_file(cmd);
+		return 0;
+	}
+
+	/*
+	 * When the command is editing the devices file, it acquires
+	 * the ex lock above, will later call device_ids_write(), and
+	 * then unlock the lock after writing the file.
+	 * When the command is just reading the devices file, it's
+	 * locked sh above just before reading the file, and unlocked
+	 * here after reading.
+	 */
+	if (lock_mode == LOCK_SH)
+		unlock_devices_file(cmd);
+
+ scan:
+	/*
+	 * Add a 'struct device' to dev-cache for each device available on the system.
+	 * This will not open or read any devices, but may look at sysfs properties.
+	 * This list of devs comes from looking /dev entries, or from asking libudev.
+	 */
+	dev_cache_scan();
+
+	/*
+	 * Match entries from cmd->use_devices with device structs in dev-cache.
+	 */
+	device_ids_match(cmd);
+
+	return 1;
+}
+
+/*
+ * The alternative to setup_devices() when the command is interested
+ * in using only one PV.
+ *
+ * Add one system device to dev-cache, and attempt to
+ * match its dev-cache entry to a devices_file entry.
+ */
+int setup_device(struct cmd_context *cmd, const char *devname)
+{
+	struct stat buf;
+	struct device *dev;
+
+	if (cmd->enable_devices_list) {
+		if (!_setup_devices_list(cmd))
+			return_0;
+		goto scan;
+	}
+
+	if (!setup_devices_file(cmd))
+		return_0;
+
+	if (!cmd->enable_devices_file)
+		goto scan;
+
+	if (!devices_file_exists(cmd)) {
+		log_debug("Devices file not found, ignoring.");
+		cmd->enable_devices_file = 0;
+		goto scan;
+	}
+
+	if (!lock_devices_file(cmd, LOCK_SH)) {
+		log_error("Failed to lock the devices file to read.");
+		return 0;
+	}
+
+	if (!device_ids_read(cmd)) {
+		log_error("Failed to read the devices file.");
+		unlock_devices_file(cmd);
+		return 0;
+	}
+
+	unlock_devices_file(cmd);
+
+ scan:
+	if (stat(devname, &buf) < 0) {
+		log_error("Cannot access device %s.", devname);
+		return 0;
+	}
+
+	if (!S_ISBLK(buf.st_mode)) {
+		log_error("Invaild device type %s.", devname);
+		return 0;
+	}
+
+	if (!_insert_dev(devname, buf.st_rdev))
+		return_0;
+
+	if (!(dev = (struct device *) dm_hash_lookup(_cache.names, devname)))
+		return_0;
+
+	/* Match this device to an entry in devices_file so it will not
+	   be rejected by filter-deviceid. */
+	if (cmd->enable_devices_file)
+		device_ids_match_dev(cmd, dev);
+
+	return 1;
+}
+

lib/device/dev-cache.h

@@ -28,13 +28,12 @@ struct cmd_context;
 struct dev_filter {
 	int (*passes_filter) (struct cmd_context *cmd, struct dev_filter *f, struct device *dev, const char *use_filter_name);
 	void (*destroy) (struct dev_filter *f);
-	void (*wipe) (struct dev_filter *f);
+	void (*wipe) (struct cmd_context *cmd, struct dev_filter *f, struct device *dev, const char *use_filter_name);
 	void *private;
 	unsigned use_count;
 	const char *name;
 };
 
-int dev_cache_index_devs(void);
 struct dm_list *dev_cache_get_dev_list_for_vgid(const char *vgid);
 struct dm_list *dev_cache_get_dev_list_for_lvid(const char *lvid);
 
@@ -54,10 +53,11 @@ int dev_cache_has_scanned(void);
 
 int dev_cache_add_dir(const char *path);
 struct device *dev_cache_get(struct cmd_context *cmd, const char *name, struct dev_filter *f);
-const char *dev_cache_filtered_reason(const char *name);
 
 struct device *dev_cache_get_by_devt(struct cmd_context *cmd, dev_t device, struct dev_filter *f, int *filtered);
 
+struct device *dev_hash_get(const char *name);
+
 void dev_set_preferred_name(struct dm_str_list *sl, struct device *dev);
 
 /*
@@ -74,4 +74,10 @@ void dev_cache_failed_path(struct device *dev, const char *path);
 
 bool dev_cache_has_md_with_end_superblock(struct dev_types *dt);
 
+int get_sysfs_value(const char *path, char *buf, size_t buf_size, int error_if_no_value);
+
+int setup_devices_file(struct cmd_context *cmd);
+int setup_devices(struct cmd_context *cmd);
+int setup_device(struct cmd_context *cmd, const char *devname);
+
 #endif

lib/device/dev-io.c

@@ -86,6 +86,9 @@ static int _dev_get_size_dev(struct device *dev, uint64_t *size)
 	int fd = dev->bcache_fd;
 	int do_close = 0;
 
+	if (dm_list_empty(&dev->aliases))
+		return 0;
+
 	if (dev->size_seqno == _dev_size_seqno) {
 		log_very_verbose("%s: using cached size %" PRIu64 " sectors",
 				 name, dev->size);
@@ -94,16 +97,16 @@ static int _dev_get_size_dev(struct device *dev, uint64_t *size)
 	}
 
 	if (fd <= 0) {
-		if (!dev_open_readonly(dev))
+		if (!dev_open_readonly_quiet(dev))
 			return_0;
 		fd = dev_fd(dev);
 		do_close = 1;
 	}
 
 	if (ioctl(fd, BLKGETSIZE64, size) < 0) {
-		log_sys_error("ioctl BLKGETSIZE64", name);
+		log_warn("WARNING: %s: ioctl BLKGETSIZE64 %s", name, strerror(errno));
 		if (do_close && !dev_close_immediate(dev))
-			log_sys_error("close", name);
+			stack;
 		return 0;
 	}
 
@@ -114,7 +117,7 @@ static int _dev_get_size_dev(struct device *dev, uint64_t *size)
 	log_very_verbose("%s: size is %" PRIu64 " sectors", name, *size);
 
 	if (do_close && !dev_close_immediate(dev))
-		log_sys_error("close", name);
+		stack;
 
 	return 1;
 }
@@ -128,11 +131,14 @@ static int _dev_read_ahead_dev(struct device *dev, uint32_t *read_ahead)
 		return 1;
 	}
 
-	if (!dev_open_readonly(dev))
-		return_0;
+	if (!dev_open_readonly_quiet(dev)) {
+		log_warn("WARNING: Failed to open %s to get readahead %s.",
+			 dev_name(dev), strerror(errno));
+		return 0;
+	}
 
 	if (ioctl(dev->fd, BLKRAGET, &read_ahead_long) < 0) {
-		log_sys_error("ioctl BLKRAGET", dev_name(dev));
+		log_warn("WARNING: %s: ioctl BLKRAGET %s.", dev_name(dev), strerror(errno));
 		if (!dev_close_immediate(dev))
 			stack;
 		return 0;
@@ -165,7 +171,7 @@ static int _dev_discard_blocks(struct device *dev, uint64_t offset_bytes, uint64
 		       test_mode() ? " (test mode - suppressed)" : "");
 
 	if (!test_mode() && ioctl(dev->fd, BLKDISCARD, &discard_range) < 0) {
-		log_error("%s: BLKDISCARD ioctl at offset %" PRIu64 " size %" PRIu64 " failed: %s.",
+		log_warn("WARNING: %s: ioctl BLKDISCARD at offset %" PRIu64 " size %" PRIu64 " failed: %s.",
 			  dev_name(dev), offset_bytes, size_bytes, strerror(errno));
 		if (!dev_close_immediate(dev))
 			stack;
@@ -194,7 +200,7 @@ int dev_get_direct_block_sizes(struct device *dev, unsigned int *physical_block_
 	}
 
 	if (fd <= 0) {
-		if (!dev_open_readonly(dev))
+		if (!dev_open_readonly_quiet(dev))
 			return 0;
 		fd = dev_fd(dev);
 		do_close = 1;
@@ -444,7 +450,7 @@ int dev_open_readonly_quiet(struct device *dev)
 static void _close(struct device *dev)
 {
 	if (close(dev->fd))
-		log_sys_error("close", dev_name(dev));
+		log_sys_debug("close", dev_name(dev));
 	dev->fd = -1;
 
 	log_debug_devs("Closed %s", dev_name(dev));

lib/device/dev-md.c

@@ -16,6 +16,7 @@
 #include "lib/misc/lib.h"
 #include "lib/device/dev-type.h"
 #include "lib/mm/xlate.h"
+#include "lib/misc/crc.h"
 #ifdef UDEV_SYNC_SUPPORT
 #include <libudev.h> /* for MD detection using udev db records */
 #include "lib/device/dev-ext-udev-constants.h"
@@ -48,44 +49,99 @@ static int _dev_has_md_magic(struct device *dev, uint64_t sb_offset)
 	return 0;
 }
 
-/*
- * Calculate the position of the superblock.
- * It is always aligned to a 4K boundary and
- * depending on minor_version, it can be:
- * 0: At least 8K, but less than 12K, from end of device
- * 1: At start of device
- * 2: 4K from start of device.
- */
-typedef enum {
-	MD_MINOR_VERSION_MIN,
-	MD_MINOR_V0 = MD_MINOR_VERSION_MIN,
-	MD_MINOR_V1,
-	MD_MINOR_V2,
-	MD_MINOR_VERSION_MAX = MD_MINOR_V2
-} md_minor_version_t;
+#define IMSM_SIGNATURE "Intel Raid ISM Cfg Sig. "
+#define IMSM_SIG_LEN (sizeof(IMSM_SIGNATURE) - 1)
 
-static uint64_t _v1_sb_offset(uint64_t size, md_minor_version_t minor_version)
+static int _dev_has_imsm_magic(struct device *dev, uint64_t devsize_sectors)
 {
-	uint64_t sb_offset;
+	char imsm_signature[IMSM_SIG_LEN];
+	uint64_t off = (devsize_sectors * 512) - 1024;
+	unsigned int physical_block_size = 0;
+	unsigned int logical_block_size = 0;
 
-	switch(minor_version) {
-	case MD_MINOR_V0:
-		sb_offset = (size - 8 * 2) & ~(4 * 2 - 1ULL);
-		break;
-	case MD_MINOR_V1:
-		sb_offset = 0;
-		break;
-	case MD_MINOR_V2:
-		sb_offset = 4 * 2;
-		break;
-	default:
-		log_warn(INTERNAL_ERROR "WARNING: Unknown minor version %d.",
-			 minor_version);
+	if (!dev_get_direct_block_sizes(dev, &physical_block_size, &logical_block_size))
+		return_0;
+
+	if (logical_block_size == 4096)
+		off = (devsize_sectors * 512) - 8192;
+	else
+		off = (devsize_sectors * 512) - 1024;
+
+	if (!dev_read_bytes(dev, off, IMSM_SIG_LEN, imsm_signature))
+		return_0;
+
+	if (!memcmp(imsm_signature, IMSM_SIGNATURE, IMSM_SIG_LEN))
+		return 1;
+
+	return 0;
+}
+
+#define DDF_MAGIC 0xDE11DE11
+struct ddf_header {
+	uint32_t magic;
+	uint32_t crc;
+	char guid[24];
+	char revision[8];
+	char padding[472];
+};
+
+static int _dev_has_ddf_magic(struct device *dev, uint64_t devsize_sectors, uint64_t *sb_offset)
+{
+	struct ddf_header hdr;
+	uint32_t crc, our_crc;
+	uint64_t off;
+	uint64_t devsize_bytes = devsize_sectors * 512;
+
+	if (devsize_bytes < 0x30000)
 		return 0;
-	}
-	sb_offset <<= SECTOR_SHIFT;
 
-	return sb_offset;
+	/* 512 bytes before the end of device (from libblkid) */
+	off = ((devsize_bytes / 0x200) - 1) * 0x200;
+
+	if (!dev_read_bytes(dev, off, 512, &hdr))
+		return_0;
+
+	if ((hdr.magic == cpu_to_be32(DDF_MAGIC)) ||
+	    (hdr.magic == cpu_to_le32(DDF_MAGIC))) {
+		crc = hdr.crc;
+		hdr.crc = 0xffffffff;
+		our_crc = calc_crc(0, (const uint8_t *)&hdr, 512);
+
+		if ((cpu_to_be32(our_crc) == crc) ||
+		    (cpu_to_le32(our_crc) == crc)) {
+			*sb_offset = off;
+			return 1;
+		} else {
+			log_debug_devs("Found md ddf magic at %llu wrong crc %x disk %x %s",
+				       (unsigned long long)off, our_crc, crc, dev_name(dev));
+			return 0;
+		}
+	}
+
+	/* 128KB before the end of device (from libblkid) */
+	off = ((devsize_bytes / 0x200) - 257) * 0x200;
+
+	if (!dev_read_bytes(dev, off, 512, &hdr))
+		return_0;
+
+	if ((hdr.magic == cpu_to_be32(DDF_MAGIC)) ||
+	    (hdr.magic == cpu_to_le32(DDF_MAGIC))) {
+		crc = hdr.crc;
+		hdr.crc = 0xffffffff;
+		our_crc = calc_crc(0, (const uint8_t *)&hdr, 512);
+
+		if ((cpu_to_be32(our_crc) == crc) ||
+		    (cpu_to_le32(our_crc) == crc)) {
+			*sb_offset = off;
+			return 1;
+		} else {
+			log_debug_devs("Found md ddf magic at %llu wrong crc %x disk %x %s",
+				       (unsigned long long)off, our_crc, crc, dev_name(dev));
+			return 0;
+		}
+	}
+
+	return 0;
 }
 
 /*
@@ -130,8 +186,7 @@ static int _udev_dev_is_md_component(struct device *dev)
  */
 static int _native_dev_is_md_component(struct device *dev, uint64_t *offset_found, int full)
 {
-	md_minor_version_t minor;
-	uint64_t size, sb_offset;
+	uint64_t size, sb_offset = 0;
 	int ret;
 
 	if (!scan_bcache)
@@ -146,9 +201,9 @@ static int _native_dev_is_md_component(struct device *dev, uint64_t *offset_foun
 		return 0;
 
 	/*
-	 * Old md versions locate the magic number at the end of the device.
-	 * Those checks can't be satisfied with the initial bcache data, and
-	 * would require an extra read i/o at the end of every device.  Issuing
+	 * Some md versions locate the magic number at the end of the device.
+	 * Those checks can't be satisfied with the initial scan data, and
+	 * require an extra read i/o at the end of every device.  Issuing
 	 * an extra read to every device in every command, just to check for
 	 * the old md format is a bad tradeoff.
 	 *
@@ -159,42 +214,81 @@ static int _native_dev_is_md_component(struct device *dev, uint64_t *offset_foun
 	 * and set it for commands that could possibly write to an md dev
 	 * (pvcreate/vgcreate/vgextend).
 	 */
-	if (!full) {
-		sb_offset = 0;
-		if (_dev_has_md_magic(dev, sb_offset)) {
-			log_debug_devs("Found md magic number at offset 0 of %s.", dev_name(dev));
-			ret = 1;
-			goto out;
-		}
 
-		sb_offset = 8 << SECTOR_SHIFT;
-		if (_dev_has_md_magic(dev, sb_offset)) {
-			log_debug_devs("Found md magic number at offset %d of %s.", (int)sb_offset, dev_name(dev));
-			ret = 1;
-			goto out;
-		}
+	/*
+	 * md superblock version 1.1 at offset 0 from start
+	 */
 
-		ret = 0;
-		goto out;
-	}
-
-	/* Check if it is an md component device. */
-	/* Version 0.90.0 */
-	sb_offset = MD_NEW_SIZE_SECTORS(size) << SECTOR_SHIFT;
-	if (_dev_has_md_magic(dev, sb_offset)) {
+	if (_dev_has_md_magic(dev, 0)) {
+		log_debug_devs("Found md magic number at offset 0 of %s.", dev_name(dev));
 		ret = 1;
 		goto out;
 	}
 
-	minor = MD_MINOR_VERSION_MIN;
-	/* Version 1, try v1.0 -> v1.2 */
-	do {
-		sb_offset = _v1_sb_offset(size, minor);
-		if (_dev_has_md_magic(dev, sb_offset)) {
-			ret = 1;
-			goto out;
-		}
-	} while (++minor <= MD_MINOR_VERSION_MAX);
+	/*
+	 * md superblock version 1.2 at offset 4KB from start
+	 */
+
+	if (_dev_has_md_magic(dev, 4096)) {
+		log_debug_devs("Found md magic number at offset 4096 of %s.", dev_name(dev));
+		ret = 1;
+		goto out;
+	}
+
+	if (!full) {
+		ret = 0;
+		goto out;
+	}
+
+	/*
+	 * Handle superblocks at the end of the device.
+	 */
+
+	/*
+	 * md superblock version 0 at 64KB from end of device
+	 * (after end is aligned to 64KB)
+	 */
+
+	sb_offset = MD_NEW_SIZE_SECTORS(size) << SECTOR_SHIFT;
+
+	if (_dev_has_md_magic(dev, sb_offset)) {
+		log_debug_devs("Found md magic number at offset %llu of %s.", (unsigned long long)sb_offset, dev_name(dev));
+		ret = 1;
+		goto out;
+	}
+
+	/*
+	 * md superblock version 1.0 at 8KB from end of device
+	 */
+
+	sb_offset = ((size - 8 * 2) & ~(4 * 2 - 1ULL)) << SECTOR_SHIFT;
+
+	if (_dev_has_md_magic(dev, sb_offset)) {
+		log_debug_devs("Found md magic number at offset %llu of %s.", (unsigned long long)sb_offset, dev_name(dev));
+		ret = 1;
+		goto out;
+	}
+
+	/*
+	 * md imsm superblock 1K from end of device
+	 */
+
+	if (_dev_has_imsm_magic(dev, size)) {
+		log_debug_devs("Found md imsm magic number at offset %llu of %s.", (unsigned long long)sb_offset, dev_name(dev));
+		sb_offset = 1024;
+		ret = 1;
+		goto out;
+	}
+
+	/*
+	 * md ddf superblock 512 bytes from end, or 128KB from end
+	 */
+
+	if (_dev_has_ddf_magic(dev, size, &sb_offset)) {
+		log_debug_devs("Found md ddf magic number at offset %llu of %s.", (unsigned long long)sb_offset, dev_name(dev));
+		ret = 1;
+		goto out;
+	}
 
 	ret = 0;
 out:

lib/device/dev-type.c

@@ -21,6 +21,7 @@
 #include "lib/metadata/metadata.h"
 #include "lib/device/bcache.h"
 #include "lib/label/label.h"
+#include "lib/commands/toolcontext.h"
 
 #ifdef BLKID_WIPING_SUPPORT
 #include <blkid.h>
@@ -35,36 +36,16 @@
 #include <ctype.h>
 
 /*
- * dev is pmem if /sys/dev/block/<major>:<minor>/queue/dax is 1
+ * An nvme device has major number 259 (BLKEXT), minor number <minor>,
+ * and reading /sys/dev/block/259:<minor>/device/dev shows a character
+ * device cmajor:cminor where cmajor matches the major number of the
+ * nvme character device entry in /proc/devices.  Checking all of that
+ * is excessive and unnecessary compared to just comparing /dev/name*.
  */
 
-int dev_is_pmem(struct device *dev)
+int dev_is_nvme(struct dev_types *dt, struct device *dev)
 {
-	FILE *fp;
-	char path[PATH_MAX];
-	int is_pmem = 0;
-
-	if (dm_snprintf(path, sizeof(path), "%sdev/block/%d:%d/queue/dax",
-			dm_sysfs_dir(),
-			(int) MAJOR(dev->dev),
-			(int) MINOR(dev->dev)) < 0) {
-		log_warn("Sysfs path for %s dax is too long.", dev_name(dev));
-		return 0;
-	}
-
-	if (!(fp = fopen(path, "r")))
-		return 0;
-
-	if (fscanf(fp, "%d", &is_pmem) != 1)
-		log_warn("Failed to parse DAX %s.", path);
-
-	if (is_pmem)
-		log_debug("%s is pmem", dev_name(dev));
-
-	if (fclose(fp))
-		log_sys_debug("fclose", path);
-
-	return is_pmem ? 1 : 0;
+	return (dev->flags & DEV_IS_NVME) ? 1 : 0;
 }
 
 int dev_is_lv(struct device *dev)
@@ -86,7 +67,7 @@ int dev_is_lv(struct device *dev)
 		return 0;
 
 	if (!fgets(buffer, sizeof(buffer), fp))
-		log_warn("Failed to read %s.", path);
+		log_debug("Failed to read %s.", path);
 	else if (!strncmp(buffer, "LVM-", 4))
 		ret = 1;
 
@@ -230,7 +211,7 @@ struct dev_types *create_dev_types(const char *proc_dir,
 				log_error("Expecting string in devices/types "
 					  "in config file");
 				if (fclose(pd))
-					log_sys_error("fclose", proc_devices);
+					log_sys_debug("fclose", proc_devices);
 				goto bad;
 			}
 			dev_len = strlen(cv->v.str);
@@ -241,7 +222,7 @@ struct dev_types *create_dev_types(const char *proc_dir,
 					  "in devices/types in config file",
 					  name);
 				if (fclose(pd))
-					log_sys_error("fclose", proc_devices);
+					log_sys_debug("fclose", proc_devices);
 				goto bad;
 			}
 			if (!cv->v.i) {
@@ -249,7 +230,7 @@ struct dev_types *create_dev_types(const char *proc_dir,
 					  "%s in devices/types in config file",
 					  name);
 				if (fclose(pd))
-					log_sys_error("fclose", proc_devices);
+					log_sys_debug("fclose", proc_devices);
 				goto bad;
 			}
 			if (dev_len <= strlen(line + i) &&
@@ -302,6 +283,9 @@ int dev_subsystem_part_major(struct dev_types *dt, struct device *dev)
 
 const char *dev_subsystem_name(struct dev_types *dt, struct device *dev)
 {
+	if (dev->flags & DEV_IS_NVME)
+		return "NVME";
+
 	if (MAJOR(dev->dev) == dt->device_mapper_major)
 		return "DM";
 
@@ -348,7 +332,6 @@ int major_is_scsi_device(struct dev_types *dt, int major)
 	return (dt->dev_type_array[major].flags & PARTITION_SCSI_DEVICE) ? 1 : 0;
 }
 
-
 static int _loop_is_with_partscan(struct device *dev)
 {
 	FILE *fp;
@@ -380,6 +363,45 @@ static int _loop_is_with_partscan(struct device *dev)
 	return partscan;
 }
 
+int dev_get_partition_number(struct device *dev, int *num)
+{
+	char path[PATH_MAX];
+	char buf[8] = { 0 };
+	dev_t devt = dev->dev;
+	struct stat sb;
+
+	if (dev->part != -1) {
+		*num = dev->part;
+		return 1;
+	}
+
+	if (dm_snprintf(path, sizeof(path), "%sdev/block/%d:%d/partition",
+			dm_sysfs_dir(), (int)MAJOR(devt), (int)MINOR(devt)) < 0) {
+		log_error("Failed to create sysfs path for %s", dev_name(dev));
+		return 0;
+	}
+
+	if (stat(path, &sb)) {
+		dev->part = 0;
+		*num = 0;
+		return 1;
+	}
+
+	if (!get_sysfs_value(path, buf, sizeof(buf), 0)) {
+		log_error("Failed to read sysfs path for %s", dev_name(dev));
+		return 0;
+	}
+
+	if (!buf[0]) {
+		log_error("Failed to read sysfs partition value for %s", dev_name(dev));
+		return 0;
+	}
+
+	dev->part = atoi(buf);
+	*num = dev->part;
+	return 1;
+}
+
 /* See linux/genhd.h and fs/partitions/msdos */
 #define PART_MAGIC 0xAA55
 #define PART_MAGIC_OFFSET UINT64_C(0x1FE)
@@ -398,6 +420,28 @@ struct partition {
 	uint32_t nr_sects;
 } __attribute__((packed));
 
+static int _has_sys_partition(struct device *dev)
+{
+	char path[PATH_MAX];
+	struct stat info;
+	int major = (int) MAJOR(dev->dev);
+	int minor = (int) MINOR(dev->dev);
+
+	/* check if dev is a partition */
+	if (dm_snprintf(path, sizeof(path), "%s/dev/block/%d:%d/partition",
+			dm_sysfs_dir(), major, minor) < 0) {
+		log_warn("WARNING: %s: partition path is too long.", dev_name(dev));
+		return 0;
+	}
+
+	if (stat(path, &info) == -1) {
+		if (errno != ENOENT)
+			log_sys_debug("stat", path);
+		return 0;
+	}
+	return 1;
+}
+
 static int _is_partitionable(struct dev_types *dt, struct device *dev)
 {
 	int parts = major_max_partitions(dt, MAJOR(dev->dev));
@@ -414,6 +458,13 @@ static int _is_partitionable(struct dev_types *dt, struct device *dev)
 	    _loop_is_with_partscan(dev))
 		return 1;
 
+	if (dev_is_nvme(dt, dev)) {
+		/* If this dev is already a partition then it's not partitionable. */
+		if (_has_sys_partition(dev))
+			return 0;
+		return 1;
+	}
+
 	if ((parts <= 1) || (MINOR(dev->dev) % parts))
 		return 0;
 
@@ -551,16 +602,22 @@ int dev_is_partitioned(struct dev_types *dt, struct device *dev)
  */
 int dev_get_primary_dev(struct dev_types *dt, struct device *dev, dev_t *result)
 {
-	const char *sysfs_dir = dm_sysfs_dir();
 	int major = (int) MAJOR(dev->dev);
 	int minor = (int) MINOR(dev->dev);
 	char path[PATH_MAX];
 	char temp_path[PATH_MAX];
 	char buffer[64];
-	struct stat info;
 	FILE *fp = NULL;
 	int parts, residue, size, ret = 0;
 
+	/*
+	 * /dev/nvme devs don't use the major:minor numbering like
+	 * block dev types that have their own major number, so
+	 * the calculation based on minor number doesn't work.
+	 */
+	if (dev_is_nvme(dt, dev))
+		goto sys_partition;
+
 	/*
 	 * Try to get the primary dev out of the
 	 * list of known device types first.
@@ -576,23 +633,14 @@ int dev_get_primary_dev(struct dev_types *dt, struct device *dev, dev_t *result)
 		goto out;
 	}
 
+ sys_partition:
 	/*
 	 * If we can't get the primary dev out of the list of known device
 	 * types, try to look at sysfs directly then. This is more complex
 	 * way and it also requires certain sysfs layout to be present
 	 * which might not be there in old kernels!
 	 */
-
-	/* check if dev is a partition */
-	if (dm_snprintf(path, sizeof(path), "%s/dev/block/%d:%d/partition",
-			sysfs_dir, major, minor) < 0) {
-		log_error("dm_snprintf partition failed");
-		goto out;
-	}
-
-	if (stat(path, &info) == -1) {
-		if (errno != ENOENT)
-			log_sys_error("stat", path);
+	if (!_has_sys_partition(dev)) {
 		*result = dev->dev;
 		ret = 1;
 		goto out; /* dev is not a partition! */
@@ -605,25 +653,31 @@ int dev_get_primary_dev(struct dev_types *dt, struct device *dev, dev_t *result)
 	 * - basename ../../block/md0/md0  = md0
 	 * Parent's 'dev' sysfs attribute  = /sys/block/md0/dev
 	 */
-	if ((size = readlink(dirname(path), temp_path, sizeof(temp_path) - 1)) < 0) {
-		log_sys_error("readlink", path);
+	if (dm_snprintf(path, sizeof(path), "%s/dev/block/%d:%d",
+			dm_sysfs_dir(), major, minor) < 0) {
+		log_warn("WARNING: %s: major:minor sysfs path is too long.", dev_name(dev));
+		return 0;
+	}
+	if ((size = readlink(path, temp_path, sizeof(temp_path) - 1)) < 0) {
+		log_warn("WARNING: Readlink of %s failed.", path);
 		goto out;
 	}
 
 	temp_path[size] = '\0';
 
 	if (dm_snprintf(path, sizeof(path), "%s/block/%s/dev",
-			sysfs_dir, basename(dirname(temp_path))) < 0) {
-		log_error("dm_snprintf dev failed");
+			dm_sysfs_dir(), basename(dirname(temp_path))) < 0) {
+		log_warn("WARNING: sysfs path for %s is too long.",
+			 basename(dirname(temp_path)));
 		goto out;
 	}
 
 	/* finally, parse 'dev' attribute and create corresponding dev_t */
 	if (!(fp = fopen(path, "r"))) {
 		if (errno == ENOENT)
-			log_error("sysfs file %s does not exist.", path);
+			log_debug("sysfs file %s does not exist.", path);
 		else
-			log_sys_error("fopen", path);
+			log_sys_debug("fopen", path);
 		goto out;
 	}
 
@@ -633,7 +687,7 @@ int dev_get_primary_dev(struct dev_types *dt, struct device *dev, dev_t *result)
 	}
 
 	if (sscanf(buffer, "%d:%d", &major, &minor) != 2) {
-		log_error("sysfs file %s not in expected MAJ:MIN format: %s",
+		log_warn("WARNING: sysfs file %s not in expected MAJ:MIN format: %s",
 			  path, buffer);
 		goto out;
 	}
@@ -641,11 +695,36 @@ int dev_get_primary_dev(struct dev_types *dt, struct device *dev, dev_t *result)
 	ret = 2;
 out:
 	if (fp && fclose(fp))
-		log_sys_error("fclose", path);
+		log_sys_debug("fclose", path);
 
 	return ret;
 }
 
+#ifdef BLKID_WIPING_SUPPORT
+int get_fs_block_size(struct device *dev, uint32_t *fs_block_size)
+{
+	char *block_size_str = NULL;
+
+	if ((block_size_str = blkid_get_tag_value(NULL, "BLOCK_SIZE", dev_name(dev)))) {
+		*fs_block_size = (uint32_t)atoi(block_size_str);
+		free(block_size_str);
+		log_debug("Found blkid BLOCK_SIZE %u for fs on %s", *fs_block_size, dev_name(dev));
+		return 1;
+	} else {
+		log_debug("No blkid BLOCK_SIZE for fs on %s", dev_name(dev));
+		*fs_block_size = 0;
+		return 0;
+	}
+}
+#else
+int get_fs_block_size(struct device *dev, uint32_t *fs_block_size)
+{
+	log_debug("Disabled blkid BLOCK_SIZE for fs.");
+	*fs_block_size = 0;
+	return 0;
+}
+#endif
+
 #ifdef BLKID_WIPING_SUPPORT
 
 static inline int _type_in_flag_list(const char *type, uint32_t flag_list)
@@ -678,7 +757,7 @@ static int _blkid_wipe(blkid_probe probe, struct device *dev, const char *name,
 				return 0;
 			}
 
-			log_error("WARNING: " MSG_FAILED_SIG_OFFSET MSG_WIPING_SKIPPED, type, name);
+			log_warn("WARNING: " MSG_FAILED_SIG_OFFSET MSG_WIPING_SKIPPED, type, name);
 			return 2;
 		}
 		if (blkid_probe_lookup_value(probe, "SBMAGIC", &magic, &len)) {
@@ -876,9 +955,9 @@ int wipe_known_signatures(struct cmd_context *cmd, struct device *dev,
 							 yes, force, wiped);
 #endif
 	if (blkid_wiping_enabled) {
-		log_warn("allocation/use_blkid_wiping=1 configuration setting is set "
+		log_warn("WARNING: allocation/use_blkid_wiping=1 configuration setting is set "
 			 "while LVM is not compiled with blkid wiping support.");
-		log_warn("Falling back to native LVM signature detection.");
+		log_warn("WARNING: Falling back to native LVM signature detection.");
 	}
 	return _wipe_known_signatures_with_lvm(dev, name,
 					       types_to_exclude,
@@ -894,25 +973,23 @@ static int _snprintf_attr(char *buf, size_t buf_size, const char *sysfs_dir,
 	if (dm_snprintf(buf, buf_size, "%s/dev/block/%d:%d/%s", sysfs_dir,
 			(int)MAJOR(dev), (int)MINOR(dev),
 			attribute) < 0) {
-		log_warn("dm_snprintf %s failed.", attribute);
+		log_warn("WARNING: sysfs path for %s attribute is too long.", attribute);
 		return 0;
 	}
 
 	return 1;
 }
 
-static unsigned long _dev_topology_attribute(struct dev_types *dt,
-					     const char *attribute,
-					     struct device *dev,
-					     unsigned long default_value)
+static int _dev_sysfs_block_attribute(struct dev_types *dt,
+				      const char *attribute,
+				      struct device *dev,
+				      unsigned long *value)
 {
 	const char *sysfs_dir = dm_sysfs_dir();
 	char path[PATH_MAX], buffer[64];
 	FILE *fp;
-	struct stat info;
-	dev_t uninitialized_var(primary);
-	unsigned long result = default_value;
-	unsigned long value = 0UL;
+	dev_t primary = 0;
+	int ret = 0;
 
 	if (!attribute || !*attribute)
 		goto_out;
@@ -921,16 +998,16 @@ static unsigned long _dev_topology_attribute(struct dev_types *dt,
 		goto_out;
 
 	if (!_snprintf_attr(path, sizeof(path), sysfs_dir, attribute, dev->dev))
-                goto_out;
+		goto_out;
 
 	/*
 	 * check if the desired sysfs attribute exists
 	 * - if not: either the kernel doesn't have topology support
 	 *   or the device could be a partition
 	 */
-	if (stat(path, &info) == -1) {
+	if (!(fp = fopen(path, "r"))) {
 		if (errno != ENOENT) {
-			log_sys_debug("stat", path);
+			log_sys_debug("fopen", path);
 			goto out;
 		}
 		if (!dev_get_primary_dev(dt, dev, &primary))
@@ -940,44 +1017,54 @@ static unsigned long _dev_topology_attribute(struct dev_types *dt,
 		if (!_snprintf_attr(path, sizeof(path), sysfs_dir, attribute, primary))
 			goto_out;
 
-		if (stat(path, &info) == -1) {
+		if (!(fp = fopen(path, "r"))) {
 			if (errno != ENOENT)
-				log_sys_debug("stat", path);
+				log_sys_debug("fopen", path);
 			goto out;
 		}
 	}
 
-	if (!(fp = fopen(path, "r"))) {
-		log_sys_debug("fopen", path);
-		goto out;
-	}
-
 	if (!fgets(buffer, sizeof(buffer), fp)) {
 		log_sys_debug("fgets", path);
 		goto out_close;
 	}
 
-	if (sscanf(buffer, "%lu", &value) != 1) {
-		log_warn("sysfs file %s not in expected format: %s", path, buffer);
+	if (sscanf(buffer, "%lu", value) != 1) {
+		log_warn("WARNING: sysfs file %s not in expected format: %s", path, buffer);
 		goto out_close;
 	}
 
-	log_very_verbose("Device %s: %s is %lu%s.",
-			 dev_name(dev), attribute, value, default_value ? "" : " bytes");
-
-	result = value >> SECTOR_SHIFT;
-
-	if (!result && value) {
-		log_warn("WARNING: Device %s: %s is %lu and is unexpectedly less than sector.",
-			 dev_name(dev), attribute, value);
-		result = 1;
-	}
+	ret = 1;
 
 out_close:
 	if (fclose(fp))
 		log_sys_debug("fclose", path);
 
 out:
+	return ret;
+}
+
+static unsigned long _dev_topology_attribute(struct dev_types *dt,
+					     const char *attribute,
+					     struct device *dev,
+					     unsigned long default_value)
+{
+	unsigned long result = default_value;
+	unsigned long value = 0UL;
+
+	if (_dev_sysfs_block_attribute(dt, attribute, dev, &value)) {
+		log_very_verbose("Device %s: %s is %lu%s.",
+				 dev_name(dev), attribute, value, default_value ? "" : " bytes");
+
+		result = value >> SECTOR_SHIFT;
+
+		if (!result && value) {
+			log_warn("WARNING: Device %s: %s is %lu and is unexpectedly less than sector.",
+				 dev_name(dev), attribute, value);
+			result = 1;
+		}
+	}
+
 	return result;
 }
 
@@ -1008,8 +1095,17 @@ unsigned long dev_discard_granularity(struct dev_types *dt, struct device *dev)
 
 int dev_is_rotational(struct dev_types *dt, struct device *dev)
 {
-	return (int) _dev_topology_attribute(dt, "queue/rotational", dev, 1UL);
+	unsigned long value;
+	return _dev_sysfs_block_attribute(dt, "queue/rotational", dev, &value) ? (int) value : 1;
 }
+
+/* dev is pmem if /sys/dev/block/<major>:<minor>/queue/dax is 1 */
+int dev_is_pmem(struct dev_types *dt, struct device *dev)
+{
+	unsigned long value;
+	return _dev_sysfs_block_attribute(dt, "queue/dax", dev, &value) ? (int) value : 0;
+}
+
 #else
 
 int dev_get_primary_dev(struct dev_types *dt, struct device *dev, dev_t *result)
@@ -1046,6 +1142,11 @@ int dev_is_rotational(struct dev_types *dt, struct device *dev)
 {
 	return 1;
 }
+
+int dev_is_pmem(struct dev_types *dt, struct device *dev)
+{
+	return 0;
+}
 #endif
 
 #ifdef UDEV_SYNC_SUPPORT

lib/device/dev-type.h

@@ -83,6 +83,7 @@ int dev_is_md_with_end_superblock(struct dev_types *dt, struct device *dev);
 int major_max_partitions(struct dev_types *dt, int major);
 int dev_is_partitioned(struct dev_types *dt, struct device *dev);
 int dev_get_primary_dev(struct dev_types *dt, struct device *dev, dev_t *result);
+int dev_get_partition_number(struct device *dev, int *num);
 
 /* Various device properties */
 unsigned long dev_alignment_offset(struct dev_types *dt, struct device *dev);
@@ -93,8 +94,12 @@ unsigned long dev_discard_granularity(struct dev_types *dt, struct device *dev);
 
 int dev_is_rotational(struct dev_types *dt, struct device *dev);
 
-int dev_is_pmem(struct device *dev);
+int dev_is_pmem(struct dev_types *dt, struct device *dev);
+
+int dev_is_nvme(struct dev_types *dt, struct device *dev);
 
 int dev_is_lv(struct device *dev);
 
+int get_fs_block_size(struct device *dev, uint32_t *fs_block_size);
+
 #endif

lib/device/device.h

@@ -38,6 +38,8 @@
 #define DEV_SCAN_FOUND_LABEL	0x00010000      /* label scan read dev and found label */
 #define DEV_IS_MD_COMPONENT	0x00020000	/* device is an md component */
 #define DEV_UDEV_INFO_MISSING   0x00040000	/* we have no udev info for this device */
+#define DEV_IS_NVME		0x00080000	/* set if dev is nvme */
+#define DEV_MATCHED_USE_ID	0x00100000	/* matched an entry from cmd->use_devices */
 
 /*
  * Support for external device info.
@@ -56,12 +58,54 @@ struct dev_ext {
 	void *handle;
 };
 
+#define DEV_ID_TYPE_SYS_WWID   0x0001
+#define DEV_ID_TYPE_SYS_SERIAL 0x0002
+#define DEV_ID_TYPE_MPATH_UUID 0x0003
+#define DEV_ID_TYPE_MD_UUID    0x0004
+#define DEV_ID_TYPE_LOOP_FILE  0x0005
+#define DEV_ID_TYPE_CRYPT_UUID 0x0006
+#define DEV_ID_TYPE_LVMLV_UUID 0x0007
+#define DEV_ID_TYPE_DEVNAME    0x0008
+
+/*
+ * A device ID of a certain type for a device.
+ * A struct device may have multiple dev_id structs on dev->ids.
+ * One of them will be the one that's used, pointed to by dev->id.
+ */
+
+struct dev_id {
+	struct dm_list list;
+	struct device *dev;
+	uint16_t idtype;	/* DEV_ID_TYPE_ */
+	char *idname;		/* id string determined by idtype */
+};
+
+/*
+ * A device listed in devices file that lvm should use.
+ * Each entry in the devices file is represented by a struct dev_use.
+ * The structs are kept on cmd->use_devices.
+ * idtype/idname/pvid/part are set when reading the devices file.
+ * du->dev is set when a struct dev_use is matched to a struct device.
+ */
+
+struct dev_use {
+	struct dm_list list;
+	struct device *dev;
+	int part;
+	uint16_t idtype;
+	char *idname;
+	char *devname;
+	char *pvid;
+};
+
 /*
  * All devices in LVM will be represented by one of these.
  * pointer comparisons are valid.
  */
 struct device {
 	struct dm_list aliases;	/* struct dm_str_list */
+	struct dm_list ids; /* struct dev_id, different entries for different idtypes */
+	struct dev_id *id; /* points to the the ids entry being used for this dev */
 	dev_t dev;
 
 	/* private */
@@ -71,7 +115,10 @@ struct device {
 	int logical_block_size;  /* From BLKSSZGET: lowest possible block size that the storage device can address */
 	int read_ahead;
 	int bcache_fd;
+	int bcache_di;
+	int part;		/* partition number */
 	uint32_t flags;
+	uint32_t filtered_flags;
 	unsigned size_seqno;
 	uint64_t size;
 	uint64_t end;

lib/device/device_id.h

@@ -0,0 +1,55 @@
+/*
+ * Copyright (C) 2001-2004 Sistina Software, Inc. All rights reserved.  
+ * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved.
+ *
+ * This file is part of LVM2.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU Lesser General Public License v.2.1.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with this program; if not, write to the Free Software Foundation,
+ * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#ifndef _LVM_DEVICE_ID_H
+#define _LVM_DEVICE_ID_H
+
+void free_du(struct dev_use *du);
+void free_dus(struct dm_list *list);
+void free_did(struct dev_id *did);
+void free_dids(struct dm_list *list);
+const char *idtype_to_str(uint16_t idtype);
+uint16_t idtype_from_str(const char *str);
+const char *dev_idtype_for_metadata(struct cmd_context *cmd, struct device *dev);
+const char *dev_idname_for_metadata(struct cmd_context *cmd, struct device *dev);
+int device_ids_use_devname(struct cmd_context *cmd);
+int device_ids_read(struct cmd_context *cmd);
+int device_ids_write(struct cmd_context *cmd);
+int device_id_add(struct cmd_context *cmd, struct device *dev, const char *pvid,
+                  const char *idtype_arg, const char *id_arg);
+void device_id_pvremove(struct cmd_context *cmd, struct device *dev);
+void device_ids_match(struct cmd_context *cmd);
+int device_ids_match_dev(struct cmd_context *cmd, struct device *dev);
+void device_ids_validate(struct cmd_context *cmd, struct dm_list *scanned_devs, int *device_ids_invalid, int noupdate);
+int device_ids_version_unchanged(struct cmd_context *cmd);
+void device_ids_find_renamed_devs(struct cmd_context *cmd, struct dm_list *dev_list, int *search_count, int noupdate);
+const char *device_id_system_read(struct cmd_context *cmd, struct device *dev, uint16_t idtype);
+
+struct dev_use *get_du_for_dev(struct cmd_context *cmd, struct device *dev);
+struct dev_use *get_du_for_pvid(struct cmd_context *cmd, const char *pvid);
+
+char *devices_file_version(void);
+int devices_file_exists(struct cmd_context *cmd);
+int devices_file_touch(struct cmd_context *cmd);
+int lock_devices_file(struct cmd_context *cmd, int mode);
+int lock_devices_file_try(struct cmd_context *cmd, int mode, int *held);
+void unlock_devices_file(struct cmd_context *cmd);
+
+void devices_file_init(struct cmd_context *cmd);
+void devices_file_exit(struct cmd_context *cmd);
+
+void unlink_searched_devnames(struct cmd_context *cmd);
+
+#endif

lib/display/display.c

@@ -399,17 +399,19 @@ int lvdisplay_full(struct cmd_context *cmd,
 		   void *handle __attribute__((unused)))
 {
 	struct lvinfo info;
-	int inkernel, snap_active = 0;
+	int inkernel, snap_active = 0, partial = 0, raid_is_avail = 1;
 	char uuid[64] __attribute__((aligned(8)));
 	const char *access_str;
 	struct lv_segment *snap_seg = NULL, *mirror_seg = NULL;
 	struct lv_segment *seg = NULL;
 	int lvm1compat;
 	dm_percent_t snap_percent;
-	int thin_data_active = 0, thin_metadata_active = 0;
-	dm_percent_t thin_data_percent, thin_metadata_percent;
+	int thin_pool_active = 0;
+	dm_percent_t thin_data_percent = 0, thin_metadata_percent = 0;
 	int thin_active = 0;
-	dm_percent_t thin_percent;
+	dm_percent_t thin_percent = 0;
+	struct lv_status_thin *thin_status = NULL;
+	struct lv_status_thin_pool *thin_pool_status = NULL;
 	struct lv_status_cache *cache_status = NULL;
 	struct lv_status_vdo *vdo_status = NULL;
 
@@ -473,7 +475,7 @@ int lvdisplay_full(struct cmd_context *cmd,
 					  snap_active ? "active" : "INACTIVE");
 		}
 		snap_seg = NULL;
-	} else if ((snap_seg = find_snapshot(lv))) {
+	} else if (lv_is_cow(lv) && (snap_seg = find_snapshot(lv))) {
 		if (inkernel &&
 		    (snap_active = lv_snapshot_percent(snap_seg->cow,
 						       &snap_percent)))
@@ -503,15 +505,18 @@ int lvdisplay_full(struct cmd_context *cmd,
 		if (seg->merge_lv)
 			log_print("LV merging to          %s",
 				  seg->merge_lv->name);
-		if (inkernel)
-			thin_active = lv_thin_percent(lv, 0, &thin_percent);
+		if (inkernel && (thin_active = lv_thin_status(lv, 0, &thin_status))) {
+			thin_percent = thin_status->usage;
+			dm_pool_destroy(thin_status->mem);
+		}
 		if (lv_is_merging_origin(lv))
 			log_print("LV merged with         %s",
 				  find_snapshot(lv)->lv->name);
 	} else if (lv_is_thin_pool(lv)) {
-		if (lv_info(cmd, lv, 1, &info, 1, 1) && info.exists) {
-			thin_data_active = lv_thin_pool_percent(lv, 0, &thin_data_percent);
-			thin_metadata_active = lv_thin_pool_percent(lv, 1, &thin_metadata_percent);
+		if ((thin_pool_active = lv_thin_pool_status(lv, 0, &thin_pool_status))) {
+			thin_data_percent = thin_pool_status->data_usage;
+			thin_metadata_percent = thin_pool_status->metadata_usage;
+			dm_pool_destroy(thin_pool_status->mem);
 		}
 		/* FIXME: display thin_pool targets transid for activated LV as well */
 		seg = first_seg(lv);
@@ -553,11 +558,18 @@ int lvdisplay_full(struct cmd_context *cmd,
 		log_print("LV VDO Pool name       %s", seg_lv(seg, 0)->name);
 	}
 
+	if (lv_is_partial(lv))
+		partial = 1;
+
+	if (lv_is_raid(lv))
+		raid_is_avail = raid_is_available(lv) ? 1 : 0;
+
 	if (inkernel && info.suspended)
 		log_print("LV Status              suspended");
 	else if (activation())
-		log_print("LV Status              %savailable",
-			  inkernel ? "" : "NOT ");
+		log_print("LV Status              %savailable%s",
+			  (inkernel && raid_is_avail) ? "" : "NOT ",
+			  partial ? " (partial)" : "");
 
 /********* FIXME lv_number
     log_print("LV #                   %u", lv->lv_number + 1);
@@ -591,13 +603,12 @@ int lvdisplay_full(struct cmd_context *cmd,
 		dm_pool_destroy(cache_status->mem);
 	}
 
-	if (thin_data_active)
+	if (thin_pool_active) {
 		log_print("Allocated pool data    %s%%",
 			  display_percent(cmd, thin_data_percent));
-
-	if (thin_metadata_active)
 		log_print("Allocated metadata     %s%%",
 			  display_percent(cmd, thin_metadata_percent));
+	}
 
 	if (thin_active)
 		log_print("Mapped size            %s%%",

lib/filters/filter-composite.c

@@ -60,13 +60,16 @@ static void _composite_destroy(struct dev_filter *f)
 	free(f);
 }
 
-static void _wipe(struct dev_filter *f)
+static void _wipe(struct cmd_context *cmd, struct dev_filter *f, struct device *dev, const char *use_filter_name)
 {
 	struct dev_filter **filters;
 
-	for (filters = (struct dev_filter **) f->private; *filters; ++filters)
+	for (filters = (struct dev_filter **) f->private; *filters; ++filters) {
+		if (use_filter_name && strcmp((*filters)->name, use_filter_name))
+			continue;
 		if ((*filters)->wipe)
-			(*filters)->wipe(*filters);
+			(*filters)->wipe(cmd, *filters, dev, use_filter_name);
+	}
 }
 
 struct dev_filter *composite_filter_create(int n, int use_dev_ext_info, struct dev_filter **filters)

lib/filters/filter-deviceid.c

@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) 2001-2004 Sistina Software, Inc. All rights reserved.
+ * Copyright (C) 2004-2012 Red Hat, Inc. All rights reserved.
+ *
+ * This file is part of LVM2.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU Lesser General Public License v.2.1.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with this program; if not, write to the Free Software Foundation,
+ * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#include "base/memory/zalloc.h"
+#include "lib/misc/lib.h"
+#include "lib/filters/filter.h"
+#include "lib/commands/toolcontext.h"
+
+static int _passes_deviceid_filter(struct cmd_context *cmd, struct dev_filter *f, struct device *dev, const char *use_filter_name)
+{
+	dev->filtered_flags &= ~DEV_FILTERED_DEVICES_FILE;
+	dev->filtered_flags &= ~DEV_FILTERED_DEVICES_LIST;
+
+	if (!cmd->enable_devices_file && !cmd->enable_devices_list)
+		return 1;
+
+	if (cmd->filter_deviceid_skip)
+		return 1;
+
+	if (dev->flags & DEV_MATCHED_USE_ID)
+		return 1;
+
+	if (cmd->enable_devices_file)
+		dev->filtered_flags |= DEV_FILTERED_DEVICES_FILE;
+	else if (cmd->enable_devices_list)
+		dev->filtered_flags |= DEV_FILTERED_DEVICES_LIST;
+
+	log_debug_devs("%s: Skipping (deviceid)", dev_name(dev));
+	return 0;
+}
+
+static void _destroy_deviceid_filter(struct dev_filter *f)
+{
+	if (f->use_count)
+		log_error(INTERNAL_ERROR "Destroying deviceid filter while in use %u times.", f->use_count);
+
+	free(f);
+}
+
+struct dev_filter *deviceid_filter_create(struct cmd_context *cmd)
+{
+	struct dev_filter *f;
+
+	if (!(f = zalloc(sizeof(struct dev_filter)))) {
+		log_error("deviceid filter allocation failed");
+		return NULL;
+	}
+
+	f->passes_filter = _passes_deviceid_filter;
+	f->destroy = _destroy_deviceid_filter;
+	f->use_count = 0;
+	f->name = "deviceid";
+
+	log_debug_devs("deviceid filter initialised.");
+
+	return f;
+}

lib/filters/filter-fwraid.c

@@ -15,6 +15,7 @@
 #include "base/memory/zalloc.h"
 #include "lib/misc/lib.h"
 #include "lib/filters/filter.h"
+#include "lib/commands/toolcontext.h"
 
 #ifdef UDEV_SYNC_SUPPORT
 #include <libudev.h>
@@ -69,6 +70,11 @@ static int _ignore_fwraid(struct cmd_context *cmd, struct dev_filter *f __attrib
 {
 	int ret;
 
+	if (cmd->filter_nodata_only)
+		return 1;
+
+	dev->filtered_flags &= ~DEV_FILTERED_FWRAID;
+
 	if (!fwraid_filtering())
 		return 1;
 
@@ -80,12 +86,14 @@ static int _ignore_fwraid(struct cmd_context *cmd, struct dev_filter *f __attrib
 		else
 			log_debug_devs(MSG_SKIPPING " [%s:%p]", dev_name(dev),
 					dev_ext_name(dev), dev->ext.handle);
+		dev->filtered_flags |= DEV_FILTERED_FWRAID;
 		return 0;
 	}
 
 	if (ret < 0) {
 		log_debug_devs("%s: Skipping: error in firmware RAID component detection",
 			       dev_name(dev));
+		dev->filtered_flags |= DEV_FILTERED_FWRAID;
 		return 0;
 	}
 

lib/filters/filter-internal.c

@@ -42,6 +42,8 @@ static int _passes_internal(struct cmd_context *cmd, struct dev_filter *f __attr
 {
 	struct device_list *devl;
 
+	dev->filtered_flags &= ~DEV_FILTERED_INTERNAL;
+
 	if (!internal_filtering())
 		return 1;
 	
@@ -50,6 +52,7 @@ static int _passes_internal(struct cmd_context *cmd, struct dev_filter *f __attr
 			return 1;
 	}
 	
+	dev->filtered_flags |= DEV_FILTERED_INTERNAL;
 	log_debug_devs("%s: Skipping for internal filtering.", dev_name(dev));
 	return 0;
 }

lib/filters/filter-md.c

@@ -86,6 +86,11 @@ static int _passes_md_filter(struct cmd_context *cmd, struct dev_filter *f __att
 {
 	int ret;
 
+	if (cmd->filter_nodata_only)
+		return 1;
+
+	dev->filtered_flags &= ~DEV_FILTERED_MD_COMPONENT;
+
 	/*
 	 * When md_component_dectection=0, don't even try to skip md
 	 * components.
@@ -112,12 +117,14 @@ static int _passes_md_filter(struct cmd_context *cmd, struct dev_filter *f __att
 		else
 			log_debug_devs(MSG_SKIPPING " [%s:%p]", dev_name(dev),
 					dev_ext_name(dev), dev->ext.handle);
+		dev->filtered_flags |= DEV_FILTERED_MD_COMPONENT;
 		return 0;
 	}
 
 	if (ret < 0) {
 		log_debug_devs("%s: Skipping: error in md component detection",
 			       dev_name(dev));
+		dev->filtered_flags |= DEV_FILTERED_MD_COMPONENT;
 		return 0;
 	}
 

lib/filters/filter-mpath.c

@@ -16,6 +16,7 @@
 #include "lib/misc/lib.h"
 #include "lib/filters/filter.h"
 #include "lib/activate/activate.h"
+#include "lib/commands/toolcontext.h"
 #ifdef UDEV_SYNC_SUPPORT
 #include <libudev.h>
 #include "lib/device/dev-ext-udev-constants.h"
@@ -27,7 +28,6 @@
 
 #define MPATH_PREFIX "mpath-"
 
-
 struct mpath_priv {
 	struct dm_pool *mem;
 	struct dev_filter f;
@@ -35,6 +35,9 @@ struct mpath_priv {
 	struct dm_hash_table *hash;
 };
 
+/*
+ * given "/dev/foo" return "foo"
+ */
 static const char *_get_sysfs_name(struct device *dev)
 {
 	const char *name;
@@ -53,6 +56,11 @@ static const char *_get_sysfs_name(struct device *dev)
 	return name;
 }
 
+/*
+ * given major:minor
+ * readlink translates /sys/dev/block/major:minor to /sys/.../foo
+ * from /sys/.../foo return "foo"
+ */
 static const char *_get_sysfs_name_by_devt(const char *sysfs_dir, dev_t devno,
 					  char *buf, size_t buf_size)
 {
@@ -60,7 +68,7 @@ static const char *_get_sysfs_name_by_devt(const char *sysfs_dir, dev_t devno,
 	char path[PATH_MAX];
 	int size;
 
-	if (dm_snprintf(path, sizeof(path), "%s/dev/block/%d:%d", sysfs_dir,
+	if (dm_snprintf(path, sizeof(path), "%sdev/block/%d:%d", sysfs_dir,
 			(int) MAJOR(devno), (int) MINOR(devno)) < 0) {
 		log_error("Sysfs path string is too long.");
 		return NULL;
@@ -102,27 +110,28 @@ static int _get_sysfs_string(const char *path, char *buffer, int max_size)
 	return r;
 }
 
-static int _get_sysfs_get_major_minor(const char *sysfs_dir, const char *kname, int *major, int *minor)
+static int _get_sysfs_dm_mpath(struct dev_types *dt, const char *sysfs_dir, const char *holder_name)
 {
-	char path[PATH_MAX], buffer[64];
+	char path[PATH_MAX];
+	char buffer[128];
 
-	if (dm_snprintf(path, sizeof(path), "%s/block/%s/dev", sysfs_dir, kname) < 0) {
+	if (dm_snprintf(path, sizeof(path), "%sblock/%s/dm/uuid", sysfs_dir, holder_name) < 0) {
 		log_error("Sysfs path string is too long.");
 		return 0;
 	}
 
+	buffer[0] = '\0';
+
 	if (!_get_sysfs_string(path, buffer, sizeof(buffer)))
 		return_0;
 
-	if (sscanf(buffer, "%d:%d", major, minor) != 2) {
-		log_error("Failed to parse major minor from %s", buffer);
-		return 0;
-	}
+	if (!strncmp(buffer, MPATH_PREFIX, 6))
+		return 1;
 
-	return 1;
+	return 0;
 }
 
-static int _get_parent_mpath(const char *dir, char *name, int max_size)
+static int _get_holder_name(const char *dir, char *name, int max_size)
 {
 	struct dirent *d;
 	DIR *dr;
@@ -155,7 +164,7 @@ static int _get_parent_mpath(const char *dir, char *name, int max_size)
 }
 
 #ifdef UDEV_SYNC_SUPPORT
-static int _udev_dev_is_mpath(struct device *dev)
+static int _udev_dev_is_mpath_component(struct device *dev)
 {
 	const char *value;
 	struct dev_ext *ext;
@@ -174,95 +183,148 @@ static int _udev_dev_is_mpath(struct device *dev)
 	return 0;
 }
 #else
-static int _udev_dev_is_mpath(struct device *dev)
+static int _udev_dev_is_mpath_component(struct device *dev)
 {
 	return 0;
 }
 #endif
 
-static int _native_dev_is_mpath(struct dev_filter *f, struct device *dev)
+static int _native_dev_is_mpath_component(struct cmd_context *cmd, struct dev_filter *f, struct device *dev)
 {
 	struct mpath_priv *mp = (struct mpath_priv *) f->private;
 	struct dev_types *dt = mp->dt;
-	const char *part_name, *name;
-	struct stat info;
-	char path[PATH_MAX], parent_name[PATH_MAX];
+	const char *part_name;
+	const char *name;               /* e.g. "sda" for "/dev/sda" */
+	char link_path[PATH_MAX];       /* some obscure, unpredictable sysfs path */
+	char holders_path[PATH_MAX];    /* e.g. "/sys/block/sda/holders/" */
+	char dm_dev_path[PATH_MAX];    /* e.g. "/dev/dm-1" */
+	char holder_name[128] = { 0 };  /* e.g. "dm-1" */
 	const char *sysfs_dir = dm_sysfs_dir();
-	int major = MAJOR(dev->dev);
-	int minor = MINOR(dev->dev);
+	int dev_major = MAJOR(dev->dev);
+	int dev_minor = MINOR(dev->dev);
+	int dm_dev_major;
+	int dm_dev_minor;
+	struct stat info;
 	dev_t primary_dev;
 	long look;
 
-	/* Limit this filter only to SCSI devices */
-	if (!major_is_scsi_device(dt, MAJOR(dev->dev)))
+	/* Limit this filter to SCSI or NVME devices */
+	if (!major_is_scsi_device(dt, dev_major) && !dev_is_nvme(dt, dev))
 		return 0;
 
 	switch (dev_get_primary_dev(dt, dev, &primary_dev)) {
+
 	case 2: /* The dev is partition. */
 		part_name = dev_name(dev); /* name of original dev for log_debug msg */
-		if (!(name = _get_sysfs_name_by_devt(sysfs_dir, primary_dev, parent_name, sizeof(parent_name))))
+
+		/* gets "foo" for "/dev/foo" where "/dev/foo" comes from major:minor */
+		if (!(name = _get_sysfs_name_by_devt(sysfs_dir, primary_dev, link_path, sizeof(link_path))))
 			return_0;
+
 		log_debug_devs("%s: Device is a partition, using primary "
 			       "device %s for mpath component detection",
 			       part_name, name);
 		break;
+
 	case 1: /* The dev is already a primary dev. Just continue with the dev. */
+
+		/* gets "foo" for "/dev/foo" */
 		if (!(name = _get_sysfs_name(dev)))
 			return_0;
 		break;
+
 	default: /* 0, error. */
-		log_warn("Failed to get primary device for %d:%d.", major, minor);
+		log_warn("Failed to get primary device for %d:%d.", dev_major, dev_minor);
 		return 0;
 	}
 
-	if (dm_snprintf(path, sizeof(path), "%s/block/%s/holders", sysfs_dir, name) < 0) {
+	if (dm_snprintf(holders_path, sizeof(holders_path), "%sblock/%s/holders", sysfs_dir, name) < 0) {
 		log_warn("Sysfs path to check mpath is too long.");
 		return 0;
 	}
 
 	/* also will filter out partitions */
-	if (stat(path, &info))
+	if (stat(holders_path, &info))
 		return 0;
 
 	if (!S_ISDIR(info.st_mode)) {
-		log_warn("Path %s is not a directory.", path);
+		log_warn("Path %s is not a directory.", holders_path);
 		return 0;
 	}
 
-	if (!_get_parent_mpath(path, parent_name, sizeof(parent_name)))
+	/*
+	 * If holders dir contains an entry such as "dm-1", then this sets
+	 * holder_name to "dm-1".
+	 *
+	 * If holders dir is empty, return 0 (this is generally where
+	 * devs that are not mpath components return.)
+	 */
+	if (!_get_holder_name(holders_path, holder_name, sizeof(holder_name)))
 		return 0;
 
-	if (!_get_sysfs_get_major_minor(sysfs_dir, parent_name, &major, &minor))
-		return_0;
-
-	if (major != dt->device_mapper_major)
+	if (dm_snprintf(dm_dev_path, sizeof(dm_dev_path), "%s/%s", cmd->dev_dir, holder_name) < 0) {
+		log_warn("dm device path to check mpath is too long.");
 		return 0;
+	}
 
-	/* Avoid repeated detection of multipath device and use first checked result */
-	look = (long) dm_hash_lookup_binary(mp->hash, &minor, sizeof(minor));
+	/*
+	 * stat "/dev/dm-1" which is the holder of the dev we're checking
+	 * dm_dev_major:dm_dev_minor come from stat("/dev/dm-1")
+	 */
+	if (stat(dm_dev_path, &info)) {
+		log_debug("filter-mpath %s holder %s stat result %d",
+			  dev_name(dev), dm_dev_path, errno);
+		return 0;
+	}
+	dm_dev_major = (int)MAJOR(info.st_rdev);
+	dm_dev_minor = (int)MINOR(info.st_rdev);
+	
+	if (dm_dev_major != dt->device_mapper_major) {
+		log_debug_devs("filter-mpath %s holder %s %d:%d does not have dm major",
+			       dev_name(dev), dm_dev_path, dm_dev_major, dm_dev_minor);
+		return 0;
+	}
+
+	/*
+	 * Save the result of checking that "/dev/dm-1" is an mpath device
+	 * to avoid repeating it for each path component.
+	 * The minor number of "/dev/dm-1" is added to the hash table with
+	 * const value 2 meaning that dm minor 1 (for /dev/dm-1) is a multipath dev
+	 * and const value 1 meaning that dm minor 1 is not a multipath dev.
+	 */
+	look = (long) dm_hash_lookup_binary(mp->hash, &dm_dev_minor, sizeof(dm_dev_minor));
 	if (look > 0) {
-		log_debug_devs("%s(%u:%u): already checked as %sbeing mpath.",
-			       parent_name, major, minor, (look > 1) ? "" : "not ");
+		log_debug_devs("filter-mpath %s holder %s %u:%u already checked as %sbeing mpath.",
+			       dev_name(dev), holder_name, dm_dev_major, dm_dev_minor, (look > 1) ? "" : "not ");
 		return (look > 1) ? 1 : 0;
 	}
 
-	if (lvm_dm_prefix_check(major, minor, MPATH_PREFIX)) {
-		(void) dm_hash_insert_binary(mp->hash, &minor, sizeof(minor), (void*)2);
+	/*
+	 * Returns 1 if /sys/block/<holder_name>/dm/uuid indicates that
+	 * <holder_name> is a dm device with dm uuid prefix mpath-.
+	 * When true, <holder_name> will be something like "dm-1".
+	 *
+	 * (Is a hash table worth it to avoid reading one sysfs file?)
+	 */
+	if (_get_sysfs_dm_mpath(dt, sysfs_dir, holder_name)) {
+		log_debug_devs("filter-mpath %s holder %s %u:%u ignore mpath component",
+			       dev_name(dev), holder_name, dm_dev_major, dm_dev_minor);
+		(void) dm_hash_insert_binary(mp->hash, &dm_dev_minor, sizeof(dm_dev_minor), (void*)2);
 		return 1;
 	}
 
-	(void) dm_hash_insert_binary(mp->hash, &minor, sizeof(minor), (void*)1);
+	(void) dm_hash_insert_binary(mp->hash, &dm_dev_minor, sizeof(dm_dev_minor), (void*)1);
 
 	return 0;
 }
 
-static int _dev_is_mpath(struct dev_filter *f, struct device *dev)
+static int _dev_is_mpath_component(struct cmd_context *cmd, struct dev_filter *f, struct device *dev)
 {
 	if (dev->ext.src == DEV_EXT_NONE)
-		return _native_dev_is_mpath(f, dev);
+		return _native_dev_is_mpath_component(cmd, f, dev);
 
 	if (dev->ext.src == DEV_EXT_UDEV)
-		return _udev_dev_is_mpath(dev);
+		return _udev_dev_is_mpath_component(dev);
 
 	log_error(INTERNAL_ERROR "Missing hook for mpath recognition "
 		  "using external device info source %s", dev_ext_name(dev));
@@ -272,14 +334,17 @@ static int _dev_is_mpath(struct dev_filter *f, struct device *dev)
 
 #define MSG_SKIPPING "%s: Skipping mpath component device"
 
-static int _ignore_mpath(struct cmd_context *cmd, struct dev_filter *f, struct device *dev, const char *use_filter_name)
+static int _ignore_mpath_component(struct cmd_context *cmd, struct dev_filter *f, struct device *dev, const char *use_filter_name)
 {
-	if (_dev_is_mpath(f, dev) == 1) {
+	dev->filtered_flags &= ~DEV_FILTERED_MPATH_COMPONENT;
+
+	if (_dev_is_mpath_component(cmd, f, dev) == 1) {
 		if (dev->ext.src == DEV_EXT_NONE)
 			log_debug_devs(MSG_SKIPPING, dev_name(dev));
 		else
 			log_debug_devs(MSG_SKIPPING " [%s:%p]", dev_name(dev),
 					dev_ext_name(dev), dev->ext.handle);
+		dev->filtered_flags |= DEV_FILTERED_MPATH_COMPONENT;
 		return 0;
 	}
 
@@ -300,8 +365,8 @@ static void _destroy(struct dev_filter *f)
 struct dev_filter *mpath_filter_create(struct dev_types *dt)
 {
 	const char *sysfs_dir = dm_sysfs_dir();
-	struct dm_pool *mem;
 	struct mpath_priv *mp;
+	struct dm_pool *mem;
 	struct dm_hash_table *hash;
 
 	if (!*sysfs_dir) {
@@ -325,19 +390,13 @@ struct dev_filter *mpath_filter_create(struct dev_types *dt)
 		goto bad;
 	}
 
-	if (!(mp = dm_pool_zalloc(mem, sizeof(*mp)))) {
-		log_error("mpath filter allocation failed.");
-		goto bad;
-	}
-
-	mp->f.passes_filter = _ignore_mpath;
+	mp->f.passes_filter = _ignore_mpath_component;
 	mp->f.destroy = _destroy;
 	mp->f.use_count = 0;
 	mp->f.private = mp;
 	mp->f.name = "mpath";
-
-	mp->mem = mem;
 	mp->dt = dt;
+	mp->mem = mem;
 	mp->hash = hash;
 
 	log_debug_devs("mpath filter initialised.");

lib/filters/filter-partitioned.c

@@ -16,6 +16,7 @@
 #include "base/memory/zalloc.h"
 #include "lib/misc/lib.h"
 #include "lib/filters/filter.h"
+#include "lib/commands/toolcontext.h"
 
 #define MSG_SKIPPING "%s: Skipping: Partition table signature found"
 
@@ -24,6 +25,11 @@ static int _passes_partitioned_filter(struct cmd_context *cmd, struct dev_filter
 	struct dev_types *dt = (struct dev_types *) f->private;
 	int ret;
 
+	if (cmd->filter_nodata_only)
+		return 1;
+
+	dev->filtered_flags &= ~DEV_FILTERED_PARTITIONED;
+
 	ret = dev_is_partitioned(dt, dev);
 
 	if (ret == -EAGAIN) {
@@ -39,6 +45,7 @@ static int _passes_partitioned_filter(struct cmd_context *cmd, struct dev_filter
 		else
 			log_debug_devs(MSG_SKIPPING " [%s:%p]", dev_name(dev),
 					dev_ext_name(dev), dev->ext.handle);
+		dev->filtered_flags |= DEV_FILTERED_PARTITIONED;
 		return 0;
 	}
 

lib/filters/filter-persistent.c

@@ -64,11 +64,17 @@ static int _init_hash(struct pfilter *pf)
 	return 1;
 }
 
-static void _persistent_filter_wipe(struct dev_filter *f)
+static void _persistent_filter_wipe(struct cmd_context *cmd, struct dev_filter *f, struct device *dev, const char *use_filter_name)
 {
 	struct pfilter *pf = (struct pfilter *) f->private;
+	struct dm_str_list *sl;
 
-	dm_hash_wipe(pf->devices);
+	if (!dev) {
+		dm_hash_wipe(pf->devices);
+	} else {
+		dm_list_iterate_items(sl, &dev->aliases)
+			dm_hash_remove(pf->devices, sl->str);
+	}
 }
 
 static int _lookup_p(struct cmd_context *cmd, struct dev_filter *f, struct device *dev, const char *use_filter_name)

lib/filters/filter-regex.c

@@ -15,6 +15,7 @@
 
 #include "lib/misc/lib.h"
 #include "lib/filters/filter.h"
+#include "lib/commands/toolcontext.h"
 
 struct rfilter {
 	struct dm_pool *mem;
@@ -151,6 +152,14 @@ static int _accept_p(struct cmd_context *cmd, struct dev_filter *f, struct devic
 	struct rfilter *rf = (struct rfilter *) f->private;
 	struct dm_str_list *sl;
 
+	dev->filtered_flags &= ~DEV_FILTERED_REGEX;
+
+	if (cmd->enable_devices_list)
+		return 1;
+
+	if (cmd->enable_devices_file && !cmd->filter_regex_with_devices_file)
+		return 1;
+
 	dm_list_iterate_items(sl, &dev->aliases) {
 		m = dm_regex_match(rf->engine, sl->str);
 
@@ -168,8 +177,10 @@ static int _accept_p(struct cmd_context *cmd, struct dev_filter *f, struct devic
 		first = 0;
 	}
 
-	if (rejected)
+	if (rejected) {
+		dev->filtered_flags |= DEV_FILTERED_REGEX;
 		log_debug_devs("%s: Skipping (regex)", dev_name(dev));
+	}
 
 	/*
 	 * pass everything that doesn't match

lib/filters/filter-signature.c

@@ -16,6 +16,7 @@
 #include "base/memory/zalloc.h"
 #include "lib/misc/lib.h"
 #include "lib/filters/filter.h"
+#include "lib/commands/toolcontext.h"
 
 #ifdef __linux__
 
@@ -27,6 +28,11 @@ static int _ignore_signature(struct cmd_context *cmd, struct dev_filter *f __att
 	char buf[BUFSIZE];
 	int ret = 0;
 
+	if (cmd->filter_nodata_only)
+		return 1;
+
+	dev->filtered_flags &= ~DEV_FILTERED_SIGNATURE;
+
 	if (!scan_bcache) {
 		/* let pass, call again after scan */
 		log_debug_devs("filter signature deferred %s", dev_name(dev));
@@ -40,18 +46,21 @@ static int _ignore_signature(struct cmd_context *cmd, struct dev_filter *f __att
 		log_debug_devs("%s: Skipping: error in signature detection",
 			       dev_name(dev));
 		ret = 0;
+		dev->filtered_flags |= DEV_FILTERED_SIGNATURE;
 		goto out;
 	}
 
 	if (dev_is_lvm1(dev, buf, BUFSIZE)) {
 		log_debug_devs("%s: Skipping lvm1 device", dev_name(dev));
 		ret = 0;
+		dev->filtered_flags |= DEV_FILTERED_SIGNATURE;
 		goto out;
 	}
 
 	if (dev_is_pool(dev, buf, BUFSIZE)) {
 		log_debug_devs("%s: Skipping gfs-pool device", dev_name(dev));
 		ret = 0;
+		dev->filtered_flags |= DEV_FILTERED_SIGNATURE;
 		goto out;
 	}
 	ret = 1;

lib/filters/filter-sysfs.c

@@ -264,6 +264,8 @@ static int _accept_p(struct cmd_context *cmd, struct dev_filter *f, struct devic
 {
 	struct dev_set *ds = (struct dev_set *) f->private;
 
+	dev->filtered_flags &= ~DEV_FILTERED_SYSFS;
+
 	if (!ds->initialised)
 		_init_devs(ds);
 
@@ -273,6 +275,7 @@ static int _accept_p(struct cmd_context *cmd, struct dev_filter *f, struct devic
 
 	if (!_set_lookup(ds, dev->dev)) {
 		log_debug_devs("%s: Skipping (sysfs)", dev_name(dev));
+		dev->filtered_flags |= DEV_FILTERED_SYSFS;
 		return 0;
 	}
 

lib/filters/filter-type.c

@@ -22,10 +22,13 @@ static int _passes_lvm_type_device_filter(struct cmd_context *cmd, struct dev_fi
 	struct dev_types *dt = (struct dev_types *) f->private;
 	const char *name = dev_name(dev);
 
+	dev->filtered_flags &= ~DEV_FILTERED_DEVTYPE;
+
 	/* Is this a recognised device type? */
 	if (!dt->dev_type_array[MAJOR(dev->dev)].max_partitions) {
 		log_debug_devs("%s: Skipping: Unrecognised LVM device type %"
 			       PRIu64, name, (uint64_t) MAJOR(dev->dev));
+		dev->filtered_flags |= DEV_FILTERED_DEVTYPE;
 		return 0;
 	}
 

lib/filters/filter-usable.c

@@ -113,6 +113,9 @@ static int _passes_usable_filter(struct cmd_context *cmd, struct dev_filter *f,
 	struct dev_usable_check_params ucp = {0};
 	int r = 1;
 
+	dev->filtered_flags &= ~DEV_FILTERED_MINSIZE;
+	dev->filtered_flags &= ~DEV_FILTERED_UNUSABLE;
+
 	/* further checks are done on dm devices only */
 	if (dm_is_dm_major(MAJOR(dev->dev))) {
 		switch (mode) {
@@ -142,8 +145,10 @@ static int _passes_usable_filter(struct cmd_context *cmd, struct dev_filter *f,
 			break;
 		}
 
-		if (!(r = device_is_usable(dev, ucp)))
+		if (!(r = device_is_usable(dev, ucp))) {
+			dev->filtered_flags |= DEV_FILTERED_UNUSABLE;
 			log_debug_devs("%s: Skipping unusable device.", dev_name(dev));
+		}
 	}
 
 	if (r) {
@@ -153,6 +158,8 @@ static int _passes_usable_filter(struct cmd_context *cmd, struct dev_filter *f,
 			/* fall through */
 		case FILTER_MODE_PRE_LVMETAD:
 			r = _check_pv_min_size(dev);
+			if (!r)
+				dev->filtered_flags |= DEV_FILTERED_MINSIZE;
 			break;
 		case FILTER_MODE_POST_LVMETAD:
 			/* nothing to do here */

lib/filters/filter.h

@@ -30,6 +30,7 @@ struct dev_filter *partitioned_filter_create(struct dev_types *dt);
 struct dev_filter *persistent_filter_create(struct dev_types *dt, struct dev_filter *f);
 struct dev_filter *sysfs_filter_create(void);
 struct dev_filter *signature_filter_create(struct dev_types *dt);
+struct dev_filter *deviceid_filter_create(struct cmd_context *cmd);
 
 struct dev_filter *internal_filter_create(void);
 int internal_filter_allow(struct dm_pool *mem, struct device *dev);
@@ -52,4 +53,18 @@ typedef enum {
 } filter_mode_t;
 struct dev_filter *usable_filter_create(struct cmd_context *cmd, struct dev_types *dt, filter_mode_t mode);
 
+#define DEV_FILTERED_FWRAID		0x00000001
+#define DEV_FILTERED_INTERNAL		0x00000002
+#define DEV_FILTERED_MD_COMPONENT	0x00000004
+#define DEV_FILTERED_MPATH_COMPONENT	0x00000008
+#define DEV_FILTERED_PARTITIONED	0x00000010
+#define DEV_FILTERED_REGEX		0x00000020
+#define DEV_FILTERED_SIGNATURE		0x00000040
+#define DEV_FILTERED_SYSFS		0x00000080
+#define DEV_FILTERED_DEVTYPE		0x00000100
+#define DEV_FILTERED_MINSIZE		0x00000200
+#define DEV_FILTERED_UNUSABLE		0x00000400
+#define DEV_FILTERED_DEVICES_FILE	0x00000800
+#define DEV_FILTERED_DEVICES_LIST	0x00001000
+
 #endif 	/* _LVM_FILTER_H */

lib/format_text/archiver.c

@@ -315,13 +315,13 @@ struct volume_group *backup_read_vg(struct cmd_context *cmd,
 	}
 
 	dm_list_iterate_items(mda, &tf->metadata_areas_in_use) {
-		if (!(vg = mda->ops->vg_read(tf, vg_name, mda, NULL, NULL)))
+		if (!(vg = mda->ops->vg_read(cmd, tf, vg_name, mda, NULL, NULL)))
 			stack;
 		break;
 	}
 
 	if (vg)
-		set_pv_devices(tf, vg, NULL);
+		set_pv_devices(tf, vg);
 
 	if (!vg)
 		tf->fmt->ops->destroy_instance(tf);

lib/format_text/export.c

@@ -23,6 +23,7 @@
 #include "lib/metadata/segtype.h"
 #include "lib/format_text/text_export.h"
 #include "lib/commands/toolcontext.h"
+#include "lib/device/device_id.h"
 #include "libdaemon/client/config-util.h"
 
 #include <stdarg.h>
@@ -527,6 +528,7 @@ static int _print_pvs(struct formatter *f, struct volume_group *vg)
 	struct physical_volume *pv;
 	char buffer[PATH_MAX * 2];
 	const char *name;
+	const char *idtype, *idname;
 
 	outf(f, "physical_volumes {");
 	_inc_indent(f);
@@ -555,6 +557,13 @@ static int _print_pvs(struct formatter *f, struct volume_group *vg)
 			dm_escape_double_quotes(buffer, pv_dev_name(pv)));
 		outnl(f);
 
+		idtype = dev_idtype_for_metadata(vg->cmd, pv->dev);
+		idname = dev_idname_for_metadata(vg->cmd, pv->dev);
+		if (idtype && idname) {
+			outf(f, "device_id_type = \"%s\"", idtype);
+			outf(f, "device_id = \"%s\"", idname);
+		}
+
 		if (!_print_flag_config(f, pv->status, PV_FLAGS))
 			return_0;
 

lib/format_text/flags.c

@@ -72,6 +72,7 @@ static const struct flag _lv_flags[] = {
 	{LV_ACTIVATION_SKIP, "ACTIVATION_SKIP", COMPATIBLE_FLAG},
 	{LV_ERROR_WHEN_FULL, "ERROR_WHEN_FULL", COMPATIBLE_FLAG},
 	{LV_METADATA_FORMAT, "METADATA_FORMAT", SEGTYPE_FLAG},
+	{LV_CROP_METADATA, "CROP_METADATA", SEGTYPE_FLAG},
 	{LV_CACHE_VOL, "CACHE_VOL", COMPATIBLE_FLAG},
 	{LV_CACHE_USES_CACHEVOL, "CACHE_USES_CACHEVOL", SEGTYPE_FLAG},
 	{LV_NOSCAN, NULL, 0},
@@ -105,9 +106,9 @@ static const struct flag _lv_flags[] = {
 	{LV_VDO_POOL_DATA, NULL, 0},
 	{WRITECACHE, NULL, 0},
 	{INTEGRITY, NULL, 0},
+	{INTEGRITY_METADATA, NULL, 0},
 	{LV_PENDING_DELETE, NULL, 0}, /* FIXME Display like COMPATIBLE_FLAG */
 	{LV_REMOVED, NULL, 0},
-	{LV_UNCOMMITTED, NULL, 0},
 	{0, NULL, 0}
 };
 

lib/format_text/format-text.c

@@ -277,7 +277,7 @@ static int _raw_write_mda_header(const struct format_type *fmt,
 	dev_set_last_byte(dev, start_byte + MDA_HEADER_SIZE);
 
 	if (!dev_write_bytes(dev, start_byte, MDA_HEADER_SIZE, mdah)) {
-		log_error("Failed to write mda header to %s fd %d", dev_name(dev), dev->bcache_fd);
+		log_error("Failed to write mda header to %s.", dev_name(dev));
 		return 0;
 	}
 	dev_unset_last_byte(dev);
@@ -290,7 +290,8 @@ static int _raw_write_mda_header(const struct format_type *fmt,
  * in the label scanning path.
  */
 
-static struct raw_locn *_read_metadata_location_vg(struct device_area *dev_area,
+static struct raw_locn *_read_metadata_location_vg(struct cmd_context *cmd,
+				       struct device_area *dev_area,
 				       struct mda_header *mdah, int primary_mda,
 				       const char *vgname,
 				       int *precommitted)
@@ -369,7 +370,7 @@ static struct raw_locn *_read_metadata_location_vg(struct device_area *dev_area,
 		  vgnamebuf, vgname);
 
 	if ((info = lvmcache_info_from_pvid(dev_area->dev->pvid, dev_area->dev, 0)) &&
-	    !lvmcache_update_vgname_and_id(info, &vgsummary_orphan))
+	    !lvmcache_update_vgname_and_id(cmd, info, &vgsummary_orphan))
 		stack;
 
 	return NULL;
@@ -447,7 +448,8 @@ static uint64_t _next_rlocn_offset(struct volume_group *vg, struct raw_locn *rlo
 	return new_start;
 }
 
-static struct volume_group *_vg_read_raw_area(struct format_instance *fid,
+static struct volume_group *_vg_read_raw_area(struct cmd_context *cmd,
+					      struct format_instance *fid,
 					      const char *vgname,
 					      struct device_area *area,
 					      struct cached_vg_fmtdata **vg_fmtdata,
@@ -468,7 +470,7 @@ static struct volume_group *_vg_read_raw_area(struct format_instance *fid,
 		goto out;
 	}
 
-	if (!(rlocn = _read_metadata_location_vg(area, mdah, primary_mda, vgname, &precommitted))) {
+	if (!(rlocn = _read_metadata_location_vg(cmd, area, mdah, primary_mda, vgname, &precommitted))) {
 		log_debug_metadata("VG %s not found on %s", vgname, dev_name(area->dev));
 		goto out;
 	}
@@ -503,7 +505,8 @@ static struct volume_group *_vg_read_raw_area(struct format_instance *fid,
 	return vg;
 }
 
-static struct volume_group *_vg_read_raw(struct format_instance *fid,
+static struct volume_group *_vg_read_raw(struct cmd_context *cmd,
+					 struct format_instance *fid,
 					 const char *vgname,
 					 struct metadata_area *mda,
 					 struct cached_vg_fmtdata **vg_fmtdata,
@@ -512,12 +515,13 @@ static struct volume_group *_vg_read_raw(struct format_instance *fid,
 	struct mda_context *mdac = (struct mda_context *) mda->metadata_locn;
 	struct volume_group *vg;
 
-	vg = _vg_read_raw_area(fid, vgname, &mdac->area, vg_fmtdata, use_previous_vg, 0, mda_is_primary(mda));
+	vg = _vg_read_raw_area(cmd, fid, vgname, &mdac->area, vg_fmtdata, use_previous_vg, 0, mda_is_primary(mda));
 
 	return vg;
 }
 
-static struct volume_group *_vg_read_precommit_raw(struct format_instance *fid,
+static struct volume_group *_vg_read_precommit_raw(struct cmd_context *cmd,
+						   struct format_instance *fid,
 						   const char *vgname,
 						   struct metadata_area *mda,
 						   struct cached_vg_fmtdata **vg_fmtdata,
@@ -526,7 +530,7 @@ static struct volume_group *_vg_read_precommit_raw(struct format_instance *fid,
 	struct mda_context *mdac = (struct mda_context *) mda->metadata_locn;
 	struct volume_group *vg;
 
-	vg = _vg_read_raw_area(fid, vgname, &mdac->area, vg_fmtdata, use_previous_vg, 1, mda_is_primary(mda));
+	vg = _vg_read_raw_area(cmd, fid, vgname, &mdac->area, vg_fmtdata, use_previous_vg, 1, mda_is_primary(mda));
 
 	return vg;
 }
@@ -968,7 +972,7 @@ static int _vg_write_raw(struct format_instance *fid, struct volume_group *vg,
 			   (unsigned long long)write2_size);
 
 	if (!dev_write_bytes(mdac->area.dev, write1_start, (size_t)write1_size, write_buf)) {
-		log_error("Failed to write metadata to %s fd %d", devname, mdac->area.dev->bcache_fd);
+		log_error("Failed to write metadata to %s.", devname);
 		goto out;
 	}
 
@@ -980,7 +984,7 @@ static int _vg_write_raw(struct format_instance *fid, struct volume_group *vg,
 
 		if (!dev_write_bytes(mdac->area.dev, write2_start, write2_size,
 				     write_buf + new_size - new_wrap)) {
-			log_error("Failed to write metadata wrap to %s fd %d", devname, mdac->area.dev->bcache_fd);
+			log_error("Failed to write metadata wrap to %s", devname);
 			goto out;
 		}
 	}
@@ -1321,7 +1325,7 @@ static struct volume_group *_vg_read_file_name(struct format_instance *fid,
 	return vg;
 }
 
-static struct volume_group *_vg_read_file(struct format_instance *fid,
+static struct volume_group *_vg_read_file(struct cmd_context *cmd, struct format_instance *fid,
 					  const char *vgname,
 					  struct metadata_area *mda,
 					  struct cached_vg_fmtdata **vg_fmtdata,
@@ -1332,7 +1336,7 @@ static struct volume_group *_vg_read_file(struct format_instance *fid,
 	return _vg_read_file_name(fid, vgname, tc->path_live);
 }
 
-static struct volume_group *_vg_read_precommit_file(struct format_instance *fid,
+static struct volume_group *_vg_read_precommit_file(struct cmd_context *cmd, struct format_instance *fid,
 						    const char *vgname,
 						    struct metadata_area *mda,
 						    struct cached_vg_fmtdata **vg_fmtdata,
@@ -1507,6 +1511,7 @@ static int _vg_remove_file(struct format_instance *fid __attribute__((unused)),
 }
 
 int read_metadata_location_summary(const struct format_type *fmt,
+		    struct metadata_area *mda,
 		    struct mda_header *mdah, int primary_mda, struct device_area *dev_area,
 		    struct lvmcache_vgsummary *vgsummary, uint64_t *mda_free_sectors)
 {
@@ -1564,6 +1569,17 @@ int read_metadata_location_summary(const struct format_type *fmt,
 		return 0;
 	}
 
+	/*
+	 * This function is used to read the vg summary during label scan.
+	 * Save the text start location and checksum during scan.  After the VG
+	 * lock is acquired in vg_read, we can reread the mda_header, and
+	 * compare rlocn->offset,checksum to what was saved during scan.  If
+	 * unchanged, it means that the metadata was not changed between scan
+	 * and the read.
+	 */
+	mda->scan_text_offset = rlocn->offset;
+	mda->scan_text_checksum = rlocn->checksum;
+
 	/*
 	 * When the current metadata wraps around the end of the metadata area
 	 * (so some is located at the end and some is located at the
@@ -1701,7 +1717,7 @@ static int _set_ext_flags(struct physical_volume *pv, struct lvmcache_info *info
 }
 
 /* Only for orphans - FIXME That's not true any more */
-static int _text_pv_write(const struct format_type *fmt, struct physical_volume *pv)
+static int _text_pv_write(struct cmd_context *cmd, const struct format_type *fmt, struct physical_volume *pv)
 {
 	struct format_instance *fid = pv->fid;
 	const char *pvid = (const char *) (*pv->old_id.uuid ? &pv->old_id : &pv->id);
@@ -1713,7 +1729,7 @@ static int _text_pv_write(const struct format_type *fmt, struct physical_volume
 	unsigned mda_index;
 
 	/* Add a new cache entry with PV info or update existing one. */
-	if (!(info = lvmcache_add(fmt->labeller, (const char *) &pv->id,
+	if (!(info = lvmcache_add(cmd, fmt->labeller, (const char *) &pv->id,
 				  pv->dev,  pv->label_sector, pv->vg_name,
 				  is_orphan_vg(pv->vg_name) ? pv->vg_name : pv->vg ? (const char *) &pv->vg->id : NULL, 0, NULL)))
 		return_0;
@@ -2200,8 +2216,10 @@ static int _create_vg_text_instance(struct format_instance *fid,
 		}
 
 		if (type & FMT_INSTANCE_MDAS) {
-			if (!(vginfo = lvmcache_vginfo_from_vgname(vg_name, vg_id)))
-				goto_out;
+			if (!(vginfo = lvmcache_vginfo_from_vgname(vg_name, vg_id))) {
+				log_debug("No cached vginfo for VG %s and ID %s.", vg_name, vg_id);
+				goto out;
+			}
 			if (!lvmcache_fid_add_mdas_vg(vginfo, fid))
 				goto_out;
 		}

lib/format_text/import-export.h

@@ -47,11 +47,15 @@ enum pv_vg_lv_e {
 
 struct text_vg_version_ops {
 	int (*check_version) (const struct dm_config_tree * cf);
-	struct volume_group *(*read_vg) (struct format_instance * fid,
-					 const struct dm_config_tree *cf,
-					 unsigned allow_lvmetad_extensions);
+
+	struct volume_group *(*read_vg) (struct cmd_context *cmd,
+					 const struct format_type *fmt,
+					 struct format_instance *fid,
+					 const struct dm_config_tree *cft);
+
 	void (*read_desc) (struct dm_pool * mem, const struct dm_config_tree *cf,
 			   time_t *when, char **desc);
+
 	int (*read_vgsummary) (const struct format_type *fmt,
 			       const struct dm_config_tree *cft,
 			       struct lvmcache_vgsummary *vgsummary);

lib/format_text/import.c

@@ -15,6 +15,7 @@
 
 #include "lib/misc/lib.h"
 #include "lib/metadata/metadata.h"
+#include "lib/commands/toolcontext.h"
 #include "import-export.h"
 
 /* FIXME Use tidier inclusion method */
@@ -181,7 +182,7 @@ struct volume_group *text_read_metadata(struct format_instance *fid,
 		if (!(*vsn)->check_version(cft))
 			continue;
 
-		if (!(vg = (*vsn)->read_vg(fid, cft, 0)))
+		if (!(vg = (*vsn)->read_vg(fid->fmt->cmd, fid->fmt, fid, cft)))
 			goto_out;
 
 		(*vsn)->read_desc(vg->vgmem, cft, when, desc);
@@ -210,9 +211,9 @@ struct volume_group *text_read_metadata_file(struct format_instance *fid,
 				  when, desc);
 }
 
-static struct volume_group *_import_vg_from_config_tree(const struct dm_config_tree *cft,
+static struct volume_group *_import_vg_from_config_tree(struct cmd_context *cmd,
 							struct format_instance *fid,
-							unsigned allow_lvmetad_extensions)
+							const struct dm_config_tree *cft)
 {
 	struct volume_group *vg = NULL;
 	struct text_vg_version_ops **vsn;
@@ -227,10 +228,10 @@ static struct volume_group *_import_vg_from_config_tree(const struct dm_config_t
 		 * The only path to this point uses cached vgmetadata,
 		 * so it can use cached PV state too.
 		 */
-		if (!(vg = (*vsn)->read_vg(fid, cft, allow_lvmetad_extensions)))
+		if (!(vg = (*vsn)->read_vg(cmd, fid->fmt, fid, cft)))
 			stack;
 		else {
-			set_pv_devices(fid, vg, NULL);
+			set_pv_devices(fid, vg);
 
 			if ((vg_missing = vg_missing_pv_count(vg)))
 				log_verbose("There are %d physical volumes missing.", vg_missing);
@@ -243,8 +244,21 @@ static struct volume_group *_import_vg_from_config_tree(const struct dm_config_t
 	return vg;
 }
 
-struct volume_group *import_vg_from_config_tree(const struct dm_config_tree *cft,
-						struct format_instance *fid)
+struct volume_group *import_vg_from_config_tree(struct cmd_context *cmd,
+						struct format_instance *fid,
+						const struct dm_config_tree *cft)
 {
-	return _import_vg_from_config_tree(cft, fid, 0);
+	return _import_vg_from_config_tree(cmd, fid, cft);
 }
+
+struct volume_group *vg_from_config_tree(struct cmd_context *cmd, const struct dm_config_tree *cft)
+{
+	static struct text_vg_version_ops *ops;
+
+	_init_text_import();
+
+	ops = _text_vsn_list[0];
+
+	return ops->read_vg(cmd, cmd->fmt, NULL, cft);
+}
+

lib/format_text/import_vsn1.c

@@ -188,7 +188,7 @@ static int _read_pv(struct cmd_context *cmd,
 	struct physical_volume *pv;
 	struct pv_list *pvl;
 	const struct dm_config_value *cv;
-	const char *device_hint;
+	const char *str;
 	uint64_t size, ba_start;
 
 	if (!(pvl = dm_pool_zalloc(mem, sizeof(*pvl))) ||
@@ -233,11 +233,21 @@ static int _read_pv(struct cmd_context *cmd,
 		return 0;
 	}
 
-	if (dm_config_get_str(pvn, "device", &device_hint)) {
-		if (!(pv->device_hint = dm_pool_strdup(mem, device_hint)))
+	if (dm_config_get_str(pvn, "device", &str)) {
+		if (!(pv->device_hint = dm_pool_strdup(mem, str)))
 			log_error("Failed to allocate memory for device hint in read_pv.");
 	}
 
+	if (dm_config_get_str(pvn, "device_id", &str)) {
+		if (!(pv->device_id = dm_pool_strdup(mem, str)))
+			log_error("Failed to allocate memory for device_id in read_pv.");
+	}
+
+	if (dm_config_get_str(pvn, "device_id_type", &str)) {
+		if (!(pv->device_id_type = dm_pool_strdup(mem, str)))
+			log_error("Failed to allocate memory for device_id_type in read_pv.");
+	}
+
 	if (!_read_uint64(pvn, "pe_start", &pv->pe_start)) {
 		log_error("Couldn't read extent start value (pe_start) "
 			  "for physical volume.");
@@ -306,7 +316,7 @@ static int _read_pvsummary(struct cmd_context *cmd,
 {
 	struct physical_volume *pv;
 	struct pv_list *pvl;
-	const char *device_hint;
+	const char *str;
 
 	if (!(pvl = dm_pool_zalloc(mem, sizeof(*pvl))) ||
 	    !(pvl->pv = dm_pool_zalloc(mem, sizeof(*pvl->pv))))
@@ -326,9 +336,19 @@ static int _read_pvsummary(struct cmd_context *cmd,
 	    !_read_uint64(pvn, "dev_size", &pv->size))
 		log_warn("Couldn't read dev size for physical volume.");
 
-	if (dm_config_get_str(pvn, "device", &device_hint)) {
-		if (!(pv->device_hint = dm_pool_strdup(mem, device_hint)))
-			log_error("Failed to allocate memory for device hint in read_pv.");
+	if (dm_config_get_str(pvn, "device", &str)) {
+		if (!(pv->device_hint = dm_pool_strdup(mem, str)))
+			log_error("Failed to allocate memory for device hint in read_pv_sum.");
+	}
+
+	if (dm_config_get_str(pvn, "device_id", &str)) {
+		if (!(pv->device_id = dm_pool_strdup(mem, str)))
+			log_error("Failed to allocate memory for device_id in read_pv_sum.");
+	}
+
+	if (dm_config_get_str(pvn, "device_id_type", &str)) {
+		if (!(pv->device_id_type = dm_pool_strdup(mem, str)))
+			log_error("Failed to allocate memory for device_id_type in read_pv_sum.");
 	}
 
 	dm_list_add(&vgsummary->pvsummaries, &pvl->list);
@@ -993,7 +1013,7 @@ static int _read_lvsegs(struct cmd_context *cmd,
 }
 
 static int _read_sections(struct cmd_context *cmd,
-			  struct format_type *fmt,
+			  const struct format_type *fmt,
 			  struct format_instance *fid,
 			  struct dm_pool *mem,
 			  const char *section, section_fn fn,
@@ -1016,19 +1036,18 @@ static int _read_sections(struct cmd_context *cmd,
 	}
 
 	for (n = n->child; n; n = n->sib) {
-		if (!fn(cmd, fmt, fid, mem, vg, vgsummary, n, vgn, pv_hash, lv_hash))
+		if (!fn(cmd, (struct format_type *)fmt, fid, mem, vg, vgsummary, n, vgn, pv_hash, lv_hash))
 			return_0;
 	}
 
 	return 1;
 }
 
-static struct volume_group *_read_vg(struct format_instance *fid,
-				     const struct dm_config_tree *cft,
-				     unsigned allow_lvmetad_extensions)
+static struct volume_group *_read_vg(struct cmd_context *cmd,
+				     const struct format_type *fmt,
+				     struct format_instance *fid,
+				     const struct dm_config_tree *cft)
 {
-	struct cmd_context *cmd = fid->fmt->cmd;
-	struct format_type *fmt = (struct format_type *)fid->fmt;
 	struct dm_pool *mem;
 	const struct dm_config_node *vgn;
 	const struct dm_config_value *cv;
@@ -1234,7 +1253,8 @@ static struct volume_group *_read_vg(struct format_instance *fid,
 	dm_hash_destroy(pv_hash);
 	dm_hash_destroy(lv_hash);
 
-	vg_set_fid(vg, fid);
+	if (fid)
+		vg_set_fid(vg, fid);
 
 	/*
 	 * Finished.

lib/format_text/layout.h

@@ -18,11 +18,10 @@
 
 #include "lib/config/config.h"
 #include "lib/metadata/metadata.h"
+#include "lib/format_text/format-text.h"
 #include "lib/cache/lvmcache.h"
 #include "lib/uuid/uuid.h"
 
-/* disk_locn and data_area_list are defined in format-text.h */
-
 /*
  * PV header extension versions:
  *   - version 1: bootloader area support
@@ -34,7 +33,7 @@ struct pv_header_extension {
 	uint32_t version;
 	uint32_t flags;
 	/* NULL-terminated list of bootloader areas */
-	struct disk_locn bootloader_areas_xl[0];
+	struct disk_locn bootloader_areas_xl[];
 } __attribute__ ((packed));
 
 /* Fields with the suffix _xl should be xlate'd wherever they appear */
@@ -47,7 +46,7 @@ struct pv_header {
 
 	/* NULL-terminated list of data areas followed by */
 	/* NULL-terminated list of metadata area headers */
-	struct disk_locn disk_areas_xl[0];	/* Two lists */
+	struct disk_locn disk_areas_xl[];	/* Two lists */
 } __attribute__ ((packed));
 
 /*
@@ -77,7 +76,7 @@ struct mda_header {
 	uint64_t start;		/* Absolute start byte of mda_header */
 	uint64_t size;		/* Size of metadata area */
 
-	struct raw_locn raw_locns[0];	/* NULL-terminated list */
+	struct raw_locn raw_locns[];	/* NULL-terminated list */
 } __attribute__ ((packed));
 
 struct mda_header *raw_read_mda_header(const struct format_type *fmt,
@@ -104,7 +103,8 @@ struct mda_context {
 #define MDA_SIZE_MIN (8 * (unsigned) lvm_getpagesize())
 #define MDA_ORIGINAL_ALIGNMENT 512	/* Original alignment used for start of VG metadata content */
 
-int read_metadata_location_summary(const struct format_type *fmt, struct mda_header *mdah, int primary_mda, 
+int read_metadata_location_summary(const struct format_type *fmt,
+		    struct metadata_area *mda, struct mda_header *mdah, int primary_mda, 
 		    struct device_area *dev_area, struct lvmcache_vgsummary *vgsummary,
 		    uint64_t *mda_free_sectors);
 

lib/format_text/text_label.c

@@ -349,7 +349,7 @@ static int _read_mda_header_and_metadata(const struct format_type *fmt,
 		return 1;
 	}
 
-	if (!read_metadata_location_summary(fmt, mdah, mda_is_primary(mda), &mdac->area,
+	if (!read_metadata_location_summary(fmt, mda, mdah, mda_is_primary(mda), &mdac->area,
 					    vgsummary, &mdac->free_sectors)) {
 		if (vgsummary->zero_offset)
 			return 1;
@@ -370,7 +370,7 @@ static int _read_mda_header_and_metadata(const struct format_type *fmt,
  * the metadata is at for those PVs.
  */
 
-static int _text_read(struct labeller *labeller, struct device *dev, void *label_buf,
+static int _text_read(struct cmd_context *cmd, struct labeller *labeller, struct device *dev, void *label_buf,
 		      uint64_t label_sector, int *is_duplicate)
 {
 	struct lvmcache_vgsummary vgsummary;
@@ -410,7 +410,7 @@ static int _text_read(struct labeller *labeller, struct device *dev, void *label
 	 *
 	 * Other reasons for lvmcache_add to return NULL are internal errors.
 	 */
-	if (!(info = lvmcache_add(labeller, (char *)pvhdr->pv_uuid, dev, label_sector,
+	if (!(info = lvmcache_add(cmd, labeller, (char *)pvhdr->pv_uuid, dev, label_sector,
 				  FMT_TEXT_ORPHAN_VG_NAME,
 				  FMT_TEXT_ORPHAN_VG_NAME, 0, is_duplicate)))
 		return_0;
@@ -503,7 +503,7 @@ static int _text_read(struct labeller *labeller, struct device *dev, void *label
 		rv1 = _read_mda_header_and_metadata(fmt, mda1, &vgsummary, &bad_fields);
 
 		if (rv1 && !vgsummary.zero_offset && !vgsummary.mda_ignored) {
-			if (!lvmcache_update_vgname_and_id(info, &vgsummary)) {
+			if (!lvmcache_update_vgname_and_id(cmd, info, &vgsummary)) {
 				/* I believe this is only an internal error. */
 
 				dm_list_del(&mda1->list);
@@ -554,7 +554,7 @@ static int _text_read(struct labeller *labeller, struct device *dev, void *label
 		rv2 = _read_mda_header_and_metadata(fmt, mda2, &vgsummary, &bad_fields);
 
 		if (rv2 && !vgsummary.zero_offset && !vgsummary.mda_ignored) {
-			if (!lvmcache_update_vgname_and_id(info, &vgsummary)) {
+			if (!lvmcache_update_vgname_and_id(cmd, info, &vgsummary)) {
 				dm_list_del(&mda2->list);
 
 				/* Are there other cases besides mismatch and internal error? */

lib/integrity/integrity.c

@@ -84,12 +84,17 @@ static int _integrity_text_import(struct lv_segment *seg,
 	if (!dm_config_get_uint32(sn, "tag_size", &set->tag_size))
 		return SEG_LOG_ERROR("integrity tag_size must be set in");
 
+	/* block_size always set */
+
+	if (!dm_config_get_uint32(sn, "block_size", &set->block_size))
+		return SEG_LOG_ERROR("integrity block_size invalid in");
+
 	/* internal_hash always set */
 
 	if (!dm_config_get_str(sn, "internal_hash", &hash))
 		return SEG_LOG_ERROR("integrity internal_hash must be set in");
 
-	if (!(set->internal_hash = strdup(hash)))
+	if (!(set->internal_hash = dm_pool_strdup(seg->lv->vg->vgmem, hash)))
 		return SEG_LOG_ERROR("integrity internal_hash failed to be set in");
 
 	/* meta_dev optional */
@@ -102,6 +107,11 @@ static int _integrity_text_import(struct lv_segment *seg,
 			return SEG_LOG_ERROR("Unknown logical volume %s specified for integrity in", meta_dev);
 	}
 
+	if (dm_config_has_node(sn, "recalculate")) {
+		if (!dm_config_get_uint32(sn, "recalculate", &seg->integrity_recalculate))
+			return SEG_LOG_ERROR("integrity recalculate error in");
+	}
+
 	/* the rest are optional */
 
 	if (dm_config_has_node(sn, "journal_sectors")) {
@@ -134,12 +144,6 @@ static int _integrity_text_import(struct lv_segment *seg,
 		set->commit_time_set = 1;
 	}
 
-	if (dm_config_has_node(sn, "block_size")) {
-		if (!dm_config_get_uint32(sn, "block_size", &set->block_size))
-			return SEG_LOG_ERROR("Unknown integrity_setting in");
-		set->block_size_set = 1;
-	}
-
 	if (dm_config_has_node(sn, "bitmap_flush_interval")) {
 		if (!dm_config_get_uint32(sn, "bitmap_flush_interval", &set->bitmap_flush_interval))
 			return SEG_LOG_ERROR("Unknown integrity_setting in");
@@ -156,6 +160,9 @@ static int _integrity_text_import(struct lv_segment *seg,
 	seg->integrity_meta_dev = meta_lv;
 	seg->lv->status |= INTEGRITY;
 
+	if (meta_lv)
+		meta_lv->status |= INTEGRITY_METADATA;
+
 	if (meta_lv && !add_seg_to_segs_using_this_lv(meta_lv, seg))
 		return_0;
 
@@ -180,11 +187,15 @@ static int _integrity_text_export(const struct lv_segment *seg,
 
 	outf(f, "mode = \"%s\"", set->mode);
 	outf(f, "tag_size = %u", set->tag_size);
+	outf(f, "block_size = %u", set->block_size);
 	outf(f, "internal_hash = \"%s\"", set->internal_hash);
 
 	if (seg->integrity_meta_dev)
 		outf(f, "meta_dev = \"%s\"", seg->integrity_meta_dev->name);
 
+	if (seg->integrity_recalculate)
+		outf(f, "recalculate = %u", seg->integrity_recalculate);
+
 	if (set->journal_sectors_set)
 		outf(f, "journal_sectors = %u", set->journal_sectors);
 
@@ -200,9 +211,6 @@ static int _integrity_text_export(const struct lv_segment *seg,
 	if (set->commit_time_set)
 		outf(f, "commit_time = %u", set->commit_time);
 
-	if (set->block_size_set)
-		outf(f, "block_size = %u", set->block_size);
-
 	if (set->bitmap_flush_interval)
 		outf(f, "bitmap_flush_interval = %u", set->bitmap_flush_interval);
 
@@ -225,13 +233,21 @@ static int _target_present(struct cmd_context *cmd,
 {
 	static int _integrity_checked = 0;
 	static int _integrity_present = 0;
+	uint32_t maj, min, patchlevel;
 
 	if (!activation())
 		return 0;
 
 	if (!_integrity_checked) {
 		_integrity_checked = 1;
-		_integrity_present =  target_present(cmd, TARGET_NAME_INTEGRITY, 0);
+		if (!(_integrity_present = target_present_version(cmd, TARGET_NAME_INTEGRITY, 1,
+								  &maj, &min, &patchlevel)))
+			return 0;
+
+		if (maj < 1 || min < 6) {
+			log_error("Integrity target version older than minimum 1.6.0");
+			return 0;
+		}
 	}
 
 	return _integrity_present;
@@ -256,7 +272,7 @@ static int _integrity_add_target_line(struct dev_manager *dm,
 				 struct cmd_context *cmd __attribute__((unused)),
 				 void **target_state __attribute__((unused)),
 				 struct lv_segment *seg,
-				 const struct lv_activate_opts *laopts __attribute__((unused)),
+				 const struct lv_activate_opts *laopts,
 				 struct dm_tree_node *node, uint64_t len,
 				 uint32_t *pvmove_mirror_count __attribute__((unused)))
 {
@@ -280,10 +296,11 @@ static int _integrity_add_target_line(struct dev_manager *dm,
 		log_error("_integrity_add_target_line zero size");
 		return_0;
 	}
-	
+
 	if (!dm_tree_node_add_integrity_target(node, seg->integrity_data_sectors,
 					       origin_uuid, meta_uuid,
-					       &seg->integrity_settings))
+					       &seg->integrity_settings,
+					       seg->integrity_recalculate))
 		return_0;
 
 	return 1;

lib/label/hints.c

@@ -135,17 +135,17 @@
  *
  */
 
-#include "base/memory/zalloc.h"
 #include "lib/misc/lib.h"
+#include "base/memory/zalloc.h"
 #include "lib/label/label.h"
 #include "lib/misc/crc.h"
-#include "lib/mm/xlate.h"
 #include "lib/cache/lvmcache.h"
 #include "lib/device/bcache.h"
 #include "lib/commands/toolcontext.h"
 #include "lib/activate/activate.h"
 #include "lib/label/hints.h"
 #include "lib/device/dev-type.h"
+#include "lib/device/device_id.h"
 
 #include <sys/stat.h>
 #include <fcntl.h>
@@ -167,8 +167,10 @@ static const char *_newhints_file = DEFAULT_RUN_DIR "/newhints";
  * than they were built with.  Increase the minor number
  * when adding features that older lvm versions can just
  * ignore while continuing to use the other content.
+ *
+ * MAJOR 2: add devices_file
  */
-#define HINTS_VERSION_MAJOR 1
+#define HINTS_VERSION_MAJOR 2
 #define HINTS_VERSION_MINOR 1
 
 #define HINT_LINE_LEN (PATH_MAX + NAME_LEN + ID_LEN + 64)
@@ -191,8 +193,10 @@ static int _hints_exists(void)
 
 	if (!stat(_hints_file, &buf))
 		return 1;
+
 	if (errno != ENOENT)
-		log_debug("hints_exist errno %d", errno);
+		log_debug("hints_exist errno %d %s", errno, _hints_file);
+
 	return 0;
 }
 
@@ -202,8 +206,10 @@ static int _nohints_exists(void)
 
 	if (!stat(_nohints_file, &buf))
 		return 1;
+
 	if (errno != ENOENT)
-		log_debug("nohints_exist errno %d", errno);
+		log_debug("nohints_exist errno %d %s", errno, _nohints_file);
+
 	return 0;
 }
 
@@ -213,8 +219,10 @@ static int _newhints_exists(void)
 
 	if (!stat(_newhints_file, &buf))
 		return 1;
+
 	if (errno != ENOENT)
-		log_debug("newhints_exist errno %d", errno);
+		log_debug("newhints_exist errno %d %s", errno, _newhints_file);
+
 	return 0;
 }
 
@@ -244,29 +252,33 @@ static int _touch_hints(void)
 {
 	FILE *fp;
 
-	if (!(fp = fopen(_hints_file, "w")))
-		return_0;
+	if (!(fp = fopen(_hints_file, "w"))) {
+		log_debug("touch_hints errno %d %s", errno, _hints_file);
+		return 0;
+	}
 	if (fclose(fp))
-		stack;
+		log_debug("touch_hints close errno %d %s", errno, _hints_file);
+
 	return 1;
 }
 
 static void _unlink_nohints(void)
 {
 	if (unlink(_nohints_file))
-		log_debug("unlink_nohints errno %d", errno);
+		log_debug("unlink_nohints errno %d %s", errno, _nohints_file);
 }
 
+
 static void _unlink_hints(void)
 {
 	if (unlink(_hints_file))
-		log_debug("unlink_hints errno %d", errno);
+		log_debug("unlink_hints errno %d %s", errno, _hints_file);
 }
 
 static void _unlink_newhints(void)
 {
 	if (unlink(_newhints_file))
-		log_debug("unlink_newhints errno %d", errno);
+		log_debug("unlink_newhints errno %d %s", errno, _newhints_file);
 }
 
 static int _clear_hints(struct cmd_context *cmd)
@@ -275,7 +287,7 @@ static int _clear_hints(struct cmd_context *cmd)
 	time_t t;
 
 	if (!(fp = fopen(_hints_file, "w"))) {
-		log_warn("Failed to clear hint file.");
+		log_debug("clear_hints open errno %d", errno);
 		/* shouldn't happen, but try to unlink in case */
 		_unlink_hints();
 		return 0;
@@ -286,10 +298,10 @@ static int _clear_hints(struct cmd_context *cmd)
 	fprintf(fp, "# Created empty by %s pid %d %s", cmd->name, getpid(), ctime(&t));
 
 	if (fflush(fp))
-		log_debug("clear_hints flush errno %d", errno);
+		log_debug("clear_hints flush errno %d %s", errno, _hints_file);
 
 	if (fclose(fp))
-		log_debug("clear_hints close errno %d", errno);
+		log_debug("clear_hints close errno %d %s", errno, _hints_file);
 
 	return 1;
 }
@@ -313,7 +325,7 @@ static int _lock_hints(struct cmd_context *cmd, int mode, int nonblock)
 
 	fd = open(_hints_file, O_RDWR);
 	if (fd < 0) {
-		log_debug("lock_hints open errno %d", errno);
+		log_debug("lock_hints open errno %d %s", errno, _hints_file);
 		return 0;
 	}
 
@@ -325,7 +337,8 @@ static int _lock_hints(struct cmd_context *cmd, int mode, int nonblock)
 	}
 
 	if (close(fd))
-		stack;
+		log_debug("lock_hints close errno %d %s", errno, _hints_file);
+
 	return 0;
 }
 
@@ -352,9 +365,20 @@ static void _unlock_hints(struct cmd_context *cmd)
 
 void hints_exit(struct cmd_context *cmd)
 {
+	free_hints(&cmd->hints);
 	if (_hints_fd == -1)
 		return;
-	return _unlock_hints(cmd);
+	_unlock_hints(cmd);
+}
+
+void free_hints(struct dm_list *hints)
+{
+	struct hint *hint, *hint2;
+
+	dm_list_iterate_items_safe(hint, hint2, hints) {
+		dm_list_del(&hint->list);
+		free(hint);
+	}
 }
 
 static struct hint *_find_hint_name(struct dm_list *hints, const char *name)
@@ -410,6 +434,9 @@ static int _dev_in_hint_hash(struct cmd_context *cmd, struct device *dev)
 {
 	uint64_t devsize = 0;
 
+	if (dm_list_empty(&dev->aliases))
+		return 0;
+
 	if (!cmd->filter->passes_filter(cmd, cmd->filter, dev, "regex"))
 		return 0;
 
@@ -421,7 +448,7 @@ static int _dev_in_hint_hash(struct cmd_context *cmd, struct device *dev)
 		return 0;
 
 	if (!dev_get_size(dev, &devsize) || !devsize)
-		return 0;
+		return_0;
 
 	return 1;
 }
@@ -650,7 +677,7 @@ static int _read_hint_file(struct cmd_context *cmd, struct dm_list *hints, int *
 	int found = 0;
 	int keylen;
 	int hv_major, hv_minor;
-	int major, minor;
+	int major = -1, minor = -1;
 	int ret = 1;
 	int i;
 
@@ -688,8 +715,9 @@ static int _read_hint_file(struct cmd_context *cmd, struct dm_list *hints, int *
 				break;
 			}
 
-			if (hv_major > HINTS_VERSION_MAJOR) {
-				log_debug("ignore hints with newer major version %d.%d", hv_major, hv_minor);
+			if (hv_major != HINTS_VERSION_MAJOR) {
+				log_debug("ignore hints with version %d.%d current %d.%d",
+					  hv_major, hv_minor, HINTS_VERSION_MAJOR, HINTS_VERSION_MINOR);
 				*needs_refresh = 1;
 				break;
 			}
@@ -724,7 +752,7 @@ static int _read_hint_file(struct cmd_context *cmd, struct dm_list *hints, int *
 
 		keylen = strlen("scan_lvs:");
 		if (!strncmp(_hint_line, "scan_lvs:", keylen)) {
-			int scan_lvs = 0;
+			unsigned scan_lvs = 0;
 			if ((sscanf(_hint_line + keylen, "%u", &scan_lvs) != 1) ||
 			    scan_lvs != cmd->scan_lvs) {
 				log_debug("ignore hints with different or unreadable scan_lvs");
@@ -734,6 +762,25 @@ static int _read_hint_file(struct cmd_context *cmd, struct dm_list *hints, int *
 			continue;
 		}
 
+		keylen = strlen("devices_file:");
+		if (!strncmp(_hint_line, "devices_file:", keylen)) {
+			const char *df_hint = _hint_line + keylen;
+			const char *df_config = find_config_tree_str(cmd, devices_devicesfile_CFG, NULL);
+			/* when a devices file is not used, hints should have devices_file:. */
+			if (!cmd->enable_devices_file || !df_hint || !df_config) {
+				if (df_hint[0] != '.') {
+					log_debug("ignore hints with different devices_file: not enabled vs %s", df_hint);
+					*needs_refresh = 1;
+					break;
+				}
+			} else if (strcmp(df_hint, df_config)) {
+				log_debug("ignore hints with different devices_file: %s vs %s", df_hint, df_config);
+				*needs_refresh = 1;
+				break;
+			}
+			continue;
+		}
+
 		keylen = strlen("devs_hash:");
 		if (!strncmp(_hint_line, "devs_hash:", keylen)) {
 			if (sscanf(_hint_line + keylen, "%u %u", &read_hash, &read_count) != 2) {
@@ -786,7 +833,7 @@ static int _read_hint_file(struct cmd_context *cmd, struct dm_list *hints, int *
 	}
 
 	if (fclose(fp))
-		stack;
+		log_debug("read_hint_file close errno %d", errno);
 
 	if (!ret)
 		return 0;
@@ -803,10 +850,13 @@ static int _read_hint_file(struct cmd_context *cmd, struct dm_list *hints, int *
 	if (!(iter = dev_iter_create(NULL, 0)))
 		return 0;
 	while ((dev = dev_iter_get(cmd, iter))) {
+		if (cmd->enable_devices_file && !get_du_for_dev(cmd, dev))
+			continue;
+
 		if (!_dev_in_hint_hash(cmd, dev))
 			continue;
-		memset(devpath, 0, sizeof(devpath));
-		strncpy(devpath, dev_name(dev), PATH_MAX);
+
+		(void) dm_strncpy(devpath, dev_name(dev), sizeof(devpath));
 		calc_hash = calc_crc(calc_hash, (const uint8_t *)devpath, strlen(devpath));
 		calc_count++;
 	}
@@ -864,6 +914,7 @@ int write_hint_file(struct cmd_context *cmd, int newhints)
 	struct device *dev;
 	const char *vgname;
 	char *filter_str = NULL;
+	const char *config_devices_file = NULL;
 	uint32_t hash = INITIAL_CRC;
 	uint32_t count = 0;
 	time_t t;
@@ -924,6 +975,19 @@ int write_hint_file(struct cmd_context *cmd, int newhints)
 
 	fprintf(fp, "scan_lvs:%d\n", cmd->scan_lvs);
 
+	/*
+	 * Only associate hints with the default/system devices file.
+	 * If no default/system devices file is used, "." is set.
+	 * If we are using a devices file other than the config setting
+	 * (from --devicesfile), then we should not be using hints and
+	 * shouldn't get here.
+	 */
+	config_devices_file = find_config_tree_str(cmd, devices_devicesfile_CFG, NULL);
+	if (cmd->enable_devices_file && !cmd->devicesfile && config_devices_file)
+		fprintf(fp, "devices_file:%s\n", config_devices_file);
+	else
+		fprintf(fp, "devices_file:.\n");
+
 	/* 
 	 * iterate through all devs and write a line for each
 	 * dev flagged DEV_SCAN_FOUND_LABEL
@@ -941,6 +1005,9 @@ int write_hint_file(struct cmd_context *cmd, int newhints)
 	 * 2. add PVs to the hint file
 	 */
 	while ((dev = dev_iter_get(cmd, iter))) {
+		if (cmd->enable_devices_file && !get_du_for_dev(cmd, dev))
+			continue;
+
 		if (!_dev_in_hint_hash(cmd, dev)) {
 			if (dev->flags & DEV_SCAN_FOUND_LABEL) {
 				/* should never happen */
@@ -954,7 +1021,7 @@ int write_hint_file(struct cmd_context *cmd, int newhints)
 		 * detect when the devices on the system change, which
 		 * invalidates the existing hints.
 		 */
-		strncpy(devpath, dev_name(dev), PATH_MAX);
+		(void) dm_strncpy(devpath, dev_name(dev), sizeof(devpath));
 		hash = calc_crc(hash, (const uint8_t *)devpath, strlen(devpath));
 		count++;
 
@@ -1008,7 +1075,7 @@ int write_hint_file(struct cmd_context *cmd, int newhints)
 
  out_close:
 	if (fclose(fp))
-		stack;
+		log_debug("write_hint_file close errno %d", errno);
 
  out_unlock:
 	/* get_hints() took ex lock before returning with newhints set */
@@ -1106,8 +1173,10 @@ void pvscan_recreate_hints_begin(struct cmd_context *cmd)
 
 	log_debug("pvscan_recreate_hints_begin");
 
-	if (!_touch_hints())
+	if (!_touch_hints()) {
+		stack;
 		return;
+	}
 
 	/* limit potential delay blocking on hints lock next */
 	if (!_touch_nohints())
@@ -1303,10 +1372,11 @@ int get_hints(struct cmd_context *cmd, struct dm_list *hints_out, int *newhints,
 	}
 
 	/*
-	 * couln't read file for some reason, not normal, just skip using hints
+	 * couldn't read file for some reason, not normal, just skip using hints
 	 */
 	if (!_read_hint_file(cmd, &hints_list, &needs_refresh)) {
 		log_debug("get_hints: read fail");
+		free_hints(&hints_list);
 		_unlock_hints(cmd);
 		return 0;
 	}
@@ -1319,6 +1389,7 @@ int get_hints(struct cmd_context *cmd, struct dm_list *hints_out, int *newhints,
 	 */
 	if (needs_refresh) {
 		log_debug("get_hints: needs refresh");
+		free_hints(&hints_list);
 
 		if (!_lock_hints(cmd, LOCK_EX, NONBLOCK))
 			return 0;
@@ -1326,7 +1397,6 @@ int get_hints(struct cmd_context *cmd, struct dm_list *hints_out, int *newhints,
 		/* create new hints after scan */
 		*newhints = NEWHINTS_REFRESH;
 		return 0;
-
 	}
 	
 	/*
@@ -1358,8 +1428,8 @@ int get_hints(struct cmd_context *cmd, struct dm_list *hints_out, int *newhints,
 
 	_apply_hints(cmd, &hints_list, vgname, devs_in, devs_out);
 
-	log_debug("get_hints: applied using %d other %d",
-		  dm_list_size(devs_out), dm_list_size(devs_in));
+	log_debug("get_hints: applied using %d other %d vgname %s",
+		  dm_list_size(devs_out), dm_list_size(devs_in), vgname ?: "");
 
 	dm_list_splice(hints_out, &hints_list);
 

lib/label/hints.h

@@ -24,6 +24,8 @@ struct hint {
 	unsigned chosen:1; /* this hint's dev was chosen for scanning */
 };
 
+void free_hints(struct dm_list *hints);
+
 int write_hint_file(struct cmd_context *cmd, int newhints);
 
 void clear_hint_file(struct cmd_context *cmd);

lib/label/label.h

@@ -64,7 +64,7 @@ struct label_ops {
 	/*
 	 * Read a label from a volume.
 	 */
-	int (*read) (struct labeller * l, struct device * dev,
+	int (*read) (struct cmd_context *cmd, struct labeller * l, struct device * dev,
 		     void *label_buf, uint64_t label_sector, int *is_duplicate);
 
 	/*
@@ -104,27 +104,22 @@ extern struct bcache *scan_bcache;
 
 int label_scan(struct cmd_context *cmd);
 int label_scan_devs(struct cmd_context *cmd, struct dev_filter *f, struct dm_list *devs);
+int label_scan_devs_cached(struct cmd_context *cmd, struct dev_filter *f, struct dm_list *devs);
 int label_scan_devs_rw(struct cmd_context *cmd, struct dev_filter *f, struct dm_list *devs);
-int label_scan_devs_excl(struct dm_list *devs);
+int label_scan_devs_excl(struct cmd_context *cmd, struct dev_filter *f, struct dm_list *devs);
+int label_scan_dev(struct device *dev);
 void label_scan_invalidate(struct device *dev);
 void label_scan_invalidate_lv(struct cmd_context *cmd, struct logical_volume *lv);
 void label_scan_drop(struct cmd_context *cmd);
 void label_scan_destroy(struct cmd_context *cmd);
-int label_read(struct device *dev);
-int label_read_sector(struct device *dev, uint64_t scan_sector);
-void label_scan_confirm(struct device *dev);
 int label_scan_setup_bcache(void);
 int label_scan_open(struct device *dev);
 int label_scan_open_excl(struct device *dev);
 int label_scan_open_rw(struct device *dev);
+int label_scan_reopen_rw(struct device *dev);
+int label_read_pvid(struct device *dev);
 
-/*
- * These are the sizes the label.c uses to set up
- * and use bcache (they are not bcache restrictions
- * or defs.)
- */
-#define BCACHE_BLOCK_SIZE_IN_SECTORS 256 /* 256*512 = 128K */
-#define BCACHE_BLOCK_SIZE_IN_BYTES 131072
+int label_scan_for_pvid(struct cmd_context *cmd, char *pvid, struct device **dev_out);
 
 /*
  * Wrappers around bcache equivalents.
@@ -134,6 +129,7 @@ bool dev_read_bytes(struct device *dev, uint64_t start, size_t len, void *data);
 bool dev_write_bytes(struct device *dev, uint64_t start, size_t len, void *data);
 bool dev_write_zeros(struct device *dev, uint64_t start, size_t len);
 bool dev_set_bytes(struct device *dev, uint64_t start, size_t len, uint8_t val);
+bool dev_invalidate_bytes(struct device *dev, uint64_t start, size_t len);
 void dev_set_last_byte(struct device *dev, uint64_t offset);
 void dev_unset_last_byte(struct device *dev);
 

lib/locking/locking.c

@@ -183,7 +183,11 @@ static int _lock_vol(struct cmd_context *cmd, const char *resource, uint32_t fla
 
 	block_signals(flags);
 
-	ret = _locking.lock_resource(cmd, resource, flags, NULL);
+	if ((ret = _locking.lock_resource(cmd, resource, flags, NULL)))
+		/* ensure signals are blocked while VG_GLOBAL lock is held */
+		_update_vg_lock_count(resource, flags);
+	else
+		stack;
 
 	_unblock_signals();
 
@@ -287,8 +291,6 @@ out_hold:
 	else if (lck_type == LCK_UNLOCK)
 		lvmcache_unlock_vgname(resource);
 
-	/* FIXME: we shouldn't need to keep track of this either. */
-	_update_vg_lock_count(resource, flags);
 	return 1;
 
 out_fail:
@@ -338,7 +340,7 @@ int sync_local_dev_names(struct cmd_context* cmd)
  * an explicitly acquired ex global lock to sh in process_each.
  */
 
-static int _lockf_global(struct cmd_context *cmd, const char *mode, int convert)
+static int _lockf_global(struct cmd_context *cmd, const char *mode, int convert, int nonblock)
 {
 	uint32_t flags = 0;
 	int ret;
@@ -346,6 +348,9 @@ static int _lockf_global(struct cmd_context *cmd, const char *mode, int convert)
 	if (convert)
 		flags |= LCK_CONVERT;
 
+	if (nonblock)
+		flags |= LCK_NONBLOCK;
+
 	if (!strcmp(mode, "ex")) {
 		flags |= LCK_WRITE;
 
@@ -379,7 +384,7 @@ static int _lockf_global(struct cmd_context *cmd, const char *mode, int convert)
 
 int lockf_global(struct cmd_context *cmd, const char *mode)
 {
-	return _lockf_global(cmd, mode, 0);
+	return _lockf_global(cmd, mode, 0, 0);
 }
 
 int lockf_global_convert(struct cmd_context *cmd, const char *mode)
@@ -388,7 +393,12 @@ int lockf_global_convert(struct cmd_context *cmd, const char *mode)
 	if (cmd->lockf_global_ex && !strcmp(mode, "ex"))
 		return 1;
 
-	return _lockf_global(cmd, mode, 1);
+	return _lockf_global(cmd, mode, 1, 0);
+}
+
+int lockf_global_nonblock(struct cmd_context *cmd, const char *mode)
+{
+	return _lockf_global(cmd, mode, 0, 1);
 }
 
 int lock_global(struct cmd_context *cmd, const char *mode)

lib/locking/locking.h

@@ -75,6 +75,7 @@ int activate_lvs(struct cmd_context *cmd, struct dm_list *lvs, unsigned exclusiv
 
 int lockf_global(struct cmd_context *cmd, const char *mode);
 int lockf_global_convert(struct cmd_context *cmd, const char *mode);
+int lockf_global_nonblock(struct cmd_context *cmd, const char *mode);
 int lock_global(struct cmd_context *cmd, const char *mode);
 int lock_global_convert(struct cmd_context *cmd, const char *mode);
 

lib/locking/lvmlockd.c

@@ -382,6 +382,7 @@ static int _extend_sanlock_lv(struct cmd_context *cmd, struct volume_group *vg,
 {
 	struct device *dev;
 	char path[PATH_MAX];
+	char *name;
 	uint64_t old_size_bytes;
 	uint64_t new_size_bytes;
 	uint32_t extend_bytes;
@@ -423,8 +424,10 @@ static int _extend_sanlock_lv(struct cmd_context *cmd, struct volume_group *vg,
 
 	new_size_bytes = lv->size * SECTOR_SIZE;
 
-	if (dm_snprintf(path, sizeof(path), "%s/mapper/%s-%s", lv->vg->cmd->dev_dir,
-			lv->vg->name, lv->name) < 0) {
+	if (!(name = dm_build_dm_name(lv->vg->cmd->mem, lv->vg->name, lv->name, NULL)))
+		return_0;
+
+	if (dm_snprintf(path, sizeof(path), "%s/%s", dm_dir(), name) < 0) {
 		log_error("Extend sanlock LV %s name too long - extended size not zeroed.",
 			  display_lvname(lv));
 		return 0;
@@ -635,7 +638,6 @@ static int _init_vg_sanlock(struct cmd_context *cmd, struct volume_group *vg, in
 	const char *vg_lock_args = NULL;
 	const char *opts = NULL;
 	struct pv_list *pvl;
-	struct device *sector_dev;
 	uint32_t sector_size = 0;
 	unsigned int physical_block_size, logical_block_size;
 	int num_mb = 0;
@@ -656,16 +658,11 @@ static int _init_vg_sanlock(struct cmd_context *cmd, struct volume_group *vg, in
 	dm_list_iterate_items(pvl, &vg->pvs) {
 		if (!dev_get_direct_block_sizes(pvl->pv->dev, &physical_block_size, &logical_block_size))
 			continue;
-
-		if (!sector_size) {
-			sector_size = logical_block_size;
-			sector_dev = pvl->pv->dev;
-		} else if (sector_size != logical_block_size) {
-			log_error("Inconsistent logical block sizes for %s and %s.",
-				  dev_name(pvl->pv->dev), dev_name(sector_dev));
-			return 0;
-		}
+		if ((physical_block_size == 4096) || (logical_block_size == 4096))
+			sector_size = 4096;
 	}
+	if (!sector_size)
+		sector_size = 512;
 
 	log_debug("Using sector size %u for sanlock LV", sector_size);
 
@@ -2092,7 +2089,8 @@ static int _query_lock_lv(struct cmd_context *cmd, struct volume_group *vg,
 		log_error("Lock query failed for LV %s/%s", vg->name, lv_name);
 		return 0;
 	} else {
-		ret = (result < 0) ? 0 : 1;
+		/* ENOENT => The lv was not active/locked. */
+		ret = (result < 0 && (result != -ENOENT)) ? 0 : 1;
 	}
 
 	if (!ret)
@@ -2110,11 +2108,7 @@ static int _query_lock_lv(struct cmd_context *cmd, struct volume_group *vg,
 
 	daemon_reply_destroy(reply);
 
-	/* The lv was not active/locked. */
-	if (result == -ENOENT)
-		return 1;
-
-	return 1;
+	return ret;
 }
 
 /*
@@ -2320,6 +2314,49 @@ static int _lockd_lv_thin(struct cmd_context *cmd, struct logical_volume *lv,
 			     pool_lv->lock_args, def_mode, flags);
 }
 
+static int _lockd_lv_vdo(struct cmd_context *cmd, struct logical_volume *lv,
+			 const char *def_mode, uint32_t flags)
+{
+	struct logical_volume *pool_lv = NULL;
+
+	if (lv_is_vdo(lv)) {
+		if (first_seg(lv))
+			pool_lv = seg_lv(first_seg(lv), 0);
+
+	} else if (lv_is_vdo_pool(lv)) {
+		pool_lv = lv;
+
+	} else if (lv_is_vdo_pool_data(lv)) {
+		return 1;
+
+	} else {
+		/* This should not happen AFAIK. */
+		log_error("Lock on incorrect vdo lv type %s/%s",
+			  lv->vg->name, lv->name);
+		return 0;
+	}
+
+	if (!pool_lv) {
+		/* This happens in lvremove where it's harmless. */
+		log_debug("No vdo pool for %s/%s", lv->vg->name, lv->name);
+		return 0;
+	}
+
+	/*
+	 * Locking a locked lv (pool in this case) is a no-op.
+	 * Unlock when the pool is no longer active.
+	 */
+
+	if (def_mode && !strcmp(def_mode, "un") &&
+	    lv_is_vdo_pool(pool_lv) && lv_is_active(lv_lock_holder(pool_lv)))
+		return 1;
+
+	flags |= LDLV_MODE_NO_SH;
+
+	return lockd_lv_name(cmd, pool_lv->vg, pool_lv->name, &pool_lv->lvid.id[1],
+			     pool_lv->lock_args, def_mode, flags);
+}
+
 /*
  * If the VG has no lock_type, then this function can return immediately.
  * The LV itself may have no lock (NULL lv->lock_args), but the lock request
@@ -2361,6 +2398,9 @@ int lockd_lv(struct cmd_context *cmd, struct logical_volume *lv,
 	if (lv_is_thin_type(lv))
 		return _lockd_lv_thin(cmd, lv, def_mode, flags);
 
+	if (lv_is_vdo_type(lv))
+		return _lockd_lv_vdo(cmd, lv, def_mode, flags);
+
 	/*
 	 * An LV with NULL lock_args does not have a lock of its own.
 	 */
@@ -2383,6 +2423,7 @@ int lockd_lv(struct cmd_context *cmd, struct logical_volume *lv,
 	    lv_is_thin_type(lv) ||
 	    lv_is_mirror_type(lv) ||
 	    lv_is_raid_type(lv) ||
+	    lv_is_vdo_type(lv) ||
 	    lv_is_cache_type(lv)) {
 		flags |= LDLV_MODE_NO_SH;
 	}
@@ -2682,7 +2723,7 @@ int lockd_init_lv(struct cmd_context *cmd, struct volume_group *vg, struct logic
 			log_error("Failed to find origin LV %s/%s", vg->name, lp->origin_name);
 			return 0;
 		}
-		if (!lockd_lv(cmd, origin_lv, "ex", LDLV_PERSISTENT)) {
+		if (!lockd_lv(cmd, origin_lv, "ex", 0)) {
 			log_error("Failed to lock origin LV %s/%s", vg->name, lp->origin_name);
 			return 0;
 		}
@@ -2732,6 +2773,27 @@ int lockd_init_lv(struct cmd_context *cmd, struct volume_group *vg, struct logic
 			return 0;
 		}
 
+	} else if (seg_is_vdo(lp)) {
+		struct lv_list *lvl;
+
+		/*
+		 * A vdo lv is being created in a vdo pool.  The vdo lv does
+		 * not have its own lock, the lock of the vdo pool is used, and
+		 * the vdo pool needs to be locked to create a vdo lv in it.
+		 */
+
+		if (!(lvl = find_lv_in_vg(vg, lp->pool_name))) {
+			log_error("Failed to find vdo pool %s/%s", vg->name, lp->pool_name);
+			return 0;
+		}
+
+		if (!lockd_lv(cmd, lvl->lv, "ex", LDLV_PERSISTENT)) {
+			log_error("Failed to lock vdo pool %s/%s", vg->name, lp->pool_name);
+			return 0;
+		}
+		lv->lock_args = NULL;
+		return 1;
+
 	} else {
 		/* Creating a normal lv. */
 		/* lv_name_lock = lv_name; */
@@ -2971,6 +3033,12 @@ int lockd_lv_uses_lock(struct logical_volume *lv)
 	if (lv_is_pool_metadata_spare(lv))
 		return 0;
 
+	if (lv_is_vdo(lv))
+		return 0;
+
+	if (lv_is_vdo_pool_data(lv))
+		return 0;
+
 	if (lv_is_cache_vol(lv))
 		return 0;