locking: allow using global lock for scanning

When vg metadata consumes a major percentage of the metadata area,
acquire the global lock prior to label_scan.  Many commands
already acquire the global lock prior to label_scan, but
VG-specific commands may not otherwise use the global lock.

This attempts to avoid the rare situation in which the metadata is
large enough to wrap around the metadata area and invalidate the
metadata location information that a single command gathered from
label_scan.  If this wrapping with large sizes occurs, the metadata
locations seen during label scan may be overwritten before the
same command is able to use them for vg_read(), causing vg_read
to see invalid metadata and the command to fail.

A large number of concurrent lvm commands is also a factor that
can lead to this problem due to longer delays between label_scan
and vg_read.

This problem can be avoided if all commands acquire the global lock
prior to label scan, and hold it across all the vg_read() calls.
This ensures that the results from label scan are unchanging during
label scan and remain valid for use in vg_read.
Commands modifying vg metadata take the global lock ex, and those
only reading vg metadata use sh.

This extra use of the global lock is usually unnecessary, so lvm
automatically detects when the extra locking may be needed before
starting to use it.  When vg metadata is a large enough percentage
of the total metadata area, lvm begins doing extra locking.
Currently this is 25% (could be configurable.)

When one command sees this threshold has been reached, it creates
the file /run/lvm/scan_lock_global.  When subsequent commands see
this file exists, then will acquire the global lock prior to their
label_scan.  When metadata goes below the threshold, the temp file
is removed, and commands no longer do the extra locking.

.gitignore

@@ -30,14 +30,19 @@ make.tmpl
 /config.log
 /config.status
 /configure.scan
-/cscope.out
+/cscope.*
 /html/
+/python/
 /reports/
 /tags
 /tmp/
 
 coverity/coverity_model.xml
 
+# gcov files:
+*.gcda
+*.gcno
+
 tools/man-generator
 tools/man-generator.c
 

Makefile.in

@@ -18,7 +18,7 @@ top_builddir = @top_builddir@
 abs_top_builddir = @abs_top_builddir@
 abs_top_srcdir = @abs_top_srcdir@
 
-SUBDIRS = conf daemons include lib libdaemon libdm man scripts tools
+SUBDIRS = libdm conf daemons include lib libdaemon man scripts tools
 
 ifeq ("@UDEV_RULES@", "yes")
   SUBDIRS += udev
@@ -47,8 +47,6 @@ include $(top_srcdir)/base/Makefile
 include $(top_srcdir)/device_mapper/Makefile
 include $(top_srcdir)/test/unit/Makefile
 
-libdm: include
-libdaemon: include
 lib: libdaemon $(BASE_TARGET) $(DEVICE_MAPPER_TARGET)
 daemons: lib libdaemon tools
 scripts: lib
@@ -56,16 +54,13 @@ tools: lib libdaemon
 po: tools daemons
 man: tools
 all_man: tools
-scripts: libdm
 test: tools daemons
 unit-test  run-unit-test: test
 
-lib.device-mapper: include.device-mapper
-libdm.device-mapper: include.device-mapper
 daemons.device-mapper: libdm.device-mapper
 tools.device-mapper: libdm.device-mapper
-scripts.device-mapper: include.device-mapper
 device-mapper: tools.device-mapper daemons.device-mapper man.device-mapper
+device_mapper: device-mapper
 
 ifeq ("@INTL@", "yes")
 lib.pofile: include.pofile
@@ -81,9 +76,10 @@ daemons.cflow: tools.cflow
 cflow: include.cflow
 endif
 
+CSCOPE_DIRS = base daemons device_mapper include lib libdaemon scripts tools libdm test
 ifneq ("@CSCOPE_CMD@", "")
 cscope.out:
-	@CSCOPE_CMD@ -b -R -s$(top_srcdir)
+	@CSCOPE_CMD@ -b -R $(patsubst %,-s%,$(addprefix $(srcdir)/,$(CSCOPE_DIRS)))
 all: cscope.out
 endif
 DISTCLEAN_TARGETS += cscope.out
@@ -116,11 +112,11 @@ rpm: dist
 	$(LN_S) -f $(abs_top_srcdir)/spec/packages.inc $(rpmbuilddir)/SOURCES
 	DM_VER=$$(cut -d- -f1 $(top_srcdir)/VERSION_DM);\
 	GIT_VER=$$(cd $(top_srcdir); git describe | cut -d- --output-delimiter=. -f2,3 || echo 0);\
-	sed -e "s,\(device_mapper_version\) [0-9.]*$$,\1 $$DM_VER," \
+	$(SED) -e "s,\(device_mapper_version\) [0-9.]*$$,\1 $$DM_VER," \
 	    -e "s,^\(Version:[^0-9%]*\)[0-9.]*$$,\1 $(LVM_VER)," \
 	    -e "s,^\(Release:[^0-9%]*\)[0-9.]\+,\1 $$GIT_VER," \
 	    $(top_srcdir)/spec/source.inc >$(rpmbuilddir)/SOURCES/source.inc
-	rpmbuild -v --define "_topdir $(rpmbuilddir)" -ba $(top_srcdir)/spec/lvm2.spec
+	V=$(V) rpmbuild -v --define "_topdir $(rpmbuilddir)" -ba $(top_srcdir)/spec/lvm2.spec
 
 generate: conf.generate man.generate
 	$(MAKE) -C conf generate
@@ -154,6 +150,31 @@ install_all_man:
 install_tmpfiles_configuration:
 	$(MAKE) -C scripts install_tmpfiles_configuration
 
+help:
+	@echo -e "\nAvailable targets:"
+	@echo "  all			Default target."
+	@echo "  all_man		Build all man pages with generators."
+	@echo "  clean			Remove all compile files."
+	@echo "  device-mapper		Device mapper part of lvm2."
+	@echo "  dist			Generate distributable file."
+	@echo "  distclean		Remove all build files."
+	@echo "  generate		Generate man pages for sources."
+	@echo "  help			Display callable targets."
+	@echo "  install		Install all files."
+	@echo "  install_all_man	Install all man pages."
+	@echo "  install_cluster	Install cmirrord."
+	@echo "  install_device-mapper	Install device mapper files."
+	@echo "  install_initscripts	Install initialization scripts."
+	@echo "  install_lvm2		Install lvm2 files."
+	@echo "  install_systemd_units	Install systemd units."
+	@echo "  lcov			Generate lcov output."
+	@echo "  lcov-dated		Generate lcov with timedate suffix."
+	@echo "  lcov-reset		Reset lcov counters"
+	@echo "  man			Build man pages."
+	@echo "  rpm			Build rpm."
+	@echo "  run-unit-test		Run unit tests."
+	@echo "  tags			Generate c/etags."
+
 ifneq ("$(LCOV)", "")
 .PHONY: lcov-reset lcov lcov-dated
 
@@ -183,8 +204,8 @@ endif
 ifneq ($(shell which ctags 2>/dev/null),)
 .PHONY: tags
 tags:
-	test -z "$(shell find $(top_srcdir) -type f -name '*.[ch]' -newer tags 2>/dev/null | head -1)" || $(RM) tags
-	test -f tags || find $(top_srcdir) -maxdepth 5 -type f -name '*.[ch]' -exec ctags -a '{}' +
+	test -z "$(shell find $(addprefix $(top_srcdir)/,$(CSCOPE_DIRS)) -type f -name '*.[ch]' -newer tags 2>/dev/null | head -1)" || $(RM) tags
+	test -f tags || find $(addprefix $(top_srcdir)/,$(CSCOPE_DIRS)) -maxdepth 5 -type f -name '*.[ch]' -exec ctags -a '{}' +
 
 CLEAN_TARGETS += tags
 endif

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 @@
-2.03.10(2)-git (2020-03-26)
+2.03.13(2)-git (2021-05-07)

VERSION_DM

@@ -1 +1 @@
-1.02.173-git (2020-03-26)
+1.02.179-git (2021-05-07)

WHATS_NEW

@@ -1,5 +1,118 @@
-Version 2.03.10 - 
-=================================
+Version 2.03.13 - 
+===============================
+  Simplified handling of archive() and backup() internal calls.
+  Fix load of kvdo target when it is not present in memory (2.03.12).
+
+Version 2.03.12 - 07th May 2021
+===============================
+  Allow attaching cache to thin data volume.
+  Fix memleak when generating list of outdated pvs.
+  Better hyphenation usage in man pages.
+  Replace use of deprecated security_context_t with char*.
+  Configure supports AIO_LIBS and AIO_CFLAGS.
+  Improve build process for static builds.
+  New --setautoactivation option to modify LV or VG auto activation.
+  New metadata based autoactivation property for LVs and VGs.
+  Improve signal handling with lvmpolld.
+  Signal handler can interrupt command also for SIGTERM.
+  Lvreduce --yes support.
+  Add configure option --with/out-symvers for non-glibc builds.
+  Report error when the filesystem is missing on fsadm resized volume.
+  Handle better blockdev with --getsize64 support for fsadm.
+  Do not include editline/history.h when using editline library.
+  Support error and zero segtype for thin-pool data for testing.
+  Support mixed extension for striped, error and zero segtypes.
+  Support resize also for stacked virtual volumes.
+  Skip dm-zero devices just like with dm-error target.
+  Reduce ioctl() calls when checking target status.
+  Merge polling does not fail, when LV is found to be already merged.
+  Poll volumes with at least 100ms delays.
+  Do not flush dm cache when cached LV is going to be removed.
+  New lvmlockctl_kill_command configuration option.
+  Support interruption while waiting on device close before deactivation.
+  Flush thin-pool messages before removing more thin volumes.
+  Improve hash function with less collisions and make it faster.
+  Reduce ioctl count when deactivating volumes.
+  Reduce number of metadata parsing.
+  Enhance performance of lvremove and vgremove commands.
+  Support interruption when taking archive and backup.
+  Accelerate large lvremoves.
+  Speedup search for cached device nodes.
+  Speedup command initialization.
+  Add devices file feature, off by default for now.
+  Support extension of writecached volumes.
+  Fix problem with unbound variable usage within fsadm.
+  Fix IMSM MD RAID detection on 4k devices.
+  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 conversion and allocation of pool metadata.
+  Support thin pool metadata 15.88GiB, adds 64MiB, thin_pool_crop_metadata=0.
+  Enhance lvdisplay to report raid available/partial.
+  Support online rename of VDO pools.
+  Improve 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).
 
@@ -153,7 +266,6 @@ Version 2.03.00 - 10th October 2018
   Remove clvmd
   Remove lvmlib (api)
   Remove lvmetad
-  lvconvert: provide possible layouts between linear and striped/raid
   Use versionsort to fix archive file expiry beyond 100000 files.
 
 Version 2.02.178-rc1 - 24th May 2018
@@ -1673,7 +1785,7 @@ Version 2.02.105 - 20th January 2014
   Allow lvmetad to reuse stale socket.
   Only unlink lvmetad socket on error if created by the same process.
   Append missing newline to lvmetad missing socket path error message.
-  Check for non-zero aligment in _text_pv_add_metadata_area() to not div by 0.
+  Check for non-zero alignment in _text_pv_add_metadata_area() to not div by 0.
   Add allocation/use_blkid_wiping to lvm.conf to enable blkid wiping.
   Enable blkid_wiping by default if the blkid library is present.
   Add configure --disable-blkid_wiping to disable libblkid signature detection.

WHATS_NEW_DM

@@ -1,9 +1,22 @@
-Version 1.02.173 - 
-==================================
+Version 1.02.179 - 
+================================
+
+Version 1.02.177 - 07th May 2021
+================================
+  Configure proceeds without libaio to allow build of device-mapper only.
+  Fix symbol versioning build with -O2 -flto.
+  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.
 
@@ -547,7 +560,7 @@ Version 1.02.86 - 23rd June 2014
   Add DM_REPORT_FIELD_TYPE_STRING_LIST: separate string and string list fields.
   Add dm_str_list to libdevmapper for string list type definition and its reuse.
   Add dmsetup -S/--select to define selection criteria for dmsetup reports.
-  Add dm_report_init_with_selection to intialize report with selection criteria.
+  Add dm_report_init_with_selection to initialize report with selection criteria.
   Add DM_REPORT_FIELD_TYPE_SIZE: separate number and size reporting fields.
   Use RemoveOnStop for dm-event.socket systemd unit.
   Document env var 'DM_DEFAULT_NAME_MANGLING_MODE' in dmsetup man page.

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

@@ -22,17 +22,26 @@ struct dm_hash_node {
 	void *data;
 	unsigned data_len;
 	unsigned keylen;
-	char key[0];
+	unsigned hash;
+	char key[];
 };
 
 struct dm_hash_table {
 	unsigned num_nodes;
-	unsigned num_slots;
+	unsigned num_hint;
+	unsigned mask_slots;    /* (slots - 1) -> used as hash mask */
+	unsigned collisions;    /* Collissions of hash keys */
+	unsigned search;        /* How many keys were searched */
+	unsigned found;         /* How many nodes were found */
+	unsigned same_hash;     /* Was there a colision with same masked hash and len ? */
 	struct dm_hash_node **slots;
 };
 
-/* Permutation of the Integers 0 through 255 */
-static unsigned char _nums[] = {
+#if 0 /* TO BE REMOVED */
+static unsigned _hash(const void *key, unsigned len)
+{
+	/* Permutation of the Integers 0 through 255 */
+	static unsigned char _nums[] = {
 	1, 14, 110, 25, 97, 174, 132, 119, 138, 170, 125, 118, 27, 233, 140, 51,
 	87, 197, 177, 107, 234, 169, 56, 68, 30, 7, 173, 73, 188, 40, 36, 65,
 	49, 213, 104, 190, 57, 211, 148, 223, 48, 115, 15, 2, 67, 186, 210, 28,
@@ -57,29 +66,16 @@ static unsigned char _nums[] = {
 	44, 38, 31, 149, 135, 0, 216, 52, 63, 23, 37, 69, 39, 117, 146, 184,
 	163, 200, 222, 235, 248, 243, 219, 10, 152, 131, 123, 229, 203, 76, 120,
 	209
-};
+	};
 
-static struct dm_hash_node *_create_node(const char *str, unsigned len)
-{
-	struct dm_hash_node *n = malloc(sizeof(*n) + len);
-
-	if (n) {
-		memcpy(n->key, str, len);
-		n->keylen = len;
-	}
-
-	return n;
-}
-
-static unsigned long _hash(const char *str, unsigned len)
-{
-	unsigned long h = 0, g;
+	const uint8_t *str = key;
+	unsigned h = 0, g;
 	unsigned i;
 
 	for (i = 0; i < len; i++) {
 		h <<= 4;
-		h += _nums[(unsigned char) *str++];
-		g = h & ((unsigned long) 0xf << 16u);
+		h += _nums[*str++];
+		g = h & ((unsigned) 0xf << 16u);
 		if (g) {
 			h ^= g >> 16u;
 			h ^= g >> 5u;
@@ -89,30 +85,99 @@ static unsigned long _hash(const char *str, unsigned len)
 	return h;
 }
 
+/* In-kernel DM hashing, still lots of collisions */
+static unsigned _hash_in_kernel(const char *key, unsigned len)
+{
+	const unsigned char *str = (unsigned char *)key;
+	const unsigned hash_mult = 2654435387U;
+	unsigned hash = 0, i;
+
+	for (i = 0; i < len; ++i)
+		hash = (hash + str[i]) * hash_mult;
+
+	return hash;
+}
+#endif
+
+#undef get16bits
+#if (defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__)))
+#define get16bits(d) (*((const uint16_t *) (d)))
+#endif
+
+#if !defined (get16bits)
+#define get16bits(d) ((((uint32_t)(((const uint8_t *)(d))[1])) << 8)\
+                       +(uint32_t)(((const uint8_t *)(d))[0]) )
+#endif
+
+/*
+ * Adapted Bob Jenkins hash to read by 2 bytes if possible.
+ * https://secure.wikimedia.org/wikipedia/en/wiki/Jenkins_hash_function
+ *
+ * Reduces amount of hash collisions
+ */
+static unsigned _hash(const void *key, unsigned len)
+{
+	const uint8_t *str = (uint8_t*) key;
+	unsigned hash = 0, i;
+	unsigned sz = len / 2;
+
+	for(i = 0; i < sz; ++i) {
+		hash += get16bits(str + 2 * i);
+		hash += (hash << 10);
+		hash ^= (hash >> 6);
+	}
+
+	if (len & 1) {
+		hash += str[len - 1];
+		hash += (hash << 10);
+		hash ^= (hash >> 6);
+	}
+
+	hash += (hash << 3);
+	hash ^= (hash >> 11);
+	hash += (hash << 15);
+
+	return hash;
+}
+
+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, key, len);
+		n->keylen = len;
+	}
+
+	return n;
+}
+
 struct dm_hash_table *dm_hash_create(unsigned size_hint)
 {
 	size_t len;
 	unsigned new_size = 16u;
 	struct dm_hash_table *hc = zalloc(sizeof(*hc));
 
-	if (!hc)
-		return_0;
+	if (!hc) {
+		log_error("Failed to allocate memory for hash.");
+		return 0;
+	}
+
+	hc->num_hint = size_hint;
 
 	/* round size hint up to a power of two */
 	while (new_size < size_hint)
 		new_size = new_size << 1;
 
-	hc->num_slots = new_size;
+	hc->mask_slots = new_size - 1;
 	len = sizeof(*(hc->slots)) * new_size;
-	if (!(hc->slots = zalloc(len)))
-		goto_bad;
+	if (!(hc->slots = zalloc(len))) {
+		free(hc);
+		log_error("Failed to allocate slots for hash.");
+		return 0;
+	}
 
 	return hc;
-
-      bad:
-	free(hc->slots);
-	free(hc);
-	return 0;
 }
 
 static void _free_nodes(struct dm_hash_table *t)
@@ -120,7 +185,16 @@ static void _free_nodes(struct dm_hash_table *t)
 	struct dm_hash_node *c, *n;
 	unsigned i;
 
-	for (i = 0; i < t->num_slots; i++)
+#ifdef DEBUG
+	log_debug("Free hash hint:%d slots:%d nodes:%d (s:%d f:%d c:%d h:%d)",
+		  t->num_hint, t->mask_slots + 1, t->num_nodes,
+		  t->search, t->found, t->collisions, t->same_hash);
+#endif
+
+	if (!t->num_nodes)
+		return;
+
+	for (i = 0; i <= t->mask_slots; i++)
 		for (c = t->slots[i]; c; c = n) {
 			n = c->next;
 			free(c);
@@ -134,23 +208,32 @@ void dm_hash_destroy(struct dm_hash_table *t)
 	free(t);
 }
 
-static struct dm_hash_node **_find(struct dm_hash_table *t, const void *key,
-				   uint32_t len)
+static struct dm_hash_node **_findh(struct dm_hash_table *t, const void *key,
+				    uint32_t len, unsigned hash)
 {
-	unsigned h = _hash(key, len) & (t->num_slots - 1);
 	struct dm_hash_node **c;
 
-	for (c = &t->slots[h]; *c; c = &((*c)->next)) {
-		if ((*c)->keylen != len)
-			continue;
-
-		if (!memcmp(key, (*c)->key, len))
-			break;
+	++t->search;
+	for (c = &t->slots[hash & t->mask_slots]; *c; c = &((*c)->next)) {
+		if ((*c)->keylen == len && (*c)->hash == hash) {
+			if (!memcmp(key, (*c)->key, len)) {
+				++t->found;
+				break;
+			}
+			++t->same_hash;
+		}
+		++t->collisions;
 	}
 
 	return c;
 }
 
+static struct dm_hash_node **_find(struct dm_hash_table *t, const void *key,
+				   uint32_t len)
+{
+	return _findh(t, key, len, _hash(key, len));
+}
+
 void *dm_hash_lookup_binary(struct dm_hash_table *t, const void *key,
 			    uint32_t len)
 {
@@ -162,7 +245,8 @@ void *dm_hash_lookup_binary(struct dm_hash_table *t, const void *key,
 int dm_hash_insert_binary(struct dm_hash_table *t, const void *key,
 			  uint32_t len, void *data)
 {
-	struct dm_hash_node **c = _find(t, key, len);
+	unsigned hash = _hash(key, len);
+	struct dm_hash_node **c = _findh(t, key, len, hash);
 
 	if (*c)
 		(*c)->data = data;
@@ -173,6 +257,7 @@ int dm_hash_insert_binary(struct dm_hash_table *t, const void *key,
 			return 0;
 
 		n->data = data;
+		n->hash = hash;
 		n->next = 0;
 		*c = n;
 		t->num_nodes++;
@@ -216,7 +301,7 @@ static struct dm_hash_node **_find_str_with_val(struct dm_hash_table *t,
 	struct dm_hash_node **c;
 	unsigned h;
        
-	h = _hash(key, len) & (t->num_slots - 1);
+	h = _hash(key, len) & t->mask_slots;
 
 	for (c = &t->slots[h]; *c; c = &((*c)->next)) {
 		if ((*c)->keylen != len)
@@ -247,7 +332,7 @@ int dm_hash_insert_allow_multiple(struct dm_hash_table *t, const char *key,
 	n->data = (void *)val;
 	n->data_len = val_len;
 
-	h = _hash(key, len) & (t->num_slots - 1);
+	h = _hash(key, len) & t->mask_slots;
 
 	first = t->slots[h];
 
@@ -315,7 +400,7 @@ void *dm_hash_lookup_with_count(struct dm_hash_table *t, const char *key, int *c
 
 	*count = 0;
 
-	h = _hash(key, len) & (t->num_slots - 1);
+	h = _hash(key, len) & t->mask_slots;
 
 	for (c = &t->slots[h]; *c; c = &((*c)->next)) {
 		if ((*c)->keylen != len)
@@ -344,7 +429,7 @@ void dm_hash_iter(struct dm_hash_table *t, dm_hash_iterate_fn f)
 	struct dm_hash_node *c, *n;
 	unsigned i;
 
-	for (i = 0; i < t->num_slots; i++)
+	for (i = 0; i <= t->mask_slots; i++)
 		for (c = t->slots[i]; c; c = n) {
 			n = c->next;
 			f(c->data);
@@ -354,8 +439,8 @@ void dm_hash_iter(struct dm_hash_table *t, dm_hash_iterate_fn f)
 void dm_hash_wipe(struct dm_hash_table *t)
 {
 	_free_nodes(t);
-	memset(t->slots, 0, sizeof(struct dm_hash_node *) * t->num_slots);
-	t->num_nodes = 0u;
+	memset(t->slots, 0, sizeof(struct dm_hash_node *) * (t->mask_slots + 1));
+	t->num_nodes = t->collisions = t->search = t->same_hash = 0u;
 }
 
 char *dm_hash_get_key(struct dm_hash_table *t __attribute__((unused)),
@@ -375,7 +460,7 @@ static struct dm_hash_node *_next_slot(struct dm_hash_table *t, unsigned s)
 	struct dm_hash_node *c = NULL;
 	unsigned i;
 
-	for (i = s; i < t->num_slots && !c; i++)
+	for (i = s; i <= t->mask_slots && !c; i++)
 		c = t->slots[i];
 
 	return c;
@@ -388,7 +473,5 @@ struct dm_hash_node *dm_hash_get_first(struct dm_hash_table *t)
 
 struct dm_hash_node *dm_hash_get_next(struct dm_hash_table *t, struct dm_hash_node *n)
 {
-	unsigned h = _hash(n->key, n->keylen) & (t->num_slots - 1);
-
-	return n->next ? n->next : _next_slot(t, h + 1);
+	return n->next ? n->next : _next_slot(t, (n->hash & t->mask_slots) + 1);
 }

base/data-struct/list.h

@@ -1,7 +1,7 @@
 #ifndef BASE_DATA_STRUCT_LIST_H
 #define BASE_DATA_STRUCT_LIST_H
 
-#include <stddef.h> /* offsetof */
+#include "base/memory/container_of.h"
 
 //----------------------------------------------------------------
 
@@ -100,7 +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) - offsetof(t, head)))
+    container_of(v, t, head)
 
 /*
  * Given the address v of an instance of 'struct dm_list list' contained in

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

@@ -18,7 +18,7 @@
 //----------------------------------------------------------------
 
 #define container_of(v, t, head) \
-    ((t *)((const char *)(v) - offsetof(t, 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"
 
@@ -118,12 +118,44 @@ 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/use_devicesfile.
+	# Enable or disable the use of a devices file.
+	# When enabled, lvm will only use devices that
+	# are lised in the devices file. A devices file will
+	# be used, regardless of this setting, when the --devicesfile
+	# option is set to a specific file name.
+	# This configuration option has an automatic default value.
+	# use_devicesfile = 0
+
+	# Configuration option devices/devicesfile.
+	# The name of the system devices file, listing devices that LVM should use.
+	# This should not be used to select a non-system devices file.
+	# The --devicesfile option is intended for alternative devices files.
+	# This configuration option has an automatic default value.
+	# devicesfile = "system.devices"
+
+	# Configuration option devices/search_for_devnames.
+	# Look outside of the devices file for missing devname entries.
+	# A devname entry is used for a device that does not have a stable
+	# device id, e.g. wwid, so the unstable device name is used as
+	# the device id. After reboot, or if the device is reattached,
+	# the device name may change, in which case lvm will not find
+	# the expected PV on the device listed in the devices file.
+	# This setting controls whether lvm will search other devices,
+	# outside the devices file, to look for the missing PV on a
+	# renamed device. If "none", lvm will not look at other devices,
+	# and the PV may appear to be missing. If "auto", lvm will look
+	# at other devices, but only those that are likely to have the PV.
+	# If "all", lvm will look at all devices on the system.
+	# This configuration option has an automatic default value.
+	# search_for_devnames = "auto"
+
 	# Configuration option devices/filter.
 	# Limit the block devices that are used by LVM commands.
 	# This is a list of regular expressions used to accept or reject block
@@ -139,7 +171,7 @@ 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 +183,7 @@ 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 +201,10 @@ 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 +246,7 @@ 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 +257,7 @@ 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"
 
@@ -238,16 +270,16 @@ devices {
 	# Configuration option devices/md_chunk_alignment.
 	# Align the start of a PV data area with md device's stripe-width.
 	# This applies if a PV is placed directly on an md device.
-	# default_data_alignment will be overriden if it is not aligned
+	# default_data_alignment will be overridden if it is not aligned
 	# with the value detected for this setting.
-	# This setting is overriden by data_alignment_detection,
+	# This setting is overridden by data_alignment_detection,
 	# data_alignment, and the --dataalignment option.
 	md_chunk_alignment = 1
 
 	# Configuration option devices/default_data_alignment.
 	# Align the start of a PV data area with this number of MiB.
 	# Set to 1 for 1MiB, 2 for 2MiB, etc. Set to 0 to disable.
-	# This setting is overriden by data_alignment and the --dataalignment
+	# This setting is overridden by data_alignment and the --dataalignment
 	# option.
 	# This configuration option has an automatic default value.
 	# default_data_alignment = 1
@@ -261,9 +293,9 @@ devices {
 	# preferred unit of receiving I/O, e.g. MD stripe width.
 	# minimum_io_size is used if optimal_io_size is undefined (0).
 	# If md_chunk_alignment is enabled, that detects the optimal_io_size.
-	# default_data_alignment and md_chunk_alignment will be overriden
+	# default_data_alignment and md_chunk_alignment will be overridden
 	# if they are not aligned with the value detected for this setting.
-	# This setting is overriden by data_alignment and the --dataalignment
+	# This setting is overridden by data_alignment and the --dataalignment
 	# option.
 	data_alignment_detection = 1
 
@@ -272,7 +304,7 @@ devices {
 	# When non-zero, this setting overrides default_data_alignment.
 	# Set to 0 to disable, in which case default_data_alignment
 	# is used to align the first PE in units of MiB.
-	# This setting is overriden by the --dataalignment option.
+	# This setting is overridden by the --dataalignment option.
 	data_alignment = 0
 
 	# Configuration option devices/data_alignment_offset_detection.
@@ -283,7 +315,7 @@ devices {
 	# partitioning will have an alignment_offset of 3584 bytes (sector 7
 	# is the lowest aligned logical block, the 4KiB sectors start at
 	# LBA -1, and consequently sector 63 is aligned on a 4KiB boundary).
-	# This setting is overriden by the --dataalignmentoffset option.
+	# This setting is overridden by the --dataalignmentoffset option.
 	data_alignment_offset_detection = 1
 
 	# Configuration option devices/ignore_suspended_devices.
@@ -367,7 +399,7 @@ 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 +407,7 @@ 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 +461,30 @@ 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 +521,16 @@ 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 +540,18 @@ 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 +563,15 @@ 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 +976,7 @@ 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 +1000,7 @@ 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 +1020,19 @@ 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 +1040,7 @@ 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 +1050,7 @@ 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 +1058,7 @@ 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 +1070,7 @@ 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.
@@ -1038,13 +1084,17 @@ global {
 
 	# Configuration option global/event_activation.
 	# Activate LVs based on system-generated device events.
-	# When a device appears on the system, a system-generated event runs
-	# the pvscan command to activate LVs if the new PV completes the VG.
-	# Use auto_activation_volume_list to select which LVs should be
-	# 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
+	# When a PV appears on the system, a system-generated uevent triggers
+	# the lvm2-pvscan service which runs the pvscan --cache -aay command.
+	# If the new PV completes a VG, pvscan autoactivates LVs in the VG.
+	# When event_activation is disabled, the lvm2-activation services are
+	# generated and run at fixed points during system startup.  These
+	# services run vgchange -aay to autoactivate LVs in VGs that happen
+	# to be present at that point in time.
+	# See the --setautoactivation option or the auto_activation_volume_list
+	# setting to configure autoactivation for specific VGs or LVs.
+	# 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.
@@ -1075,6 +1125,17 @@ global {
 	# This configuration option has an automatic default value.
 	# sanlock_lv_extend = 256
 
+	# Configuration option global/lvmlockctl_kill_command.
+	# The command that lvmlockctl --kill should use to force LVs offline.
+	# The lvmlockctl --kill command is run when a shared VG has lost
+	# access to locks (e.g. when sanlock has lost access to storage.)
+	# An empty string means that there will be no automatic attempt by
+	# lvmlockctl --kill to forcibly shut down LVs in the VG, and the user
+	# can manually intervene as described in lvmlockd(8).
+	# The VG name will be appended to the command specified here.
+	# This configuration option has an automatic default value.
+	# lvmlockctl_kill_command = ""
+
 	# Configuration option global/thin_check_executable.
 	# The full path to the thin_check command.
 	# LVM uses this command to check that a thin metadata device is in a
@@ -1121,20 +1182,20 @@ 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 +1247,16 @@ 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 +1269,7 @@ 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 +1286,7 @@ 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.
@@ -1267,7 +1338,7 @@ activation {
 
 	# Configuration option activation/udev_sync.
 	# Use udev notifications to synchronize udev and LVM.
-	# The --nodevsync option overrides this setting.
+	# The --noudevsync option overrides this setting.
 	# When disabled, LVM commands will not wait for notifications from
 	# udev, but continue irrespective of any possible udev processing in
 	# the background. Only use this if udev is not running or has rules
@@ -1288,7 +1359,8 @@ 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 +1385,34 @@ 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.
@@ -1350,30 +1426,30 @@ 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.
-	# Only LVs selected by this list are auto-activated.
-	# This list works like volume_list, but it is used only by
-	# auto-activation commands. It does not apply to direct activation
-	# commands. If this list is defined, an LV is only auto-activated
-	# if it matches an entry in this list. If this list is undefined, it
-	# imposes no limits on LV auto-activation (all are allowed.) If this
-	# list is defined and empty, i.e. "[]", then no LVs are selected for
-	# auto-activation. An LV that is selected by this list for
-	# auto-activation, must also be selected by volume_list (if defined)
-	# before it is activated. Auto-activation is an activation command that
-	# includes the 'a' argument: --activate ay or -a ay. The 'a' (auto)
-	# argument for auto-activation is meant to be used by activation
-	# commands that are run automatically by the system, as opposed to LVM
-	# 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.
-	# 
+	# A list of VGs or LVs that should be autoactivated.
+	# Autoactivation is an activation command run with -aay,
+	# i.e. vgchange -aay, lvchange -aay, or pvscan --cache -aay.
+	# When this list is defined, an autoactivation command will only
+	# activate LVs included in the list. If this list is undefined,
+	# it has no effect. If this list is defined but empty, then no
+	# LVs will be autoactivated. LVs can be included in the list by
+	# LV name, VG name (applies to all LVs in the VG), or tag name.
+	# VGs and LVs can also have an autoactivation property set in
+	# metadata, see --setautoactivation. LVs included in this list
+	# will not be autoactivated if the VG or LV autoactivation
+	# property is disabled (see vgs or lvs "-o autoactivation").
+	# The volume_list setting and the "activation skip" property
+	# also apply to autoactivation.
+	# The -aay option is meant to be used by activation commands that
+	# are run automatically by the system, e.g. from systemd services.
+	#
 	# Accepted values:
 	#   vgname
 	#     The VG name is matched exactly and selects all LVs in the VG.
@@ -1387,10 +1463,10 @@ 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 +1475,7 @@ 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 +1489,10 @@ 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 +1515,15 @@ 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 +1533,7 @@ 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 +1544,7 @@ 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 +1556,7 @@ 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 +1581,7 @@ 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 +1596,26 @@ 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 +1624,26 @@ 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 +1652,21 @@ 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 +1685,10 @@ 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 +1696,8 @@ 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 +1712,8 @@ 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 +1729,7 @@ 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 +1744,7 @@ 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 +1792,7 @@ 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 +1802,7 @@ 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 +1952,7 @@ 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 +2075,7 @@ 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 +2269,8 @@ 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 +2281,16 @@ 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 +2344,12 @@ 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

@@ -640,6 +640,7 @@ LVMLOCKD_PIDFILE
 LVMPOLLD_PIDFILE
 DMEVENTD_PIDFILE
 WRITE_INSTALL
+WRITECACHE
 VDO_LIB
 VDO_INCLUDE
 VDO
@@ -702,6 +703,7 @@ LIB_SUFFIX
 LDDEPS
 JOBS
 INTL
+INTEGRITY
 HAVE_VALGRIND
 HAVE_REALTIME
 HAVE_LIBDL
@@ -745,6 +747,7 @@ BUILD_DMFILEMAPD
 BUILD_LOCKDDLM_CONTROL
 BUILD_LOCKDDLM
 BUILD_LOCKDSANLOCK
+BUILD_LOCKDIDM
 BUILD_LVMLOCKD
 BUILD_LVMPOLLD
 BUILD_LVMDBUSD
@@ -753,6 +756,8 @@ BUILD_CMIRRORD
 BLKID_PC
 MODPROBE_CMD
 MSGFMT
+EDITLINE_LIBS
+EDITLINE_CFLAGS
 PYTHON3_CONFIG
 pkgpyexecdir
 pyexecdir
@@ -778,6 +783,8 @@ LOCKD_DLM_LIBS
 LOCKD_DLM_CFLAGS
 LOCKD_SANLOCK_LIBS
 LOCKD_SANLOCK_CFLAGS
+LOCKD_IDM_LIBS
+LOCKD_IDM_CFLAGS
 VALGRIND_LIBS
 VALGRIND_CFLAGS
 GENPNG
@@ -793,6 +800,8 @@ PKGCONFIGINIT_CFLAGS
 PKG_CONFIG_LIBDIR
 PKG_CONFIG_PATH
 PKG_CONFIG
+AIO_LIBS
+AIO_CFLAGS
 VDO_FORMAT_CMD
 CACHE_RESTORE_CMD
 CACHE_REPAIR_CMD
@@ -866,6 +875,7 @@ infodir
 docdir
 oldincludedir
 includedir
+runstatedir
 localstatedir
 sharedstatedir
 sysconfdir
@@ -920,6 +930,7 @@ with_vdo_format
 with_writecache
 with_integrity
 enable_readline
+enable_editline
 enable_realtime
 enable_ocf
 with_ocfdir
@@ -930,6 +941,7 @@ enable_cmirrord
 with_cmirrord_pidfile
 enable_debug
 with_optimisation
+with_symvers
 enable_profiling
 enable_valgrind_pool
 enable_devmapper
@@ -937,6 +949,7 @@ enable_lvmpolld
 enable_lvmlockd_sanlock
 enable_lvmlockd_dlm
 enable_lvmlockd_dlmcontrol
+enable_lvmlockd_idm
 enable_use_lvmlockd
 with_lvmlockd_pidfile
 enable_use_lvmpolld
@@ -960,6 +973,7 @@ enable_fsadm
 enable_blkdeactivate
 enable_dmeventd
 enable_selinux
+enable_blkzeroout
 enable_nls
 with_localedir
 with_confdir
@@ -992,6 +1006,8 @@ CXX
 CXXFLAGS
 CCC
 CPP
+AIO_CFLAGS
+AIO_LIBS
 PKG_CONFIG
 PKG_CONFIG_PATH
 PKG_CONFIG_LIBDIR
@@ -1007,6 +1023,8 @@ LOCKD_DLM_CFLAGS
 LOCKD_DLM_LIBS
 LOCKD_DLM_CONTROL_CFLAGS
 LOCKD_DLM_CONTROL_LIBS
+LOCKD_IDM_CFLAGS
+LOCKD_IDM_LIBS
 NOTIFY_DBUS_CFLAGS
 NOTIFY_DBUS_LIBS
 BLKID_CFLAGS
@@ -1015,7 +1033,9 @@ SYSTEMD_CFLAGS
 SYSTEMD_LIBS
 UDEV_CFLAGS
 UDEV_LIBS
-PYTHON'
+PYTHON
+EDITLINE_CFLAGS
+EDITLINE_LIBS'
 
 
 # Initialize some variables set by options.
@@ -1054,6 +1074,7 @@ datadir='${datarootdir}'
 sysconfdir='${prefix}/etc'
 sharedstatedir='${prefix}/com'
 localstatedir='${prefix}/var'
+runstatedir='${localstatedir}/run'
 includedir='${prefix}/include'
 oldincludedir='/usr/include'
 docdir='${datarootdir}/doc/${PACKAGE}'
@@ -1306,6 +1327,15 @@ do
   | -silent | --silent | --silen | --sile | --sil)
     silent=yes ;;
 
+  -runstatedir | --runstatedir | --runstatedi | --runstated \
+  | --runstate | --runstat | --runsta | --runst | --runs \
+  | --run | --ru | --r)
+    ac_prev=runstatedir ;;
+  -runstatedir=* | --runstatedir=* | --runstatedi=* | --runstated=* \
+  | --runstate=* | --runstat=* | --runsta=* | --runst=* | --runs=* \
+  | --run=* | --ru=* | --r=*)
+    runstatedir=$ac_optarg ;;
+
   -sbindir | --sbindir | --sbindi | --sbind | --sbin | --sbi | --sb)
     ac_prev=sbindir ;;
   -sbindir=* | --sbindir=* | --sbindi=* | --sbind=* | --sbin=* \
@@ -1443,7 +1473,7 @@ fi
 for ac_var in	exec_prefix prefix bindir sbindir libexecdir datarootdir \
 		datadir sysconfdir sharedstatedir localstatedir includedir \
 		oldincludedir docdir infodir htmldir dvidir pdfdir psdir \
-		libdir localedir mandir
+		libdir localedir mandir runstatedir
 do
   eval ac_val=\$$ac_var
   # Remove trailing slashes.
@@ -1596,6 +1626,7 @@ Fine tuning of the installation directories:
   --sysconfdir=DIR        read-only single-machine data [PREFIX/etc]
   --sharedstatedir=DIR    modifiable architecture-independent data [PREFIX/com]
   --localstatedir=DIR     modifiable single-machine data [PREFIX/var]
+  --runstatedir=DIR       modifiable per-process data [LOCALSTATEDIR/run]
   --libdir=DIR            object code libraries [EPREFIX/lib]
   --includedir=DIR        C header files [PREFIX/include]
   --oldincludedir=DIR     C header files for non-gcc [/usr/include]
@@ -1638,6 +1669,7 @@ 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
@@ -1652,6 +1684,7 @@ Optional Features:
   --enable-lvmlockd-dlm   enable the LVM lock daemon using dlm
   --enable-lvmlockd-dlmcontrol
                           enable lvmlockd remote refresh using libdlmcontrol
+  --enable-lvmlockd-idm   enable the LVM lock daemon using idm
   --disable-use-lvmlockd  disable usage of LVM lock daemon
   --disable-use-lvmpolld  disable usage of LVM Poll Daemon
   --enable-dmfilemapd     enable the dmstats filemap daemon
@@ -1678,6 +1711,7 @@ 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:
@@ -1692,22 +1726,21 @@ Optional Packages:
                           create nodes on resume or create [ON=resume]
   --with-default-name-mangling=MANGLING
                           default name mangling: auto/none/hex [auto]
-  --with-snapshots=TYPE   snapshot support: internal/shared/none [internal]
-  --with-mirrors=TYPE     mirror support: internal/shared/none [internal]
+  --with-snapshots=TYPE   snapshot support: internal/none [internal]
+  --with-mirrors=TYPE     mirror support: internal/none [internal]
   --with-default-mirror-segtype=TYPE
                           default mirror segtype: raid1/mirror [raid1]
   --with-default-raid10-segtype=TYPE
                           default mirror segtype: raid10/mirror [raid10]
   --with-default-sparse-segtype=TYPE
                           default sparse segtype: thin/snapshot [thin]
-  --with-thin=TYPE        thin provisioning support: internal/shared/none
-                          [internal]
+  --with-thin=TYPE        thin provisioning support: internal/none [internal]
   --with-thin-check=PATH  thin_check tool: [autodetect]
   --with-thin-dump=PATH   thin_dump tool: [autodetect]
   --with-thin-repair=PATH thin_repair tool: [autodetect]
   --with-thin-restore=PATH
                           thin_restore tool: [autodetect]
-  --with-cache=TYPE       cache support: internal/shared/none [internal]
+  --with-cache=TYPE       cache support: internal/none [internal]
   --with-cache-check=PATH cache_check tool: [autodetect]
   --with-cache-dump=PATH  cache_dump tool: [autodetect]
   --with-cache-repair=PATH
@@ -1716,19 +1749,21 @@ 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-integrity=TYPE   integrity 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]
+  --with-symvers=STYLE    use symbol versioning of the shared library
+                          [default=gnu]
   --with-lvmlockd-pidfile=PATH
                           lvmlockd pidfile [PID_DIR/lvmlockd.pid]
   --with-lvmpolld-pidfile=PATH
@@ -1775,6 +1810,8 @@ Some influential environment variables:
   CXX         C++ compiler command
   CXXFLAGS    C++ compiler flags
   CPP         C preprocessor
+  AIO_CFLAGS  C compiler flags for AIO
+  AIO_LIBS    linker flags for AIO
   PKG_CONFIG  path to pkg-config utility
   PKG_CONFIG_PATH
               directories to add to pkg-config's search path
@@ -1802,6 +1839,10 @@ Some influential environment variables:
               C compiler flags for LOCKD_DLM_CONTROL, overriding pkg-config
   LOCKD_DLM_CONTROL_LIBS
               linker flags for LOCKD_DLM_CONTROL, overriding pkg-config
+  LOCKD_IDM_CFLAGS
+              C compiler flags for LOCKD_IDM, overriding pkg-config
+  LOCKD_IDM_LIBS
+              linker flags for LOCKD_IDM, overriding pkg-config
   NOTIFY_DBUS_CFLAGS
               C compiler flags for NOTIFY_DBUS, overriding pkg-config
   NOTIFY_DBUS_LIBS
@@ -1816,6 +1857,10 @@ 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.
@@ -3079,19 +3124,18 @@ if test -z "$CFLAGS"; then :
 fi
 case "$host_os" in
 	linux*)
-		CLDFLAGS="${CLDFLAGS-"$LDFLAGS"} -Wl,--version-script,.export.sym"
 		# equivalent to -rdynamic
 		ELDFLAGS="-Wl,--export-dynamic"
 		# FIXME Generate list and use --dynamic-list=.dlopen.sym
 		CLDWHOLEARCHIVE="-Wl,-whole-archive"
 		CLDNOWHOLEARCHIVE="-Wl,-no-whole-archive"
-		LDDEPS="$LDDEPS .export.sym"
 		LIB_SUFFIX=so
 		DEVMAPPER=yes
 		BUILD_LVMPOLLD=no
 		LOCKDSANLOCK=no
 		LOCKDDLM=no
 		LOCKDDLM_CONTROL=no
+		LOCKDIDM=no
 		ODIRECT=yes
 		DM_IOCTLS=yes
 		SELINUX=yes
@@ -3100,7 +3144,6 @@ case "$host_os" in
 		;;
 	darwin*)
 		CFLAGS="$CFLAGS -no-cpp-precomp -fno-common"
-		CLDFLAGS="${CLDFLAGS-"$LDFLAGS"}"
 		ELDFLAGS=
 		CLDWHOLEARCHIVE="-all_load"
 		CLDNOWHOLEARCHIVE=
@@ -6065,7 +6108,7 @@ fi
 
 
 for ac_header in assert.h ctype.h dirent.h errno.h fcntl.h float.h \
-  getopt.h inttypes.h langinfo.h libaio.h libgen.h limits.h locale.h paths.h \
+  getopt.h inttypes.h langinfo.h libgen.h limits.h locale.h paths.h \
   signal.h stdarg.h stddef.h stdio.h stdlib.h string.h sys/file.h \
   sys/ioctl.h syslog.h sys/mman.h sys/param.h sys/resource.h sys/stat.h \
   sys/time.h sys/types.h sys/utsname.h sys/wait.h time.h \
@@ -6098,6 +6141,19 @@ fi
 
 done
 
+for ac_header in libaio.h
+do :
+  ac_fn_c_check_header_mongrel "$LINENO" "libaio.h" "ac_cv_header_libaio_h" "$ac_includes_default"
+if test "x$ac_cv_header_libaio_h" = xyes; then :
+  cat >>confdefs.h <<_ACEOF
+#define HAVE_LIBAIO_H 1
+_ACEOF
+ LVM_NEEDS_LIBAIO_WARN=
+else
+  LVM_NEEDS_LIBAIO_WARN=y
+fi
+
+done
 
 case "$host_os" in
 	linux*)
@@ -8361,7 +8417,7 @@ fi
 
 case "$MANGLING" in
  auto) mangling=DM_STRING_MANGLING_AUTO;;
- none|disabled) mangling=DM_STRING_MANGLING_NONE;;
+ no|none|disabled) mangling=DM_STRING_MANGLING_NONE;;
  hex) mangling=DM_STRING_MANGLING_HEX;;
  *) as_fn_error $? "--with-default-name-mangling parameter invalid" "$LINENO" 5;;
 esac
@@ -8388,7 +8444,7 @@ fi
 $as_echo "$SNAPSHOTS" >&6; }
 
 case "$SNAPSHOTS" in
-  none|shared) ;;
+  no|none|shared) ;;
   internal)
 $as_echo "#define SNAPSHOT_INTERNAL 1" >>confdefs.h
  ;;
@@ -8410,7 +8466,7 @@ fi
 $as_echo "$MIRRORS" >&6; }
 
 case "$MIRRORS" in
-  none|shared) ;;
+  no|none|shared) ;;
   internal)
 $as_echo "#define MIRRORED_INTERNAL 1" >>confdefs.h
  ;;
@@ -8455,7 +8511,10 @@ _ACEOF
 
 # Check whether --with-default-sparse-segtype was given.
 if test "${with_default_sparse_segtype+set}" = set; then :
-  withval=$with_default_sparse_segtype; DEFAULT_SPARSE_SEGTYPE=$withval
+  withval=$with_default_sparse_segtype;  case "$withval" in
+				thin|snapshot) DEFAULT_SPARSE_SEGTYPE=$withval ;;
+				*) as_fn_error $? "--with-default-sparse-segtype parameter invalid" "$LINENO" 5 ;;
+			     esac
 else
   DEFAULT_SPARSE_SEGTYPE="thin"
 fi
@@ -8509,7 +8568,7 @@ fi
 $as_echo "$THIN" >&6; }
 
 case "$THIN" in
-  none)  test "$DEFAULT_SPARSE_SEGTYPE" = "thin" && DEFAULT_SPARSE_SEGTYPE="snapshot" ;;
+  no|none)  test "$DEFAULT_SPARSE_SEGTYPE" = "thin" && DEFAULT_SPARSE_SEGTYPE="snapshot" ;;
   shared) ;;
   internal)
 $as_echo "#define THIN_INTERNAL 1" >>confdefs.h
@@ -8990,7 +9049,6 @@ $as_echo "$THIN_CHECK_NEEDS_CHECK" >&6; }
 $as_echo "#define THIN_CHECK_NEEDS_CHECK 1" >>confdefs.h
 
 	fi
-
 	;;
 esac
 
@@ -9065,7 +9123,7 @@ fi
 $as_echo "$CACHE" >&6; }
 
 case "$CACHE" in
- none|shared) ;;
+ no|none|shared) ;;
  internal)
 $as_echo "#define CACHE_INTERNAL 1" >>confdefs.h
  ;;
@@ -9586,7 +9644,7 @@ $as_echo_n "checking whether to include vdo... " >&6; }
 if test "${with_vdo+set}" = set; then :
   withval=$with_vdo; VDO=$withval
 else
-  VDO="none"
+  VDO="internal"
 fi
 
 
@@ -9602,7 +9660,7 @@ else
 fi
 
 case "$VDO" in
- none) ;;
+ no|none) ;;
  internal)
 
 $as_echo "#define VDO_INTERNAL 1" >>confdefs.h
@@ -9746,7 +9804,7 @@ $as_echo_n "checking whether to include writecache... " >&6; }
 if test "${with_writecache+set}" = set; then :
   withval=$with_writecache; WRITECACHE=$withval
 else
-  WRITECACHE="none"
+  WRITECACHE="internal"
 fi
 
 
@@ -9754,7 +9812,7 @@ fi
 $as_echo "$WRITECACHE" >&6; }
 
 case "$WRITECACHE" in
- none) ;;
+ no|none) ;;
  internal)
 
 $as_echo "#define WRITECACHE_INTERNAL 1" >>confdefs.h
@@ -9771,7 +9829,7 @@ $as_echo_n "checking whether to include integrity... " >&6; }
 if test "${with_integrity+set}" = set; then :
   withval=$with_integrity; INTEGRITY=$withval
 else
-  INTEGRITY="none"
+  INTEGRITY="internal"
 fi
 
 
@@ -9779,7 +9837,7 @@ fi
 $as_echo "$INTEGRITY" >&6; }
 
 case "$INTEGRITY" in
- none) ;;
+ no|none) ;;
  internal)
 
 $as_echo "#define INTEGRITY_INTERNAL 1" >>confdefs.h
@@ -9788,6 +9846,14 @@ $as_echo "#define INTEGRITY_INTERNAL 1" >>confdefs.h
  *) as_fn_error $? "--with-integrity parameter invalid" "$LINENO" 5 ;;
 esac
 
+################################################################################
+# Allow users to override default location for libaio
+# there seems to be no pkg-config support available
+AIO_CFLAGS=
+AIO_LIBS=${AIO_LIBS:--laio}
+
+
+
 ################################################################################
 # Check whether --enable-readline was given.
 if test "${enable_readline+set}" = set; then :
@@ -9797,6 +9863,15 @@ 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; }
@@ -10360,6 +10435,35 @@ fi
 { $as_echo "$as_me:${as_lineno-$LINENO}: result: $COPTIMISE_FLAG" >&5
 $as_echo "$COPTIMISE_FLAG" >&6; }
 
+################################################################################
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to use symbol versioning" >&5
+$as_echo_n "checking whether to use symbol versioning... " >&6; }
+
+# Check whether --with-symvers was given.
+if test "${with_symvers+set}" = set; then :
+  withval=$with_symvers;  case "$withval" in
+				gnu|no) symvers=$withval ;;
+				*) as_fn_error $? "--with-symvers parameter invalid" "$LINENO" 5 ;;
+			     esac
+else
+  symvers=gnu
+fi
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $symvers" >&5
+$as_echo "$symvers" >&6; }
+
+if test "$GCC" = "yes" && test "$symvers" = "gnu" ; then
+
+$as_echo "#define GNU_SYMVER 1" >>confdefs.h
+
+		   case "$host_os" in
+			linux*)
+			CLDFLAGS="${CLDFLAGS-"$LDFLAGS"} -Wl,--version-script,.export.sym"
+			LDDEPS="$LDDEPS .export.sym"
+			;;
+		   esac
+fi
+
 ################################################################################
 { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to gather gcov profiling data" >&5
 $as_echo_n "checking whether to gather gcov profiling data... " >&6; }
@@ -10696,7 +10800,6 @@ cat >>confdefs.h <<_ACEOF
 _ACEOF
 
 
-
 ################################################################################
 { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to enable valgrind awareness of pools" >&5
 $as_echo_n "checking whether to enable valgrind awareness of pools... " >&6; }
@@ -11100,6 +11203,167 @@ $as_echo "#define LOCKDDLM_CONTROL_SUPPORT 1" >>confdefs.h
 	BUILD_LVMLOCKD=yes
 fi
 
+################################################################################
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to build lvmlockdidm" >&5
+$as_echo_n "checking whether to build lvmlockdidm... " >&6; }
+# Check whether --enable-lvmlockd-idm was given.
+if test "${enable_lvmlockd_idm+set}" = set; then :
+  enableval=$enable_lvmlockd_idm; LOCKDIDM=$enableval
+fi
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $LOCKDIDM" >&5
+$as_echo "$LOCKDIDM" >&6; }
+
+BUILD_LOCKDIDM=$LOCKDIDM
+
+if test "$BUILD_LOCKDIDM" = yes; then
+
+pkg_failed=no
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for LOCKD_IDM" >&5
+$as_echo_n "checking for LOCKD_IDM... " >&6; }
+
+if test -n "$LOCKD_IDM_CFLAGS"; then
+    pkg_cv_LOCKD_IDM_CFLAGS="$LOCKD_IDM_CFLAGS"
+ elif test -n "$PKG_CONFIG"; then
+    if test -n "$PKG_CONFIG" && \
+    { { $as_echo "$as_me:${as_lineno-$LINENO}: \$PKG_CONFIG --exists --print-errors \"libseagate_ilm >= 0.1.0\""; } >&5
+  ($PKG_CONFIG --exists --print-errors "libseagate_ilm >= 0.1.0") 2>&5
+  ac_status=$?
+  $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+  test $ac_status = 0; }; then
+  pkg_cv_LOCKD_IDM_CFLAGS=`$PKG_CONFIG --cflags "libseagate_ilm >= 0.1.0" 2>/dev/null`
+		      test "x$?" != "x0" && pkg_failed=yes
+else
+  pkg_failed=yes
+fi
+ else
+    pkg_failed=untried
+fi
+if test -n "$LOCKD_IDM_LIBS"; then
+    pkg_cv_LOCKD_IDM_LIBS="$LOCKD_IDM_LIBS"
+ elif test -n "$PKG_CONFIG"; then
+    if test -n "$PKG_CONFIG" && \
+    { { $as_echo "$as_me:${as_lineno-$LINENO}: \$PKG_CONFIG --exists --print-errors \"libseagate_ilm >= 0.1.0\""; } >&5
+  ($PKG_CONFIG --exists --print-errors "libseagate_ilm >= 0.1.0") 2>&5
+  ac_status=$?
+  $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+  test $ac_status = 0; }; then
+  pkg_cv_LOCKD_IDM_LIBS=`$PKG_CONFIG --libs "libseagate_ilm >= 0.1.0" 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 $_pkg_short_errors_supported = yes; then
+	        LOCKD_IDM_PKG_ERRORS=`$PKG_CONFIG --short-errors --print-errors --cflags --libs "libseagate_ilm >= 0.1.0" 2>&1`
+        else
+	        LOCKD_IDM_PKG_ERRORS=`$PKG_CONFIG --print-errors --cflags --libs "libseagate_ilm >= 0.1.0" 2>&1`
+        fi
+	# Put the nasty error message in config.log where it belongs
+	echo "$LOCKD_IDM_PKG_ERRORS" >&5
+
+	$bailout
+elif test $pkg_failed = untried; then
+	{ $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+	$bailout
+else
+	LOCKD_IDM_CFLAGS=$pkg_cv_LOCKD_IDM_CFLAGS
+	LOCKD_IDM_LIBS=$pkg_cv_LOCKD_IDM_LIBS
+        { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5
+$as_echo "yes" >&6; }
+fi
+
+pkg_failed=no
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for BLKID" >&5
+$as_echo_n "checking for BLKID... " >&6; }
+
+if test -n "$BLKID_CFLAGS"; then
+    pkg_cv_BLKID_CFLAGS="$BLKID_CFLAGS"
+ elif test -n "$PKG_CONFIG"; then
+    if test -n "$PKG_CONFIG" && \
+    { { $as_echo "$as_me:${as_lineno-$LINENO}: \$PKG_CONFIG --exists --print-errors \"blkid >= 2.24\""; } >&5
+  ($PKG_CONFIG --exists --print-errors "blkid >= 2.24") 2>&5
+  ac_status=$?
+  $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+  test $ac_status = 0; }; then
+  pkg_cv_BLKID_CFLAGS=`$PKG_CONFIG --cflags "blkid >= 2.24" 2>/dev/null`
+		      test "x$?" != "x0" && pkg_failed=yes
+else
+  pkg_failed=yes
+fi
+ else
+    pkg_failed=untried
+fi
+if test -n "$BLKID_LIBS"; then
+    pkg_cv_BLKID_LIBS="$BLKID_LIBS"
+ elif test -n "$PKG_CONFIG"; then
+    if test -n "$PKG_CONFIG" && \
+    { { $as_echo "$as_me:${as_lineno-$LINENO}: \$PKG_CONFIG --exists --print-errors \"blkid >= 2.24\""; } >&5
+  ($PKG_CONFIG --exists --print-errors "blkid >= 2.24") 2>&5
+  ac_status=$?
+  $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+  test $ac_status = 0; }; then
+  pkg_cv_BLKID_LIBS=`$PKG_CONFIG --libs "blkid >= 2.24" 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 $_pkg_short_errors_supported = yes; then
+	        BLKID_PKG_ERRORS=`$PKG_CONFIG --short-errors --print-errors --cflags --libs "blkid >= 2.24" 2>&1`
+        else
+	        BLKID_PKG_ERRORS=`$PKG_CONFIG --print-errors --cflags --libs "blkid >= 2.24" 2>&1`
+        fi
+	# Put the nasty error message in config.log where it belongs
+	echo "$BLKID_PKG_ERRORS" >&5
+
+	$bailout
+elif test $pkg_failed = untried; then
+     	{ $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+	$bailout
+else
+	BLKID_CFLAGS=$pkg_cv_BLKID_CFLAGS
+	BLKID_LIBS=$pkg_cv_BLKID_LIBS
+        { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5
+$as_echo "yes" >&6; }
+	HAVE_LOCKD_IDM=yes
+fi
+
+$as_echo "#define LOCKDIDM_SUPPORT 1" >>confdefs.h
+
+	BUILD_LVMLOCKD=yes
+fi
+
 ################################################################################
 { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to build lvmlockd" >&5
 $as_echo_n "checking whether to build lvmlockd... " >&6; }
@@ -11824,6 +12088,7 @@ if test "$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
@@ -11859,7 +12124,7 @@ 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
@@ -11940,7 +12205,7 @@ $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; }
@@ -12688,6 +12953,61 @@ 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
@@ -12808,6 +13128,86 @@ 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 $? "libedit could not be found which is required for the --enable-editline option." "$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 $? "libedit could not be found which is required for the --enable-editline option." "$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
@@ -13246,6 +13646,27 @@ $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 "$EDITLINE" = yes; then
+	for ac_header in editline/readline.h
+do :
+  ac_fn_c_check_header_mongrel "$LINENO" "editline/readline.h" "ac_cv_header_editline_readline_h" "$ac_includes_default"
+if test "x$ac_cv_header_editline_readline_h" = xyes; then :
+  cat >>confdefs.h <<_ACEOF
+#define HAVE_EDITLINE_READLINE_H 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 :
@@ -13925,6 +14346,9 @@ _ACEOF
 
 
 
+
+
+
 
 
 
@@ -15299,10 +15723,14 @@ $as_echo "$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
 
+if test -n "$LVM_NEEDS_LIBAIO_WARN"; then :
+  { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: Only libdm part can be build without libaio:  make [install_]device-mapper" >&5
+$as_echo "$as_me: WARNING: Only libdm part can be build without libaio:  make [install_]device-mapper" >&2;}
+fi
 
 if test "$ODIRECT" != yes; then :
   { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: O_DIRECT disabled: low-memory pvmove may lock up" >&5

configure.ac

@@ -30,19 +30,18 @@ AC_CANONICAL_TARGET([])
 AS_IF([test -z "$CFLAGS"], [COPTIMISE_FLAG="-O2"])
 case "$host_os" in
 	linux*)
-		CLDFLAGS="${CLDFLAGS-"$LDFLAGS"} -Wl,--version-script,.export.sym"
 		# equivalent to -rdynamic
 		ELDFLAGS="-Wl,--export-dynamic"
 		# FIXME Generate list and use --dynamic-list=.dlopen.sym
 		CLDWHOLEARCHIVE="-Wl,-whole-archive"
 		CLDNOWHOLEARCHIVE="-Wl,-no-whole-archive"
-		LDDEPS="$LDDEPS .export.sym"
 		LIB_SUFFIX=so
 		DEVMAPPER=yes
 		BUILD_LVMPOLLD=no
 		LOCKDSANLOCK=no
 		LOCKDDLM=no
 		LOCKDDLM_CONTROL=no
+		LOCKDIDM=no
 		ODIRECT=yes
 		DM_IOCTLS=yes
 		SELINUX=yes
@@ -51,7 +50,6 @@ case "$host_os" in
 		;;
 	darwin*)
 		CFLAGS="$CFLAGS -no-cpp-precomp -fno-common"
-		CLDFLAGS="${CLDFLAGS-"$LDFLAGS"}"
 		ELDFLAGS=
 		CLDWHOLEARCHIVE="-all_load"
 		CLDNOWHOLEARCHIVE=
@@ -104,14 +102,14 @@ AC_HEADER_SYS_WAIT
 AC_HEADER_TIME
 
 AC_CHECK_HEADERS([assert.h ctype.h dirent.h errno.h fcntl.h float.h \
-  getopt.h inttypes.h langinfo.h libaio.h libgen.h limits.h locale.h paths.h \
+  getopt.h inttypes.h langinfo.h libgen.h limits.h locale.h paths.h \
   signal.h stdarg.h stddef.h stdio.h stdlib.h string.h sys/file.h \
   sys/ioctl.h syslog.h sys/mman.h sys/param.h sys/resource.h sys/stat.h \
   sys/time.h sys/types.h sys/utsname.h sys/wait.h time.h \
   unistd.h], , [AC_MSG_ERROR(bailing out)])
 
 AC_CHECK_HEADERS(termios.h sys/statvfs.h sys/timerfd.h sys/vfs.h linux/magic.h linux/fiemap.h)
-
+AC_CHECK_HEADERS(libaio.h,LVM_NEEDS_LIBAIO_WARN=,LVM_NEEDS_LIBAIO_WARN=y)
 case "$host_os" in
 	linux*)
 		AC_CHECK_HEADERS(asm/byteorder.h linux/fs.h malloc.h,,AC_MSG_ERROR(bailing out)) ;;
@@ -292,7 +290,7 @@ AC_ARG_WITH(default-name-mangling,
 	    MANGLING=$withval, MANGLING=auto)
 case "$MANGLING" in
  auto) mangling=DM_STRING_MANGLING_AUTO;;
- none|disabled) mangling=DM_STRING_MANGLING_NONE;;
+ no|none|disabled) mangling=DM_STRING_MANGLING_NONE;;
  hex) mangling=DM_STRING_MANGLING_HEX;;
  *) AC_MSG_ERROR([--with-default-name-mangling parameter invalid]);;
 esac
@@ -304,12 +302,12 @@ dnl -- snapshots inclusion type
 AC_MSG_CHECKING(whether to include snapshots)
 AC_ARG_WITH(snapshots,
 	    AC_HELP_STRING([--with-snapshots=TYPE],
-			   [snapshot support: internal/shared/none [internal]]),
+			   [snapshot support: internal/none [internal]]),
 	    SNAPSHOTS=$withval, SNAPSHOTS=internal)
 AC_MSG_RESULT($SNAPSHOTS)
 
 case "$SNAPSHOTS" in
-  none|shared) ;;
+  no|none|shared) ;;
   internal) AC_DEFINE([SNAPSHOT_INTERNAL], 1,
 		      [Define to 1 to include built-in support for snapshots.]) ;;
   *) AC_MSG_ERROR([--with-snapshots parameter invalid]) ;;
@@ -320,12 +318,12 @@ dnl -- mirrors inclusion type
 AC_MSG_CHECKING(whether to include mirrors)
 AC_ARG_WITH(mirrors,
 	    AC_HELP_STRING([--with-mirrors=TYPE],
-			   [mirror support: internal/shared/none [internal]]),
+			   [mirror support: internal/none [internal]]),
 	    MIRRORS=$withval, MIRRORS=internal)
 AC_MSG_RESULT($MIRRORS)
 
 case "$MIRRORS" in
-  none|shared) ;;
+  no|none|shared) ;;
   internal) AC_DEFINE([MIRRORED_INTERNAL], 1,
 		      [Define to 1 to include built-in support for mirrors.]) ;;
   *) AC_MSG_ERROR([--with-mirrors parameter invalid]) ;;
@@ -355,14 +353,17 @@ AC_DEFINE_UNQUOTED([DEFAULT_RAID10_SEGTYPE], ["$DEFAULT_RAID10_SEGTYPE"],
 AC_ARG_WITH(default-sparse-segtype,
 	    AC_HELP_STRING([--with-default-sparse-segtype=TYPE],
 			   [default sparse segtype: thin/snapshot [thin]]),
-			   DEFAULT_SPARSE_SEGTYPE=$withval, DEFAULT_SPARSE_SEGTYPE="thin")
+			   [ case "$withval" in
+				thin|snapshot) DEFAULT_SPARSE_SEGTYPE=$withval ;;
+				*) AC_MSG_ERROR(--with-default-sparse-segtype parameter invalid) ;;
+			     esac], DEFAULT_SPARSE_SEGTYPE="thin")
 
 ################################################################################
 dnl -- thin provisioning
 AC_MSG_CHECKING(whether to include thin provisioning)
 AC_ARG_WITH(thin,
 	    AC_HELP_STRING([--with-thin=TYPE],
-			   [thin provisioning support: internal/shared/none [internal]]),
+			   [thin provisioning support: internal/none [internal]]),
 	    THIN=$withval, THIN=internal)
 AC_ARG_WITH(thin-check,
 	    AC_HELP_STRING([--with-thin-check=PATH],
@@ -384,7 +385,7 @@ AC_ARG_WITH(thin-restore,
 AC_MSG_RESULT($THIN)
 
 case "$THIN" in
-  none)  test "$DEFAULT_SPARSE_SEGTYPE" = "thin" && DEFAULT_SPARSE_SEGTYPE="snapshot" ;;
+  no|none)  test "$DEFAULT_SPARSE_SEGTYPE" = "thin" && DEFAULT_SPARSE_SEGTYPE="snapshot" ;;
   shared) ;;
   internal) AC_DEFINE([THIN_INTERNAL], 1,
 		      [Define to 1 to include built-in support for thin provisioning.]) ;;
@@ -461,7 +462,6 @@ case "$THIN" in
 	if test "$THIN_CHECK_NEEDS_CHECK" = yes; then
 		AC_DEFINE([THIN_CHECK_NEEDS_CHECK], 1, [Define to 1 if the external 'thin_check' tool requires the --clear-needs-check-flag option])
 	fi
-
 	;;
 esac
 
@@ -482,7 +482,7 @@ dnl -- cache inclusion type
 AC_MSG_CHECKING(whether to include cache)
 AC_ARG_WITH(cache,
 	    AC_HELP_STRING([--with-cache=TYPE],
-			   [cache support: internal/shared/none [internal]]),
+			   [cache support: internal/none [internal]]),
 			   CACHE=$withval, CACHE="internal")
 AC_ARG_WITH(cache-check,
 	    AC_HELP_STRING([--with-cache-check=PATH],
@@ -503,7 +503,7 @@ AC_ARG_WITH(cache-restore,
 AC_MSG_RESULT($CACHE)
 
 case "$CACHE" in
- none|shared) ;;
+ no|none|shared) ;;
  internal) AC_DEFINE([CACHE_INTERNAL], 1, [Define to 1 to include built-in support for cache.]) ;;
  *) AC_MSG_ERROR([--with-cache parameter invalid]) ;;
 esac
@@ -607,7 +607,7 @@ AC_MSG_CHECKING(whether to include vdo)
 AC_ARG_WITH(vdo,
 	    AC_HELP_STRING([--with-vdo=TYPE],
 			   [vdo support: internal/none [internal]]),
-			   VDO=$withval, VDO="none")
+			   VDO=$withval, VDO="internal")
 
 AC_MSG_RESULT($VDO)
 
@@ -616,8 +616,8 @@ AC_ARG_WITH(vdo-format,
 			   [vdoformat tool: [autodetect]]),
 			   VDO_FORMAT_CMD=$withval, VDO_FORMAT_CMD="autodetect")
 case "$VDO" in
- none) ;;
- internal) 
+ no|none) ;;
+ internal)
 	AC_DEFINE([VDO_INTERNAL], 1, [Define to 1 to include built-in support for vdo.])
 	if test "$VDO_FORMAT_CMD" = "autodetect"; then
 		AC_PATH_TOOL(VDO_FORMAT_CMD, vdoformat, [], [$PATH])
@@ -646,7 +646,7 @@ AC_DEFINE_UNQUOTED([VDO_FORMAT_CMD], ["$VDO_FORMAT_CMD"],
 #AC_ARG_WITH(vdo-lib,
 #            AC_HELP_STRING([--with-vdo-lib=PATH],
 #                           [vdo support: Path to utils lib: [/usr/lib]]),
-#                           VDO_LIB=$withval, VDO_LIB="/usr/lib") 
+#                           VDO_LIB=$withval, VDO_LIB="/usr/lib")
 #AC_MSG_RESULT($VDO_LIB)
 
 ################################################################################
@@ -654,14 +654,14 @@ 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)
 
 case "$WRITECACHE" in
- none) ;;
- internal) 
+ no|none) ;;
+ internal)
 	AC_DEFINE([WRITECACHE_INTERNAL], 1, [Define to 1 to include built-in support for writecache.])
 	;;
  *) AC_MSG_ERROR([--with-writecache parameter invalid]) ;;
@@ -672,25 +672,39 @@ dnl -- integrity inclusion type
 AC_MSG_CHECKING(whether to include integrity)
 AC_ARG_WITH(integrity,
 	    AC_HELP_STRING([--with-integrity=TYPE],
-			   [integrity support: internal/none [none]]),
-			   INTEGRITY=$withval, INTEGRITY="none")
+			   [integrity support: internal/none [internal]]),
+			   INTEGRITY=$withval, INTEGRITY="internal")
 
 AC_MSG_RESULT($INTEGRITY)
 
 case "$INTEGRITY" in
- none) ;;
+ no|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
 
+################################################################################
+# Allow users to override default location for libaio
+# there seems to be no pkg-config support available
+AIO_CFLAGS=
+AIO_LIBS=${AIO_LIBS:--laio}
+AC_ARG_VAR([AIO_CFLAGS], [C compiler flags for AIO])
+AC_ARG_VAR([AIO_LIBS], [linker flags for AIO])
+
 ################################################################################
 dnl -- Disable readline
 AC_ARG_ENABLE([readline],
 	      AC_HELP_STRING([--disable-readline], [disable readline support]),
 	      READLINE=$enableval, READLINE=maybe)
 
+################################################################################
+dnl -- Disable editline
+AC_ARG_ENABLE([editline],
+	      AC_HELP_STRING([--enable-editline], [enable editline support]),
+	      EDITLINE=$enableval, EDITLINE=no)
+
 ################################################################################
 dnl -- Disable realtime clock support
 AC_MSG_CHECKING(whether to enable realtime support)
@@ -734,7 +748,7 @@ dnl -- Set up pidfile and run directory
 AH_TEMPLATE(DEFAULT_PID_DIR)
 AC_ARG_WITH(default-pid-dir,
 	    AC_HELP_STRING([--with-default-pid-dir=PID_DIR],
-			   [Default directory to keep PID files in. [autodetect]]),
+			   [default directory to keep PID files in [autodetect]]),
 	    DEFAULT_PID_DIR="$withval", DEFAULT_PID_DIR=$RUN_DIR)
 AC_DEFINE_UNQUOTED(DEFAULT_PID_DIR, ["$DEFAULT_PID_DIR"],
 		   [Default directory to keep PID files in.])
@@ -742,7 +756,7 @@ 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.])
@@ -750,7 +764,7 @@ 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.])
@@ -819,6 +833,29 @@ AC_ARG_WITH(optimisation,
 	    COPTIMISE_FLAG=$withval)
 AC_MSG_RESULT($COPTIMISE_FLAG)
 
+################################################################################
+dnl -- Symbol versioning
+AC_MSG_CHECKING(whether to use symbol versioning)
+AC_ARG_WITH(symvers,
+	    AC_HELP_STRING([--with-symvers=STYLE],
+			   [use symbol versioning of the shared library [default=gnu]]),
+			   [ case "$withval" in
+				gnu|no) symvers=$withval ;;
+				*) AC_MSG_ERROR(--with-symvers parameter invalid) ;;
+			     esac], symvers=gnu)
+AC_MSG_RESULT($symvers)
+
+if test "$GCC" = "yes" && test "$symvers" = "gnu" ; then
+	AC_DEFINE(GNU_SYMVER, 1,
+		  [Define to use GNU versioning in the shared library.])
+		   case "$host_os" in
+			linux*)
+			CLDFLAGS="${CLDFLAGS-"$LDFLAGS"} -Wl,--version-script,.export.sym"
+			LDDEPS="$LDDEPS .export.sym"
+			;;
+		   esac
+fi
+
 ################################################################################
 dnl -- Enable profiling
 AC_MSG_CHECKING(whether to gather gcov profiling data)
@@ -853,7 +890,6 @@ TESTSUITE_DATA='${datarootdir}/lvm2-testsuite'
 # double eval needed ${datarootdir} -> ${prefix}/share -> real path
 AC_DEFINE_UNQUOTED(TESTSUITE_DATA, ["$(eval echo $(eval echo $TESTSUITE_DATA))"], [Path to testsuite data])
 
-
 ################################################################################
 dnl -- Enable valgrind awareness of memory pools
 AC_MSG_CHECKING(whether to enable valgrind awareness of pools)
@@ -954,6 +990,25 @@ if test "$BUILD_LOCKDDLM_CONTROL" = yes; then
 	BUILD_LVMLOCKD=yes
 fi
 
+################################################################################
+dnl -- Build lvmlockdidm
+AC_MSG_CHECKING(whether to build lvmlockdidm)
+AC_ARG_ENABLE(lvmlockd-idm,
+	      AC_HELP_STRING([--enable-lvmlockd-idm],
+			     [enable the LVM lock daemon using idm]),
+	      LOCKDIDM=$enableval)
+AC_MSG_RESULT($LOCKDIDM)
+
+BUILD_LOCKDIDM=$LOCKDIDM
+
+dnl -- Look for Seagate IDM libraries
+if test "$BUILD_LOCKDIDM" = yes; then
+	PKG_CHECK_MODULES(LOCKD_IDM, libseagate_ilm >= 0.1.0, [HAVE_LOCKD_IDM=yes], $bailout)
+	PKG_CHECK_MODULES(BLKID, blkid >= 2.24, [HAVE_LOCKD_IDM=yes], $bailout)
+	AC_DEFINE([LOCKDIDM_SUPPORT], 1, [Define to 1 to include code that uses lvmlockd IDM option.])
+	BUILD_LVMLOCKD=yes
+fi
+
 ################################################################################
 dnl -- Build lvmlockd
 AC_MSG_CHECKING(whether to build lvmlockd)
@@ -1047,26 +1102,6 @@ if test "$NOTIFYDBUS_SUPPORT" = yes; then
 	PKG_CHECK_MODULES(NOTIFY_DBUS, systemd >= 221, [HAVE_NOTIFY_DBUS=yes], $bailout)
 fi
 
-################################################################################
-dnl -- Build appmachineid
-AC_MSG_CHECKING(whether to build appmachineid)
-AC_ARG_ENABLE(app-machineid,
-	      AC_HELP_STRING([--enable-app-machineid],
-			     [enable LVM system ID using app-specific machine-id]),
-	      APP_MACHINEID_SUPPORT=$enableval, APP_MACHINEID_SUPPORT=no)
-AC_MSG_RESULT($APP_MACHINEID_SUPPORT)
-
-if test "$APP_MACHINEID_SUPPORT" = yes; then
-	AC_DEFINE([APP_MACHINEID_SUPPORT], 1, [Define to 1 to include code that uses libsystemd machine-id apis.])
-	SYSTEMD_LIBS="-lsystemd"
-fi
-
-################################################################################
-dnl -- Look for libsystemd libraries
-if test "$APP_MACHINEID_SUPPORT" = yes; then
-	PKG_CHECK_MODULES(APP_MACHINEID, systemd >= 234, [HAVE_APP_MACHINEID=yes], $bailout)
-fi
-
 ################################################################################
 
 dnl -- Enable blkid wiping functionality
@@ -1238,6 +1273,9 @@ 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 "$PYTHON3" && AC_MSG_ERROR([python3 is required for --enable-python3_bindings or --enable-dbus-service but cannot be found])
@@ -1365,6 +1403,33 @@ if test "$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=
@@ -1398,6 +1463,16 @@ 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 "$EDITLINE" == yes; then
+	PKG_CHECK_MODULES([EDITLINE], [libedit], [
+		AC_DEFINE([EDITLINE_SUPPORT], 1,
+			[Define to 1 to include the LVM editline shell.])], AC_MSG_ERROR(
+[libedit could not be found which is required for the --enable-editline option.])
+	)
+fi
+
 ################################################################################
 dnl -- Check for readline (Shamelessly copied from parted 1.4.17)
 if test "$READLINE" != no; then
@@ -1530,6 +1605,12 @@ fi
 AC_MSG_CHECKING(whether to enable readline)
 AC_MSG_RESULT($READLINE)
 
+if test "$EDITLINE" = yes; then
+	AC_CHECK_HEADERS(editline/readline.h,,hard_bailout)
+fi
+AC_MSG_CHECKING(whether to enable editline)
+AC_MSG_RESULT($EDITLINE)
+
 if test "$BUILD_CMIRRORD" = yes; then
 	AC_CHECK_FUNCS(atexit,,hard_bailout)
 fi
@@ -1747,6 +1828,7 @@ AC_SUBST(BLKDEACTIVATE)
 AC_SUBST(HAVE_LIBDL)
 AC_SUBST(HAVE_REALTIME)
 AC_SUBST(HAVE_VALGRIND)
+AC_SUBST(INTEGRITY)
 AC_SUBST(INTL)
 AC_SUBST(JOBS)
 AC_SUBST(LDDEPS)
@@ -1785,6 +1867,7 @@ AC_SUBST(QUORUM_CFLAGS)
 AC_SUBST(QUORUM_LIBS)
 AC_SUBST(RT_LIBS)
 AC_SUBST(READLINE_LIBS)
+AC_SUBST(EDITLINE_LIBS)
 AC_SUBST(REPLICATORS)
 AC_SUBST(SACKPT_CFLAGS)
 AC_SUBST(SACKPT_LIBS)
@@ -1822,6 +1905,7 @@ AC_SUBST(VDO)
 AC_SUBST(VDO_FORMAT_CMD)
 AC_SUBST(VDO_INCLUDE)
 AC_SUBST(VDO_LIB)
+AC_SUBST(WRITECACHE)
 AC_SUBST(WRITE_INSTALL)
 AC_SUBST(DMEVENTD_PIDFILE)
 AC_SUBST(LVMPOLLD_PIDFILE)
@@ -1920,8 +2004,10 @@ AS_IF([test -n "$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 -n "$LVM_NEEDS_LIBAIO_WARN"],
+      [AC_MSG_WARN([Only libdm part can be build without libaio:  make [[install_]]device-mapper])])
 
 AS_IF([test "$ODIRECT" != yes],
       [AC_MSG_WARN([O_DIRECT disabled: low-memory pvmove may lock up])])

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/cmirrord/Makefile.in

@@ -22,6 +22,9 @@ SOURCES = clogd.c cluster.c compat.c functions.c link_mon.c local.c logging.c
 
 TARGETS = cmirrord
 
+CFLOW_SOURCES = $(addprefix $(srcdir)/, $(SOURCES))
+CFLOW_TARGET := $(TARGETS)
+
 include $(top_builddir)/make.tmpl
 
 LMLIBS += $(CPG_LIBS)
@@ -33,6 +36,8 @@ cmirrord: $(OBJECTS)
 	$(Q) $(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJECTS) \
 		$(LMLIBS) -L$(top_builddir)/libdm -ldevmapper $(LIBS)
 
-install: $(TARGETS)
+install_cluster: $(TARGETS)
 	@echo "    [INSTALL] $<"
-	$(Q) $(INSTALL_PROGRAM) -D cmirrord $(usrsbindir)/cmirrord
+	$(Q) $(INSTALL_PROGRAM) -D $< $(usrsbindir)/$(<F)
+
+install: install_cluster

daemons/cmirrord/cluster.c

@@ -1548,7 +1548,7 @@ static void cpg_config_callback(cpg_handle_t handle, const struct cpg_name *gnam
 				   member_list, member_list_entries);
 }
 
-cpg_callbacks_t cpg_callbacks = {
+static cpg_callbacks_t cpg_callbacks = {
 	.cpg_deliver_fn = cpg_message_callback,
 	.cpg_confchg_fn = cpg_config_callback,
 };

daemons/cmirrord/cluster.h

@@ -39,7 +39,7 @@ struct clog_request {
 	 * machine.  If the two are equal, there is no need
 	 * to do endian conversions.
 	 */
-	union {
+	union version_u {
 		uint64_t version[2]; /* LE version and native version */
 		struct dm_list list;
 	} u;

daemons/cmirrord/functions.c

@@ -658,8 +658,7 @@ static int clog_dtr(struct dm_ulog_request *rq)
 	if (lc->disk_fd != -1 && close(lc->disk_fd))
 		LOG_ERROR("Failed to close disk log: %s",
 			  strerror(errno));
-	if (lc->disk_buffer)
-		free(lc->disk_buffer);
+	free(lc->disk_buffer);
 	free(lc->clean_bits);
 	free(lc->sync_bits);
 	free(lc);

daemons/dmeventd/Makefile.in

@@ -14,11 +14,21 @@
 srcdir = @srcdir@
 top_srcdir = @top_srcdir@
 top_builddir = @top_builddir@
+abs_srcdir = @abs_srcdir@
 
 SOURCES = libdevmapper-event.c
 SOURCES2 = dmeventd.c
 
 TARGETS = dmeventd
+CFLOW_SOURCES = $(addprefix $(srcdir)/, $(SOURCES) $(SOURCES2) \
+	plugins/lvm2/dmeventd_lvm.c \
+	plugins/mirror/dmeventd_mirror.c \
+	plugins/raid/dmeventd_raid.c \
+	plugins/snapshot/dmeventd_snapshot.c \
+	plugins/thin/dmeventd_thin.c \
+	plugins/vdo/dmeventd_vdo.c \
+	)
+CFLOW_TARGET := $(TARGETS)
 
 .PHONY: install_lib_dynamic install_lib_static install_include \
 	install_pkgconfig install_dmeventd_dynamic install_dmeventd_static \
@@ -37,6 +47,7 @@ endif
 
 LIB_VERSION = $(LIB_VERSION_DM)
 LIB_SHARED = $(LIB_NAME).$(LIB_SUFFIX)
+LIBS = $(PTHREAD_LIBS) -L$(interfacebuilddir) -ldevmapper
 
 CLEAN_TARGETS = dmeventd.static $(LIB_NAME).a
 
@@ -46,7 +57,6 @@ endif
 
 CFLOW_LIST = $(SOURCES)
 CFLOW_LIST_TARGET = $(LIB_NAME).cflow
-CFLOW_TARGET = dmeventd
 
 EXPORTED_HEADER = $(srcdir)/libdevmapper-event.h
 EXPORTED_FN_PREFIX = dm_event
@@ -55,34 +65,26 @@ include $(top_builddir)/make.tmpl
 
 all: device-mapper
 device-mapper: $(TARGETS)
+plugins.device-mapper: $(LIB_SHARED)
 
 CFLAGS_dmeventd.o += $(EXTRA_EXEC_CFLAGS)
-LIBS += $(PTHREAD_LIBS) -L$(top_builddir)/libdm -ldevmapper
 
 dmeventd: $(LIB_SHARED) dmeventd.o
 	@echo "    [CC] $@"
-	$(Q) $(CC) $(CFLAGS) -L. $(LDFLAGS) $(EXTRA_EXEC_LDFLAGS) $(ELDFLAGS) dmeventd.o \
-		-o $@ $(DL_LIBS) $(DMEVENT_LIBS) $(LIBS) -lm
+	$(Q) $(CC) $(CFLAGS) $(LDFLAGS) $(EXTRA_EXEC_LDFLAGS) $(ELDFLAGS) dmeventd.o \
+		-o $@ $(DL_LIBS) $(DMEVENT_LIBS) $(LIBS)
 
 dmeventd.static: $(LIB_STATIC) dmeventd.o
 	@echo "    [CC] $@"
-	$(Q) $(CC) $(CFLAGS) $(LDFLAGS) -static -L. -L$(interfacebuilddir) dmeventd.o \
+	$(Q) $(CC) $(CFLAGS) $(LDFLAGS) -static dmeventd.o \
 		-o $@ $(DL_LIBS) $(DMEVENT_LIBS) $(LIBS) $(STATIC_LIBS)
 
 ifeq ("@PKGCONFIG@", "yes")
   INSTALL_LIB_TARGETS += install_pkgconfig
 endif
 
-ifneq ("$(CFLOW_CMD)", "")
-CFLOW_SOURCES = $(addprefix $(srcdir)/, $(SOURCES))
--include $(top_builddir)/lib/liblvm-internal.cflow
--include $(top_builddir)/lib/liblvm2cmd.cflow
--include $(top_builddir)/daemons/dmeventd/$(LIB_NAME).cflow
--include $(top_builddir)/daemons/dmeventd/plugins/mirror/$(LIB_NAME)-lvm2mirror.cflow
-endif
-
 install_include: $(srcdir)/libdevmapper-event.h
-	@echo "    [INSTALL] $<"
+	@echo "    [INSTALL] $(<F)"
 	$(Q) $(INSTALL_DATA) -D $< $(includedir)/$(<F)
 
 install_pkgconfig: libdevmapper-event.pc

daemons/dmeventd/dmeventd.c

@@ -1742,7 +1742,8 @@ static void _init_thread_signals(void)
 	sigset_t my_sigset;
 	struct sigaction act = { .sa_handler = _sig_alarm };
 
-	sigaction(SIGALRM, &act, NULL);
+	if (sigaction(SIGALRM, &act, NULL))
+		log_sys_debug("sigaction", "SIGLARM");
 	sigfillset(&my_sigset);
 
 	/* These are used for exiting */
@@ -2028,8 +2029,8 @@ 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

daemons/dmeventd/libdevmapper-event.c

@@ -615,8 +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/dmeventd/plugins/mirror/Makefile.in

@@ -25,9 +25,6 @@ LIB_NAME = libdevmapper-event-lvm2mirror
 LIB_SHARED = $(LIB_NAME).$(LIB_SUFFIX)
 LIB_VERSION = $(LIB_VERSION_LVM)
 
-CFLOW_LIST = $(SOURCES)
-CFLOW_LIST_TARGET = $(LIB_NAME).cflow
-
 include $(top_builddir)/make.tmpl
 
 install_lvm2: install_dm_plugin

daemons/dmeventd/plugins/raid/Makefile.in

@@ -24,9 +24,6 @@ LIB_NAME = libdevmapper-event-lvm2raid
 LIB_SHARED = $(LIB_NAME).$(LIB_SUFFIX)
 LIB_VERSION = $(LIB_VERSION_LVM)
 
-CFLOW_LIST = $(SOURCES)
-CFLOW_LIST_TARGET = $(LIB_NAME).cflow
-
 include $(top_builddir)/make.tmpl
 
 install_lvm2: install_dm_plugin

daemons/dmeventd/plugins/raid/dmeventd_raid.c

@@ -77,7 +77,7 @@ static int _process_raid_event(struct dso_state *state, char *params, const char
 
 	if (dead) {
 		/*
-		 * Use the first event to run a repair ignoring any additonal ones.
+		 * Use the first event to run a repair ignoring any additional ones.
 		 *
 		 * We presume lvconvert to do pre-repair
 		 * checks to avoid bloat in this plugin.

daemons/dmeventd/plugins/thin/Makefile.in

@@ -24,9 +24,6 @@ LIB_NAME = libdevmapper-event-lvm2thin
 LIB_SHARED = $(LIB_NAME).$(LIB_SUFFIX)
 LIB_VERSION = $(LIB_VERSION_LVM)
 
-CFLOW_LIST = $(SOURCES)
-CFLOW_LIST_TARGET = $(LIB_NAME).cflow
-
 include $(top_builddir)/make.tmpl
 
 install_lvm2: install_dm_plugin

daemons/dmeventd/plugins/vdo/Makefile.in

@@ -24,9 +24,6 @@ LIB_NAME = libdevmapper-event-lvm2vdo
 LIB_SHARED = $(LIB_NAME).$(LIB_SUFFIX)
 LIB_VERSION = $(LIB_VERSION_LVM)
 
-CFLOW_LIST = $(SOURCES)
-CFLOW_LIST_TARGET = $(LIB_NAME).cflow
-
 include $(top_builddir)/make.tmpl
 
 install_lvm2: install_dm_plugin

daemons/lvmdbusd/Makefile.in

@@ -15,7 +15,8 @@ srcdir = @srcdir@
 top_srcdir = @top_srcdir@
 top_builddir = @top_builddir@
 
-lvmdbusdir = $(python3dir)/lvmdbusd
+lvmdbuspydir = $(python3dir)/lvmdbusd
+lvmdbusdir = $(DESTDIR)$(lvmdbuspydir)
 
 LVMDBUS_SRCDIR_FILES = \
 	automatedproperties.py \
@@ -53,16 +54,16 @@ include $(top_builddir)/make.tmpl
 all:
 	$(Q) test -x $(LVMDBUSD) || chmod 755 $(LVMDBUSD)
 
-install_lvmdbusd:
+install_lvmdbusd: $(LVMDBUSD)
 	@echo "    [INSTALL] $<"
 	$(Q) $(INSTALL_DIR) $(sbindir)
 	$(Q) $(INSTALL_SCRIPT) $(LVMDBUSD) $(sbindir)
-	$(Q) $(INSTALL_DIR) $(DESTDIR)$(lvmdbusdir)
-	$(Q) (cd $(srcdir); $(INSTALL_DATA) $(LVMDBUS_SRCDIR_FILES) $(DESTDIR)$(lvmdbusdir))
-	$(Q) $(INSTALL_DATA) $(LVMDBUS_BUILDDIR_FILES) $(DESTDIR)$(lvmdbusdir)
-	$(Q) PYTHON=$(PYTHON3) $(PYCOMPILE) --destdir "$(DESTDIR)" --basedir "$(lvmdbusdir)" $(LVMDBUS_SRCDIR_FILES) $(LVMDBUS_BUILDDIR_FILES)
-	$(Q) $(CHMOD) 755 $(DESTDIR)$(lvmdbusdir)/__pycache__
-	$(Q) $(CHMOD) 444 $(DESTDIR)$(lvmdbusdir)/__pycache__/*.py[co]
+	$(Q) $(INSTALL_DIR) $(lvmdbusdir)
+	$(Q) (cd $(srcdir); $(INSTALL_DATA) $(LVMDBUS_SRCDIR_FILES) $(lvmdbusdir))
+	$(Q) $(INSTALL_DATA) $(LVMDBUS_BUILDDIR_FILES) $(lvmdbusdir)
+	$(Q) PYTHON=$(PYTHON3) $(PYCOMPILE) --destdir "$(DESTDIR)" --basedir "$(lvmdbuspydir)" $(LVMDBUS_SRCDIR_FILES) $(LVMDBUS_BUILDDIR_FILES)
+	$(Q) $(CHMOD) 755 $(lvmdbusdir)/__pycache__
+	$(Q) $(CHMOD) 444 $(lvmdbusdir)/__pycache__/*.py[co]
 
 install_lvm2: install_lvmdbusd
 

daemons/lvmdbusd/cmdhandler.py

@@ -453,6 +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:

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')

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/lvmlockd/Makefile.in

@@ -30,33 +30,39 @@ ifeq ("@BUILD_LOCKDDLM@", "yes")
   LOCK_LIBS += -ldlmcontrol
 endif
 
+ifeq ("@BUILD_LOCKDIDM@", "yes")
+  SOURCES += lvmlockd-idm.c
+  LOCK_LIBS += -lseagate_ilm -lblkid
+endif
+
 SOURCES2 = lvmlockctl.c
 
 TARGETS = lvmlockd lvmlockctl
 
-.PHONY: install_lvmlockd
+CFLOW_SOURCES = $(addprefix $(srcdir)/, $(SOURCES))
+CFLOW_TARGET = lvmlockd
+
+.PHONY: install_lvmlockd install_lvmlockctl
 
 include $(top_builddir)/make.tmpl
 
 CFLAGS += $(EXTRA_EXEC_CFLAGS)
 INCLUDES += -I$(top_srcdir)/libdaemon/server
 LDFLAGS += -L$(top_builddir)/libdaemon/server $(EXTRA_EXEC_LDFLAGS) $(ELDFLAGS)
-LIBS += $(RT_LIBS) $(DAEMON_LIBS) $(PTHREAD_LIBS)
-
+LIBS += $(DAEMON_LIBS) $(PTHREAD_LIBS)
 
 ifeq ($(USE_SD_NOTIFY),yes)
 	CFLAGS += $(shell pkg-config --cflags libsystemd) -DUSE_SD_NOTIFY
 	LIBS += $(shell pkg-config --libs libsystemd)
 endif
 
-lvmlockd: $(OBJECTS) $(top_builddir)/libdaemon/client/libdaemonclient.a \
-		    $(top_builddir)/libdaemon/server/libdaemonserver.a
+lvmlockd: $(OBJECTS) $(top_builddir)/libdaemon/server/libdaemonserver.a $(INTERNAL_LIBS)
 	@echo "    [CC] $@"
-	$(Q) $(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJECTS) $(LOCK_LIBS) -ldaemonserver $(INTERNAL_LIBS) $(LIBS)
+	$(Q) $(CC) $(CFLAGS) $(LDFLAGS) -o $@ $+ $(LOCK_LIBS) $(LIBS)
 
-lvmlockctl: lvmlockctl.o $(top_builddir)/libdaemon/client/libdaemonclient.a
+lvmlockctl: lvmlockctl.o $(INTERNAL_LIBS)
 	@echo "    [CC] $@"
-	$(Q) $(CC) $(CFLAGS) $(LDFLAGS) -o $@ lvmlockctl.o $(INTERNAL_LIBS) $(LIBS)
+	$(Q) $(CC) $(CFLAGS) $(LDFLAGS) -o $@ $+ $(LIBS)
 
 install_lvmlockd: lvmlockd
 	@echo "    [INSTALL] $<"

daemons/lvmlockd/lvmlockctl.c

@@ -18,8 +18,11 @@
 #include <errno.h>
 #include <fcntl.h>
 #include <syslog.h>
+#include <ctype.h>
 #include <sys/socket.h>
 #include <sys/un.h>
+#include <unistd.h>
+#include <sys/wait.h>
 
 static int quit = 0;
 static int info = 0;
@@ -30,6 +33,7 @@ static int kill_vg = 0;
 static int drop_vg = 0;
 static int gl_enable = 0;
 static int gl_disable = 0;
+static int use_stderr = 0;
 static int stop_lockspaces = 0;
 static char *arg_vg_name = NULL;
 
@@ -47,6 +51,22 @@ do { \
 	printf(fmt "\n", ##args); \
 } while (0)
 
+#define log_sys_emerg(fmt, args...) \
+do { \
+	if (use_stderr) \
+		fprintf(stderr, fmt "\n", ##args); \
+	else \
+		syslog(LOG_EMERG, fmt, ##args); \
+} while (0)
+
+#define log_sys_warn(fmt, args...) \
+do { \
+	if (use_stderr) \
+		fprintf(stderr, fmt "\n", ##args); \
+	else \
+		syslog(LOG_WARNING, fmt, ##args); \
+} while (0)
+
 #define MAX_LINE 512
 
 /* copied from lvmlockd-internal.h */
@@ -502,51 +522,274 @@ static int do_stop_lockspaces(void)
 	return rv;
 }
 
-static int do_kill(void)
+static int _reopen_fd_to_null(int fd)
 {
-	daemon_reply reply;
-	int result;
-	int rv;
+	int null_fd;
+	int r = 0;
 
-	syslog(LOG_EMERG, "Lost access to sanlock lease storage in VG %s.", arg_vg_name);
-	/* These two lines explain the manual alternative to the FIXME below. */
-	syslog(LOG_EMERG, "Immediately deactivate LVs in VG %s.", arg_vg_name);
-	syslog(LOG_EMERG, "Once VG is unused, run lvmlockctl --drop %s.", arg_vg_name);
-
-	/*
-	 * It may not be strictly necessary to notify lvmlockd of the kill, but
-	 * lvmlockd can use this information to avoid attempting any new lock
-	 * requests in the VG (which would fail anyway), and can return an
-	 * error indicating that the VG has been killed.
-	 */
-
-	reply = _lvmlockd_send("kill_vg",
-				"cmd = %s", "lvmlockctl",
-				"pid = " FMTd64, (int64_t) getpid(),
-				"vg_name = %s", arg_vg_name,
-				NULL);
-
-	if (!_lvmlockd_result(reply, &result)) {
-		log_error("lvmlockd result %d", result);
-		rv = result;
-	} else {
-		rv = 0;
+	if ((null_fd = open("/dev/null", O_RDWR)) == -1) {
+		log_error("open error /dev/null %d", errno);
+		return 0;
 	}
 
-	daemon_reply_destroy(reply);
+	if (close(fd)) {
+		log_error("close error fd %d %d", fd, errno);
+		goto out;
+	}
 
-	/*
-	 * FIXME: here is where we should implement a strong form of
-	 * blkdeactivate, and if it completes successfully, automatically call
-	 * do_drop() afterward.  (The drop step may not always be necessary
-	 * if the lvm commands run while shutting things down release all the
-	 * leases.)
-	 *
-	 * run_strong_blkdeactivate();
-	 * do_drop();
-	 */
+	if (dup2(null_fd, fd) == -1) {
+		log_error("dup2 error %d", errno);
+		goto out;
+	}
 
-	return rv;
+	r = 1;
+out:
+	if (close(null_fd)) {
+		log_error("close error fd %d %d", null_fd, errno);
+		return 0;
+	}
+
+	return r;
+}
+
+#define MAX_AV_COUNT 32
+#define ONE_ARG_LEN 1024
+
+static void _run_command_pipe(const char *cmd_str, pid_t *pid_out, FILE **fp_out)
+{
+	char arg[ONE_ARG_LEN];
+	char *av[MAX_AV_COUNT + 1]; /* +1 for NULL */
+	char *arg_dup;
+	int av_count = 0;
+	int cmd_len;
+	int arg_len;
+	pid_t pid = 0;
+	FILE *fp = NULL;
+	int pipefd[2];
+	int i;
+
+	for (i = 0; i < MAX_AV_COUNT + 1; i++)
+		av[i] = NULL;
+
+	cmd_len = strlen(cmd_str);
+
+	memset(&arg, 0, sizeof(arg));
+	arg_len = 0;
+
+	for (i = 0; i < cmd_len; i++) {
+		if (!cmd_str[i])
+			break;
+
+		if (av_count == MAX_AV_COUNT)
+			goto out;
+
+		if (cmd_str[i] == '\\') {
+			if (i == (cmd_len - 1))
+				break;
+			i++;
+
+			if (cmd_str[i] == '\\') {
+				arg[arg_len++] = cmd_str[i];
+				continue;
+			}
+			if (isspace(cmd_str[i])) {
+				arg[arg_len++] = cmd_str[i];
+				continue;
+			} else {
+				break;
+			}
+		}
+
+		if (isalnum(cmd_str[i]) || ispunct(cmd_str[i])) {
+			arg[arg_len++] = cmd_str[i];
+		} else if (isspace(cmd_str[i])) {
+			if (arg_len) {
+				if (!(arg_dup = strdup(arg)))
+					goto out;
+				av[av_count++] = arg_dup;
+			}
+
+			memset(arg, 0, sizeof(arg));
+			arg_len = 0;
+		} else {
+			break;
+		}
+	}
+
+	if (arg_len) {
+		if (av_count >= MAX_AV_COUNT)
+			goto out;
+		if (!(arg_dup = strdup(arg)))
+			goto out;
+		av[av_count++] = arg_dup;
+	}
+
+	if (pipe(pipefd)) {
+		log_error("pipe error %d", errno);
+		goto out;
+	}
+
+	pid = fork();
+
+	if (pid < 0) {
+		log_error("fork error %d", errno);
+		pid = 0;
+		goto out;
+	}
+
+	if (pid == 0) {
+		/* Child -> writer, convert pipe[0] to STDOUT */
+		if (!_reopen_fd_to_null(STDIN_FILENO))
+			log_error("reopen STDIN error");
+		else if (close(pipefd[0 /*read*/]))
+			log_error("close error pipe[0] %d", errno);
+		else if (close(STDOUT_FILENO))
+			log_error("close error STDOUT %d", errno);
+		else if (dup2(pipefd[1 /*write*/], STDOUT_FILENO) == -1)
+			log_error("dup2 error STDOUT %d", errno);
+		else if (close(pipefd[1]))
+			log_error("close error pipe[1] %d", errno);
+		else {
+			execvp(av[0], av);
+			log_error("execvp error %d", errno);
+		}
+		_exit(errno);
+	}
+
+	/* Parent -> reader */
+	if (close(pipefd[1 /*write*/]))
+		log_error("close error STDOUT %d", errno);
+
+	if (!(fp = fdopen(pipefd[0 /*read*/],  "r"))) {
+		log_error("fdopen STDIN error %d", errno);
+		if (close(pipefd[0]))
+			log_error("close error STDIN %d", errno);
+	}
+
+ out:
+	for (i = 0; i < MAX_AV_COUNT + 1; i++)
+		free(av[i]);
+
+	*pid_out = pid;
+	*fp_out = fp;
+}
+
+/* Returns -1 on error, 0 on success. */
+
+static int _close_command_pipe(pid_t pid, FILE *fp)
+{
+	int status, estatus;
+	int ret = -1;
+
+	if (waitpid(pid, &status, 0) != pid) {
+		log_error("waitpid error pid %d %d", pid, errno);
+		goto out;
+	}
+
+	if (WIFEXITED(status)) {
+		/* pid exited with an exit code */
+		estatus = WEXITSTATUS(status);
+
+		/* exit status 0: child success */
+		if (!estatus) {
+			ret = 0;
+			goto out;
+		}
+
+		/* exit status not zero: child error */
+		log_error("child exit error %d", estatus);
+		goto out;
+	}
+
+	if (WIFSIGNALED(status)) {
+		/* pid terminated due to a signal */
+		log_error("child exit from signal");
+		goto out;
+	}
+
+	log_error("child exit problem");
+
+out:
+	if (fp && fclose(fp))
+		log_error("fclose error STDIN %d", errno);
+	return ret;
+}
+
+/* Returns -1 on error, 0 on success. */
+
+static int _get_kill_command(char *kill_cmd)
+{
+	char config_cmd[PATH_MAX + 128] = { 0 };
+	char config_val[1024] = { 0 };
+	char line[PATH_MAX] = { 0 };
+	pid_t pid = 0;
+	FILE *fp = NULL;
+
+	snprintf(config_cmd, PATH_MAX, "%s config --typeconfig full global/lvmlockctl_kill_command", LVM_PATH);
+
+	_run_command_pipe(config_cmd, &pid, &fp);
+
+	if (!pid) {
+		log_error("failed to run %s", config_cmd);
+		return -1;
+	}
+
+	if (!fp) {
+		log_error("failed to get output %s", config_cmd);
+		_close_command_pipe(pid, fp);
+		return -1;
+	}
+
+	if (!fgets(line, sizeof(line), fp)) {
+		log_error("no output from %s", config_cmd);
+		goto bad;
+	}
+
+	if (sscanf(line, "lvmlockctl_kill_command=\"%256[^\n\"]\"", config_val) != 1) {
+		log_error("unrecognized config value from %s", config_cmd);
+		goto bad;
+	}
+
+	if (!config_val[0] || (config_val[0] == ' ')) {
+		log_error("invalid config value from %s", config_cmd);
+		goto bad;
+	}
+
+	if (config_val[0] != '/') {
+		log_error("lvmlockctl_kill_command must be full path");
+		goto bad;
+	}
+
+	printf("Found lvmlockctl_kill_command: %s\n", config_val);
+
+	snprintf(kill_cmd, PATH_MAX, "%s %s", config_val, arg_vg_name);
+	kill_cmd[PATH_MAX-1] = '\0';
+
+	_close_command_pipe(pid, fp);
+	return 0;
+bad:
+	_close_command_pipe(pid, fp);
+	return -1;
+}
+
+/* Returns -1 on error, 0 on success. */
+
+static int _run_kill_command(char *kill_cmd)
+{
+	pid_t pid = 0;
+	FILE *fp = NULL;
+	int rv;
+
+	_run_command_pipe(kill_cmd, &pid, &fp);
+	rv = _close_command_pipe(pid, fp);
+
+	if (!pid)
+		return -1;
+
+	if (rv < 0)
+		return -1;
+
+	return 0;
 }
 
 static int do_drop(void)
@@ -555,7 +798,7 @@ static int do_drop(void)
 	int result;
 	int rv;
 
-	syslog(LOG_WARNING, "Dropping locks for VG %s.", arg_vg_name);
+	log_sys_warn("Dropping locks for VG %s.", arg_vg_name);
 
 	/*
 	 * Check for misuse by looking for any active LVs in the VG
@@ -583,6 +826,84 @@ static int do_drop(void)
 	return rv;
 }
 
+static int do_kill(void)
+{
+	char kill_cmd[PATH_MAX] = { 0 };
+	daemon_reply reply;
+	int no_kill_command = 0;
+	int result;
+	int rv;
+
+	log_sys_emerg("lvmlockd lost access to locks in VG %s.", arg_vg_name);
+
+	rv = _get_kill_command(kill_cmd);
+	if (rv < 0) {
+		log_sys_emerg("Immediately deactivate LVs in VG %s.", arg_vg_name);
+		log_sys_emerg("Once VG is unused, run lvmlockctl --drop %s.", arg_vg_name);
+		no_kill_command = 1;
+	}
+
+	/*
+	 * It may not be strictly necessary to notify lvmlockd of the kill, but
+	 * lvmlockd can use this information to avoid attempting any new lock
+	 * requests in the VG (which would fail anyway), and can return an
+	 * error indicating that the VG has been killed.
+	 */
+	_lvmlockd = lvmlockd_open(NULL);
+	if (_lvmlockd.socket_fd < 0 || _lvmlockd.error) {
+		log_error("Cannot connect to lvmlockd for kill_vg.");
+		goto run;
+	}
+	reply = _lvmlockd_send("kill_vg",
+				"cmd = %s", "lvmlockctl",
+				"pid = " FMTd64, (int64_t) getpid(),
+				"vg_name = %s", arg_vg_name,
+				NULL);
+	if (!_lvmlockd_result(reply, &result))
+		log_error("lvmlockd result %d kill_vg", result);
+	daemon_reply_destroy(reply);
+	lvmlockd_close(_lvmlockd);
+
+ run:
+	if (no_kill_command)
+		return 0;
+
+	rv = _run_kill_command(kill_cmd);
+	if (rv < 0) {
+		log_sys_emerg("Failed to run VG %s kill command %s", arg_vg_name, kill_cmd);
+		log_sys_emerg("Immediately deactivate LVs in VG %s.", arg_vg_name);
+		log_sys_emerg("Once VG is unused, run lvmlockctl --drop %s.", arg_vg_name);
+		return -1;
+	}
+
+	log_sys_warn("Successful VG %s kill command %s", arg_vg_name, kill_cmd);
+
+	/*
+	 * If kill command was successfully, call do_drop().  (The drop step
+	 * may not always be necessary if the lvm commands run while shutting
+	 * things down release all the leases.)
+	 */
+	rv = 0;
+	_lvmlockd = lvmlockd_open(NULL);
+	if (_lvmlockd.socket_fd < 0 || _lvmlockd.error) {
+		log_sys_emerg("Failed to connect to lvmlockd to drop locks in VG %s.", arg_vg_name);
+		return -1;
+	}
+	reply = _lvmlockd_send("drop_vg",
+				"cmd = %s", "lvmlockctl",
+				"pid = " FMTd64, (int64_t) getpid(),
+				"vg_name = %s", arg_vg_name,
+				NULL);
+	if (!_lvmlockd_result(reply, &result)) {
+		log_sys_emerg("Failed to drop locks in VG %s", arg_vg_name);
+		rv = result;
+	}
+	daemon_reply_destroy(reply);
+	lvmlockd_close(_lvmlockd);
+
+	return rv;
+}
+
 static void print_usage(void)
 {
 	printf("lvmlockctl options\n");
@@ -600,7 +921,7 @@ static void print_usage(void)
 	printf("--force | -f 0|1>\n");
 	printf("      Force option for other commands.\n");
 	printf("--kill | -k <vgname>\n");
-	printf("      Kill access to the VG when sanlock cannot renew lease.\n");
+	printf("      Kill access to the VG locks are lost (see lvmlockctl_kill_command).\n");
 	printf("--drop | -r <vgname>\n");
 	printf("      Clear locks for the VG when it is unused after kill (-k).\n");
 	printf("--gl-enable | -E <vgname>\n");
@@ -609,6 +930,8 @@ static void print_usage(void)
 	printf("      Tell lvmlockd to disable the global lock in a sanlock VG.\n");
 	printf("--stop-lockspaces | -S\n");
 	printf("      Stop all lockspaces.\n");
+	printf("--stderr | -e\n");
+	printf("      Send kill and drop messages to stderr instead of syslog\n");
 }
 
 static int read_options(int argc, char *argv[])
@@ -628,6 +951,7 @@ static int read_options(int argc, char *argv[])
 		{"gl-enable",       required_argument, 0,  'E' },
 		{"gl-disable",      required_argument, 0,  'D' },
 		{"stop-lockspaces", no_argument,       0,  'S' },
+		{"stderr",          no_argument,       0,  'e' },
 		{0, 0, 0, 0 }
 	};
 
@@ -637,7 +961,7 @@ static int read_options(int argc, char *argv[])
 	}
 
 	while (1) {
-		c = getopt_long(argc, argv, "hqidE:D:w:k:r:S", long_options, &option_index);
+		c = getopt_long(argc, argv, "hqidE:D:w:k:r:Se", long_options, &option_index);
 		if (c == -1)
 			break;
 
@@ -663,23 +987,30 @@ static int read_options(int argc, char *argv[])
 			break;
 		case 'k':
 			kill_vg = 1;
+			free(arg_vg_name);
 			arg_vg_name = strdup(optarg);
 			break;
 		case 'r':
 			drop_vg = 1;
+			free(arg_vg_name);
 			arg_vg_name = strdup(optarg);
 			break;
 		case 'E':
 			gl_enable = 1;
+			free(arg_vg_name);
 			arg_vg_name = strdup(optarg);
 			break;
 		case 'D':
 			gl_disable = 1;
+			free(arg_vg_name);
 			arg_vg_name = strdup(optarg);
 			break;
 		case 'S':
 			stop_lockspaces = 1;
 			break;
+		case 'e':
+			use_stderr = 1;
+			break;
 		default:
 			print_usage();
 			exit(1);
@@ -698,8 +1029,12 @@ int main(int argc, char **argv)
 	if (rv < 0)
 		return rv;
 
-	_lvmlockd = lvmlockd_open(NULL);
+	/* do_kill handles lvmlockd connections itself */
+	if (kill_vg)
+		return do_kill();
 
+
+	_lvmlockd = lvmlockd_open(NULL);
 	if (_lvmlockd.socket_fd < 0 || _lvmlockd.error) {
 		log_error("Cannot connect to lvmlockd.");
 		return -1;
@@ -720,11 +1055,6 @@ int main(int argc, char **argv)
 		goto out;
 	}
 
-	if (kill_vg) {
-		rv = do_kill();
-		goto out;
-	}
-
 	if (drop_vg) {
 		rv = do_drop();
 		goto out;

daemons/lvmlockd/lvmlockd-client.h

@@ -23,9 +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);
@@ -33,7 +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

@@ -421,6 +421,63 @@ struct lockspace *alloc_lockspace(void)
 	return ls;
 }
 
+static char **alloc_pvs_path(struct pvs *pvs, int num)
+{
+	if (!num)
+		return NULL;
+
+	pvs->path = malloc(sizeof(char *) * num);
+	if (!pvs->path)
+		return NULL;
+
+	memset(pvs->path, 0x0, sizeof(char *) * num);
+	return pvs->path;
+}
+
+static void free_pvs_path(struct pvs *pvs)
+{
+	int i;
+
+	for (i = 0; i < pvs->num; i++) {
+		if (!pvs->path[i])
+			continue;
+
+		free((char *)pvs->path[i]);
+		pvs->path[i] = NULL;
+	}
+
+	if (!pvs->path) {
+		free(pvs->path);
+		pvs->path = NULL;
+	}
+}
+
+static char **alloc_and_copy_pvs_path(struct pvs *dst, struct pvs *src)
+{
+	int i;
+
+	if (!alloc_pvs_path(dst, src->num))
+		return NULL;
+
+	dst->num = 0;
+	for (i = 0; i < src->num; i++) {
+		if (!src->path[i] || !strcmp(src->path[i], "none"))
+			continue;
+
+		dst->path[dst->num] = strdup(src->path[i]);
+		if (!dst->path[dst->num]) {
+			log_error("out of memory for copying pvs path");
+			goto failed;
+		}
+		dst->num++;
+	}
+	return dst->path;
+
+failed:
+	free_pvs_path(dst);
+	return NULL;
+}
+
 static struct action *alloc_action(void)
 {
 	struct action *act;
@@ -510,6 +567,9 @@ static void free_action(struct action *act)
 		free(act->path);
 		act->path = NULL;
 	}
+
+	free_pvs_path(&act->pvs);
+
 	pthread_mutex_lock(&unused_struct_mutex);
 	if (unused_action_count >= MAX_UNUSED_ACTION) {
 		free(act);
@@ -564,9 +624,12 @@ static int setup_structs(void)
 	struct lock *lk;
 	int data_san = lm_data_size_sanlock();
 	int data_dlm = lm_data_size_dlm();
+	int data_idm = lm_data_size_idm();
 	int i;
 
 	resource_lm_data_size = data_san > data_dlm ? data_san : data_dlm;
+	resource_lm_data_size = resource_lm_data_size > data_idm ?
+					resource_lm_data_size : data_idm;
 
 	pthread_mutex_init(&unused_struct_mutex, NULL);
 	INIT_LIST_HEAD(&unused_action);
@@ -683,6 +746,8 @@ static const char *lm_str(int x)
 		return "dlm";
 	case LD_LM_SANLOCK:
 		return "sanlock";
+	case LD_LM_IDM:
+		return "idm";
 	default:
 		return "lm_unknown";
 	}
@@ -872,7 +937,7 @@ static int read_adopt_file(struct list_head *vg_lockd)
 	char vg_uuid[72];
 	char lm_type_str[16];
 	char mode[8];
-	struct lockspace *ls, *ls2;
+	struct lockspace *ls = NULL, *ls2;
 	struct resource *r;
 	FILE *fp;
 
@@ -887,8 +952,8 @@ static int read_adopt_file(struct list_head *vg_lockd)
 			continue;
 		else if (!strncmp(adopt_line, "lvmlockd", 8)) {
 			unsigned int v_major = 0, v_minor = 0;
-			sscanf(adopt_line, "lvmlockd adopt_version %u.%u", &v_major, &v_minor);
-			if (v_major != ADOPT_VERSION_MAJOR)
+			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)) {
@@ -896,8 +961,9 @@ static int read_adopt_file(struct list_head *vg_lockd)
 				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 %16s %64s",
+			if (sscanf(adopt_line, "VG: %63s %64s %15s %64s",
 				   vg_uuid, ls->vg_name, lm_type_str, ls->vg_args) != 4) {
 				goto fail;
 			}
@@ -916,8 +982,9 @@ static int read_adopt_file(struct list_head *vg_lockd)
 			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 %8s %u",
+			if (sscanf(adopt_line, "LV: %64s %64s %s %7s %u",
 				   vg_uuid, r->name, r->lv_args, mode, &r->version) != 5) {
 				goto fail;
 			}
@@ -966,6 +1033,8 @@ static int lm_prepare_lockspace(struct lockspace *ls, struct action *act)
 		rv = lm_prepare_lockspace_dlm(ls);
 	else if (ls->lm_type == LD_LM_SANLOCK)
 		rv = lm_prepare_lockspace_sanlock(ls);
+	else if (ls->lm_type == LD_LM_IDM)
+		rv = lm_prepare_lockspace_idm(ls);
 	else
 		return -1;
 
@@ -982,6 +1051,8 @@ static int lm_add_lockspace(struct lockspace *ls, struct action *act, int adopt)
 		rv = lm_add_lockspace_dlm(ls, adopt);
 	else if (ls->lm_type == LD_LM_SANLOCK)
 		rv = lm_add_lockspace_sanlock(ls, adopt);
+	else if (ls->lm_type == LD_LM_IDM)
+		rv = lm_add_lockspace_idm(ls, adopt);
 	else
 		return -1;
 
@@ -998,6 +1069,8 @@ static int lm_rem_lockspace(struct lockspace *ls, struct action *act, int free_v
 		rv = lm_rem_lockspace_dlm(ls, free_vg);
 	else if (ls->lm_type == LD_LM_SANLOCK)
 		rv = lm_rem_lockspace_sanlock(ls, free_vg);
+	else if (ls->lm_type == LD_LM_IDM)
+		rv = lm_rem_lockspace_idm(ls, free_vg);
 	else
 		return -1;
 
@@ -1015,6 +1088,9 @@ static int lm_lock(struct lockspace *ls, struct resource *r, int mode, struct ac
 		rv = lm_lock_dlm(ls, r, mode, vb_out, adopt);
 	else if (ls->lm_type == LD_LM_SANLOCK)
 		rv = lm_lock_sanlock(ls, r, mode, vb_out, retry, adopt);
+	else if (ls->lm_type == LD_LM_IDM)
+		rv = lm_lock_idm(ls, r, mode, vb_out, act->lv_uuid,
+				 &act->pvs, adopt);
 	else
 		return -1;
 
@@ -1032,6 +1108,8 @@ static int lm_convert(struct lockspace *ls, struct resource *r,
 		rv = lm_convert_dlm(ls, r, mode, r_version);
 	else if (ls->lm_type == LD_LM_SANLOCK)
 		rv = lm_convert_sanlock(ls, r, mode, r_version);
+	else if (ls->lm_type == LD_LM_IDM)
+		rv = lm_convert_idm(ls, r, mode, r_version);
 	else
 		return -1;
 
@@ -1049,6 +1127,8 @@ static int lm_unlock(struct lockspace *ls, struct resource *r, struct action *ac
 		rv = lm_unlock_dlm(ls, r, r_version, lmu_flags);
 	else if (ls->lm_type == LD_LM_SANLOCK)
 		rv = lm_unlock_sanlock(ls, r, r_version, lmu_flags);
+	else if (ls->lm_type == LD_LM_IDM)
+		rv = lm_unlock_idm(ls, r, r_version, lmu_flags);
 	else
 		return -1;
 
@@ -1063,6 +1143,8 @@ static int lm_hosts(struct lockspace *ls, int notify)
 		return lm_hosts_dlm(ls, notify);
 	else if (ls->lm_type == LD_LM_SANLOCK)
 		return lm_hosts_sanlock(ls, notify);
+	else if (ls->lm_type == LD_LM_IDM)
+		return lm_hosts_idm(ls, notify);
 	return -1;
 }
 
@@ -1072,6 +1154,8 @@ static void lm_rem_resource(struct lockspace *ls, struct resource *r)
 		lm_rem_resource_dlm(ls, r);
 	else if (ls->lm_type == LD_LM_SANLOCK)
 		lm_rem_resource_sanlock(ls, r);
+	else if (ls->lm_type == LD_LM_IDM)
+		lm_rem_resource_idm(ls, r);
 }
 
 static int lm_find_free_lock(struct lockspace *ls, uint64_t *free_offset, int *sector_size, int *align_size)
@@ -1080,6 +1164,8 @@ static int lm_find_free_lock(struct lockspace *ls, uint64_t *free_offset, int *s
 		return 0;
 	else if (ls->lm_type == LD_LM_SANLOCK)
 		return lm_find_free_lock_sanlock(ls, free_offset, sector_size, align_size);
+	else if (ls->lm_type == LD_LM_IDM)
+		return 0;
 	return -1;
 }
 
@@ -1688,8 +1774,8 @@ static int res_update(struct lockspace *ls, struct resource *r,
 }
 
 /*
- * There is nothing to deallocate when freeing a dlm LV, the LV
- * will simply be unlocked by rem_resource.
+ * For DLM and IDM locking scheme, there is nothing to deallocate when freeing a
+ * LV, the LV will simply be unlocked by rem_resource.
  */
 
 static int free_lv(struct lockspace *ls, struct resource *r)
@@ -1698,6 +1784,8 @@ static int free_lv(struct lockspace *ls, struct resource *r)
 		return lm_free_lv_sanlock(ls, r);
 	else if (ls->lm_type == LD_LM_DLM)
 		return 0;
+	else if (ls->lm_type == LD_LM_IDM)
+		return 0;
 	else
 		return -EINVAL;
 }
@@ -1798,9 +1886,7 @@ static void res_process(struct lockspace *ls, struct resource *r,
 			act->result = -EINVAL;
 			list_del(&act->list);
 			add_client_result(act);
-		}
-
-		if (act->op == LD_OP_LOCK && act->mode == LD_LK_UN) {
+		} else if (act->op == LD_OP_LOCK && act->mode == LD_LK_UN) {
 			rv = res_unlock(ls, r, act);
 
 			if (rv == -ENOENT && (act->flags & LD_AF_UNLOCK_CANCEL))
@@ -2680,7 +2766,7 @@ out_rem:
 
 	log_debug("S %s clearing locks", ls->name);
 
-	rv = clear_locks(ls, free_vg, drop_vg);
+	(void) clear_locks(ls, free_vg, drop_vg);
 
 	/*
 	 * Tell any other hosts in the lockspace to leave it
@@ -2758,6 +2844,8 @@ out_act:
 	ls->drop_vg = drop_vg;
 	if (ls->lm_type == LD_LM_DLM && !strcmp(ls->name, gl_lsname_dlm))
 		global_dlm_lockspace_exists = 0;
+	if (ls->lm_type == LD_LM_IDM && !strcmp(ls->name, gl_lsname_idm))
+		global_idm_lockspace_exists = 0;
 
 	/*
 	 * Avoid a name collision of the same lockspace is added again before
@@ -2849,6 +2937,8 @@ static void gl_ls_name(char *ls_name)
 		memcpy(ls_name, gl_lsname_dlm, MAX_NAME);
 	else if (gl_use_sanlock)
 		memcpy(ls_name, gl_lsname_sanlock, MAX_NAME);
+	else if (gl_use_idm)
+		memcpy(ls_name, gl_lsname_idm, MAX_NAME);
 	else
 		memset(ls_name, 0, MAX_NAME);
 }
@@ -2877,9 +2967,20 @@ static int add_lockspace_thread(const char *ls_name,
 	strncpy(ls->name, ls_name, MAX_NAME);
 	ls->lm_type = lm_type;
 
-	if (act)
+	if (act) {
 		ls->start_client_id = act->client_id;
 
+		/*
+		 * Copy PV list to lockspact structure, so this is
+		 * used for VG locking for idm scheme.
+		 */
+		if (lm_type == LD_LM_IDM &&
+				!alloc_and_copy_pvs_path(&ls->pvs, &act->pvs)) {
+			free(ls);
+			return -ENOMEM;
+		}
+	}
+
 	if (vg_uuid)
 		strncpy(ls->vg_uuid, vg_uuid, 64);
 
@@ -2906,6 +3007,18 @@ static int add_lockspace_thread(const char *ls_name,
 	pthread_mutex_lock(&lockspaces_mutex);
 	ls2 = find_lockspace_name(ls->name);
 	if (ls2) {
+		/*
+		 * If find an existed lockspace, we need to update the PV list
+		 * based on the latest information, and release for the old
+		 * PV list in case it keeps stale information.
+		 */
+		free_pvs_path(&ls2->pvs);
+		if (lm_type == LD_LM_IDM &&
+				!alloc_and_copy_pvs_path(&ls2->pvs, &ls->pvs)) {
+			log_debug("add_lockspace_thread %s fails to allocate pvs", ls->name);
+			rv = -ENOMEM;
+		}
+
 		if (ls2->thread_stop) {
 			log_debug("add_lockspace_thread %s exists and stopping", ls->name);
 			rv = -EAGAIN;
@@ -2918,6 +3031,7 @@ static int add_lockspace_thread(const char *ls_name,
 		}
 		pthread_mutex_unlock(&lockspaces_mutex);
 		free_resource(r);
+		free_pvs_path(&ls->pvs);
 		free(ls);
 		return rv;
 	}
@@ -2931,6 +3045,8 @@ static int add_lockspace_thread(const char *ls_name,
 
 	if (ls->lm_type == LD_LM_DLM && !strcmp(ls->name, gl_lsname_dlm))
 		global_dlm_lockspace_exists = 1;
+	if (ls->lm_type == LD_LM_IDM && !strcmp(ls->name, gl_lsname_idm))
+		global_idm_lockspace_exists = 1;
 	list_add_tail(&ls->list, &lockspaces);
 	pthread_mutex_unlock(&lockspaces_mutex);
 
@@ -2941,6 +3057,7 @@ static int add_lockspace_thread(const char *ls_name,
 		list_del(&ls->list);
 		pthread_mutex_unlock(&lockspaces_mutex);
 		free_resource(r);
+		free_pvs_path(&ls->pvs);
 		free(ls);
 		return rv;
 	}
@@ -2949,16 +3066,15 @@ static int add_lockspace_thread(const char *ls_name,
 }
 
 /*
- * There is no add_sanlock_global_lockspace or
- * rem_sanlock_global_lockspace because with sanlock,
- * the global lockspace is one of the vg lockspaces.
+ * There is no variant for sanlock because, with sanlock, the global
+ * lockspace is one of the vg lockspaces.
  */
-
-static int add_dlm_global_lockspace(struct action *act)
+static int add_global_lockspace(char *ls_name, int lm_type,
+				struct action *act)
 {
 	int rv;
 
-	if (global_dlm_lockspace_exists)
+	if (global_dlm_lockspace_exists || global_idm_lockspace_exists)
 		return 0;
 
 	/*
@@ -2966,9 +3082,9 @@ static int add_dlm_global_lockspace(struct action *act)
 	 * lock request, insert an internal gl sh lock request?
 	 */
 
-	rv = add_lockspace_thread(gl_lsname_dlm, NULL, NULL, LD_LM_DLM, NULL, act);
+	rv = add_lockspace_thread(ls_name, NULL, NULL, lm_type, NULL, act);
 	if (rv < 0)
-		log_debug("add_dlm_global_lockspace add_lockspace_thread %d", rv);
+		log_debug("add_global_lockspace add_lockspace_thread %d", rv);
 
 	/*
 	 * EAGAIN may be returned for a short period because
@@ -2981,12 +3097,12 @@ static int add_dlm_global_lockspace(struct action *act)
 }
 
 /*
- * If dlm gl lockspace is the only one left, then stop it.
- * This is not used for an explicit rem_lockspace action from
- * the client, only for auto remove.
+ * When DLM or IDM locking scheme is used for global lock, if the global
+ * lockspace is the only one left, then stop it.  This is not used for
+ * an explicit rem_lockspace action from the client, only for auto
+ * remove.
  */
-
-static int rem_dlm_global_lockspace(void)
+static int rem_global_lockspace(char *ls_name)
 {
 	struct lockspace *ls, *ls_gl = NULL;
 	int others = 0;
@@ -2994,7 +3110,7 @@ static int rem_dlm_global_lockspace(void)
 
 	pthread_mutex_lock(&lockspaces_mutex);
 	list_for_each_entry(ls, &lockspaces, list) {
-		if (!strcmp(ls->name, gl_lsname_dlm)) {
+		if (!strcmp(ls->name, ls_name)) {
 			ls_gl = ls;
 			continue;
 		}
@@ -3026,6 +3142,26 @@ out:
 	return rv;
 }
 
+static int add_dlm_global_lockspace(struct action *act)
+{
+	return add_global_lockspace(gl_lsname_dlm, LD_LM_DLM, act);
+}
+
+static int rem_dlm_global_lockspace(void)
+{
+	return rem_global_lockspace(gl_lsname_dlm);
+}
+
+static int add_idm_global_lockspace(struct action *act)
+{
+	return add_global_lockspace(gl_lsname_idm, LD_LM_IDM, act);
+}
+
+static int rem_idm_global_lockspace(void)
+{
+	return rem_global_lockspace(gl_lsname_idm);
+}
+
 /*
  * When the first dlm lockspace is added for a vg, automatically add a separate
  * dlm lockspace for the global lock.
@@ -3051,6 +3187,9 @@ static int add_lockspace(struct action *act)
 		if (gl_use_dlm) {
 			rv = add_dlm_global_lockspace(act);
 			return rv;
+		} else if (gl_use_idm) {
+			rv = add_idm_global_lockspace(act);
+			return rv;
 		} else {
 			return -EINVAL;
 		}
@@ -3059,6 +3198,8 @@ static int add_lockspace(struct action *act)
 	if (act->rt == LD_RT_VG) {
 		if (gl_use_dlm)
 			add_dlm_global_lockspace(NULL);
+		else if (gl_use_idm)
+			add_idm_global_lockspace(NULL);
 
 		vg_ls_name(act->vg_name, ls_name);
 
@@ -3126,14 +3267,15 @@ static int rem_lockspace(struct action *act)
 	pthread_mutex_unlock(&lockspaces_mutex);
 
 	/*
-	 * The dlm global lockspace was automatically added when
-	 * the first dlm vg lockspace was added, now reverse that
-	 * by automatically removing the dlm global lockspace when
-	 * the last dlm vg lockspace is removed.
+	 * For DLM and IDM locking scheme, the global lockspace was
+	 * automatically added when the first vg lockspace was added,
+	 * now reverse that by automatically removing the dlm global
+	 * lockspace when the last vg lockspace is removed.
 	 */
-
 	if (rt == LD_RT_VG && gl_use_dlm)
 		rem_dlm_global_lockspace();
+	else if (rt == LD_RT_VG && gl_use_idm)
+		rem_idm_global_lockspace();
 
 	return 0;
 }
@@ -3257,6 +3399,7 @@ static int for_each_lockspace(int do_stop, int do_free, int do_force)
 				if (ls->free_vg) {
 					/* In future we may need to free ls->actions here */
 					free_ls_resources(ls);
+					free_pvs_path(&ls->pvs);
 					free(ls);
 					free_count++;
 				}
@@ -3270,6 +3413,7 @@ static int for_each_lockspace(int do_stop, int do_free, int do_force)
 		if (!gl_type_static) {
 			gl_use_dlm = 0;
 			gl_use_sanlock = 0;
+			gl_use_idm = 0;
 		}
 	}
 	pthread_mutex_unlock(&lockspaces_mutex);
@@ -3345,6 +3489,9 @@ static int work_init_vg(struct action *act)
 		rv = lm_init_vg_sanlock(ls_name, act->vg_name, act->flags, act->vg_args);
 	else if (act->lm_type == LD_LM_DLM)
 		rv = lm_init_vg_dlm(ls_name, act->vg_name, act->flags, act->vg_args);
+	else if (act->lm_type == LD_LM_IDM)
+		/* Non't do anything for IDM when initialize VG */
+		rv = 0;
 	else
 		rv = -EINVAL;
 
@@ -3448,6 +3595,8 @@ static int work_init_lv(struct action *act)
 
 	} else if (act->lm_type == LD_LM_DLM) {
 		return 0;
+	} else if (act->lm_type == LD_LM_IDM) {
+		return 0;
 	} else {
 		log_error("init_lv ls_name %s bad lm_type %d", ls_name, act->lm_type);
 		return -EINVAL;
@@ -3511,20 +3660,29 @@ static void *worker_thread_main(void *arg_in)
 		if (act->op == LD_OP_RUNNING_LM) {
 			int run_sanlock = lm_is_running_sanlock();
 			int run_dlm = lm_is_running_dlm();
+			int run_idm = lm_is_running_idm();
 
 			if (daemon_test) {
 				run_sanlock = gl_use_sanlock;
 				run_dlm = gl_use_dlm;
+				run_idm = gl_use_idm;
 			}
 
-			if (run_sanlock && run_dlm)
+			/*
+			 * It's not possible to enable multiple locking schemes
+			 * for global lock, otherwise, it must be conflict and
+			 * reports it!
+			 */
+			if ((run_sanlock + run_dlm + run_idm) >= 2)
 				act->result = -EXFULL;
-			else if (!run_sanlock && !run_dlm)
+			else if (!run_sanlock && !run_dlm && !run_idm)
 				act->result = -ENOLCK;
 			else if (run_sanlock)
 				act->result = LD_LM_SANLOCK;
 			else if (run_dlm)
 				act->result = LD_LM_DLM;
+			else if (run_idm)
+				act->result = LD_LM_IDM;
 			add_client_result(act);
 
 		} else if ((act->op == LD_OP_LOCK) && (act->flags & LD_AF_SEARCH_LS)) {
@@ -3812,6 +3970,9 @@ static int client_send_result(struct client *cl, struct action *act)
 		} else if (gl_use_dlm) {
 			if (!gl_lsname_dlm[0])
 				strcat(result_flags, "NO_GL_LS,");
+		} else if (gl_use_idm) {
+			if (!gl_lsname_idm[0])
+				strcat(result_flags, "NO_GL_LS,");
 		} else {
 			int found_lm = 0;
 
@@ -3819,6 +3980,8 @@ static int client_send_result(struct client *cl, struct action *act)
 				found_lm++;
 			if (lm_support_sanlock() && lm_is_running_sanlock())
 				found_lm++;
+			if (lm_support_idm() && lm_is_running_idm())
+				found_lm++;
 
 			if (!found_lm)
 				strcat(result_flags, "NO_GL_LS,NO_LM");
@@ -3994,11 +4157,13 @@ static int add_lock_action(struct action *act)
 		if (gl_use_sanlock && (act->op == LD_OP_ENABLE || act->op == LD_OP_DISABLE)) {
 			vg_ls_name(act->vg_name, ls_name);
 		} else {
-			if (!gl_use_dlm && !gl_use_sanlock) {
+			if (!gl_use_dlm && !gl_use_sanlock && !gl_use_idm) {
 				if (lm_is_running_dlm())
 					gl_use_dlm = 1;
 				else if (lm_is_running_sanlock())
 					gl_use_sanlock = 1;
+				else if (lm_is_running_idm())
+					gl_use_idm = 1;
 			}
 			gl_ls_name(ls_name);
 		}
@@ -4046,6 +4211,17 @@ static int add_lock_action(struct action *act)
 			add_dlm_global_lockspace(NULL);
 			goto retry;
 
+		} else if (act->op == LD_OP_LOCK && act->rt == LD_RT_GL && act->mode != LD_LK_UN && gl_use_idm) {
+			/*
+			 * Automatically start the idm global lockspace when
+			 * a command tries to acquire the global lock.
+			 */
+			log_debug("lockspace \"%s\" not found for idm gl, adding...", ls_name);
+			act->flags |= LD_AF_SEARCH_LS;
+			act->flags |= LD_AF_WAIT_STARTING;
+			add_idm_global_lockspace(NULL);
+			goto retry;
+
 		} else if (act->op == LD_OP_LOCK && act->mode == LD_LK_UN) {
 			log_debug("lockspace \"%s\" not found for unlock ignored", ls_name);
 			return -ENOLS;
@@ -4266,6 +4442,8 @@ static int str_to_lm(const char *str)
 		return LD_LM_SANLOCK;
 	if (!strcmp(str, "dlm"))
 		return LD_LM_DLM;
+	if (!strcmp(str, "idm"))
+		return LD_LM_IDM;
 	return -2; 
 }
 
@@ -4601,12 +4779,14 @@ static void client_recv_action(struct client *cl)
 	const char *vg_sysid;
 	const char *path;
 	const char *str;
+	struct pvs pvs;
+	char buf[17];	/* "path[%d]\0", %d outputs signed integer so max to 10 bytes */
 	int64_t val;
 	uint32_t opts = 0;
 	int result = 0;
 	int cl_pid;
 	int op, rt, lm, mode;
-	int rv;
+	int rv, i;
 
 	buffer_init(&req.buffer);
 
@@ -4695,11 +4875,13 @@ static void client_recv_action(struct client *cl)
 	if (!cl->name[0] && cl_name)
 		strncpy(cl->name, cl_name, MAX_NAME);
 
-	if (!gl_use_dlm && !gl_use_sanlock && (lm > 0)) {
+	if (!gl_use_dlm && !gl_use_sanlock && !gl_use_idm && (lm > 0)) {
 		if (lm == LD_LM_DLM && lm_support_dlm())
 			gl_use_dlm = 1;
 		else if (lm == LD_LM_SANLOCK && lm_support_sanlock())
 			gl_use_sanlock = 1;
+		else if (lm == LD_LM_IDM && lm_support_idm())
+			gl_use_idm = 1;
 
 		log_debug("set gl_use_%s", lm_str(lm));
 	}
@@ -4756,6 +4938,40 @@ static void client_recv_action(struct client *cl)
 	if (val)
 		act->host_id = val;
 
+	/* Create PV list for idm */
+	if (lm == LD_LM_IDM) {
+		memset(&pvs, 0x0, sizeof(pvs));
+
+		pvs.num = daemon_request_int(req, "path_num", 0);
+		log_error("pvs_num = %d", pvs.num);
+
+		if (!pvs.num)
+			goto skip_pvs_path;
+
+		/* Receive the pv list which is transferred from LVM command */
+		if (!alloc_pvs_path(&pvs, pvs.num)) {
+			log_error("fail to allocate pvs path");
+			rv = -ENOMEM;
+			goto out;
+		}
+
+		for (i = 0; i < pvs.num; i++) {
+			snprintf(buf, sizeof(buf), "path[%d]", i);
+			pvs.path[i] = (char *)daemon_request_str(req, buf, NULL);
+		}
+
+		if (!alloc_and_copy_pvs_path(&act->pvs, &pvs)) {
+			log_error("fail to allocate pvs path");
+			rv = -ENOMEM;
+			goto out;
+		}
+
+		if (pvs.path)
+			free(pvs.path);
+		pvs.path = NULL;
+	}
+
+skip_pvs_path:
 	act->max_retries = daemon_request_int(req, "max_retries", DEFAULT_MAX_RETRIES);
 
 	dm_config_destroy(req.cft);
@@ -4777,6 +4993,12 @@ static void client_recv_action(struct client *cl)
 		goto out;
 	}
 
+	if (lm == LD_LM_IDM && !lm_support_idm()) {
+		log_debug("idm not supported");
+		rv = -EPROTONOSUPPORT;
+		goto out;
+	}
+
 	if (act->op == LD_OP_LOCK && act->mode != LD_LK_UN)
 		cl->lock_ops = 1;
 
@@ -4966,7 +5188,7 @@ static void *client_thread_main(void *arg_in)
 	}
 out:
 	if (adopt_opt && lock_acquire_written)
-		unlink(adopt_file);
+		(void) unlink(adopt_file);
 	return NULL;
 }
 
@@ -5375,6 +5597,7 @@ static void adopt_locks(void)
 		}
 		
 		list_del(&ls->list);
+		free_pvs_path(&ls->pvs);
 		free(ls);
 	}
 
@@ -5415,6 +5638,7 @@ static void adopt_locks(void)
 		if (rv < 0) {
 			log_error("Failed to create lockspace thread for VG %s", ls->vg_name);
 			list_del(&ls->list);
+			free_pvs_path(&ls->pvs);
 			free(ls);
 			free_action(act);
 			count_start_fail++;
@@ -5738,13 +5962,13 @@ static void adopt_locks(void)
 	if (count_start_fail || count_adopt_fail)
 		goto fail;
 
-	unlink(adopt_file);
+	(void) unlink(adopt_file);
 	write_adopt_file();
 	log_debug("adopt_locks done");
 	return;
 
 fail:
-	unlink(adopt_file);
+	(void) unlink(adopt_file);
 	log_error("adopt_locks failed, reset host");
 }
 
@@ -5857,6 +6081,7 @@ static int main_loop(daemon_state *ds_arg)
 	}
 
 	strcpy(gl_lsname_dlm, S_NAME_GL_DLM);
+	strcpy(gl_lsname_idm, S_NAME_GL_IDM);
 
 	INIT_LIST_HEAD(&lockspaces);
 	pthread_mutex_init(&lockspaces_mutex, NULL);
@@ -6038,14 +6263,14 @@ 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[] = {
@@ -6110,6 +6335,8 @@ int main(int argc, char *argv[])
 				gl_use_dlm = 1;
 			else if (lm == LD_LM_SANLOCK && lm_support_sanlock())
 				gl_use_sanlock = 1;
+			else if (lm == LD_LM_IDM && lm_support_idm())
+				gl_use_idm = 1;
 			else {
 				fprintf(stderr, "invalid gl-type option\n");
 				exit(EXIT_FAILURE);

daemons/lvmlockd/lvmlockd-dlm.c

@@ -327,8 +327,7 @@ int lm_rem_resource_dlm(struct lockspace *ls, struct resource *r)
 		log_error("S %s R %s rem_resource_dlm unlock error %d", ls->name, r->name, rv);
 	}
  out:
-	if (rdd->vb)
-		free(rdd->vb);
+	free(rdd->vb);
 
 	memset(rdd, 0, sizeof(struct rd_dlm));
 	r->lm_init = 0;

daemons/lvmlockd/lvmlockd-idm.c

@@ -0,0 +1,837 @@
+/*
+ * Copyright (C) 2020-2021 Seagate Ltd.
+ *
+ * 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.
+ */
+
+#define _XOPEN_SOURCE 500  /* pthread */
+#define _ISOC99_SOURCE
+
+#include "tools/tool.h"
+
+#include "daemon-server.h"
+#include "lib/mm/xlate.h"
+
+#include "lvmlockd-internal.h"
+#include "daemons/lvmlockd/lvmlockd-client.h"
+
+#include "ilm.h"
+
+#include <blkid/blkid.h>
+#include <ctype.h>
+#include <dirent.h>
+#include <errno.h>
+#include <poll.h>
+#include <regex.h>
+#include <stddef.h>
+#include <syslog.h>
+#include <sys/sysmacros.h>
+#include <time.h>
+
+#define IDM_TIMEOUT	60000	/* unit: millisecond, 60 seconds */
+
+/*
+ * Each lockspace thread has its own In-Drive Mutex (IDM) lock manager's
+ * connection.  After established socket connection, the lockspace has
+ * been created in IDM lock manager and afterwards use the socket file
+ * descriptor to send any requests for lock related operations.
+ */
+
+struct lm_idm {
+	int sock;	/* IDM lock manager connection */
+};
+
+struct rd_idm {
+	struct idm_lock_id id;
+	struct idm_lock_op op;
+	uint64_t vb_timestamp;
+	struct val_blk *vb;
+};
+
+int lm_data_size_idm(void)
+{
+	return sizeof(struct rd_idm);
+}
+
+static uint64_t read_utc_us(void)
+{
+	struct timespec cur_time;
+
+	clock_gettime(CLOCK_REALTIME, &cur_time);
+
+	/*
+	 * Convert to microseconds unit.  IDM reserves the MSB in 8 bytes
+	 * and the low 56 bits are used for timestamp; 56 bits can support
+	 * calendar year to 2284, so it has 260 years for overflow.  Thus it
+	 * is quite safe for overflow issue when wrote this code.
+	 */
+	return cur_time.tv_sec * 1000000 + cur_time.tv_nsec / 1000;
+}
+
+static int uuid_read_format(char *uuid_str, const char *buffer)
+{
+	int out = 0;
+
+	/* just strip out any dashes */
+	while (*buffer) {
+
+		if (*buffer == '-') {
+			buffer++;
+			continue;
+		}
+
+		if (out >= 32) {
+			log_error("Too many characters to be uuid.");
+			return -1;
+		}
+
+		uuid_str[out++] = *buffer;
+		buffer++;
+	}
+
+	if (out != 32) {
+		log_error("Couldn't read uuid: incorrect number of "
+			  "characters.");
+		return -1;
+	}
+
+	return 0;
+}
+
+#define SYSFS_ROOT		"/sys"
+#define BUS_SCSI_DEVS		"/bus/scsi/devices"
+
+static struct idm_lock_op glb_lock_op;
+
+static void lm_idm_free_dir_list(struct dirent **dir_list, int dir_num)
+{
+	int i;
+
+	for (i = 0; i < dir_num; ++i)
+		free(dir_list[i]);
+	free(dir_list);
+}
+
+static int lm_idm_scsi_directory_select(const struct dirent *s)
+{
+	regex_t regex;
+	int ret;
+
+	/* Only select directory with the format x:x:x:x */
+	ret = regcomp(&regex, "^[0-9]+:[0-9]+:[0-9]+:[0-9]+$", REG_EXTENDED);
+	if (ret)
+		return 0;
+
+	ret = regexec(&regex, s->d_name, 0, NULL, 0);
+	if (!ret) {
+		regfree(&regex);
+		return 1;
+	}
+
+	regfree(&regex);
+	return 0;
+}
+
+static int lm_idm_scsi_find_block_dirctory(const char *block_path)
+{
+	struct stat stats;
+
+	if ((stat(block_path, &stats) >= 0) && S_ISDIR(stats.st_mode))
+		return 0;
+
+	return -1;
+}
+
+static int lm_idm_scsi_block_node_select(const struct dirent *s)
+{
+	if (DT_LNK != s->d_type && DT_DIR != s->d_type)
+		return 0;
+
+	if (DT_DIR == s->d_type) {
+		/* Skip this directory: '.' and parent: '..' */
+		if (!strcmp(s->d_name, ".") || !strcmp(s->d_name, ".."))
+			return 0;
+	}
+
+	return 1;
+}
+
+static int lm_idm_scsi_find_block_node(const char *blk_path, char **blk_dev)
+{
+        struct dirent **dir_list;
+        int dir_num;
+
+        dir_num = scandir(blk_path, &dir_list, lm_idm_scsi_block_node_select, NULL);
+        if (dir_num < 0) {
+		log_error("Cannot find valid directory entry in %s", blk_path);
+                return -1;
+	}
+
+	/*
+	 * Should have only one block name under the path, if the dir_num is
+	 * not 1 (e.g. 0 or any number bigger than 1), it must be wrong and
+	 * should never happen.
+	 */
+	if (dir_num == 1)
+		*blk_dev = strdup(dir_list[0]->d_name);
+	else
+		*blk_dev = NULL;
+
+	lm_idm_free_dir_list(dir_list, dir_num);
+
+	if (!*blk_dev)
+		return -1;
+
+        return dir_num;
+}
+
+static int lm_idm_scsi_search_propeller_partition(char *dev)
+{
+	int i, nparts;
+	blkid_probe pr;
+	blkid_partlist ls;
+	int found = -1;
+
+	pr = blkid_new_probe_from_filename(dev);
+	if (!pr) {
+		log_error("%s: failed to create a new libblkid probe", dev);
+		return -1;
+	}
+
+	/* Binary interface */
+	ls = blkid_probe_get_partitions(pr);
+	if (!ls) {
+		log_error("%s: failed to read partitions", dev);
+		return -1;
+	}
+
+	/* List partitions */
+	nparts = blkid_partlist_numof_partitions(ls);
+	if (!nparts)
+		goto done;
+
+	for (i = 0; i < nparts; i++) {
+		const char *p;
+		blkid_partition par = blkid_partlist_get_partition(ls, i);
+
+		p = blkid_partition_get_name(par);
+		if (p) {
+			log_debug("partition name='%s'", p);
+
+			if (!strcmp(p, "propeller"))
+				found = blkid_partition_get_partno(par);
+		}
+
+		if (found >= 0)
+			break;
+	}
+
+done:
+	blkid_free_probe(pr);
+	return found;
+}
+
+static char *lm_idm_scsi_get_block_device_node(const char *scsi_path)
+{
+	char *blk_path = NULL;
+	char *blk_dev = NULL;
+	char *dev_node = NULL;
+	int ret;
+
+	/*
+	 * Locate the "block" directory, such like:
+	 * /sys/bus/scsi/devices/1:0:0:0/block
+	 */
+	ret = asprintf(&blk_path, "%s/%s", scsi_path, "block");
+	if (ret < 0) {
+		log_error("Fail to allocate block path for %s", scsi_path);
+		goto fail;
+	}
+
+	ret = lm_idm_scsi_find_block_dirctory(blk_path);
+	if (ret < 0) {
+		log_error("Fail to find block path %s", blk_path);
+		goto fail;
+	}
+
+	/*
+	 * Locate the block device name, such like:
+	 * /sys/bus/scsi/devices/1:0:0:0/block/sdb
+	 *
+	 * After return from this function and if it makes success,
+	 * the global variable "blk_dev" points to the block device
+	 * name, in this example it points to string "sdb".
+	 */
+	ret = lm_idm_scsi_find_block_node(blk_path, &blk_dev);
+	if (ret < 0) {
+		log_error("Fail to find block node");
+		goto fail;
+	}
+
+	ret = asprintf(&dev_node, "/dev/%s", blk_dev);
+	if (ret < 0) {
+		log_error("Fail to allocate memory for blk node path");
+		goto fail;
+	}
+
+	ret = lm_idm_scsi_search_propeller_partition(dev_node);
+	if (ret < 0)
+		goto fail;
+
+	free(blk_path);
+	free(blk_dev);
+	return dev_node;
+
+fail:
+	free(blk_path);
+	free(blk_dev);
+	free(dev_node);
+	return NULL;
+}
+
+static int lm_idm_get_gl_lock_pv_list(void)
+{
+	struct dirent **dir_list;
+	char scsi_bus_path[PATH_MAX];
+	char *drive_path;
+	int i, dir_num, ret;
+
+	if (glb_lock_op.drive_num)
+		return 0;
+
+	snprintf(scsi_bus_path, sizeof(scsi_bus_path), "%s%s",
+		 SYSFS_ROOT, BUS_SCSI_DEVS);
+
+	dir_num = scandir(scsi_bus_path, &dir_list,
+			  lm_idm_scsi_directory_select, NULL);
+	if (dir_num < 0) {  /* scsi mid level may not be loaded */
+		log_error("Attached devices: none");
+		return -1;
+	}
+
+	for (i = 0; i < dir_num; i++) {
+		char *scsi_path;
+
+		ret = asprintf(&scsi_path, "%s/%s", scsi_bus_path,
+			       dir_list[i]->d_name);
+		if (ret < 0) {
+			log_error("Fail to allocate memory for scsi directory");
+			goto failed;
+		}
+
+		if (glb_lock_op.drive_num >= ILM_DRIVE_MAX_NUM) {
+			log_error("Global lock: drive number %d exceeds limitation (%d) ?!",
+				  glb_lock_op.drive_num, ILM_DRIVE_MAX_NUM);
+			free(scsi_path);
+			goto failed;
+		}
+
+		drive_path = lm_idm_scsi_get_block_device_node(scsi_path);
+		if (!drive_path) {
+			free(scsi_path);
+			continue;
+		}
+
+		glb_lock_op.drives[glb_lock_op.drive_num] = drive_path;
+		glb_lock_op.drive_num++;
+
+		free(scsi_path);
+	}
+
+	lm_idm_free_dir_list(dir_list, dir_num);
+	return 0;
+
+failed:
+	lm_idm_free_dir_list(dir_list, dir_num);
+
+	for (i = 0; i < glb_lock_op.drive_num; i++) {
+		if (glb_lock_op.drives[i]) {
+			free(glb_lock_op.drives[i]);
+			glb_lock_op.drives[i] = NULL;
+		}
+	}
+
+	return -1;
+}
+
+static void lm_idm_update_vb_timestamp(uint64_t *vb_timestamp)
+{
+	uint64_t utc_us = read_utc_us();
+
+	/*
+	 * It's possible that the multiple nodes have no clock
+	 * synchronization with microsecond prcision and the time
+	 * is going backward.  For this case, simply increment the
+	 * existing timestamp and write out to drive.
+	 */
+	if (*vb_timestamp >= utc_us)
+		(*vb_timestamp)++;
+	else
+		*vb_timestamp = utc_us;
+}
+
+int lm_prepare_lockspace_idm(struct lockspace *ls)
+{
+	struct lm_idm *lm = NULL;
+
+	lm = malloc(sizeof(struct lm_idm));
+	if (!lm) {
+		log_error("S %s prepare_lockspace_idm fail to allocate lm_idm for %s",
+			  ls->name, ls->vg_name);
+		return -ENOMEM;
+	}
+	memset(lm, 0x0, sizeof(struct lm_idm));
+
+	ls->lm_data = lm;
+	log_debug("S %s prepare_lockspace_idm done", ls->name);
+	return 0;
+}
+
+int lm_add_lockspace_idm(struct lockspace *ls, int adopt)
+{
+	char killpath[IDM_FAILURE_PATH_LEN];
+	char killargs[IDM_FAILURE_ARGS_LEN];
+	struct lm_idm *lmi = (struct lm_idm *)ls->lm_data;
+	int rv;
+
+	if (daemon_test)
+		return 0;
+
+	if (!strcmp(ls->name, S_NAME_GL_IDM)) {
+		/*
+		 * Prepare the pv list for global lock, if the drive contains
+		 * "propeller" partition, then this drive will be considered
+		 * as a member of pv list.
+		 */
+		rv = lm_idm_get_gl_lock_pv_list();
+		if (rv < 0) {
+			log_error("S %s add_lockspace_idm fail to get pv list for glb lock",
+				  ls->name);
+			return -EIO;
+		} else {
+			log_error("S %s add_lockspace_idm get pv list for glb lock",
+				  ls->name);
+		}
+	}
+
+	/*
+	 * Construct the execution path for command "lvmlockctl" by using the
+	 * path to the lvm binary and appending "lockctl".
+	 */
+	memset(killpath, 0, sizeof(killpath));
+	snprintf(killpath, IDM_FAILURE_PATH_LEN, "%slockctl", LVM_PATH);
+
+	/* Pass the argument "--kill vg_name" for killpath */
+	memset(killargs, 0, sizeof(killargs));
+	snprintf(killargs, IDM_FAILURE_ARGS_LEN, "--kill %s", ls->vg_name);
+
+	/* Connect with IDM lock manager per every lockspace. */
+	rv = ilm_connect(&lmi->sock);
+	if (rv < 0) {
+		log_error("S %s add_lockspace_idm fail to connect the lock manager %d",
+			  ls->name, lmi->sock);
+		lmi->sock = 0;
+		rv = -EMANAGER;
+		goto fail;
+	}
+
+	rv = ilm_set_killpath(lmi->sock, killpath, killargs);
+	if (rv < 0) {
+		log_error("S %s add_lockspace_idm fail to set kill path %d",
+			  ls->name, rv);
+		rv = -EMANAGER;
+		goto fail;
+	}
+
+	log_debug("S %s add_lockspace_idm kill path is: \"%s %s\"",
+		  ls->name, killpath, killargs);
+
+	log_debug("S %s add_lockspace_idm done", ls->name);
+	return 0;
+
+fail:
+	if (lmi && lmi->sock)
+		close(lmi->sock);
+	if (lmi)
+		free(lmi);
+	return rv;
+}
+
+int lm_rem_lockspace_idm(struct lockspace *ls, int free_vg)
+{
+	struct lm_idm *lmi = (struct lm_idm *)ls->lm_data;
+	int i, rv = 0;
+
+	if (daemon_test)
+		goto out;
+
+	rv = ilm_disconnect(lmi->sock);
+	if (rv < 0)
+		log_error("S %s rem_lockspace_idm error %d", ls->name, rv);
+
+	/* Release pv list for global lock */
+	if (!strcmp(ls->name, "lvm_global")) {
+		for (i = 0; i < glb_lock_op.drive_num; i++) {
+			if (glb_lock_op.drives[i]) {
+				free(glb_lock_op.drives[i]);
+				glb_lock_op.drives[i] = NULL;
+			}
+		}
+	}
+
+out:
+	free(lmi);
+	ls->lm_data = NULL;
+	return rv;
+}
+
+static int lm_add_resource_idm(struct lockspace *ls, struct resource *r)
+{
+	struct rd_idm *rdi = (struct rd_idm *)r->lm_data;
+
+	if (r->type == LD_RT_GL || r->type == LD_RT_VG) {
+		rdi->vb = zalloc(sizeof(struct val_blk));
+		if (!rdi->vb)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+int lm_rem_resource_idm(struct lockspace *ls, struct resource *r)
+{
+	struct rd_idm *rdi = (struct rd_idm *)r->lm_data;
+
+	if (rdi->vb)
+		free(rdi->vb);
+
+	memset(rdi, 0, sizeof(struct rd_idm));
+	r->lm_init = 0;
+	return 0;
+}
+
+static int to_idm_mode(int ld_mode)
+{
+	switch (ld_mode) {
+	case LD_LK_EX:
+		return IDM_MODE_EXCLUSIVE;
+	case LD_LK_SH:
+		return IDM_MODE_SHAREABLE;
+	default:
+		break;
+	};
+
+	return -1;
+}
+
+int lm_lock_idm(struct lockspace *ls, struct resource *r, int ld_mode,
+		struct val_blk *vb_out, char *lv_uuid, struct pvs *pvs,
+		int adopt)
+{
+	struct lm_idm *lmi = (struct lm_idm *)ls->lm_data;
+	struct rd_idm *rdi = (struct rd_idm *)r->lm_data;
+	char **drive_path = NULL;
+	uint64_t timestamp;
+	int reset_vb = 0;
+	int rv, i;
+
+	if (!r->lm_init) {
+		rv = lm_add_resource_idm(ls, r);
+		if (rv < 0)
+			return rv;
+		r->lm_init = 1;
+	}
+
+	rdi->op.mode = to_idm_mode(ld_mode);
+	if (rv < 0) {
+		log_error("lock_idm invalid mode %d", ld_mode);
+		return -EINVAL;
+	}
+
+	log_debug("S %s R %s lock_idm", ls->name, r->name);
+
+	if (daemon_test) {
+		if (rdi->vb) {
+			vb_out->version = le16_to_cpu(rdi->vb->version);
+			vb_out->flags = le16_to_cpu(rdi->vb->flags);
+			vb_out->r_version = le32_to_cpu(rdi->vb->r_version);
+		}
+		return 0;
+	}
+
+	rdi->op.timeout = IDM_TIMEOUT;
+
+	/*
+	 * Generate the UUID string, for RT_VG, it only needs to generate
+	 * UUID string for VG level, for RT_LV, it needs to generate
+	 * UUID strings for both VG and LV levels.  At the end, these IDs
+	 * are used as identifier for IDM in drive firmware.
+	 */
+	if (r->type == LD_RT_VG || r->type == LD_RT_LV)
+		log_debug("S %s R %s VG uuid %s", ls->name, r->name, ls->vg_uuid);
+	if (r->type == LD_RT_LV)
+		log_debug("S %s R %s LV uuid %s", ls->name, r->name, lv_uuid);
+
+	memset(&rdi->id, 0x0, sizeof(struct idm_lock_id));
+	if (r->type == LD_RT_VG) {
+		uuid_read_format(rdi->id.vg_uuid, ls->vg_uuid);
+	} else if (r->type == LD_RT_LV) {
+		uuid_read_format(rdi->id.vg_uuid, ls->vg_uuid);
+		uuid_read_format(rdi->id.lv_uuid, lv_uuid);
+	}
+
+	/*
+	 * Establish the drive path list for lock, since different lock type
+	 * has different drive list; the GL lock uses the global pv list,
+	 * the VG lock uses the pv list spanned for the whole volume group,
+	 * the LV lock uses the pv list for the logical volume.
+	 */
+	switch (r->type) {
+	case LD_RT_GL:
+		drive_path = glb_lock_op.drives;
+		rdi->op.drive_num = glb_lock_op.drive_num;
+		break;
+	case LD_RT_VG:
+		drive_path = (char **)ls->pvs.path;
+		rdi->op.drive_num = ls->pvs.num;
+		break;
+	case LD_RT_LV:
+		drive_path = (char **)pvs->path;
+		rdi->op.drive_num = pvs->num;
+		break;
+	default:
+		break;
+	}
+
+	if (!drive_path) {
+		log_error("S %s R %s cannot find the valid drive path array",
+			  ls->name, r->name);
+		return -EINVAL;
+	}
+
+	if (rdi->op.drive_num >= ILM_DRIVE_MAX_NUM) {
+		log_error("S %s R %s exceeds limitation for drive path array",
+			  ls->name, r->name);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < rdi->op.drive_num; i++)
+		rdi->op.drives[i] = drive_path[i];
+
+	log_debug("S %s R %s mode %d drive_num %d timeout %d",
+		  ls->name, r->name, rdi->op.mode,
+		  rdi->op.drive_num, rdi->op.timeout);
+
+	for (i = 0; i < rdi->op.drive_num; i++)
+		log_debug("S %s R %s drive path[%d] %s",
+			  ls->name, r->name, i, rdi->op.drives[i]);
+
+	rv = ilm_lock(lmi->sock, &rdi->id, &rdi->op);
+	if (rv < 0) {
+		log_debug("S %s R %s lock_idm acquire mode %d rv %d",
+			  ls->name, r->name, ld_mode, rv);
+		return -ELOCKIO;
+	}
+
+	if (rdi->vb) {
+		rv = ilm_read_lvb(lmi->sock, &rdi->id, (char *)&timestamp,
+				  sizeof(uint64_t));
+
+		/*
+		 * If fail to read value block, which might be caused by drive
+		 * failure, notify up layer to invalidate metadata.
+		 */
+		if (rv < 0) {
+			log_error("S %s R %s lock_idm get_lvb error %d",
+				  ls->name, r->name, rv);
+			reset_vb = 1;
+
+			/* Reset timestamp */
+			rdi->vb_timestamp = 0;
+
+		/*
+		 * If the cached timestamp mismatches with the stored value
+		 * in the IDM, this means another host has updated timestamp
+		 * for the new VB.  Let's reset VB and notify up layer to
+		 * invalidate metadata.
+		 */
+		} else if (rdi->vb_timestamp != timestamp) {
+			log_debug("S %s R %s lock_idm get lvb timestamp %lu:%lu",
+				  ls->name, r->name, rdi->vb_timestamp,
+				  timestamp);
+
+			rdi->vb_timestamp = timestamp;
+			reset_vb = 1;
+		}
+
+		if (reset_vb == 1) {
+			memset(rdi->vb, 0, sizeof(struct val_blk));
+			memset(vb_out, 0, sizeof(struct val_blk));
+
+			/*
+			 * The lock is still acquired, but the vb values has
+			 * been invalidated.
+			 */
+			rv = 0;
+			goto out;
+		}
+
+		/* Otherwise, copy the cached VB to up layer */
+		memcpy(vb_out, rdi->vb, sizeof(struct val_blk));
+	}
+
+out:
+	return rv;
+}
+
+int lm_convert_idm(struct lockspace *ls, struct resource *r,
+		   int ld_mode, uint32_t r_version)
+{
+	struct lm_idm *lmi = (struct lm_idm *)ls->lm_data;
+	struct rd_idm *rdi = (struct rd_idm *)r->lm_data;
+	int mode, rv;
+
+	if (rdi->vb && r_version && (r->mode == LD_LK_EX)) {
+		if (!rdi->vb->version) {
+			/* first time vb has been written */
+			rdi->vb->version = VAL_BLK_VERSION;
+		}
+		rdi->vb->r_version = r_version;
+
+		log_debug("S %s R %s convert_idm set r_version %u",
+			  ls->name, r->name, r_version);
+
+		lm_idm_update_vb_timestamp(&rdi->vb_timestamp);
+		log_debug("S %s R %s convert_idm vb %x %x %u timestamp %lu",
+			  ls->name, r->name, rdi->vb->version, rdi->vb->flags,
+			  rdi->vb->r_version, rdi->vb_timestamp);
+	}
+
+	mode = to_idm_mode(ld_mode);
+	if (mode < 0) {
+		log_error("S %s R %s convert_idm invalid mode %d",
+			  ls->name, r->name, ld_mode);
+		return -EINVAL;
+	}
+
+	log_debug("S %s R %s convert_idm", ls->name, r->name);
+
+	if (daemon_test)
+		return 0;
+
+	if (rdi->vb && r_version && (r->mode == LD_LK_EX)) {
+		rv = ilm_write_lvb(lmi->sock, &rdi->id,
+				   (char *)rdi->vb_timestamp, sizeof(uint64_t));
+		if (rv < 0) {
+			log_error("S %s R %s convert_idm write lvb error %d",
+				  ls->name, r->name, rv);
+			return -ELMERR;
+		}
+	}
+
+	rv = ilm_convert(lmi->sock, &rdi->id, mode);
+	if (rv < 0)
+		log_error("S %s R %s convert_idm convert error %d",
+			  ls->name, r->name, rv);
+
+	return rv;
+}
+
+int lm_unlock_idm(struct lockspace *ls, struct resource *r,
+		  uint32_t r_version, uint32_t lmu_flags)
+{
+	struct lm_idm *lmi = (struct lm_idm *)ls->lm_data;
+	struct rd_idm *rdi = (struct rd_idm *)r->lm_data;
+	int rv;
+
+	if (rdi->vb && r_version && (r->mode == LD_LK_EX)) {
+		if (!rdi->vb->version) {
+			/* first time vb has been written */
+			rdi->vb->version = VAL_BLK_VERSION;
+		}
+		if (r_version)
+			rdi->vb->r_version = r_version;
+
+		lm_idm_update_vb_timestamp(&rdi->vb_timestamp);
+		log_debug("S %s R %s unlock_idm vb %x %x %u timestamp %lu",
+			  ls->name, r->name, rdi->vb->version, rdi->vb->flags,
+			  rdi->vb->r_version, rdi->vb_timestamp);
+	}
+
+	log_debug("S %s R %s unlock_idm", ls->name, r->name);
+
+	if (daemon_test)
+		return 0;
+
+	if (rdi->vb && r_version && (r->mode == LD_LK_EX)) {
+		rv = ilm_write_lvb(lmi->sock, &rdi->id,
+				   (char *)&rdi->vb_timestamp, sizeof(uint64_t));
+		if (rv < 0) {
+			log_error("S %s R %s unlock_idm set_lvb error %d",
+				  ls->name, r->name, rv);
+			return -ELMERR;
+		}
+	}
+
+	rv = ilm_unlock(lmi->sock, &rdi->id);
+	if (rv < 0)
+		log_error("S %s R %s unlock_idm error %d", ls->name, r->name, rv);
+
+	return rv;
+}
+
+int lm_hosts_idm(struct lockspace *ls, int notify)
+{
+	struct resource *r;
+	struct lm_idm *lmi = (struct lm_idm *)ls->lm_data;
+	struct rd_idm *rdi;
+	int count, self, found_others = 0;
+	int rv;
+
+	list_for_each_entry(r, &ls->resources, list) {
+		if (!r->lm_init)
+			continue;
+
+		rdi = (struct rd_idm *)r->lm_data;
+
+		rv = ilm_get_host_count(lmi->sock, &rdi->id, &rdi->op,
+					&count, &self);
+		if (rv < 0) {
+			log_error("S %s lm_hosts_idm error %d", ls->name, rv);
+			return rv;
+		}
+
+		/* Fixup: need to reduce self count */
+		if (count > found_others)
+			found_others = count;
+	}
+
+	return found_others;
+}
+
+int lm_get_lockspaces_idm(struct list_head *ls_rejoin)
+{
+	/* TODO: Need to add support for adoption. */
+	return -1;
+}
+
+int lm_is_running_idm(void)
+{
+	int sock, rv;
+
+	if (daemon_test)
+		return gl_use_idm;
+
+	rv = ilm_connect(&sock);
+	if (rv < 0) {
+		log_error("Fail to connect seagate IDM lock manager %d", rv);
+		return 0;
+	}
+
+	ilm_disconnect(sock);
+	return 1;
+}

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
 
@@ -18,6 +20,7 @@
 #define R_NAME_GL          "GLLK"
 #define R_NAME_VG          "VGLK"
 #define S_NAME_GL_DLM      "lvm_global"
+#define S_NAME_GL_IDM      "lvm_global"
 #define LVM_LS_PREFIX      "lvm_"           /* ls name is prefix + vg_name */
 /* global lockspace name for sanlock is a vg name */
 
@@ -27,6 +30,7 @@ enum {
 	LD_LM_UNUSED = 1, /* place holder so values match lib/locking/lvmlockd.h */
 	LD_LM_DLM = 2,
 	LD_LM_SANLOCK = 3,
+	LD_LM_IDM = 4,
 };
 
 /* operation types */
@@ -116,6 +120,11 @@ struct client {
  */
 #define DEFAULT_MAX_RETRIES 4
 
+struct pvs {
+	char **path;
+	int num;
+};
+
 struct action {
 	struct list_head list;
 	uint32_t client_id;
@@ -138,6 +147,7 @@ struct action {
 	char vg_args[MAX_ARGS+1];
 	char lv_args[MAX_ARGS+1];
 	char vg_sysid[MAX_NAME+1];
+	struct pvs pvs;			/* PV list for idm */
 };
 
 struct resource {
@@ -156,7 +166,7 @@ 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
@@ -182,6 +192,7 @@ struct lockspace {
 	uint64_t free_lock_offset;	/* for sanlock, start search for free lock here */
 	int free_lock_sector_size;	/* for sanlock */
 	int free_lock_align_size;	/* for sanlock */
+	struct pvs pvs;			/* for idm: PV list */
 
 	uint32_t start_client_id;	/* client_id that started the lockspace */
 	pthread_t thread;		/* makes synchronous lock requests */
@@ -217,10 +228,6 @@ 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;
@@ -327,10 +334,13 @@ static inline int list_empty(const struct list_head *head)
 EXTERN int gl_type_static;
 EXTERN int gl_use_dlm;
 EXTERN int gl_use_sanlock;
+EXTERN int gl_use_idm;
 EXTERN int gl_vg_removed;
 EXTERN char gl_lsname_dlm[MAX_NAME+1];
 EXTERN char gl_lsname_sanlock[MAX_NAME+1];
+EXTERN char gl_lsname_idm[MAX_NAME+1];
 EXTERN int global_dlm_lockspace_exists;
+EXTERN int global_idm_lockspace_exists;
 
 EXTERN int daemon_test; /* run as much as possible without a live lock manager */
 EXTERN int daemon_debug;
@@ -621,4 +631,102 @@ static inline int lm_support_sanlock(void)
 
 #endif /* sanlock support */
 
+#ifdef LOCKDIDM_SUPPORT
+
+int lm_data_size_idm(void);
+int lm_init_vg_idm(char *ls_name, char *vg_name, uint32_t flags, char *vg_args);
+int lm_prepare_lockspace_idm(struct lockspace *ls);
+int lm_add_lockspace_idm(struct lockspace *ls, int adopt);
+int lm_rem_lockspace_idm(struct lockspace *ls, int free_vg);
+int lm_lock_idm(struct lockspace *ls, struct resource *r, int ld_mode,
+		struct val_blk *vb_out, char *lv_uuid, struct pvs *pvs,
+		int adopt);
+int lm_convert_idm(struct lockspace *ls, struct resource *r,
+		   int ld_mode, uint32_t r_version);
+int lm_unlock_idm(struct lockspace *ls, struct resource *r,
+		  uint32_t r_version, uint32_t lmu_flags);
+int lm_hosts_idm(struct lockspace *ls, int notify);
+int lm_get_lockspaces_idm(struct list_head *ls_rejoin);
+int lm_is_running_idm(void);
+int lm_rem_resource_idm(struct lockspace *ls, struct resource *r);
+
+static inline int lm_support_idm(void)
+{
+	return 1;
+}
+
+#else
+
+static inline int lm_data_size_idm(void)
+{
+	return -1;
+}
+
+static inline int lm_init_vg_idm(char *ls_name, char *vg_name, uint32_t flags,
+			  char *vg_args)
+{
+	return -1;
+}
+
+static inline int lm_prepare_lockspace_idm(struct lockspace *ls)
+{
+	return -1;
+}
+
+static inline int lm_add_lockspace_idm(struct lockspace *ls, int adopt)
+{
+	return -1;
+}
+
+static inline int lm_rem_lockspace_idm(struct lockspace *ls, int free_vg)
+{
+	return -1;
+}
+
+static inline int lm_lock_idm(struct lockspace *ls, struct resource *r, int ld_mode,
+		       struct val_blk *vb_out, char *lv_uuid, struct pvs *pvs,
+		       int adopt)
+{
+	return -1;
+}
+
+static inline int lm_convert_idm(struct lockspace *ls, struct resource *r,
+			  int ld_mode, uint32_t r_version)
+{
+	return -1;
+}
+
+static inline int lm_unlock_idm(struct lockspace *ls, struct resource *r,
+			 uint32_t r_version, uint32_t lmu_flags)
+{
+	return -1;
+}
+
+static inline int lm_hosts_idm(struct lockspace *ls, int notify)
+{
+	return -1;
+}
+
+static inline int lm_get_lockspaces_idm(struct list_head *ls_rejoin)
+{
+	return -1;
+}
+
+static inline int lm_is_running_idm(void)
+{
+	return 0;
+}
+
+static inline int lm_rem_resource_idm(struct lockspace *ls, struct resource *r)
+{
+	return -1;
+}
+
+static inline int lm_support_idm(void)
+{
+	return 0;
+}
+
+#endif /* Seagate IDM support */
+
 #endif	/* _LVM_LVMLOCKD_INTERNAL_H */

daemons/lvmlockd/lvmlockd-sanlock.c

@@ -1503,8 +1503,7 @@ out:
 fail:
 	if (lms && lms->sock)
 		close(lms->sock);
-	if (lms)
-		free(lms);
+	free(lms);
 	return ret;
 }
 
@@ -1634,8 +1633,7 @@ int lm_rem_resource_sanlock(struct lockspace *ls, struct resource *r)
 
 	/* FIXME: assert r->mode == UN or unlock if it's not? */
 
-	if (rds->vb)
-		free(rds->vb);
+	free(rds->vb);
 
 	memset(rds, 0, sizeof(struct rd_sanlock));
 	r->lm_init = 0;

daemons/lvmpolld/Makefile.in

@@ -19,11 +19,10 @@ SOURCES = lvmpolld-core.c lvmpolld-data-utils.c lvmpolld-cmd-utils.c
 
 TARGETS = lvmpolld
 
-.PHONY: install_lvmpolld
+CFLOW_SOURCES = $(addprefix $(srcdir)/, $(SOURCES))
+CFLOW_TARGET := $(TARGETS)
 
-CFLOW_LIST = $(SOURCES)
-CFLOW_LIST_TARGET = $(LIB_NAME).cflow
-CFLOW_TARGET = lvmpolld
+.PHONY: install_lvmpolld
 
 include $(top_builddir)/make.tmpl
 

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

@@ -149,7 +149,7 @@ static void _lvmpolld_global_unlock(struct lvmpolld_state *ls)
 static int _fini(struct daemon_state *s)
 {
 	int done;
-	const struct timespec t = { .tv_nsec = 250000000 }; /* .25 sec */
+	const struct timespec t = { .tv_nsec = 10000000 }; /* .01 sec */
 	struct lvmpolld_state *ls = s->private;
 
 	DEBUGLOG(s, "fini");
@@ -236,9 +236,7 @@ static int poll_for_output(struct lvmpolld_lv *pdlv, struct lvmpolld_thread_data
 	}
 
 	while (1) {
-		do {
-			r = poll(fds, 2, pdlv_get_timeout(pdlv) * 1000);
-		} while (r < 0 && errno == EINTR);
+		r = poll(fds, 2, pdlv_get_timeout(pdlv) * 1000);
 
 		DEBUGLOG(pdlv->ls, "%s: %s %d", PD_LOG_PREFIX, "poll() returned", r);
 		if (r < 0) {
@@ -555,14 +553,15 @@ 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 +620,7 @@ 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 +680,7 @@ 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);
@@ -951,6 +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
@@ -970,6 +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,
@@ -1015,6 +1019,7 @@ int dm_tree_node_add_integrity_target(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 *param);
@@ -1067,10 +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)
 
@@ -1083,6 +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 */
@@ -1313,7 +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/datastruct/bitset.c

@@ -242,18 +242,3 @@ bad:
 	}
 	return NULL;
 }
-
-#if defined(__GNUC__)
-/*
- * Maintain backward compatibility with older versions that did not
- * accept a 'min_num_bits' argument to dm_bitset_parse_list().
- */
-dm_bitset_t dm_bitset_parse_list_v1_02_129(const char *str, struct dm_pool *mem);
-dm_bitset_t dm_bitset_parse_list_v1_02_129(const char *str, struct dm_pool *mem)
-{
-	return dm_bitset_parse_list(str, mem, 0);
-}
-
-#else /* if defined(__GNUC__) */
-
-#endif

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;
@@ -493,7 +493,10 @@ static void _dm_task_free_targets(struct dm_task *dmt)
 
 	for (t = dmt->head; t; t = n) {
 		n = t->next;
-		_dm_zfree_string(t->params);
+		if (dmt->secure_data)
+			_dm_zfree_string(t->params);
+		else
+			free(t->params);
 		free(t->type);
 		free(t);
 	}
@@ -504,7 +507,10 @@ static void _dm_task_free_targets(struct dm_task *dmt)
 void dm_task_destroy(struct dm_task *dmt)
 {
 	_dm_task_free_targets(dmt);
-	_dm_zfree_dmi(dmt->dmi.v4);
+	if (dmt->secure_data)
+		_dm_zfree_dmi(dmt->dmi.v4);
+	else
+		free(dmt->dmi.v4);
 	free(dmt->dev_name);
 	free(dmt->mangled_dev_name);
 	free(dmt->newname);
@@ -1112,7 +1118,7 @@ static int _add_params(int type)
 
 static struct dm_ioctl *_flatten(struct dm_task *dmt, unsigned repeat_count)
 {
-	const size_t min_size = 16 * 1024;
+	size_t min_size;
 	const int (*version)[3];
 
 	struct dm_ioctl *dmi;
@@ -1131,6 +1137,18 @@ static struct dm_ioctl *_flatten(struct dm_task *dmt, unsigned repeat_count)
 	else if (dmt->head)
 		log_debug_activation(INTERNAL_ERROR "dm '%s' ioctl should not define parameters.",
 				     _cmd_data_v4[dmt->type].name);
+	switch (dmt->type) {
+	case DM_DEVICE_CREATE:
+	case DM_DEVICE_DEPS:
+	case DM_DEVICE_LIST:
+	case DM_DEVICE_STATUS:
+	case DM_DEVICE_TABLE:
+	case DM_DEVICE_TARGET_MSG:
+		min_size = 16 * 1024;
+		break;
+	default:
+		min_size = 2 * 1024;
+	}
 
 	if (count && (dmt->sector || dmt->message)) {
 		log_error("targets and message are incompatible");
@@ -1334,7 +1352,7 @@ static int _process_mapper_dir(struct dm_task *dmt)
 	}
 
 	if (closedir(d))
-		log_sys_error("closedir", dir);
+		log_sys_debug("closedir", dir);
 
 	return r;
 }
@@ -1582,23 +1600,30 @@ static int _reload_with_suppression_v4(struct dm_task *dmt)
 			t2->params[len] = '\0';
 
 		if (t1->start != t2->start) {
-			log_debug("reload %u:%u start diff", task->major, task->minor);
+			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 length diff", task->major, task->minor);
+			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 type diff %s %s", task->major, task->minor, 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 skip params ignore %s %s",
-					  task->major, task->minor, t1->params, t2->params);
-			else {
-				log_debug("reload %u:%u params diff", task->major, task->minor);
+			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;
 			}
 		}
@@ -2184,52 +2209,3 @@ void dm_lib_exit(void)
 	_version_ok = 1;
 	_version_checked = 0;
 }
-
-#if defined(__GNUC__)
-/*
- * Maintain binary backward compatibility.
- * Version script mechanism works with 'gcc' compatible compilers only.
- */
-
-/*
- * This following code is here to retain ABI compatibility after adding
- * the field deferred_remove to struct dm_info in version 1.02.89.
- *
- * Binaries linked against version 1.02.88 of libdevmapper or earlier
- * will use this function that returns dm_info without the
- * deferred_remove field.
- *
- * Binaries compiled against version 1.02.89 onwards will use
- * the new function dm_task_get_info_with_deferred_remove due to the
- * #define.
- *
- * N.B. Keep this function at the end of the file to make sure that
- * no code in this file accidentally calls it.
- */
-
-int dm_task_get_info_base(struct dm_task *dmt, struct dm_info *info);
-int dm_task_get_info_base(struct dm_task *dmt, struct dm_info *info)
-{
-	struct dm_info new_info;
-
-	if (!dm_task_get_info(dmt, &new_info))
-		return 0;
-
-	memcpy(info, &new_info, offsetof(struct dm_info, deferred_remove));
-
-	return 1;
-}
-
-int dm_task_get_info_with_deferred_remove(struct dm_task *dmt, struct dm_info *info);
-int dm_task_get_info_with_deferred_remove(struct dm_task *dmt, struct dm_info *info)
-{
-	struct dm_info new_info;
-
-	if (!dm_task_get_info(dmt, &new_info))
-		return 0;
-
-	memcpy(info, &new_info, offsetof(struct dm_info, internal_suspend));
-
-	return 1;
-}
-#endif

device_mapper/libdm-common.c

@@ -382,7 +382,7 @@ static int _find_dm_name_of_device(dev_t st_rdev, char *buf, size_t buf_len)
 	}
 
 	if (closedir(d))
-		log_sys_error("closedir", _dm_dir);
+		log_sys_debug("closedir", _dm_dir);
 
 	return r;
 }
@@ -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)
@@ -931,7 +931,7 @@ int dm_task_add_target(struct dm_task *dmt, uint64_t start, uint64_t size,
 
 #ifdef HAVE_SELINUX
 static int _selabel_lookup(const char *path, mode_t mode,
-			   security_context_t *scontext)
+			   char **scontext)
 {
 #ifdef HAVE_SELINUX_LABEL_H
 	if (!_selabel_handle &&
@@ -974,7 +974,7 @@ static int _is_selinux_enabled(void)
 int dm_prepare_selinux_context(const char *path, mode_t mode)
 {
 #ifdef HAVE_SELINUX
-	security_context_t scontext = NULL;
+	char *scontext = NULL;
 
 	if (_is_selinux_enabled() <= 0)
 		return 1;
@@ -1002,7 +1002,7 @@ int dm_prepare_selinux_context(const char *path, mode_t mode)
 int dm_set_selinux_context(const char *path, mode_t mode)
 {
 #ifdef HAVE_SELINUX
-	security_context_t scontext = NULL;
+	char *scontext = NULL;
 
 	if (_is_selinux_enabled() <= 0)
 		return 1;
@@ -1224,7 +1224,7 @@ int get_dev_node_read_ahead(const char *dev_name, uint32_t major, uint32_t minor
 	int len;
 	int r = 1;
 	int fd;
-	long read_ahead_long;
+	long read_ahead_long = 0;
 
 	/*
 	 * If we know the device number, use sysfs if we can.
@@ -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-config.c

@@ -599,7 +599,7 @@ static struct dm_config_node *_section(struct parser *p, struct dm_config_node *
 		match(TOK_IDENTIFIER);
 	}
 
-	if (!strlen(str)) {
+	if (!*str) {
 		log_error("Parse error at byte %" PRIptrdiff_t " (line %d): empty section identifier",
 			  p->tb - p->fb + 1, p->line);
 		return NULL;
@@ -983,7 +983,7 @@ static const char *_find_config_str(const void *start, node_lookup_fn find_fn,
 	}
 
 	if (fail)
-		log_very_verbose("%s not found in config: defaulting to %s",
+		log_very_verbose("%s not found in config: defaulting to \"%s\"",
 				 path, fail);
 	return fail;
 }

device_mapper/libdm-deptree.c

@@ -380,13 +380,13 @@ struct dm_tree *dm_tree_create(void)
 	dtree->mem = dmem;
 	dtree->optional_uuid_suffixes = NULL;
 
-	if (!(dtree->devs = dm_hash_create(8))) {
+	if (!(dtree->devs = dm_hash_create(61))) {
 		log_error("dtree hash creation failed");
 		dm_pool_destroy(dtree->mem);
 		return NULL;
 	}
 
-	if (!(dtree->uuids = dm_hash_create(32))) {
+	if (!(dtree->uuids = dm_hash_create(31))) {
 		log_error("dtree uuid hash creation failed");
 		dm_hash_destroy(dtree->devs);
 		dm_pool_destroy(dtree->mem);
@@ -1589,8 +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;
 }
@@ -1637,6 +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;
@@ -2098,7 +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;
@@ -2147,38 +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)) {
@@ -2367,7 +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)
@@ -2569,7 +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;
@@ -2670,6 +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;
 
@@ -2713,6 +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,
@@ -2797,6 +2824,9 @@ static int _integrity_emit_segment_line(struct dm_task *dmt,
 	if (set->sectors_per_bit_set)
 		EMIT_PARAMS(pos, " sectors_per_bit:%llu", (unsigned long long)set->sectors_per_bit);
 
+	if (!dm_task_secure_data(dmt))
+		stack;
+
 	return 1;
 }
 
@@ -2900,7 +2930,6 @@ 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];
 
@@ -2911,8 +2940,7 @@ 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:
@@ -2933,7 +2961,7 @@ 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:
@@ -2962,9 +2990,8 @@ 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;
@@ -3005,10 +3032,9 @@ 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,
@@ -3179,6 +3205,16 @@ 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)
@@ -3208,7 +3244,7 @@ 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 */
@@ -3218,24 +3254,15 @@ 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 */
@@ -3253,28 +3280,19 @@ 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;
 			}
@@ -3959,6 +3977,24 @@ 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;
@@ -3986,17 +4022,18 @@ 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);
@@ -4291,63 +4328,9 @@ void dm_tree_node_set_callback(struct dm_tree_node *dnode,
 	dnode->callback_data = data;
 }
 
-#if defined(__GNUC__)
-/*
- * Backward compatible implementations.
- *
- * Keep these at the end of the file to make sure that
- * no code in this file accidentally calls it.
- */
-
-/* Backward compatible dm_tree_node_size_changed() implementations. */
-int dm_tree_node_size_changed_base(const struct dm_tree_node *dnode);
-int dm_tree_node_size_changed_base(const struct dm_tree_node *dnode)
-{
-	/* Base does not make difference between smaller and bigger */
-	return dm_tree_node_size_changed(dnode) ? 1 : 0;
-}
-
-/*
- * Retain ABI compatibility after adding the DM_CACHE_FEATURE_METADATA2
- * in version 1.02.138.
- *
- * Binaries compiled against version 1.02.138 onwards will use
- * the new function dm_tree_node_add_cache_target which detects unknown
- * feature flags and returns error for them.
- */
-int dm_tree_node_add_cache_target_base(struct dm_tree_node *node,
-				       uint64_t size,
-				       uint64_t feature_flags, /* DM_CACHE_FEATURE_* */
-				       const char *metadata_uuid,
-				       const char *data_uuid,
-				       const char *origin_uuid,
-				       const char *policy_name,
-				       const struct dm_config_node *policy_settings,
-				       uint32_t data_block_size);
-int dm_tree_node_add_cache_target_base(struct dm_tree_node *node,
-				       uint64_t size,
-				       uint64_t feature_flags,
-				       const char *metadata_uuid,
-				       const char *data_uuid,
-				       const char *origin_uuid,
-				       const char *policy_name,
-				       const struct dm_config_node *policy_settings,
-				       uint32_t data_block_size)
-{
-	/* Old version supported only these FEATURE bits, others were ignored so masked them */
-	static const uint64_t _mask =
-		DM_CACHE_FEATURE_WRITEBACK |
-		DM_CACHE_FEATURE_WRITETHROUGH |
-		DM_CACHE_FEATURE_PASSTHROUGH;
-
-	return dm_tree_node_add_cache_target(node, size, feature_flags & _mask,
-					     metadata_uuid, data_uuid, origin_uuid,
-					     policy_name, policy_settings, 0, 0, 0, 0, data_block_size);
-}
-#endif
-
 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)
@@ -4369,7 +4352,7 @@ 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-file.c

@@ -110,7 +110,7 @@ int dm_is_empty_dir(const char *dir)
 	DIR *d;
 
 	if (!(d = opendir(dir))) {
-		log_sys_error("opendir", dir);
+		log_sys_debug("opendir", dir);
 		return 0;
 	}
 
@@ -119,7 +119,7 @@ int dm_is_empty_dir(const char *dir)
 			break;
 
 	if (closedir(d))
-		log_sys_error("closedir", dir);
+		log_sys_debug("closedir", dir);
 
 	return dirent ? 0 : 1;
 }

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(" ");
@@ -2473,7 +2474,7 @@ dm_percent_t dm_make_percent(uint64_t numerator, uint64_t denominator)
 
 int dm_report_value_cache_set(struct dm_report *rh, const char *name, const void *data)
 {
-	if (!rh->value_cache && (!(rh->value_cache = dm_hash_create(64)))) {
+	if (!rh->value_cache && (!(rh->value_cache = dm_hash_create(63)))) {
 		log_error("Failed to create cache for values used during reporting.");
 		return 0;
 	}
@@ -3773,7 +3774,7 @@ static struct selection_node *_parse_selection(struct dm_report *rh,
 	struct field_selection *fs;
 	struct selection_node *sn;
 	const char *ws, *we; /* field name */
-	const char *vs, *ve; /* value */
+	const char *vs = NULL, *ve = NULL; /* value */
 	const char *last;
 	uint32_t flags, field_num;
 	int implicit;

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);

doc/kernel/integrity.txt

@@ -94,7 +94,7 @@ journal_watermark:number
 
 commit_time:number
 	Commit time in milliseconds. When this time passes, the journal is
-	written. The journal is also written immediatelly if the FLUSH
+	written. The journal is also written immediately if the FLUSH
 	request is received.
 
 internal_hash:algorithm(:key)	(the key is optional)

include/.gitignore

@@ -1 +1,3 @@
 *.h
+.symlinks
+.symlinks_created

include/configure.h.in

@@ -126,9 +126,15 @@
 /* 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
 
+/* Define to use GNU versioning in the shared library. */
+#undef GNU_SYMVER
+
 /* Define to 1 if you have the `alarm' function. */
 #undef HAVE_ALARM
 
@@ -151,6 +157,9 @@
 /* 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 +185,9 @@
 /* Define to 1 if you don't have `vprintf' but do have `_doprnt.' */
 #undef HAVE_DOPRNT
 
+/* 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
 
@@ -546,6 +561,9 @@
 /* Define to 1 to include code that uses lvmlockd sanlock option. */
 #undef LOCKDSANLOCK_SUPPORT
 
+/* Define to 1 to include code that uses lvmlockd IDM option. */
+#undef LOCKDIDM_SUPPORT
+
 /* Define to 1 if `lstat' dereferences a symlink specified with a trailing
    slash. */
 #undef LSTAT_FOLLOWS_SLASHED_SYMLINK
@@ -678,9 +696,6 @@
 /* Define to 1 to include built-in support for writecache. */
 #undef WRITECACHE_INTERNAL
 
-/* Define to 1 to include built-in support for integrity. */
-#undef INTEGRITY_INTERNAL
-
 /* Define to get access to GNU/Linux extension */
 #undef _GNU_SOURCE
 

lib/Makefile.in

@@ -15,6 +15,7 @@
 srcdir = @srcdir@
 top_srcdir = @top_srcdir@
 top_builddir = @top_builddir@
+abs_srcdir = @abs_srcdir@
 
 SOURCES =\
 	activate/activate.c \
@@ -29,6 +30,7 @@ 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 +54,7 @@ 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 \

lib/activate/activate.c

@@ -29,6 +29,7 @@
 #include "lib/metadata/segtype.h"
 #include "lib/misc/sharedlib.h"
 #include "lib/metadata/metadata.h"
+#include "lib/misc/lvm-signal.h"
 
 #include <limits.h>
 #include <fcntl.h>
@@ -177,6 +178,22 @@ int lv_passes_auto_activation_filter(struct cmd_context *cmd, struct logical_vol
 	return _lv_passes_volumes_filter(cmd, lv, cn, activation_auto_activation_volume_list_CFG);
 }
 
+static int _passes_readonly_filter(struct cmd_context *cmd,
+				   const struct logical_volume *lv)
+{
+	const struct dm_config_node *cn;
+
+	if (!(cn = find_config_tree_array(cmd, activation_read_only_volume_list_CFG, NULL)))
+		return 0;
+
+	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);
+}
+
 #ifndef DEVMAPPER_SUPPORT
 void set_activation(int act, int silent)
 {
@@ -185,8 +202,8 @@ 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 +238,13 @@ 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 +291,21 @@ 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_raid_status(const struct logical_volume *lv, struct lv_status_raid **status)
 {
 	return 0;
 }
-int lv_thin_percent(const struct logical_volume *lv, int mapped,
-		    dm_percent_t *percent)
+int lv_writecache_message(const struct logical_volume *lv, const char *msg)
 {
 	return 0;
 }
-int lv_thin_pool_transaction_id(const struct logical_volume *lv,
-				uint64_t *transaction_id)
+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_status(const struct logical_volume *lv, int flush,
+		   struct lv_status_thin **thin_status)
 {
 	return 0;
 }
@@ -303,6 +313,15 @@ 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;
@@ -394,7 +413,7 @@ int add_areas_line(struct dev_manager *dm, struct lv_segment *seg,
 {
         return 0;
 }
-int device_is_usable(struct device *dev, struct dev_usable_check_params check)
+int device_is_usable(struct device *dev, struct dev_usable_check_params check, int *is_lv)
 {
         return 0;
 }
@@ -457,17 +476,6 @@ static int _passes_activation_filter(struct cmd_context *cmd,
 	return _lv_passes_volumes_filter(cmd, lv, cn, activation_volume_list_CFG);
 }
 
-static int _passes_readonly_filter(struct cmd_context *cmd,
-				   const struct logical_volume *lv)
-{
-	const struct dm_config_node *cn;
-
-	if (!(cn = find_config_tree_array(cmd, activation_read_only_volume_list_CFG, NULL)))
-		return 0;
-
-	return _lv_passes_volumes_filter(cmd, lv, cn, activation_read_only_volume_list_CFG);
-}
-
 int library_version(char *version, size_t size)
 {
 	if (!activation())
@@ -566,13 +574,9 @@ int module_present(struct cmd_context *cmd, const char *target_name)
 	}
 
 #ifdef MODPROBE_CMD
-	if (strcmp(target_name, MODULE_NAME_VDO) == 0) {
-		argv[1] = target_name;		/* ATM kvdo is without dm- prefix */
-		if ((ret = exec_cmd(cmd, argv, NULL, 0)))
-			return ret;
-	}
-
-	if (dm_snprintf(module, sizeof(module), "dm-%s", target_name) < 0) {
+	if (strcmp(target_name, TARGET_NAME_VDO) == 0)
+		argv[1] = MODULE_NAME_VDO; /* ATM kvdo is without dm- prefix */
+	else if (dm_snprintf(module, sizeof(module), "dm-%s", target_name) < 0) {
 		log_error("module_present module name too long: %s",
 			  target_name);
 		return 0;
@@ -825,12 +829,15 @@ int lv_info_with_seg_status(struct cmd_context *cmd,
 #define OPEN_COUNT_CHECK_USLEEP_DELAY 200000
 
 /* Only report error if error_if_used is set */
+/* Returns 0 if in use,  1 if it is unused, 2 when it is not present in table */
 int lv_check_not_in_use(const struct logical_volume *lv, int error_if_used)
 {
 	struct lvinfo info;
 	unsigned int open_count_check_retries;
 
-	if (!lv_info(lv->vg->cmd, lv, 0, &info, 1, 0) || !info.exists || !info.open_count)
+	if (!lv_info(lv->vg->cmd, lv, 0, &info, 1, 0) || !info.exists)
+		return 2;
+	else if (!info.open_count)
 		return 1;
 
 	/* If sysfs is not used, use open_count information only. */
@@ -857,25 +864,24 @@ int lv_check_not_in_use(const struct logical_volume *lv, int error_if_used)
 	}
 
 	open_count_check_retries = retry_deactivation() ? OPEN_COUNT_CHECK_RETRIES : 1;
-	while (info.open_count > 0 && open_count_check_retries--) {
-		if (!open_count_check_retries) {
-			if (error_if_used)
-				log_error("Logical volume %s in use.", display_lvname(lv));
-			else
-				log_debug_activation("Logical volume %s in use.", display_lvname(lv));
-			return 0;
-		}
+	while (open_count_check_retries--) {
+		if (interruptible_usleep(OPEN_COUNT_CHECK_USLEEP_DELAY))
+			break;  /* interrupted */
 
-		usleep(OPEN_COUNT_CHECK_USLEEP_DELAY);
 		log_debug_activation("Retrying open_count check for %s.",
 				     display_lvname(lv));
-		if (!lv_info(lv->vg->cmd, lv, 0, &info, 1, 0)) {
+		if (!lv_info(lv->vg->cmd, lv, 0, &info, 1, 0) || !info.exists) {
 			stack; /* device dissappeared? */
-			break;
-		}
+			return 1;
+		} else if (!info.open_count)
+			return 1;
 	}
 
-	return 1;
+	if (error_if_used)
+		log_error("Logical volume %s in use.", display_lvname(lv));
+	else
+		log_debug_activation("Logical volume %s in use.", display_lvname(lv));
+	return 0;
 }
 
 /*
@@ -966,35 +972,28 @@ int lv_raid_percent(const struct logical_volume *lv, dm_percent_t *percent)
 
 int lv_raid_data_offset(const struct logical_volume *lv, uint64_t *data_offset)
 {
-	int r;
-	struct dev_manager *dm;
-	struct dm_status_raid *status;
+	struct lv_status_raid *raid_status;
 
 	if (!lv_info(lv->vg->cmd, lv, 0, NULL, 0, 0))
 		return 0;
 
 	log_debug_activation("Checking raid data offset and dev sectors for LV %s/%s",
 			     lv->vg->name, lv->name);
-	if (!(dm = dev_manager_create(lv->vg->cmd, lv->vg->name, 1)))
-		return_0;
 
-	if (!(r = dev_manager_raid_status(dm, lv, &status))) {
-		dev_manager_destroy(dm);
-		return_0;
-	}
+	if (!lv_raid_status(lv, &raid_status))
+                return_0;
 
-	*data_offset = status->data_offset;
+	*data_offset = raid_status->raid->data_offset;
 
-	dev_manager_destroy(dm);
+	dm_pool_destroy(raid_status->mem);
 
-	return r;
+	return 1;
 }
 
 int lv_raid_dev_health(const struct logical_volume *lv, char **dev_health)
 {
-	int r;
-	struct dev_manager *dm;
-	struct dm_status_raid *status;
+	int r = 1;
+	struct lv_status_raid *raid_status;
 
 	*dev_health = NULL;
 
@@ -1004,25 +1003,23 @@ int lv_raid_dev_health(const struct logical_volume *lv, char **dev_health)
 	log_debug_activation("Checking raid device health for LV %s.",
 			     display_lvname(lv));
 
-	if (!(dm = dev_manager_create(lv->vg->cmd, lv->vg->name, 1)))
-		return_0;
+	if (!lv_raid_status(lv, &raid_status))
+                return_0;
 
-	if (!(r = dev_manager_raid_status(dm, lv, &status)) ||
-	    !(*dev_health = dm_pool_strdup(lv->vg->cmd->mem,
-					   status->dev_health))) {
-		dev_manager_destroy(dm);
-		return_0;
+	if (!(*dev_health = dm_pool_strdup(lv->vg->cmd->mem,
+					  raid_status->raid->dev_health))) {
+		stack;
+                r = 0;
 	}
 
-	dev_manager_destroy(dm);
+	dm_pool_destroy(raid_status->mem);
 
 	return r;
 }
 
 int lv_raid_dev_count(const struct logical_volume *lv, uint32_t *dev_cnt)
 {
-	struct dev_manager *dm;
-	struct dm_status_raid *status;
+	struct lv_status_raid *raid_status;
 
 	*dev_cnt = 0;
 
@@ -1031,24 +1028,20 @@ int lv_raid_dev_count(const struct logical_volume *lv, uint32_t *dev_cnt)
 
 	log_debug_activation("Checking raid device count for LV %s/%s",
 			     lv->vg->name, lv->name);
-	if (!(dm = dev_manager_create(lv->vg->cmd, lv->vg->name, 1)))
+
+	if (!lv_raid_status(lv, &raid_status))
 		return_0;
 
-	if (!dev_manager_raid_status(dm, lv, &status)) {
-		dev_manager_destroy(dm);
-		return_0;
-	}
-	*dev_cnt = status->dev_count;
+	*dev_cnt = raid_status->raid->dev_count;
 
-	dev_manager_destroy(dm);
+	dm_pool_destroy(raid_status->mem);
 
 	return 1;
 }
 
 int lv_raid_mismatch_count(const struct logical_volume *lv, uint64_t *cnt)
 {
-	struct dev_manager *dm;
-	struct dm_status_raid *status;
+	struct lv_status_raid *raid_status;
 
 	*cnt = 0;
 
@@ -1058,25 +1051,20 @@ int lv_raid_mismatch_count(const struct logical_volume *lv, uint64_t *cnt)
 	log_debug_activation("Checking raid mismatch count for LV %s.",
 			     display_lvname(lv));
 
-	if (!(dm = dev_manager_create(lv->vg->cmd, lv->vg->name, 1)))
+	if (!lv_raid_status(lv, &raid_status))
 		return_0;
 
-	if (!dev_manager_raid_status(dm, lv, &status)) {
-		dev_manager_destroy(dm);
-		return_0;
-	}
-	*cnt = status->mismatch_count;
+	*cnt = raid_status->raid->mismatch_count;
 
-	dev_manager_destroy(dm);
+	dm_pool_destroy(raid_status->mem);
 
 	return 1;
 }
 
 int lv_raid_sync_action(const struct logical_volume *lv, char **sync_action)
 {
-	struct dev_manager *dm;
-	struct dm_status_raid *status;
-	char *action;
+	struct lv_status_raid *raid_status;
+	int r = 1;
 
 	*sync_action = NULL;
 
@@ -1086,30 +1074,27 @@ int lv_raid_sync_action(const struct logical_volume *lv, char **sync_action)
 	log_debug_activation("Checking raid sync_action for LV %s.",
 			     display_lvname(lv));
 
-	if (!(dm = dev_manager_create(lv->vg->cmd, lv->vg->name, 1)))
+	if (!lv_raid_status(lv, &raid_status))
 		return_0;
 
 	/* status->sync_action can be NULL if dm-raid version < 1.5.0 */
-	if (!dev_manager_raid_status(dm, lv, &status) ||
-	    !status->sync_action ||
-	    !(action = dm_pool_strdup(lv->vg->cmd->mem,
-				      status->sync_action))) {
-		dev_manager_destroy(dm);
-		return_0;
+	if (!raid_status->raid->sync_action ||
+	    !(*sync_action = dm_pool_strdup(lv->vg->cmd->mem,
+					    raid_status->raid->sync_action))) {
+		stack;
+		r = 0;
 	}
 
-	*sync_action = action;
+	dm_pool_destroy(raid_status->mem);
 
-	dev_manager_destroy(dm);
-
-	return 1;
+	return r;
 }
 
 int lv_raid_message(const struct logical_volume *lv, const char *msg)
 {
+	struct lv_status_raid *raid_status;
+	struct dev_manager *dm = NULL;
 	int r = 0;
-	struct dev_manager *dm;
-	struct dm_status_raid *status;
 
 	if (!seg_is_raid(first_seg(lv))) {
 		/*
@@ -1134,16 +1119,10 @@ int lv_raid_message(const struct logical_volume *lv, const char *msg)
 		return 0;
 	}
 
-	if (!(dm = dev_manager_create(lv->vg->cmd, lv->vg->name, 1)))
+	if (!lv_raid_status(lv, &raid_status))
 		return_0;
 
-	if (!(r = dev_manager_raid_status(dm, lv, &status))) {
-		log_error("Failed to retrieve status of %s.",
-			  display_lvname(lv));
-		goto out;
-	}
-
-	if (!status->sync_action) {
+	if (!raid_status->raid->sync_action) {
 		log_error("Kernel driver does not support this action: %s", msg);
 		goto out;
 	}
@@ -1165,19 +1144,43 @@ int lv_raid_message(const struct logical_volume *lv, const char *msg)
 		log_error("\"%s\" is not a supported sync operation.", msg);
 		goto out;
 	}
-	if (strcmp(status->sync_action, "idle")) {
+	if (strcmp(raid_status->raid->sync_action, "idle")) {
 		log_error("%s state is currently \"%s\".  Unable to switch to \"%s\".",
-			  display_lvname(lv), status->sync_action, msg);
+			  display_lvname(lv), raid_status->raid->sync_action, msg);
 		goto out;
 	}
 
+	if (!(dm = dev_manager_create(lv->vg->cmd, lv->vg->name, 1)))
+		return_0;
+
 	r = dev_manager_raid_message(dm, lv, msg);
 out:
-	dev_manager_destroy(dm);
+	if (dm)
+		dev_manager_destroy(dm);
+	dm_pool_destroy(raid_status->mem);
 
 	return r;
 }
 
+int lv_raid_status(const struct logical_volume *lv, struct lv_status_raid **status)
+{
+	struct dev_manager *dm;
+	int exists;
+
+	if (!(dm = dev_manager_create(lv->vg->cmd, lv->vg->name, 1)))
+		return_0;
+
+	if (!dev_manager_raid_status(dm, lv, status, &exists)) {
+		dev_manager_destroy(dm);
+		if (exists)
+			stack;
+		return 0;
+	}
+	/* User has to call dm_pool_destroy(status->mem)! */
+
+	return 1;
+}
+
 int lv_writecache_message(const struct logical_volume *lv, const char *msg)
 {
 	int r = 0;
@@ -1210,6 +1213,7 @@ int lv_cache_status(const struct logical_volume *cache_lv,
 {
 	struct dev_manager *dm;
 	struct lv_segment *cache_seg;
+	int exists;
 
 	if (lv_is_cache_pool(cache_lv)) {
 		if (dm_list_empty(&cache_lv->segs_using_this_lv) ||
@@ -1227,125 +1231,74 @@ int lv_cache_status(const struct logical_volume *cache_lv,
 		return 0;
 	}
 
-	if (!lv_info(cache_lv->vg->cmd, cache_lv, 1, NULL, 0, 0)) {
-		log_error("Cannot check status for locally inactive cache volume %s.",
-			  display_lvname(cache_lv));
-		return 0;
-	}
-
-	log_debug_activation("Checking status for cache volume %s.",
-			     display_lvname(cache_lv));
-
 	if (!(dm = dev_manager_create(cache_lv->vg->cmd, cache_lv->vg->name, 1)))
 		return_0;
 
-	if (!dev_manager_cache_status(dm, cache_lv, status)) {
+	if (!dev_manager_cache_status(dm, cache_lv, status, &exists)) {
 		dev_manager_destroy(dm);
-		return_0;
+		if (exists)
+			stack;
+		return 0;
 	}
 	/* User has to call dm_pool_destroy(status->mem)! */
 
 	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));
+	int exists;
 
 	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, &exists)) {
+		dev_manager_destroy(dm);
+		if (exists)
+			stack;
+		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.",
-			     display_lvname(lv));
+	int exists;
 
 	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))
+	if (!dev_manager_thin_status(dm, lv, flush, thin_status, &exists)) {
+		dev_manager_destroy(dm);
+		if (exists)
+			stack;
 		return 0;
+	}
 
-	log_debug_activation("Checking thin-pool transaction id for LV %s.",
-			     display_lvname(lv));
+	/* User has to call dm_pool_destroy(thin_status->mem)! */
 
-	if (!(dm = dev_manager_create(lv->vg->cmd, lv->vg->name, 1)))
-		return_0;
-
-	if (!(r = dev_manager_thin_pool_status(dm, lv, &status, 0)))
-		stack;
-	else
-		*transaction_id = status->transaction_id;
-
-	dev_manager_destroy(dm);
-
-	return r;
+	return 1;
 }
 
 int lv_thin_device_id(const struct logical_volume *lv, uint32_t *device_id)
 {
-	int r;
 	struct dev_manager *dm;
-
-	if (!lv_info(lv->vg->cmd, lv, 0, NULL, 0, 0))
-		return 0;
-
-	log_debug_activation("Checking device id for LV %s.",
-			     display_lvname(lv));
+	int exists;
+	int r;
 
 	if (!(dm = dev_manager_create(lv->vg->cmd, lv->vg->name, 1)))
 		return_0;
 
-	if (!(r = dev_manager_thin_device_id(dm, lv, device_id)))
-		stack;
+	if (!(r = dev_manager_thin_device_id(dm, lv, device_id, &exists)))
+		if (exists)
+			stack;
 
 	dev_manager_destroy(dm);
 
@@ -1362,28 +1315,22 @@ int lv_thin_device_id(const struct logical_volume *lv, uint32_t *device_id)
 int lv_vdo_pool_status(const struct logical_volume *lv, int flush,
 		       struct lv_status_vdo **vdo_status)
 {
-	int r = 0;
 	struct dev_manager *dm;
-
-	if (!lv_info(lv->vg->cmd, lv, 1, NULL, 0, 0))
-		return 0;
-
-	log_debug_activation("Checking VDO pool status for LV %s.",
-			     display_lvname(lv));
+	int exists;
 
 	if (!(dm = dev_manager_create(lv->vg->cmd, lv->vg->name, !lv_is_pvmove(lv))))
 		return_0;
 
-	if (!dev_manager_vdo_pool_status(dm, lv, vdo_status, flush))
-		goto_out;
+	if (!dev_manager_vdo_pool_status(dm, lv, flush, vdo_status, &exists)) {
+		dev_manager_destroy(dm);
+		if (exists)
+			stack;
+		return 0;
+	}
 
 	/* User has to call dm_pool_destroy(vdo_status->mem) */
-	r = 1;
-out:
-	if (!r)
-		dev_manager_destroy(dm);
 
-	return r;
+	return 1;
 }
 
 int lv_vdo_pool_percent(const struct logical_volume *lv, dm_percent_t *percent)
@@ -2079,12 +2026,6 @@ static int _lv_suspend(struct cmd_context *cmd, const char *lvid_s,
 	if (!activation())
 		return 1;
 
-	/* Ignore origin_only unless LV is origin in both old and new metadata */
-	/* or LV is thin or thin pool volume */
-	if (!lv_is_thin_volume(lv) && !lv_is_thin_pool(lv) &&
-	    !(lv_is_origin(lv) && lv_is_origin(lv_pre)))
-		laopts->origin_only = 0;
-
 	if (test_mode()) {
 		_skip("Suspending %s%s.", display_lvname(lv),
 		      laopts->origin_only ? " origin without snapshots" : "");
@@ -2106,6 +2047,12 @@ static int _lv_suspend(struct cmd_context *cmd, const char *lvid_s,
 
 	lv_calculate_readahead(lv, NULL);
 
+	/* Ignore origin_only unless LV is origin in both old and new metadata */
+	/* or LV is thin or thin pool volume */
+	if (!lv_is_thin_volume(lv) && !lv_is_thin_pool(lv) &&
+	    !(lv_is_origin(lv) && lv_is_origin(lv_pre)))
+		laopts->origin_only = 0;
+
 	/*
 	 * Preload devices for the LV.
 	 * If the PVMOVE LV is being removed, it's only present in the old
@@ -2197,8 +2144,6 @@ 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 +2185,23 @@ 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 +2221,8 @@ 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 +2274,9 @@ 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 +2336,8 @@ 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
 	};
 
@@ -2431,44 +2386,47 @@ int lv_deactivate(struct cmd_context *cmd, const char *lvid_s, const struct logi
 
 	log_debug_activation("Deactivating %s.", display_lvname(lv));
 
-	if (!lv_info(cmd, lv, 0, &info, 0, 0))
-		goto_out;
-
-	if (!info.exists) {
-		r = 1;
-		/* Check attached snapshot segments are also inactive */
-		dm_list_iterate(snh, &lv->snapshot_segs) {
-			if (!lv_info(cmd, dm_list_struct_base(snh, struct lv_segment, origin_list)->cow,
-				     0, &info, 0, 0))
-				goto_out;
-			if (info.exists) {
-				r = 0; /* Snapshot left in table? */
-				break;
-			}
-		}
-
-		if (lv_is_vdo_pool(lv)) {
-			/* If someone has remove 'linear' mapping over VDO device
-			 * we may still be able to deactivate the rest of the tree
-			 * i.e. in test-suite we simulate this via 'dmsetup remove' */
-			if (!lv_info(cmd, lv, 1, &info, 1, 0))
-				goto_out;
-
-			if (info.exists && !info.open_count)
-				r = 0; /* Unused VDO device left in table? */
-		}
-
-		if (r)
-			goto out;
-	}
-
 	if (lv_is_visible(lv) || lv_is_virtual_origin(lv) ||
 	    lv_is_merging_thin_snapshot(lv)) {
-		if (!lv_check_not_in_use(lv, 1))
-			goto_out;
+		switch (lv_check_not_in_use(lv, 1)) {
+		case 0: goto_out;
+		case 2: goto no_exists;
+		}
 
 		if (lv_is_origin(lv) && _lv_has_open_snapshots(lv))
 			goto_out;
+	} else {
+		if (!lv_info(cmd, lv, 0, &info, 0, 0))
+			goto_out;
+
+		if (!info.exists) {
+	no_exists:
+			r = 1;
+			/* Check attached snapshot segments are also inactive */
+			dm_list_iterate(snh, &lv->snapshot_segs) {
+				if (!lv_info(cmd, dm_list_struct_base(snh, struct lv_segment, origin_list)->cow,
+					     0, &info, 0, 0))
+					goto_out;
+				if (info.exists) {
+					r = 0; /* Snapshot left in table? */
+					break;
+				}
+			}
+
+			if (lv_is_vdo_pool(lv)) {
+				/* If someone has remove 'linear' mapping over VDO device
+				 * we may still be able to deactivate the rest of the tree
+				 * i.e. in test-suite we simulate this via 'dmsetup remove' */
+				if (!lv_info(cmd, lv, 1, &info, 1, 0))
+					goto_out;
+
+				if (info.exists && !info.open_count)
+					r = 0; /* Unused VDO device left in table? */
+			}
+
+			if (r)
+				goto out;
+		}
 	}
 
 	if (!monitor_dev_for_events(cmd, lv, &laopts, 0))
@@ -2558,6 +2516,14 @@ 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));
@@ -2857,7 +2823,7 @@ static int _deactivate_sub_lv_cb(struct logical_volume *lv, void *data)
  */
 int deactivate_lv_with_sub_lv(const struct logical_volume *lv)
 {
-	struct logical_volume *flv;
+	struct logical_volume *flv = NULL;
 
 	if (!deactivate_lv(lv->vg->cmd, lv)) {
 		log_error("Cannot deactivate logical volume %s.",
@@ -2867,7 +2833,7 @@ int deactivate_lv_with_sub_lv(const struct logical_volume *lv)
 
 	if (!for_each_sub_lv((struct logical_volume *)lv, _deactivate_sub_lv_cb, &flv)) {
 		log_error("Cannot deactivate subvolume %s of logical volume %s.",
-			  display_lvname(flv), display_lvname(lv));
+			  (flv) ? display_lvname(flv) : "", display_lvname(lv));
 		return 0;
 	}
 
@@ -2962,8 +2928,7 @@ 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

@@ -188,16 +188,15 @@ int lv_raid_dev_health(const struct logical_volume *lv, char **dev_health);
 int lv_raid_mismatch_count(const struct logical_volume *lv, uint64_t *cnt);
 int lv_raid_sync_action(const struct logical_volume *lv, char **sync_action);
 int lv_raid_message(const struct logical_volume *lv, const char *msg);
+int lv_raid_status(const struct logical_volume *lv, struct lv_status_raid **status);
 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 +209,8 @@ 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);
@@ -253,7 +254,7 @@ struct dev_usable_check_params {
  * Returns 1 if mapped device is not suspended, blocked or
  * is using a reserved name.
  */
-int device_is_usable(struct device *dev, struct dev_usable_check_params check);
+int device_is_usable(struct device *dev, struct dev_usable_check_params check, int *is_lv);
 
 /*
  * Declaration moved here from fs.h to keep header fs.h hidden

lib/activate/dev_manager.c

@@ -26,6 +26,7 @@
 #include "lib/activate/activate.h"
 #include "lib/misc/lvm-exec.h"
 #include "lib/datastruct/str_list.h"
+#include "lib/misc/lvm-signal.h"
 
 #include <limits.h>
 #include <dirent.h>
@@ -261,7 +262,7 @@ 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 +298,7 @@ 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 +311,9 @@ 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 */
@@ -403,7 +406,7 @@ static int _ignore_blocked_mirror_devices(struct device *dev,
 					       .check_blocked = 1,
 					       .check_suspended = ignore_suspended_devices(),
 					       .check_error_target = 1,
-					       .check_reserved = 0 }))
+					       .check_reserved = 0 }, NULL))
 				goto out; /* safe to use */
 			stack;
 		}
@@ -618,16 +621,17 @@ static int _ignore_frozen_raid(struct device *dev, const char *params)
  *
  * Returns: 1 if usable, 0 otherwise
  */
-int device_is_usable(struct device *dev, struct dev_usable_check_params check)
+int device_is_usable(struct device *dev, struct dev_usable_check_params check, int *is_lv)
 {
 	struct dm_task *dmt;
 	struct dm_info info;
 	const char *name, *uuid;
 	uint64_t start, length;
 	char *target_type = NULL;
-	char *params, *vgname = NULL, *lvname, *layer;
+	char *params, *vgname, *lvname, *layer;
+	char vg_name[NAME_LEN];
 	void *next = NULL;
-	int only_error_target = 1;
+	int only_error_or_zero_target = 1;
 	int r = 0;
 
 	if (!(dmt = _setup_task_run(DM_DEVICE_STATUS, &info, NULL, NULL, NULL,
@@ -650,44 +654,51 @@ int device_is_usable(struct device *dev, struct dev_usable_check_params check)
 		goto out;
 	}
 
-	/* Check internal lvm devices */
-	if (check.check_reserved &&
-	    uuid && !strncmp(uuid, UUID_PREFIX, sizeof(UUID_PREFIX) - 1)) {
-		if (strlen(uuid) > (sizeof(UUID_PREFIX) + 2 * ID_LEN)) { /* 68 */
-			log_debug_activation("%s: Reserved uuid %s on internal LV device %s not usable.",
-					     dev_name(dev), uuid, name);
-			goto out;
+	if (uuid && (check.check_reserved || check.check_lv)) {
+		if (!strncmp(uuid, UUID_PREFIX, sizeof(UUID_PREFIX) - 1)) { /* with LVM- prefix */
+			if (check.check_reserved) {
+				/* Check internal lvm devices */
+				if (strlen(uuid) > (sizeof(UUID_PREFIX) + 2 * ID_LEN)) { /* 68 with suffix */
+					log_debug_activation("%s: Reserved uuid %s on internal LV device %s not usable.",
+							     dev_name(dev), uuid, name);
+					goto out;
+				}
+
+				/* Recognize some older reserved LVs just from the LV name (snapshot, pvmove...) */
+				vgname = vg_name;
+				if (!dm_strncpy(vg_name, name, sizeof(vg_name)) ||
+				    !dm_split_lvm_name(NULL, NULL, &vgname, &lvname, &layer))
+					goto_out;
+
+				/* FIXME: fails to handle dev aliases i.e. /dev/dm-5, replace with UUID suffix */
+				if (lvname && (is_reserved_lvname(lvname) || *layer)) {
+					log_debug_activation("%s: Reserved internal LV device %s/%s%s%s not usable.",
+							     dev_name(dev), vgname, lvname, *layer ? "-" : "", layer);
+					goto out;
+				}
+			}
+
+			if (check.check_lv) {
+				/* Skip LVs */
+				if (is_lv)
+					*is_lv = 1;
+				goto out;
+			}
 		}
 
-		if (!(vgname = strdup(name)) ||
-		    !dm_split_lvm_name(NULL, NULL, &vgname, &lvname, &layer))
-			goto_out;
-
-		/* FIXME: fails to handle dev aliases i.e. /dev/dm-5, replace with UUID suffix */
-		if (lvname && (is_reserved_lvname(lvname) || *layer)) {
-			log_debug_activation("%s: Reserved internal LV device %s/%s%s%s not usable.",
-					     dev_name(dev), vgname, lvname, *layer ? "-" : "", layer);
+		if (check.check_reserved &&
+		    (!strncmp(uuid, CRYPT_TEMP, sizeof(CRYPT_TEMP) - 1) ||
+		     !strncmp(uuid, CRYPT_SUBDEV, sizeof(CRYPT_SUBDEV) - 1) ||
+		     !strncmp(uuid, STRATIS, sizeof(STRATIS) - 1))) {
+			/* Skip private crypto devices */
+			log_debug_activation("%s: Reserved uuid %s on %s device %s not usable.",
+					     dev_name(dev), uuid,
+					     uuid[0] == 'C' ? "crypto" : "stratis",
+					     name);
 			goto out;
 		}
 	}
 
-	if (check.check_lv && uuid && !strncmp(uuid, "LVM-", 4)) {
-		/* Skip LVs */
-		goto out;
-	}
-
-	if (check.check_reserved && uuid &&
-	    (!strncmp(uuid, CRYPT_TEMP, sizeof(CRYPT_TEMP) - 1) ||
-	     !strncmp(uuid, CRYPT_SUBDEV, sizeof(CRYPT_SUBDEV) - 1) ||
-	     !strncmp(uuid, STRATIS, sizeof(STRATIS) - 1))) {
-		/* Skip private crypto devices */
-		log_debug_activation("%s: Reserved uuid %s on %s device %s not usable.",
-				     dev_name(dev), uuid,
-				     uuid[0] == 'C' ? "crypto" : "stratis",
-				     name);
-		goto out;
-	}
-
 	/* FIXME Also check for mpath no paths */
 	do {
 		next = dm_get_next_target(dmt, next, &start, &length,
@@ -756,13 +767,15 @@ int device_is_usable(struct device *dev, struct dev_usable_check_params check)
 			goto out;
 		}
 
-		if (strcmp(target_type, TARGET_NAME_ERROR))
-			only_error_target = 0;
+		if (only_error_or_zero_target &&
+		    strcmp(target_type, TARGET_NAME_ERROR) &&
+		    strcmp(target_type, TARGET_NAME_ZERO))
+			only_error_or_zero_target = 0;
 	} while (next);
 
-	/* Skip devices consisting entirely of error targets. */
+	/* Skip devices consisting entirely of error or zero targets. */
 	/* FIXME Deal with device stacked above error targets? */
-	if (check.check_error_target && only_error_target) {
+	if (check.check_error_target && only_error_or_zero_target) {
 		log_debug_activation("%s: Error device %s not usable.",
 				     dev_name(dev), name);
 		goto out;
@@ -773,7 +786,6 @@ int device_is_usable(struct device *dev, struct dev_usable_check_params check)
 	r = 1;
 
       out:
-	free(vgname);
 	dm_task_destroy(dmt);
 	return r;
 }
@@ -830,8 +842,7 @@ static int _info(struct cmd_context *cmd,
 			if (strcmp(suffix_position + 1, suffix))
 				continue;
 
-			(void) strncpy(old_style_dlid, dlid, sizeof(old_style_dlid));
-			old_style_dlid[sizeof(old_style_dlid) - 1] = '\0';
+			(void) dm_strncpy(old_style_dlid, dlid, sizeof(old_style_dlid));
 			if (!_info_run(old_style_dlid, dminfo, read_ahead, seg_status,
 				       name_check, with_open_count, with_read_ahead,
 				       0, 0))
@@ -1113,7 +1124,8 @@ static int _percent_run(struct dev_manager *dm, const char *name,
 			const char *dlid,
 			const char *target_type, int wait,
 			const struct logical_volume *lv, dm_percent_t *overall_percent,
-			uint32_t *event_nr, int fail_if_percent_unsupported)
+			uint32_t *event_nr, int fail_if_percent_unsupported,
+			int *interrupted)
 {
 	int r = 0;
 	struct dm_task *dmt;
@@ -1134,9 +1146,12 @@ static int _percent_run(struct dev_manager *dm, const char *name,
 	if (!(segtype = get_segtype_from_string(dm->cmd, target_type)))
 		return_0;
 
+	if (wait)
+		sigint_allow();
+
 	if (!(dmt = _setup_task_run(wait ? DM_DEVICE_WAITEVENT : DM_DEVICE_STATUS, &info,
 				    name, dlid, event_nr, 0, 0, 0, 0, 0)))
-		return_0;
+		goto_bad;
 
 	if (!info.exists)
 		goto_out;
@@ -1204,8 +1219,19 @@ static int _percent_run(struct dev_manager *dm, const char *name,
 			     display_percent(dm->cmd, *overall_percent));
 	r = 1;
 
-      out:
+    out:
 	dm_task_destroy(dmt);
+
+    bad:
+	if (wait) {
+		sigint_restore();
+
+		if (sigint_caught()) {
+			*interrupted = 1;
+			return_0;
+		}
+	}
+
 	return r;
 }
 
@@ -1214,20 +1240,24 @@ static int _percent(struct dev_manager *dm, const char *name, const char *dlid,
 		    const struct logical_volume *lv, dm_percent_t *percent,
 		    uint32_t *event_nr, int fail_if_percent_unsupported)
 {
+	int interrupted = 0;
+
 	if (dlid && *dlid) {
 		if (_percent_run(dm, NULL, dlid, target_type, wait, lv, percent,
-				 event_nr, fail_if_percent_unsupported))
+				 event_nr, fail_if_percent_unsupported, &interrupted))
 			return 1;
 
-		if (_original_uuid_format_check_required(dm->cmd) &&
+		if (!interrupted &&
+		    _original_uuid_format_check_required(dm->cmd) &&
 		    _percent_run(dm, NULL, dlid + sizeof(UUID_PREFIX) - 1,
 				 target_type, wait, lv, percent,
-				 event_nr, fail_if_percent_unsupported))
+				 event_nr, fail_if_percent_unsupported, &interrupted))
 			return 1;
 	}
 
-	if (name && _percent_run(dm, name, NULL, target_type, wait, lv, percent,
-				 event_nr, fail_if_percent_unsupported))
+	if (!interrupted && name &&
+	    _percent_run(dm, name, NULL, target_type, wait, lv, percent,
+				 event_nr, fail_if_percent_unsupported, &interrupted))
 		return 1;
 
 	return_0;
@@ -1429,7 +1459,7 @@ int dev_manager_mirror_percent(struct dev_manager *dm,
 
 int dev_manager_raid_status(struct dev_manager *dm,
 			    const struct logical_volume *lv,
-			    struct dm_status_raid **status)
+			    struct lv_status_raid **status, int *exists)
 {
 	int r = 0;
 	const char *dlid;
@@ -1439,6 +1469,11 @@ int dev_manager_raid_status(struct dev_manager *dm,
 	char *type = NULL;
 	char *params = NULL;
 	const char *layer = lv_layer(lv);
+	struct dm_status_raid *sr;
+
+	*exists = -1;
+	if (!(*status = dm_pool_zalloc(dm->mem, sizeof(struct lv_status_cache))))
+		return_0;
 
 	if (!(dlid = build_dm_uuid(dm->mem, lv, layer)))
 		return_0;
@@ -1446,8 +1481,11 @@ int dev_manager_raid_status(struct dev_manager *dm,
 	if (!(dmt = _setup_task_run(DM_DEVICE_STATUS, &info, NULL, dlid, 0, 0, 0, 0, 0, 0)))
 		return_0;
 
-	if (!info.exists)
-		goto_out;
+	if (!(*exists = info.exists))
+		goto out;
+
+	log_debug_activation("Checking raid status for volume %s.",
+			     display_lvname(lv));
 
 	dm_get_next_target(dmt, NULL, &start, &length, &type, &params);
 
@@ -1459,9 +1497,13 @@ int dev_manager_raid_status(struct dev_manager *dm,
 
 	/* FIXME Check there's only one target */
 
-	if (!dm_get_status_raid(dm->mem, params, status))
+	if (!dm_get_status_raid(dm->mem, params, &sr))
 		goto_out;
 
+	(*status)->mem = dm->mem; /* User has to destroy this mem pool later */
+	(*status)->raid = sr;
+	(*status)->in_sync = dm_make_percent(sr->insync_regions, sr->total_regions);
+
 	r = 1;
 out:
 	dm_task_destroy(dmt);
@@ -1550,7 +1592,7 @@ out:
 
 int dev_manager_cache_status(struct dev_manager *dm,
 			     const struct logical_volume *lv,
-			     struct lv_status_cache **status)
+			     struct lv_status_cache **status, int *exists)
 {
 	int r = 0;
 	const char *dlid;
@@ -1561,17 +1603,18 @@ int dev_manager_cache_status(struct dev_manager *dm,
 	char *params = NULL;
 	struct dm_status_cache *c;
 
+	*exists = -1;
 	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;
 
-	if (!info.exists)
-		goto_out;
+	if (!(*exists = info.exists))
+		goto out;
+
+	log_debug_activation("Checking status for cache volume %s.",
+			     display_lvname(lv));
 
 	dm_get_next_target(dmt, NULL, &start, &length, &type, &params);
 
@@ -1589,8 +1632,11 @@ 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 +1658,10 @@ 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, int *exists)
 {
+	struct dm_status_thin_pool *dm_status;
 	const char *dlid;
 	struct dm_task *dmt;
 	struct dm_info info;
@@ -1624,6 +1670,10 @@ int dev_manager_thin_pool_status(struct dev_manager *dm,
 	char *params = NULL;
 	int r = 0;
 
+	*exists = -1;
+	if (!(*status = dm_pool_zalloc(dm->mem, sizeof(struct lv_status_thin_pool))))
+		return_0;
+
 	/* Build dlid for the thin pool layer */
 	if (!(dlid = build_dm_uuid(dm->mem, lv, lv_layer(lv))))
 		return_0;
@@ -1631,16 +1681,36 @@ int dev_manager_thin_pool_status(struct dev_manager *dm,
 	if (!(dmt = _setup_task_run(DM_DEVICE_STATUS, &info, NULL, dlid, 0, 0, 0, 0, flush, 0)))
 		return_0;
 
-	if (!info.exists)
-		goto_out;
+	if (!(*exists = info.exists))
+		goto out;
+
+	log_debug_activation("Checking thin pool status for LV %s.",
+			     display_lvname(lv));
 
 	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;
 
+	(*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 +1718,72 @@ 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, int *exists)
 {
-	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)))
+	*exists = -1;
+	if (!(*status = dm_pool_zalloc(dm->mem, sizeof(struct lv_status_thin))))
 		return_0;
 
-	if (!(dlid = build_dm_uuid(dm->mem, lv, layer)))
+	if (!(dlid = build_dm_uuid(dm->mem, lv, lv_layer(lv))))
 		return_0;
 
-	log_debug_activation("Getting device status percentage for %s.", name);
-
-	if (!(_percent(dm, name, dlid, TARGET_NAME_THIN_POOL, 0,
-		       (metadata) ? lv : NULL, percent, NULL, 1)))
+	if (!(dmt = _setup_task_run(DM_DEVICE_STATUS, &info, NULL, dlid, 0, 0, 0, 0, flush, 0)))
 		return_0;
 
-	return 1;
-}
+	if (!(*exists = info.exists))
+		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);
+	log_debug_activation("Checking thin status for LV %s.",
+			     display_lvname(lv));
 
-	/* Build a name for the top layer */
-	if (!(name = dm_build_dm_name(dm->mem, lv->vg->name, lv->name, layer)))
-		return_0;
+	dm_get_next_target(dmt, NULL, &start, &length, &type, &params);
 
-	if (!(dlid = build_dm_uuid(dm->mem, lv, layer)))
-		return_0;
+	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;
+	}
 
-	log_debug_activation("Getting device status percentage for %s", name);
+	if (!dm_get_status_thin(dm->mem, params, &dm_status))
+		goto_out;
 
-	if (!(_percent(dm, name, dlid, TARGET_NAME_THIN, 0,
-		       (mapped) ? NULL : lv, percent, NULL, 1)))
-		return_0;
+	(*status)->mem = dm->mem;
+	(*status)->thin = dm_status;
 
-	return 1;
+	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);
+	}
+
+	r = 1;
+out:
+	dm_task_destroy(dmt);
+
+	return r;
 }
 
 /*
@@ -1701,7 +1791,7 @@ int dev_manager_thin_percent(struct dev_manager *dm,
  */
 int dev_manager_thin_device_id(struct dev_manager *dm,
 			       const struct logical_volume *lv,
-			       uint32_t *device_id)
+			       uint32_t *device_id, int *exists)
 {
 	const char *dlid;
 	struct dm_task *dmt;
@@ -1711,6 +1801,7 @@ int dev_manager_thin_device_id(struct dev_manager *dm,
 	const char *layer = lv_layer(lv);
 	int r = 0;
 
+	*exists = -1;
 	if (lv_is_merging_origin(lv) && !lv_info(lv->vg->cmd, lv, 1, NULL, 0, 0))
 		/* If the merge has already happened, that table
 		 * can already be using correct LV without -real layer */
@@ -1723,8 +1814,11 @@ int dev_manager_thin_device_id(struct dev_manager *dm,
 	if (!(dmt = _setup_task_run(DM_DEVICE_TABLE, &info, NULL, dlid, 0, 0, 0, 0, 1, 0)))
 		return_0;
 
-	if (!info.exists)
-		goto_out;
+	if (!(*exists = info.exists))
+		goto out;
+
+	log_debug_activation("Checking device id for LV %s.",
+			     display_lvname(lv));
 
 	if (dm_get_next_target(dmt, NULL, &start, &length,
 			       &target_type, &params)) {
@@ -1753,11 +1847,9 @@ out:
 }
 
 int dev_manager_vdo_pool_status(struct dev_manager *dm,
-				const struct logical_volume *lv,
-				struct lv_status_vdo **vdo_status,
-				int flush)
+				const struct logical_volume *lv, int flush,
+				struct lv_status_vdo **status, int *exists)
 {
-	struct lv_status_vdo *status;
 	const char *dlid;
 	struct dm_info info;
 	uint64_t start, length;
@@ -1766,12 +1858,9 @@ int dev_manager_vdo_pool_status(struct dev_manager *dm,
 	char *params = NULL;
 	int r = 0;
 
-	*vdo_status = NULL;
-
-	if (!(status = dm_pool_zalloc(dm->mem, sizeof(struct lv_status_vdo)))) {
-		log_error("Cannot allocate VDO status structure.");
-		return 0;
-	}
+	*exists = -1;
+	if (!(*status = dm_pool_zalloc(dm->mem, sizeof(struct lv_status_vdo))))
+		return_0;
 
 	if (!(dlid = build_dm_uuid(dm->mem, lv, lv_layer(lv))))
 		return_0;
@@ -1779,8 +1868,11 @@ int dev_manager_vdo_pool_status(struct dev_manager *dm,
 	if (!(dmt = _setup_task_run(DM_DEVICE_STATUS, &info, NULL, dlid, 0, 0, 0, 0, flush, 0)))
 		return_0;
 
-	if (!info.exists)
-		goto_out;
+	if (!(*exists = info.exists))
+		goto out;
+
+	log_debug_activation("Checking VDO pool status for LV %s.",
+			     display_lvname(lv));
 
 	if (dm_get_next_target(dmt, NULL, &start, &length, &type, &params)) {
 		log_error("More then one table line found for %s.",
@@ -1794,11 +1886,10 @@ int dev_manager_vdo_pool_status(struct dev_manager *dm,
 		goto out;
 	}
 
-	if (!parse_vdo_pool_status(dm->mem, lv, params, status))
+	if (!parse_vdo_pool_status(dm->mem, lv, params, *status))
 		goto_out;
 
-	status->mem = dm->mem;
-	*vdo_status = status;
+	(*status)->mem = dm->mem;
 
 	r = 1;
 out:
@@ -2234,21 +2325,31 @@ 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 +2377,7 @@ 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 +2399,7 @@ 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 +2408,7 @@ 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 +2452,6 @@ 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;
@@ -3447,6 +3544,12 @@ 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

@@ -59,7 +59,7 @@ int dev_manager_mirror_percent(struct dev_manager *dm,
 			       dm_percent_t *percent, uint32_t *event_nr);
 int dev_manager_raid_status(struct dev_manager *dm,
 			    const struct logical_volume *lv,
-			    struct dm_status_raid **status);
+			    struct lv_status_raid **status, int *exists);
 int dev_manager_raid_message(struct dev_manager *dm,
 			     const struct logical_volume *lv,
 			     const char *msg);
@@ -68,24 +68,19 @@ int dev_manager_writecache_message(struct dev_manager *dm,
                                    const char *msg);
 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);
+			     struct lv_status_cache **status, int *exists);
+int dev_manager_thin_status(struct dev_manager *dm,
+			    const struct logical_volume *lv, int flush,
+			    struct lv_status_thin **status, int *exists);
 int dev_manager_thin_device_id(struct dev_manager *dm,
 			       const struct logical_volume *lv,
-			       uint32_t *device_id);
+			       uint32_t *device_id, int *exist);
+int dev_manager_thin_pool_status(struct dev_manager *dm,
+				 const struct logical_volume *lv, int flush,
+				 struct lv_status_thin_pool **status, int *exists);
 int dev_manager_vdo_pool_status(struct dev_manager *dm,
-				const struct logical_volume *lv,
-				struct lv_status_vdo **vdo_status,
-				int flush);
+				const struct logical_volume *lv, int flush,
+				struct lv_status_vdo **status, int *exists);
 int dev_manager_suspend(struct dev_manager *dm, const struct logical_volume *lv,
 			struct lv_activate_opts *laopts, int lockfs, int flush_required);
 int dev_manager_activate(struct dev_manager *dm, const struct logical_volume *lv,

lib/activate/fs.c

@@ -76,7 +76,7 @@ static int _rm_dir(const char *dev_dir, const char *vg_name)
 		return 0;
 	}
 
-	if (dir_exists(vg_path) && is_empty_dir(vg_path)) {
+	if (dir_exists(vg_path) && dm_is_empty_dir(vg_path)) {
 		log_very_verbose("Removing directory %s", vg_path);
 		rmdir(vg_path);
 	}
@@ -93,7 +93,7 @@ static void _rm_blks(const char *dir)
 	DIR *d;
 
 	if (!(d = opendir(dir))) {
-		log_sys_error("opendir", dir);
+		log_sys_debug("opendir", dir);
 		return;
 	}
 
@@ -104,7 +104,7 @@ static void _rm_blks(const char *dir)
 			continue;
 
 		if (dm_snprintf(path, sizeof(path), "%s/%s", dir, name) == -1) {
-			log_error("Couldn't create path for %s", name);
+			log_debug("Couldn't create path for %s.", name);
 			continue;
 		}
 
@@ -113,12 +113,12 @@ static void _rm_blks(const char *dir)
 				continue;
 			log_very_verbose("Removing %s", path);
 			if (unlink(path) < 0)
-				log_sys_error("unlink", path);
+				log_sys_debug("unlink", path);
 		}
 	}
 
 	if (closedir(d))
-		log_sys_error("closedir", dir);
+		log_sys_debug("closedir", dir);
 }
 
 static int _mk_link(const char *dev_dir, const char *vg_name,
@@ -169,7 +169,7 @@ static int _mk_link(const char *dev_dir, const char *vg_name,
 
 			log_very_verbose("Removing %s", lvm1_group_path);
 			if (unlink(lvm1_group_path) < 0)
-				log_sys_error("unlink", lvm1_group_path);
+				log_sys_debug("unlink", lvm1_group_path);
 		}
 	}
 
@@ -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.c

@@ -18,11 +18,13 @@
 #include "lib/cache/lvmcache.h"
 #include "lib/commands/toolcontext.h"
 #include "lib/device/dev-cache.h"
+#include "lib/device/device_id.h"
 #include "lib/locking/locking.h"
 #include "lib/metadata/metadata.h"
 #include "lib/mm/memlock.h"
 #include "lib/format_text/format-text.h"
 #include "lib/config/config.h"
+#include "lib/filters/filter.h"
 
 /* One per device */
 struct lvmcache_info {
@@ -42,9 +44,9 @@ struct lvmcache_info {
 	bool mda1_bad;		/* label scan found bad metadata in mda1 */
 	bool mda2_bad;		/* label scan found bad metadata in mda2 */
 	bool summary_seqno_mismatch; /* two mdas on this dev has mismatching metadata */
-	int summary_seqno;      /* vg seqno found on this dev during scan */
-	int mda1_seqno;
-	int mda2_seqno;
+	uint32_t summary_seqno;      /* vg seqno found on this dev during scan */
+	uint32_t mda1_seqno;
+	uint32_t mda2_seqno;
 };
 
 /* One per VG */
@@ -63,7 +65,7 @@ struct lvmcache_vginfo {
 	char *lock_type;
 	uint32_t mda_checksum;
 	size_t mda_size;
-	int seqno;
+	uint32_t seqno;
 	bool scan_summary_mismatch; /* vgsummary from devs had mismatching seqno or checksum */
 	bool has_duplicate_local_vgname;   /* this local vg and another local vg have same name */
 	bool has_duplicate_foreign_vgname; /* this foreign vg and another foreign vg have same name */
@@ -84,6 +86,10 @@ static DM_LIST_INIT(_unused_duplicates);
 static DM_LIST_INIT(_prev_unused_duplicate_devs);
 static int _vgs_locked = 0;
 static int _found_duplicate_vgnames = 0;
+static int _outdated_warning = 0;
+
+static const char *_scan_lock_global_file = DEFAULT_RUN_DIR "/scan_lock_global";
+static int _scan_lock_global_file_exists = 0;
 
 int lvmcache_init(struct cmd_context *cmd)
 {
@@ -98,13 +104,13 @@ int lvmcache_init(struct cmd_context *cmd)
 	dm_list_init(&_unused_duplicates);
 	dm_list_init(&_prev_unused_duplicate_devs);
 
-	if (!(_vgname_hash = dm_hash_create(128)))
+	if (!(_vgname_hash = dm_hash_create(127)))
 		return 0;
 
-	if (!(_vgid_hash = dm_hash_create(128)))
+	if (!(_vgid_hash = dm_hash_create(126)))
 		return 0;
 
-	if (!(_pvid_hash = dm_hash_create(128)))
+	if (!(_pvid_hash = dm_hash_create(125)))
 		return 0;
 
 	return 1;
@@ -123,6 +129,19 @@ void lvmcache_unlock_vgname(const char *vgname)
 	}
 }
 
+unsigned int lvmcache_vg_info_count(void)
+{
+	struct lvmcache_vginfo *vginfo;
+	unsigned int count = 0;
+
+	dm_list_iterate_items(vginfo, &_vginfos) {
+		if (is_orphan_vg(vginfo->vgname))
+			continue;
+		count++;
+	}
+	return count;
+}
+
 int lvmcache_found_duplicate_vgnames(void)
 {
 	return _found_duplicate_vgnames;
@@ -269,6 +288,21 @@ void lvmcache_get_mdas(struct cmd_context *cmd,
 	}
 }
 
+struct metadata_area *lvmcache_get_dev_mda(struct device *dev, int mda_num)
+{
+	struct lvmcache_info *info;
+	struct metadata_area *mda;
+
+	if (!(info = lvmcache_info_from_pvid(dev->pvid, dev, 0)))
+		return NULL;
+
+	dm_list_iterate_items(mda, &info->mdas) {
+		if (mda->mda_num == mda_num)
+			return mda;
+	}
+	return NULL;
+}
+
 static void _vginfo_detach_info(struct lvmcache_info *info)
 {
 	if (!dm_list_empty(&info->list)) {
@@ -324,7 +358,7 @@ static struct lvmcache_vginfo *_vginfo_lookup(const char *vgname, const char *vg
 		if ((vginfo = dm_hash_lookup(_vgname_hash, vgname))) {
 			if (vginfo->has_duplicate_local_vgname) {
 				/* should never happen, found_duplicate_vgnames should be set */
-				log_error(INTERNAL_ERROR "vginfo_lookup %s %s has_duplicate_local_vgname", vgname, vgid);
+				log_error(INTERNAL_ERROR "vginfo_lookup %s has_duplicate_local_vgname.", vgname);
 				return NULL;
 			}
 			return vginfo;
@@ -334,7 +368,7 @@ static struct lvmcache_vginfo *_vginfo_lookup(const char *vgname, const char *vg
 	if (vgname && _found_duplicate_vgnames) {
 		if ((vginfo = _search_vginfos_list(vgname, vgid))) {
 			if (vginfo->has_duplicate_local_vgname) {
-				log_debug("vginfo_lookup %s %s has_duplicate_local_vgname return none", vgname, vgid);
+				log_debug("vginfo_lookup %s has_duplicate_local_vgname return none.", vgname);
 				return NULL;
 			}
 			return vginfo;
@@ -490,6 +524,25 @@ static const char *_get_pvsummary_device_hint(char *pvid)
 	return NULL;
 }
 
+static const char *_get_pvsummary_device_id(char *pvid, const char **device_id_type)
+{
+	char pvid_s[ID_LEN + 1] __attribute__((aligned(8)));
+	struct lvmcache_vginfo *vginfo;
+	struct pv_list *pvl;
+
+	dm_list_iterate_items(vginfo, &_vginfos) {
+		dm_list_iterate_items(pvl, &vginfo->pvsummaries) {
+			(void) dm_strncpy(pvid_s, (char *) &pvl->pv->id, sizeof(pvid_s));
+			if (!strcmp(pvid_s, pvid)) {
+				*device_id_type = pvl->pv->device_id_type;
+				return pvl->pv->device_id;
+			}
+		}
+	}
+
+	return NULL;
+}
+
 /*
  * Check if any PVs in vg->pvs have the same PVID as any
  * entries in _unused_duplicates.
@@ -595,6 +648,8 @@ static void _choose_duplicates(struct cmd_context *cmd,
 	struct device_list *devl, *devl_safe, *devl_add, *devl_del;
 	struct lvmcache_info *info;
 	struct device *dev1, *dev2;
+	const char *device_id = NULL, *device_id_type = NULL;
+	const char *idname1 = NULL, *idname2 = NULL;
 	uint32_t dev1_major, dev1_minor, dev2_major, dev2_minor;
 	uint64_t dev1_size, dev2_size, pvsummary_size;
 	int in_subsys1, in_subsys2;
@@ -603,6 +658,7 @@ static void _choose_duplicates(struct cmd_context *cmd,
 	int has_lv1, has_lv2;
 	int same_size1, same_size2;
 	int same_name1 = 0, same_name2 = 0;
+	int same_id1 = 0, same_id2 = 0;
 	int prev_unchosen1, prev_unchosen2;
 	int change;
 
@@ -733,6 +789,19 @@ next:
 			same_name2 = !strcmp(device_hint, dev_name(dev2));
 		}
 
+		if ((device_id = _get_pvsummary_device_id(devl->dev->pvid, &device_id_type))) {
+			uint16_t idtype = idtype_from_str(device_id_type);
+
+			if (idtype) {
+				idname1 = device_id_system_read(cmd, dev1, idtype);
+				idname2 = device_id_system_read(cmd, dev2, idtype);
+			}
+			if (idname1)
+				same_id1 = !strcmp(idname1, device_id);
+			if (idname2)
+				same_id2 = !strcmp(idname2, device_id);
+		}
+
 		has_lv1 = (dev1->flags & DEV_USED_FOR_LV) ? 1 : 0;
 		has_lv2 = (dev2->flags & DEV_USED_FOR_LV) ? 1 : 0;
 
@@ -751,6 +820,12 @@ next:
 				dev_name(dev2), dev2_major, dev2_minor,
 				device_hint ?: "none");
 
+		log_debug_cache("PV %s: device_id %s. %s is %s. %s is %s.",
+				devl->dev->pvid,
+				device_id ?: ".",
+				dev_name(dev1), idname1 ?: ".",
+				dev_name(dev2), idname2 ?: ".");
+
 		log_debug_cache("PV %s: size %llu. %s is %llu. %s is %llu.",
 				devl->dev->pvid,
 				(unsigned long long)pvsummary_size,
@@ -791,6 +866,13 @@ next:
 		} else if (prev_unchosen2 && !prev_unchosen1) {
 			/* keep 1 (NB when unchosen is set we unprefer) */
 			reason = "of previous preference";
+		} else if (same_id1 && !same_id2) {
+			/* keep 1 */
+			reason = "device id";
+		} else if (same_id2 && !same_id1) {
+			/* change to 2 */
+			change = 1;
+			reason = "device id";
 		} else if (has_lv1 && !has_lv2) {
 			/* keep 1 */
 			reason = "device is used by LV";
@@ -995,6 +1077,143 @@ int lvmcache_label_rescan_vg_rw(struct cmd_context *cmd, const char *vgname, con
 	return _label_rescan_vg(cmd, vgname, vgid, 1);
 }
 
+int lvmcache_label_reopen_vg_rw(struct cmd_context *cmd, const char *vgname, const char *vgid)
+{
+	struct lvmcache_vginfo *vginfo;
+	struct lvmcache_info *info;
+
+	if (!(vginfo = lvmcache_vginfo_from_vgname(vgname, vgid)))
+		return_0;
+
+	dm_list_iterate_items(info, &vginfo->infos) {
+		if (!label_scan_reopen_rw(info->dev))
+			return_0;
+	}
+
+	return 1;
+}
+
+/*
+ * During label_scan, the md component filter is applied to each device after
+ * the device header has been read.  This often just checks the start of the
+ * device for an md header, and if the device has an md header at the end, the
+ * md component filter wouldn't detect it.  In some cases, the full md filter
+ * is enabled during label_scan, in which case the md component filter will
+ * check both the start and end of the device for md superblocks.
+ *
+ * In this function, after label_scan is done, we may decide that a full md
+ * component check should be applied to a device if it hasn't been yet.  This
+ * is based on some clues or uncertainty that arose during label_scan.
+ *
+ * label_scan saved metadata info about pvs in lvmcache pvsummaries.  That
+ * pvsummary metadata includes the pv size.  So now, after label_scan is done,
+ * we can compare the pv size with the size of the device the pv was read from.
+ * If the pv and dev sizes do not match, it can sometimes be normal, but other
+ * times it can be a clue that label_scan mistakenly read the pv from an md
+ * component device instead of from the md device itself.  So for unmatching
+ * sizes, we do a full md component check on the device.
+ */
+
+void lvmcache_extra_md_component_checks(struct cmd_context *cmd)
+{
+	struct lvmcache_vginfo *vginfo, *vginfo2;
+	struct lvmcache_info *info, *info2;
+	struct device *dev;
+	const char *device_hint;
+	uint64_t devsize, pvsize;
+	int do_check_size, do_check_name;
+	int md_check_start;
+
+	/*
+	 * use_full_md_check: if set then no more needs to be done here,
+	 * all devs have already been fully checked as md components.
+	 *
+	 * md_component_checks "full": use_full_md_check was set, and caused
+	 *  filter-md to already do a full check, no more is needed.
+	 *
+	 * md_component_checks "start": skip end of device md component checks,
+	 *  the start of device has already been checked by filter-md.
+	 *
+	 * md_component_checks "auto": do full checks only when lvm finds some
+	 * clue or reasons to believe it might be useful, which is what this
+	 * function is looking for.
+	 */
+	if (!cmd->md_component_detection || cmd->use_full_md_check ||
+	    !strcmp(cmd->md_component_checks, "none"))
+		return;
+
+	md_check_start = !strcmp(cmd->md_component_checks, "start");
+
+	/*
+	 * We want to avoid extra scanning for end-of-device md superblocks
+	 * whenever possible, since it can add up to a lot of extra io if we're
+	 * not careful to do it only when there's a good reason to believe a
+	 * dev is an md component.
+	 *
+	 * If the pv/dev size mismatches are commonly occuring for
+	 * non-md-components then we'll want to stop using that as a trigger
+	 * for the full md check.
+	 */
+
+	dm_list_iterate_items_safe(vginfo, vginfo2, &_vginfos) {
+		dm_list_iterate_items_safe(info, info2, &vginfo->infos) {
+			dev = info->dev;
+			device_hint = _get_pvsummary_device_hint(dev->pvid);
+			pvsize = _get_pvsummary_size(dev->pvid);
+			devsize = dev->size;
+			do_check_size = 0;
+			do_check_name = 0;
+
+			if (!devsize && !dev_get_size(dev, &devsize))
+				log_debug("No size for %s.", dev_name(dev));
+
+			/*
+			 * PV larger than dev not common; dev larger than PV
+			 * can be common, but not as often as PV larger.
+			 */
+			if (pvsize && devsize && (pvsize != devsize))
+				do_check_size = 1;
+			if (device_hint && !strncmp(device_hint, "/dev/md", 7))
+				do_check_name = 1;
+
+			if (!do_check_size && !do_check_name)
+				continue;
+
+			/*
+			 * If only the size is different (which can be fairly
+			 * common for non-md-component devs) and the user has
+			 * set "start" to disable full md checks, then skip it.
+			 * If the size is different, *and* the device name hint
+			 * looks like an md device, then it seems very likely
+			 * to be an md component, so do a full check on it even
+			 * if the user has set "start".
+			 * 
+			 * In "auto" mode, do a full check if either the size
+			 * or the name indicates a possible md component.
+			 */
+			if (do_check_size && !do_check_name && md_check_start) {
+				log_debug("extra md component check skip %llu %llu device_hint %s dev %s",
+					  (unsigned long long)pvsize, (unsigned long long)devsize,
+					  device_hint ?: "none", dev_name(dev));
+				continue;
+			}
+
+			log_debug("extra md component check %llu %llu device_hint %s dev %s",
+				  (unsigned long long)pvsize, (unsigned long long)devsize,
+				  device_hint ?: "none", dev_name(dev));
+
+			if (dev_is_md_component(dev, NULL, 1)) {
+				log_debug("dropping PV from md component %s", dev_name(dev));
+				dev->flags &= ~DEV_SCAN_FOUND_LABEL;
+				/* lvmcache_del will also delete vginfo if info was last one */
+				lvmcache_del(info);
+				lvmcache_del_dev_from_duplicates(dev);
+				cmd->filter->wipe(cmd, cmd->filter, dev, NULL);
+			}
+		}
+	}
+}
+
 /*
  * Uses label_scan to populate lvmcache with 'vginfo' struct for each VG
  * and associated 'info' structs for those VGs.  Only VG summary information
@@ -1023,14 +1242,13 @@ int lvmcache_label_scan(struct cmd_context *cmd)
 {
 	struct dm_list del_cache_devs;
 	struct dm_list add_cache_devs;
+	struct dm_list renamed_devs;
 	struct lvmcache_info *info;
-	struct lvmcache_vginfo *vginfo;
 	struct device_list *devl;
-	int vginfo_count = 0;
 
-	int r = 0;
+	dm_list_init(&renamed_devs);
 
-	log_debug_cache("Finding VG info");
+	log_debug_cache("lvmcache label scan begin");
 
 	/*
 	 * Duplicates found during this label scan are added to _initial_duplicates.
@@ -1042,13 +1260,24 @@ int lvmcache_label_scan(struct cmd_context *cmd)
 	 * Do the actual scanning.  This populates lvmcache
 	 * with infos/vginfos based on reading headers from
 	 * each device, and a vg summary from each mda.
-	 *
-	 * Note that this will *skip* scanning a device if
-	 * an info struct already exists in lvmcache for
-	 * the device.
 	 */
 	label_scan(cmd);
 
+	/*
+	 * When devnames are used as device ids (which is dispreferred),
+	 * changing/unstable devnames can lead to entries in the devices file
+	 * not being matched to a dev even if the PV is present on the system.
+	 * Or, a devices file entry may have been matched to the wrong device
+	 * (with the previous name) that does not have the PVID specified in
+	 * the entry.  This function detects that problem, scans labels on all
+	 * devs on the system to find the missing PVIDs, and corrects the
+	 * devices file.  We then need to run label scan on these correct
+	 * devices.
+	 */
+	device_ids_find_renamed_devs(cmd, &renamed_devs, NULL, 0);
+	if (!dm_list_empty(&renamed_devs))
+		label_scan_devs(cmd, cmd->filter, &renamed_devs);
+
 	/*
 	 * _choose_duplicates() returns:
 	 *
@@ -1083,7 +1312,7 @@ int lvmcache_label_scan(struct cmd_context *cmd)
 
 		dm_list_iterate_items(devl, &add_cache_devs) {
 			log_debug_cache("Adding chosen duplicate %s", dev_name(devl->dev));
-			label_read(devl->dev);
+			label_scan_dev(devl->dev);
 		}
 
 		dm_list_splice(&_unused_duplicates, &del_cache_devs);
@@ -1092,17 +1321,8 @@ int lvmcache_label_scan(struct cmd_context *cmd)
 		_warn_unused_duplicates(cmd);
 	}
 
-	r = 1;
-
-	dm_list_iterate_items(vginfo, &_vginfos) {
-		if (is_orphan_vg(vginfo->vgname))
-			continue;
-		vginfo_count++;
-	}
-
-	log_debug_cache("Found VG info for %d VGs", vginfo_count);
-
-	return r;
+	log_debug_cache("lvmcache label scan done");
+	return 1;
 }
 
 int lvmcache_get_vgnameids(struct cmd_context *cmd,
@@ -1189,8 +1409,7 @@ static void _free_vginfo(struct lvmcache_vginfo *vginfo)
 	free(vginfo->vgname);
 	free(vginfo->system_id);
 	free(vginfo->creation_host);
-	if (vginfo->lock_type)
-		free(vginfo->lock_type);
+	free(vginfo->lock_type);
 	free(vginfo);
 }
 
@@ -1646,6 +1865,9 @@ int lvmcache_update_vgname_and_id(struct cmd_context *cmd, struct lvmcache_info
 		 * second updated to seqno 4, first comes back and second goes
 		 * missing, first updated to seqno 4, second comes back, now
 		 * both are present with same seqno but different checksums.
+		 * FIXME: we should check if the majority of mda copies have one
+		 * checksum and if so use that copy of metadata, but if there's
+		 * not a majority, don't allow the VG to be modified/activated.
 		 */
 
 		if ((vginfo->mda_size != vgsummary->mda_size) || (vginfo->mda_checksum != vgsummary->mda_checksum)) {
@@ -1707,8 +1929,8 @@ int lvmcache_update_vg_from_write(struct volume_group *vg)
 	char pvid_s[ID_LEN + 1] __attribute__((aligned(8)));
 	struct lvmcache_vgsummary vgsummary = {
 		.vgname = vg->name,
-		.vgstatus = vg->status,
 		.vgid = vg->id,
+		.vgstatus = vg->status,
 		.system_id = vg->system_id,
 		.lock_type = vg->lock_type
 	};
@@ -1744,8 +1966,8 @@ int lvmcache_update_vg_from_read(struct volume_group *vg, unsigned precommitted)
 	char pvid_s[ID_LEN + 1] __attribute__((aligned(8)));
 	struct lvmcache_vgsummary vgsummary = {
 		.vgname = vg->name,
-		.vgstatus = vg->status,
 		.vgid = vg->id,
+		.vgstatus = vg->status,
 		.system_id = vg->system_id,
 		.lock_type = vg->lock_type
 	};
@@ -1776,6 +1998,9 @@ int lvmcache_update_vg_from_read(struct volume_group *vg, unsigned precommitted)
 		log_warn("WARNING: outdated PV %s seqno %u has been removed in current VG %s seqno %u.",
 			 dev_name(info->dev), info->summary_seqno, vg->name, vginfo->seqno);
 
+		if (!_outdated_warning++)
+			log_warn("See vgck --updatemetadata to clear outdated metadata.");
+
 		_drop_vginfo(info, vginfo); /* remove from vginfo->infos */
 		dm_list_add(&vginfo->outdated_infos, &info->list);
 	}
@@ -2520,19 +2745,115 @@ bool lvmcache_scan_mismatch(struct cmd_context *cmd, const char *vgname, const c
 	return true;
 }
 
-static uint64_t _max_metadata_size;
+/*
+ * max_size_bytes and max_size_percent may come from different areas and
+ * different vgs because of different area sizes.
+ */
+static uint64_t _max_metadata_size_bytes;
+static dm_percent_t _max_metadata_size_percent = DM_PERCENT_INVALID;
 
-void lvmcache_save_metadata_size(uint64_t val)
+void lvmcache_save_metadata_size_bytes(uint64_t val)
 {
-	if (!_max_metadata_size)
-		_max_metadata_size = val;
-	else if (_max_metadata_size < val)
-		_max_metadata_size = val;
+	if (!_max_metadata_size_bytes)
+		_max_metadata_size_bytes = val;
+	else if (_max_metadata_size_bytes < val)
+		_max_metadata_size_bytes = val;
 }
 
-uint64_t lvmcache_max_metadata_size(void)
+uint64_t lvmcache_max_metadata_size_bytes(void)
 {
-	return _max_metadata_size;
+	return _max_metadata_size_bytes;
+}
+
+/*
+ * TODO: enable/disable scan_lock_global with config setting:
+ * y: always use it
+ * n: never use it
+ * auto (default): use based on /run/lvm/scan_lock_global
+ */
+void lvmcache_save_metadata_size_percent(uint64_t meta_size, uint64_t mdah_size)
+{
+
+	dm_percent_t pc = dm_make_percent(meta_size, mdah_size);
+
+	if (pc == DM_PERCENT_INVALID || pc == DM_PERCENT_FAILED ||
+	    pc == DM_PERCENT_0 || pc == DM_PERCENT_1)
+		return;
+
+	if (_max_metadata_size_percent == DM_PERCENT_INVALID) {
+		_max_metadata_size_percent = pc;
+		return;
+	}
+
+	if (_max_metadata_size_percent < pc)
+		_max_metadata_size_percent = pc;
+}
+
+/*
+ * TODO: make the percent at which scan_lock_global is used
+ * configurable?
+ */
+#define SCAN_LOCK_GLOBAL_METADATA_PERCENT (DM_PERCENT_1 * 25)
+
+void set_scan_lock_global(struct cmd_context *cmd)
+{
+	FILE *fp;
+
+	if (_max_metadata_size_percent == DM_PERCENT_INVALID)
+		return;
+
+	if (_max_metadata_size_percent >= SCAN_LOCK_GLOBAL_METADATA_PERCENT) {
+		if (_scan_lock_global_file_exists)
+			return;
+		log_debug("Creating %s.", _scan_lock_global_file);
+		if (!(fp = fopen(_scan_lock_global_file, "w")))
+			return;
+		if (fclose(fp))
+			stack;
+	} else {
+		if (_scan_lock_global_file_exists) {
+			log_debug("Unlinking %s.", _scan_lock_global_file);
+			if (unlink(_scan_lock_global_file))
+				stack;
+		}
+	}
+}
+
+int do_scan_lock_global(struct cmd_context *cmd, int *gl_ex)
+{
+	struct stat buf;
+
+	if (cmd->nolocking)
+		return 0;
+
+	/* global lock is already held */
+	if (cmd->lockf_global_ex)
+		return 0;
+
+	if (!stat(_scan_lock_global_file, &buf)) {
+		_scan_lock_global_file_exists = 1;
+
+		/*
+		 * Tell the caller to use sh or ex.  A command that may write
+		 * vg metadata should use ex, otherwise sh.
+		 *
+		 * lockd_vg_default_sh/LOCKD_VG_SH is set for commands that
+		 * do not modify vg metadata.
+		 *
+		 * FIXME: this variable/flag was previously used only for
+		 * lvmlockd locking logic, but is now more general, so
+		 * it should be renamed.
+		 */
+		if (cmd->lockd_vg_default_sh)
+			*gl_ex = 0;
+		else
+			*gl_ex = 1;
+
+		return 1;
+
+	}
+
+	return 0;
 }
 
 int lvmcache_vginfo_has_pvid(struct lvmcache_vginfo *vginfo, char *pvid)
@@ -2596,7 +2917,7 @@ void lvmcache_get_outdated_devs(struct cmd_context *cmd,
 	}
 
 	dm_list_iterate_items(info, &vginfo->outdated_infos) {
-		if (!(devl = zalloc(sizeof(*devl))))
+		if (!(devl = dm_pool_zalloc(cmd->mem, sizeof(*devl))))
 			return;
 		devl->dev = info->dev;
 		dm_list_add(devs, &devl->list);
@@ -2660,3 +2981,56 @@ bool lvmcache_is_outdated_dev(struct cmd_context *cmd,
 
 	return false;
 }
+
+const char *dev_filtered_reason(struct device *dev)
+{
+	if (dev->filtered_flags & DEV_FILTERED_REGEX)
+		return "device is rejected by filter config";
+	if (dev->filtered_flags & DEV_FILTERED_INTERNAL)
+		return "device is restricted internally";
+	if (dev->filtered_flags & DEV_FILTERED_MD_COMPONENT)
+		return "device is an md component";
+	if (dev->filtered_flags & DEV_FILTERED_MPATH_COMPONENT)
+		return "device is a multipath component";
+	if (dev->filtered_flags & DEV_FILTERED_PARTITIONED)
+		return "device is partitioned";
+	if (dev->filtered_flags & DEV_FILTERED_SIGNATURE)
+		return "device has a signature";
+	if (dev->filtered_flags & DEV_FILTERED_SYSFS)
+		return "device is missing sysfs info";
+	if (dev->filtered_flags & DEV_FILTERED_DEVTYPE)
+		return "device type is unknown";
+	if (dev->filtered_flags & DEV_FILTERED_MINSIZE)
+		return "device is too small (pv_min_size)";
+	if (dev->filtered_flags & DEV_FILTERED_UNUSABLE)
+		return "device is not in a usable state";
+	if (dev->filtered_flags & DEV_FILTERED_DEVICES_FILE)
+		return "device is not in devices file";
+	if (dev->filtered_flags & DEV_FILTERED_DEVICES_LIST)
+		return "device is not in devices list";
+	if (dev->filtered_flags & DEV_FILTERED_IS_LV)
+		return "device is an LV";
+
+	/* flag has not been added here */
+	if (dev->filtered_flags)
+		return "device is filtered";
+
+	return "device cannot be used";
+}
+
+const char *devname_error_reason(const char *devname)
+{
+	struct device *dev;
+
+	if ((dev = dev_hash_get(devname))) {
+		if (dev->filtered_flags)
+			return dev_filtered_reason(dev);
+		if (lvmcache_dev_is_unused_duplicate(dev))
+			return "device is a duplicate";
+		/* Avoid this case by adding by adding other more descriptive checks above. */
+		return "device cannot be used";
+	}
+
+	return "device not found";
+}
+

lib/cache/lvmcache.h

@@ -69,6 +69,7 @@ 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 cmd_context *cmd, struct labeller *labeller, const char *pvid,
@@ -182,8 +183,9 @@ bool lvmcache_scan_mismatch(struct cmd_context *cmd, const char *vgname, const c
 
 int lvmcache_vginfo_has_pvid(struct lvmcache_vginfo *vginfo, char *pvid);
 
-uint64_t lvmcache_max_metadata_size(void);
-void lvmcache_save_metadata_size(uint64_t val);
+uint64_t lvmcache_max_metadata_size_bytes(void);
+void lvmcache_save_metadata_size_bytes(uint64_t val);
+void lvmcache_save_metadata_size_percent(uint64_t meta_size, uint64_t mdah_size);
 
 int dev_in_device_list(struct device *dev, struct dm_list *head);
 
@@ -216,4 +218,17 @@ 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);
+
+void set_scan_lock_global(struct cmd_context *cmd);
+int do_scan_lock_global(struct cmd_context *cmd, int *gl_ex);
+
+
 #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>
@@ -40,10 +41,6 @@
 #include <syslog.h>
 #include <time.h>
 
-#ifdef APP_MACHINEID_SUPPORT
-#include <systemd/sd-id128.h>
-#endif
-
 #ifdef __linux__
 #  include <malloc.h>
 #endif
@@ -132,12 +129,9 @@ static const char *_read_system_id_from_file(struct cmd_context *cmd, const char
 	return system_id;
 }
 
-/* systemd-id128 new produced: f64406832c2140e8ac5422d1089aae03 */
-#define LVM_APPLICATION_ID SD_ID128_MAKE(f6,44,06,83,2c,21,40,e8,ac,54,22,d1,08,9a,ae,03)
-
 static const char *_system_id_from_source(struct cmd_context *cmd, const char *source)
 {
-	char buf[PATH_MAX];
+	char filebuf[PATH_MAX];
 	const char *file;
 	const char *etc_str;
 	const char *str;
@@ -156,23 +150,10 @@ static const char *_system_id_from_source(struct cmd_context *cmd, const char *s
 		goto out;
 	}
 
-#ifdef APP_MACHINEID_SUPPORT
-	if (!strcasecmp(source, "appmachineid")) {
-		sd_id128_t id;
-
-		sd_id128_get_machine_app_specific(LVM_APPLICATION_ID, &id);
-
-		if (dm_snprintf(buf, PATH_MAX, SD_ID128_FORMAT_STR, SD_ID128_FORMAT_VAL(id)) < 0)
-			stack;
-		system_id = system_id_from_string(cmd, buf);
-		goto out;
-	}
-#endif
-
 	if (!strcasecmp(source, "machineid") || !strcasecmp(source, "machine-id")) {
 		etc_str = find_config_tree_str(cmd, global_etc_CFG, NULL);
-		if (dm_snprintf(buf, sizeof(buf), "%s/machine-id", etc_str) != -1)
-			system_id = _read_system_id_from_file(cmd, buf);
+		if (dm_snprintf(filebuf, sizeof(filebuf), "%s/machine-id", etc_str) != -1)
+			system_id = _read_system_id_from_file(cmd, filebuf);
 		goto out;
 	}
 
@@ -249,7 +230,7 @@ static void _get_sysfs_dir(struct cmd_context *cmd, char *buf, size_t buf_size)
 		return;
 	}
 
-	strncpy(buf, sys_mnt, buf_size);
+	(void) dm_strncpy(buf, sys_mnt, buf_size);
 }
 
 static uint32_t _parse_debug_fields(struct cmd_context *cmd, int cfg, const char *cfgname)
@@ -680,6 +661,8 @@ static int _process_config(struct cmd_context *cmd)
 	 */
 	cmd->default_settings.udev_fallback = udev_disabled ? 1 : -1;
 
+	cmd->default_settings.issue_discards = find_config_tree_bool(cmd, devices_issue_discards_CFG, NULL);
+
 	init_retry_deactivation(find_config_tree_bool(cmd, activation_retry_deactivation_CFG, NULL));
 
 	init_activation_checks(find_config_tree_bool(cmd, activation_checks_CFG, NULL));
@@ -983,8 +966,8 @@ static void _destroy_config(struct cmd_context *cmd)
 	/* CONFIG_FILE/CONFIG_MERGED_FILES */
 	if ((cft = remove_config_tree_by_source(cmd, CONFIG_MERGED_FILES)))
 		config_destroy(cft);
-	else
-		remove_config_tree_by_source(cmd, CONFIG_FILE);
+	else if ((cft = remove_config_tree_by_source(cmd, CONFIG_FILE)))
+		config_destroy(cft);
 
 	dm_list_iterate_items(cfl, &cmd->config_files)
 		config_destroy(cfl->cft);
@@ -1086,7 +1069,7 @@ 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)
 {
@@ -1105,6 +1088,9 @@ 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()))
@@ -1120,7 +1106,7 @@ static struct dev_filter *_init_filter_chain(struct cmd_context *cmd)
 
 	/* global regex filter. Optional. */
 	if ((cn = find_config_tree_node(cmd, devices_global_filter_CFG, NULL))) {
-		if (!(filters[nr_filt] = regex_filter_create(cn->v))) {
+		if (!(filters[nr_filt] = regex_filter_create(cn->v, 0, 1))) {
 			log_error("Failed to create global regex device filter");
 			goto bad;
 		}
@@ -1129,7 +1115,7 @@ static struct dev_filter *_init_filter_chain(struct cmd_context *cmd)
 
 	/* regex filter. Optional. */
 	if ((cn = find_config_tree_node(cmd, devices_filter_CFG, NULL))) {
-		if (!(filters[nr_filt] = regex_filter_create(cn->v))) {
+		if (!(filters[nr_filt] = regex_filter_create(cn->v, 1, 0))) {
 			log_error("Failed to create regex device filter");
 			goto bad;
 		}
@@ -1143,6 +1129,13 @@ 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");
@@ -1505,6 +1498,7 @@ 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;
 }
@@ -1737,6 +1731,8 @@ 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))
@@ -1862,6 +1858,7 @@ 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);
@@ -1941,6 +1938,8 @@ int refresh_toolcontext(struct cmd_context *cmd)
 	if (!_init_dev_cache(cmd))
 		return_0;
 
+	devices_file_init(cmd);
+
 	if (!_init_formats(cmd))
 		return_0;
 
@@ -1990,6 +1989,7 @@ 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

@@ -39,7 +39,7 @@ struct config_info {
 	int udev_rules;
 	int udev_sync;
 	int udev_fallback;
-	int cache_vgmetadata;
+	int issue_discards;
 	const char *msg_prefix;
 	const char *fmt_name;
 	const char *dmeventd_executable;
@@ -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.
@@ -241,6 +256,7 @@ struct cmd_context {
 	unsigned rand_seed;
 	struct dm_list pending_delete;		/* list of LVs for removal */
 	struct dm_pool *pending_delete_mem;	/* memory pool for pending deletes */
+	int early_lock_vg_mode;
 };
 
 /*

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;
 	}
@@ -1147,8 +1141,10 @@ int config_def_check(struct cft_check_handle *handle)
 	 * sections and settings with full path as a key.
 	 * If section name is variable, use '#' as a substitute.
 	 */
+	*vp = 0;
+	*rp = 0;
 	if (!handle->cmd->cft_def_hash) {
-		if (!(handle->cmd->cft_def_hash = dm_hash_create(64))) {
+		if (!(handle->cmd->cft_def_hash = dm_hash_create(60))) {
 			log_error("Failed to create configuration definition hash.");
 			r = 0; goto out;
 		}
@@ -1714,6 +1710,7 @@ 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 +1724,14 @@ 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 +1742,14 @@ 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 +1777,7 @@ 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

@@ -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"
@@ -401,15 +427,15 @@ cfg(devices_fw_raid_component_detection_CFG, "fw_raid_component_detection", devi
 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,
 	"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"
+	"default_data_alignment will be overridden if it is not aligned\n"
 	"with the value detected for this setting.\n"
-	"This setting is overriden by data_alignment_detection,\n"
+	"This setting is overridden by data_alignment_detection,\n"
 	"data_alignment, and the --dataalignment option.\n")
 
 cfg(devices_default_data_alignment_CFG, "default_data_alignment", devices_CFG_SECTION, CFG_DEFAULT_COMMENTED, CFG_TYPE_INT, FIRST_PE_AT_ONE_MB_IN_MB, vsn(2, 2, 75), NULL, 0, NULL,
 	"Align the start of a PV data area with this number of MiB.\n"
 	"Set to 1 for 1MiB, 2 for 2MiB, etc. Set to 0 to disable.\n"
-	"This setting is overriden by data_alignment and the --dataalignment\n"
+	"This setting is overridden 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,
@@ -421,9 +447,9 @@ cfg(devices_data_alignment_detection_CFG, "data_alignment_detection", devices_CF
 	"preferred unit of receiving I/O, e.g. MD stripe width.\n"
 	"minimum_io_size is used if optimal_io_size is undefined (0).\n"
 	"If md_chunk_alignment is enabled, that detects the optimal_io_size.\n"
-	"default_data_alignment and md_chunk_alignment will be overriden\n"
+	"default_data_alignment and md_chunk_alignment will be overridden\n"
 	"if they are not aligned with the value detected for this setting.\n"
-	"This setting is overriden by data_alignment and the --dataalignment\n"
+	"This setting is overridden 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,
@@ -431,7 +457,7 @@ cfg(devices_data_alignment_CFG, "data_alignment", devices_CFG_SECTION, 0, CFG_TY
 	"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")
+	"This setting is overridden 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,
 	"Shift the start of an aligned PV data area based on sysfs information.\n"
@@ -441,7 +467,7 @@ cfg(devices_data_alignment_offset_detection_CFG, "data_alignment_offset_detectio
 	"partitioning will have an alignment_offset of 3584 bytes (sector 7\n"
 	"is the lowest aligned logical block, the 4KiB sectors start at\n"
 	"LBA -1, and consequently sector 63 is aligned on a 4KiB boundary).\n"
-	"This setting is overriden by the --dataalignmentoffset option.\n")
+	"This setting is overridden 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,
 	"Ignore DM devices that have I/O suspended while scanning devices.\n"
@@ -467,7 +493,7 @@ cfg(devices_ignore_lvm_mirrors_CFG, "ignore_lvm_mirrors", devices_CFG_SECTION, 0
 	"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")
+	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,
 	"Allow use of pvcreate --uuid without requiring --restorefile.\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"
@@ -940,13 +974,13 @@ 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)
 
@@ -957,16 +991,16 @@ cfg(global_etc_CFG, "etc", global_CFG_SECTION, 0, CFG_TYPE_STRING, DEFAULT_ETC_D
 	"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.")
+    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,
 	"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")
+	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")
+	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,
 	"Directory to use for LVM command file locks.\n"
@@ -979,14 +1013,13 @@ cfg(global_prioritise_write_locks_CFG, "prioritise_write_locks", global_CFG_SECT
 	"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,
 	"Abort a command that encounters an internal error.\n"
@@ -994,7 +1027,7 @@ cfg(global_abort_on_internal_errors_CFG, "abort_on_internal_errors", global_CFG_
 	"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")
+	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,
 	"No operations that change on-disk metadata are permitted.\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"
@@ -1082,20 +1115,23 @@ 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"
-	"Use auto_activation_volume_list to select which LVs should be\n"
-	"activated from these events (the default is all.)\n"
-	"When event_activation is disabled, the system will generally run\n"
-	"a direct activation command to activate LVs in complete VGs.\n")
+	"When a PV appears on the system, a system-generated uevent triggers\n"
+	"the lvm2-pvscan service which runs the pvscan --cache -aay command.\n"
+	"If the new PV completes a VG, pvscan autoactivates LVs in the VG.\n"
+	"When event_activation is disabled, the lvm2-activation services are\n"
+	"generated and run at fixed points during system startup.  These\n"
+	"services run vgchange -aay to autoactivate LVs in VGs that happen\n"
+	"to be present at that point in time.\n"
+	"See the --setautoactivation option or the auto_activation_volume_list\n"
+	"setting to configure autoactivation for specific VGs or LVs.\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")
+	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")
@@ -1119,6 +1155,15 @@ cfg(global_sanlock_lv_extend_CFG, "sanlock_lv_extend", global_CFG_SECTION, CFG_D
 	"and can cause lvcreate to fail. Applicable only if LVM is compiled\n"
 	"with lockd support\n")
 
+cfg(global_lvmlockctl_kill_command_CFG, "lvmlockctl_kill_command", global_CFG_SECTION, CFG_ALLOW_EMPTY | CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, "", vsn(2, 3, 12), NULL, 0, NULL,
+	"The command that lvmlockctl --kill should use to force LVs offline.\n"
+	"The lvmlockctl --kill command is run when a shared VG has lost\n"
+	"access to locks (e.g. when sanlock has lost access to storage.)\n"
+	"An empty string means that there will be no automatic attempt by\n"
+	"lvmlockctl --kill to forcibly shut down LVs in the VG, and the user\n"
+	"can manually intervene as described in lvmlockd(8).\n"
+	"The VG name will be appended to the command specified here.\n")
+
 cfg(global_thin_check_executable_CFG, "thin_check_executable", global_CFG_SECTION, CFG_ALLOW_EMPTY | CFG_DEFAULT_COMMENTED, CFG_TYPE_STRING, THIN_CHECK_CMD, vsn(2, 2, 94), "@THIN_CHECK_CMD@", 0, NULL,
 	"The full path to the thin_check command.\n"
 	"LVM uses this command to check that a thin metadata device is in a\n"
@@ -1204,6 +1249,15 @@ 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")
@@ -1224,12 +1278,10 @@ cfg(global_system_id_source_CFG, "system_id_source", global_CFG_SECTION, 0, CFG_
 	"  uname\n"
 	"    Set the system ID from the hostname (uname) of the system.\n"
 	"    System IDs beginning localhost are not permitted.\n"
-	"  appmachineid\n"
-	"    Use an LVM-specific derivation of the local machine-id as the\n"
-	"    system ID. See 'man machine-id'.\n"
 	"  machineid\n"
-	"    Use the contents of the machine-id file to set the system ID\n"
-	"    (appmachineid is recommended.)\n"
+	"    Use the contents of the machine-id file to set the system ID.\n"
+	"    Some systems create this file at installation time.\n"
+	"    See 'man machine-id' and global/etc.\n"
 	"  file\n"
 	"    Use the contents of another file (system_id_file) to set the\n"
 	"    system ID.\n"
@@ -1274,7 +1326,7 @@ cfg(global_io_memory_size_CFG, "io_memory_size", global_CFG_SECTION, CFG_DEFAULT
 
 cfg(activation_udev_sync_CFG, "udev_sync", activation_CFG_SECTION, 0, 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"
+	"The --noudevsync option overrides this setting.\n"
 	"When disabled, LVM commands will not wait for notifications from\n"
 	"udev, but continue irrespective of any possible udev processing in\n"
 	"the background. Only use this if udev is not running or has rules\n"
@@ -1288,7 +1340,7 @@ cfg(activation_udev_rules_CFG, "udev_rules", activation_CFG_SECTION, 0, CFG_TYPE
 	"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"
@@ -1309,21 +1361,21 @@ 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")
@@ -1353,22 +1405,22 @@ cfg_array(activation_volume_list_CFG, "volume_list", activation_CFG_SECTION, CFG
 	"#\n")
 
 cfg_array(activation_auto_activation_volume_list_CFG, "auto_activation_volume_list", activation_CFG_SECTION, CFG_ALLOW_EMPTY | CFG_DEFAULT_UNDEFINED, CFG_TYPE_STRING, NULL, vsn(2, 2, 97), NULL, 0, NULL,
-	"Only LVs selected by this list are auto-activated.\n"
-	"This list works like volume_list, but it is used only by\n"
-	"auto-activation commands. It does not apply to direct activation\n"
-	"commands. If this list is defined, an LV is only auto-activated\n"
-	"if it matches an entry in this list. If this list is undefined, it\n"
-	"imposes no limits on LV auto-activation (all are allowed.) If this\n"
-	"list is defined and empty, i.e. \"[]\", then no LVs are selected for\n"
-	"auto-activation. An LV that is selected by this list for\n"
-	"auto-activation, must also be selected by volume_list (if defined)\n"
-	"before it is activated. Auto-activation is an activation command that\n"
-	"includes the 'a' argument: --activate ay or -a ay. The 'a' (auto)\n"
-	"argument for auto-activation is meant to be used by activation\n"
-	"commands that are run automatically by the system, as opposed to LVM\n"
-	"commands run directly by a user. A user may also use the 'a' flag\n"
-	"directly to perform auto-activation. Also see pvscan(8) for more\n"
-	"information about auto-activation.\n"
+	"A list of VGs or LVs that should be autoactivated.\n"
+	"Autoactivation is an activation command run with -aay,\n"
+	"i.e. vgchange -aay, lvchange -aay, or pvscan --cache -aay.\n"
+	"When this list is defined, an autoactivation command will only\n"
+	"activate LVs included in the list. If this list is undefined,\n"
+	"it has no effect. If this list is defined but empty, then no\n"
+	"LVs will be autoactivated. LVs can be included in the list by\n"
+	"LV name, VG name (applies to all LVs in the VG), or tag name.\n"
+	"VGs and LVs can also have an autoactivation property set in\n"
+	"metadata, see --setautoactivation. LVs included in this list\n"
+	"will not be autoactivated if the VG or LV autoactivation\n"
+	"property is disabled (see vgs or lvs \"-o autoactivation\").\n"
+	"The volume_list setting and the \"activation skip\" property\n"
+	"also apply to autoactivation.\n"
+	"The -aay option is meant to be used by activation commands that\n"
+	"are run automatically by the system, e.g. from systemd services.\n"
 	"#\n"
 	"Accepted values:\n"
 	"  vgname\n"
@@ -1432,7 +1484,7 @@ 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"
@@ -1560,7 +1612,7 @@ 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"
@@ -1600,7 +1652,7 @@ 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")
@@ -1610,7 +1662,7 @@ cfg(activation_monitoring_CFG, "monitoring", activation_CFG_SECTION, 0, CFG_TYPE
 	"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"
@@ -1724,7 +1776,7 @@ 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)
@@ -2049,7 +2101,7 @@ 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"
@@ -2058,13 +2110,13 @@ 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"

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/datastruct/str_list.c

@@ -218,7 +218,7 @@ struct dm_list *str_to_str_list(struct dm_pool *mem, const char *str,
 		return NULL;
 	}
 
-	p1 = p2 = str;
+	p1 = str;
 	while (*p1) {
 		if (!(p2 = strstr(p1, delim)))
 			next = p2 = str + strlen(str);

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);
@@ -79,7 +79,7 @@ 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 fd, uint64_t start, size_t len)
+bool bcache_invalidate_bytes(struct bcache *cache, int di, uint64_t start, size_t len)
 {
 	block_address bb, be;
 	bool result = true;
@@ -87,7 +87,7 @@ bool bcache_invalidate_bytes(struct bcache *cache, int fd, uint64_t start, size_
 	byte_range_to_block_range(cache, start, len, &bb, &be);
 
 	for (; bb != be; bb++) {
-		if (!bcache_invalidate(cache, fd, bb))
+		if (!bcache_invalidate(cache, di, bb))
 			result = false;
 	}
 
@@ -101,8 +101,8 @@ bool bcache_invalidate_bytes(struct bcache *cache, int fd, uint64_t start, size_
  
 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;
@@ -111,7 +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;
@@ -124,12 +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;
@@ -141,7 +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;
@@ -151,17 +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);
@@ -171,7 +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;
@@ -179,7 +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;
@@ -189,7 +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;
 
@@ -198,16 +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);
@@ -216,12 +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);
 	}
@@ -229,7 +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;
 
@@ -238,17 +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);
@@ -257,14 +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);
@@ -273,7 +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;
 
@@ -282,6 +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)
 		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;
@@ -526,9 +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;
@@ -688,7 +686,7 @@ struct bcache {
 //----------------------------------------------------------------
 
 struct key_parts {
-	uint32_t fd;
+	uint32_t di;
 	uint64_t b;
 } __attribute__ ((packed));
 
@@ -697,12 +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))
@@ -716,7 +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;
 
@@ -727,7 +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));
@@ -869,7 +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;
@@ -945,21 +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;
 			}
 		}
@@ -968,7 +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;
@@ -1014,10 +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
@@ -1042,7 +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);
@@ -1087,6 +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.");
@@ -1147,6 +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;
 }
 
@@ -1162,6 +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)
@@ -1179,13 +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);
@@ -1203,12 +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) {
@@ -1227,10 +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;
 }
 
@@ -1294,7 +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;
 	}
 
@@ -1311,9 +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));
 }
 
 //----------------------------------------------------------------
@@ -1329,27 +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;
 	}
@@ -1362,24 +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));
+		(void) radix_tree_remove_prefix(cache->rtree, k.bytes, k.bytes + sizeof(k.parts.di));
 
 	return it.success;
 }
@@ -1393,7 +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;
 	}
 
@@ -1405,35 +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);
+	(void) 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

@@ -34,7 +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);
@@ -48,7 +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;
 
@@ -106,12 +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);
 
@@ -129,38 +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_invalidate_bytes(struct bcache *cache, int fd, uint64_t start, size_t len);
+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.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-dasd.c

@@ -81,7 +81,7 @@ typedef struct dasd_information2_t {
 int dasd_is_cdl_formatted(struct device *dev)
 {
 	int ret = 0;
-	dasd_information2_t dasd_info2;
+	dasd_information2_t dasd_info2 = { 0 };
 
 	if (!dev_open_readonly(dev))
 		return_0;

lib/device/dev-io.c

@@ -104,9 +104,9 @@ static int _dev_get_size_dev(struct device *dev, uint64_t *size)
 	}
 
 	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;
 	}
 
@@ -117,14 +117,14 @@ 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;
 }
 
 static int _dev_read_ahead_dev(struct device *dev, uint32_t *read_ahead)
 {
-	long read_ahead_long;
+	long read_ahead_long = 0;
 
 	if (dev->read_ahead != -1) {
 		*read_ahead = (uint32_t) dev->read_ahead;
@@ -132,12 +132,13 @@ static int _dev_read_ahead_dev(struct device *dev, uint32_t *read_ahead)
 	}
 
 	if (!dev_open_readonly_quiet(dev)) {
-		log_error("Failed to open to get readahead %s", dev_name(dev));
-		return_0;
+		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;
@@ -170,7 +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;
@@ -449,7 +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;
+	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;
 }
 
 /*
@@ -110,17 +166,14 @@ static int _udev_dev_is_md_component(struct device *dev)
 	if (!(ext = dev_ext_get(dev)))
 		return_0;
 
-	if (!(value = udev_device_get_property_value((struct udev_device *)ext->handle, DEV_EXT_UDEV_BLKID_TYPE))) {
-		dev->flags |= DEV_UDEV_INFO_MISSING;
+	if (!(value = udev_device_get_property_value((struct udev_device *)ext->handle, DEV_EXT_UDEV_BLKID_TYPE)))
 		return 0;
-	}
 
 	return !strcmp(value, DEV_EXT_UDEV_BLKID_TYPE_SW_RAID);
 }
 #else
 static int _udev_dev_is_md_component(struct device *dev)
 {
-	dev->flags |= DEV_UDEV_INFO_MISSING;
 	return 0;
 }
 #endif
@@ -130,8 +183,7 @@ 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 +198,9 @@ 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 +211,81 @@ 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)
@@ -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;
 	}
@@ -641,45 +695,31 @@ 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)
+int get_fs_block_size(const char *pathname, uint32_t *fs_block_size)
 {
-	blkid_probe probe = NULL;
-	const char *block_size_str = NULL;
-	uint64_t block_size_val;
-	int r = 0;
+	char *block_size_str = NULL;
 
-	*fs_block_size = 0;
-
-	if (!(probe = blkid_new_probe_from_filename(dev_name(dev)))) {
-		log_error("Failed to create a new blkid probe for device %s.", dev_name(dev));
-		goto out;
+	if ((block_size_str = blkid_get_tag_value(NULL, "BLOCK_SIZE", pathname))) {
+		*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, pathname);
+		return 1;
+	} else {
+		log_debug("No blkid BLOCK_SIZE for fs on %s", pathname);
+		*fs_block_size = 0;
+		return 0;
 	}
-
-	blkid_probe_enable_partitions(probe, 1);
-
-	(void) blkid_probe_lookup_value(probe, "BLOCK_SIZE", &block_size_str, NULL);
-
-	if (!block_size_str)
-		goto out;
-
-	block_size_val = strtoull(block_size_str, NULL, 10);
-
-	*fs_block_size = (uint32_t)block_size_val;
-	r = 1;
-out:
-	if (probe)
-		blkid_free_probe(probe);
-	return r;
 }
 #else
-int get_fs_block_size(struct device *dev, uint32_t *fs_block_size)
+int get_fs_block_size(const char *pathname, uint32_t *fs_block_size)
 {
+	log_debug("Disabled blkid BLOCK_SIZE for fs.");
 	*fs_block_size = 0;
 	return 0;
 }
@@ -717,7 +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)) {
@@ -851,7 +891,7 @@ static int _wipe_signature(struct device *dev, const char *type, const char *nam
 			   int (*signature_detection_fn)(struct device *dev, uint64_t *offset_found, int full))
 {
 	int wipe;
-	uint64_t offset_found;
+	uint64_t offset_found = 0;
 
 	wipe = signature_detection_fn(dev, &offset_found, 1);
 	if (wipe == -1) {
@@ -915,9 +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,
@@ -933,25 +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;
@@ -960,16 +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))
@@ -979,44 +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;
 }
 
@@ -1047,8 +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)
@@ -1085,6 +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
@@ -1199,10 +1261,8 @@ int udev_dev_is_md_component(struct device *dev)
 	const char *value;
 	int ret = 0;
 
-	if (!obtain_device_list_from_udev()) {
-		dev->flags |= DEV_UDEV_INFO_MISSING;
+	if (!obtain_device_list_from_udev())
 		return 0;
-	}
 
 	if (!(udev_device = _udev_get_dev(dev)))
 		return 0;
@@ -1229,7 +1289,6 @@ int udev_dev_is_mpath_component(struct device *dev)
 
 int udev_dev_is_md_component(struct device *dev)
 {
-	dev->flags |= DEV_UDEV_INFO_MISSING;
 	return 0;
 }
 

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);
@@ -93,10 +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);
+int get_fs_block_size(const char *pathname, uint32_t *fs_block_size);
 
 #endif

lib/device/device.h

@@ -37,7 +37,8 @@
 #define DEV_BCACHE_WRITE	0x00008000      /* bcache_fd is open with RDWR */
 #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		0x00040000	/* set if dev is nvme */
+#define DEV_MATCHED_USE_ID	0x00080000	/* matched an entry from cmd->use_devices */
 
 /*
  * Support for external device info.
@@ -56,12 +57,54 @@ 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 +114,10 @@ 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

@@ -95,6 +95,8 @@ const char *get_lock_type_string(lock_type_t lock_type)
 		return "dlm";
 	case LOCK_TYPE_SANLOCK:
 		return "sanlock";
+	case LOCK_TYPE_IDM:
+		return "idm";
 	}
 	return "invalid";
 }
@@ -111,6 +113,8 @@ lock_type_t get_lock_type_from_string(const char *str)
 		return LOCK_TYPE_DLM;
 	if (!strcmp(str, "sanlock"))
 		return LOCK_TYPE_SANLOCK;
+	if (!strcmp(str, "idm"))
+		return LOCK_TYPE_IDM;
 	return LOCK_TYPE_INVALID;
 }
 
@@ -399,17 +403,19 @@ 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 +479,7 @@ 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 +509,18 @@ 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 +562,18 @@ 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 +607,12 @@ 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;
@@ -149,13 +158,13 @@ static int _get_parent_mpath(const char *dir, char *name, int max_size)
 	}
 
 	if (closedir(dr))
-		log_sys_error("closedir", dir);
+		log_sys_debug("closedir", dir);
 
 	return r;
 }
 
 #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[256];		/* 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) {
@@ -309,7 +374,7 @@ struct dev_filter *mpath_filter_create(struct dev_types *dt)
 		return NULL;
 	}
 
-	if (!(hash = dm_hash_create(128))) {
+	if (!(hash = dm_hash_create(110))) {
 		log_error("mpath hash table creation failed.");
 		return NULL;
 	}
@@ -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

@@ -58,17 +58,23 @@ static int _init_hash(struct pfilter *pf)
 	if (pf->devices)
 		dm_hash_destroy(pf->devices);
 
-	if (!(pf->devices = dm_hash_create(128)))
+	if (!(pf->devices = dm_hash_create(111)))
 		return_0;
 
 	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

@@ -15,11 +15,16 @@
 
 #include "lib/misc/lib.h"
 #include "lib/filters/filter.h"
+#include "lib/commands/toolcontext.h"
 
 struct rfilter {
 	struct dm_pool *mem;
 	dm_bitset_t accept;
 	struct dm_regex *engine;
+	unsigned config_filter:1;
+	unsigned config_global_filter:1;
+	unsigned warned_filter:1;
+	unsigned warned_global_filter:1;
 };
 
 static int _extract_pattern(struct dm_pool *mem, const char *pat,
@@ -151,6 +156,24 @@ 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) {
+		/* can't warn in create_filter because enable_devices_file is set later */
+		if (rf->config_filter && !rf->warned_filter) {
+			log_warn("Please remove the lvm.conf filter, it is ignored with the devices file.");
+			rf->warned_filter = 1;
+		}
+		if (rf->config_global_filter && !rf->warned_global_filter) {
+			log_warn("Please remove the lvm.conf global_filter, it is ignored with the devices file.");
+			rf->warned_global_filter = 1;
+		}
+		return 1;
+	}
+
 	dm_list_iterate_items(sl, &dev->aliases) {
 		m = dm_regex_match(rf->engine, sl->str);
 
@@ -168,8 +191,10 @@ 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
@@ -188,7 +213,7 @@ static void _regex_destroy(struct dev_filter *f)
 	dm_pool_destroy(rf->mem);
 }
 
-struct dev_filter *regex_filter_create(const struct dm_config_value *patterns)
+struct dev_filter *regex_filter_create(const struct dm_config_value *patterns, int config_filter, int config_global_filter)
 {
 	struct dm_pool *mem = dm_pool_create("filter regex", 10 * 1024);
 	struct rfilter *rf;
@@ -202,6 +227,9 @@ struct dev_filter *regex_filter_create(const struct dm_config_value *patterns)
 
 	rf->mem = mem;
 
+	rf->config_filter = config_filter;
+	rf->config_global_filter = config_global_filter;
+
 	if (!_build_matcher(rf, patterns))
 		goto_bad;
 

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

@@ -218,15 +218,15 @@ static int _read_devs(struct dev_set *ds, const char *dir, unsigned sysfs_depth)
 
 		if (dm_snprintf(path, sizeof(path), "%s/%s", dir,
 				 d->d_name) < 0) {
-			log_error("sysfs path name too long: %s in %s",
-				  d->d_name, dir);
+			log_warn("WARNING: sysfs path name too long: %s in %s.",
+				 d->d_name, dir);
 			continue;
 		}
 
 		/* devices have a "dev" file */
 		if (dm_snprintf(file, sizeof(file), "%s/dev", path) < 0) {
-			log_error("sysfs path name too long: %s in %s",
-				  d->d_name, dir);
+			log_warn("WARNING: sysfs path name too long: %s in %s.",
+				 d->d_name, dir);
 			continue;
 		}
 
@@ -242,7 +242,7 @@ static int _read_devs(struct dev_set *ds, const char *dir, unsigned sysfs_depth)
 	}
 
 	if (closedir(dr))
-		log_sys_error("closedir", dir);
+		log_sys_debug("closedir", dir);
 
 	return r;
 }
@@ -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;
 	}