filter: use wwid for mpath filter

Fix versioning for updated symbols dm_stats_create_region
and dm_stats_create_region.

Only the latest symbol should have global entry.

Since I'm not sure what is currenlty the best option for
old symbols - we added support for easy commenting of them
(so we do not lose information when the symbol appeared
for the first time.)

Note: some old already deleted symbols should have been
restored as comments.

.gitignore

@@ -25,29 +25,17 @@ make.tmpl
 
 /autom4te.cache/
 /autoscan.log
-/build/
-/config.cache
 /config.log
 /config.status
 /configure.scan
-/cscope.*
-/html/
-/reports/
+/cscope.out
 /tags
 /tmp/
 
-coverity/coverity_model.xml
-
-# gcov files:
-*.gcda
-*.gcno
 
 tools/man-generator
 tools/man-generator.c
 
-test/.lib-dir-stamp
-test/.tests-stamp
-test/lib/dmsecuretest
 test/lib/lvchange
 test/lib/lvconvert
 test/lib/lvcreate
@@ -72,7 +60,6 @@ test/lib/pvremove
 test/lib/pvresize
 test/lib/pvs
 test/lib/pvscan
-test/lib/securetest
 test/lib/vgcfgbackup
 test/lib/vgcfgrestore
 test/lib/vgchange

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 = conf daemons include lib libdaemon libdm man scripts device_mapper tools
 
 ifeq ("@UDEV_RULES@", "yes")
   SUBDIRS += udev
@@ -28,6 +28,14 @@ ifeq ("@INTL@", "yes")
   SUBDIRS += po
 endif
 
+ifeq ("@APPLIB@", "yes")
+  SUBDIRS += liblvm
+endif
+
+ifeq ("@PYTHON_BINDINGS@", "yes")
+  SUBDIRS += python
+endif
+
 ifeq ($(MAKECMDGOALS),clean)
   SUBDIRS += test
 endif
@@ -35,7 +43,7 @@ endif
 ifeq ($(MAKECMDGOALS),distclean)
   SUBDIRS = conf include man test scripts \
     libdaemon lib tools daemons libdm \
-    udev po
+    udev po liblvm python device_mapper
 tools.distclean: test.distclean
 endif
 DISTCLEAN_DIRS += lcov_reports*
@@ -43,25 +51,23 @@ DISTCLEAN_TARGETS += config.cache config.log config.status make.tmpl
 
 include make.tmpl
 
-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)
+lib: libdm libdaemon
+liblvm: lib
 daemons: lib libdaemon tools
-scripts: lib
-tools: lib libdaemon
+tools: lib libdaemon device-mapper
 po: tools daemons
 man: tools
 all_man: tools
-scripts: libdm
+scripts: liblvm libdm
 test: tools daemons
-unit-test  run-unit-test: test
+unit-test: lib
+run-unit-test: unit-test
 
 lib.device-mapper: include.device-mapper
 libdm.device-mapper: include.device-mapper
+liblvm.device-mapper: include.device-mapper
 daemons.device-mapper: libdm.device-mapper
 tools.device-mapper: libdm.device-mapper
 scripts.device-mapper: include.device-mapper
@@ -75,6 +81,10 @@ po.pofile: tools.pofile daemons.pofile
 pofile: po.pofile
 endif
 
+ifeq ("@PYTHON_BINDINGS@", "yes")
+python: liblvm
+endif
+
 ifneq ("$(CFLOW_CMD)", "")
 tools.cflow: libdm.cflow lib.cflow
 daemons.cflow: tools.cflow
@@ -89,7 +99,7 @@ endif
 DISTCLEAN_TARGETS += cscope.out
 CLEAN_DIRS += autom4te.cache
 
-check check_system check_cluster check_local check_lvmpolld check_lvmlockd_test check_lvmlockd_dlm check_lvmlockd_sanlock: test
+check check_system check_cluster check_local check_lvmetad check_lvmpolld check_lvmlockd_test check_lvmlockd_dlm check_lvmlockd_sanlock unit-test run-unit-test: test
 	$(MAKE) -C test $(@)
 
 conf.generate man.generate: tools
@@ -151,11 +161,27 @@ install_systemd_units:
 install_all_man:
 	$(MAKE) -C man install_all_man
 
+ifeq ("@PYTHON_BINDINGS@", "yes")
+install_python_bindings:
+	$(MAKE) -C liblvm/python install_python_bindings
+endif
+
 install_tmpfiles_configuration:
 	$(MAKE) -C scripts install_tmpfiles_configuration
 
+LCOV_TRACES = libdm.info lib.info liblvm.info tools.info \
+	libdaemon/client.info libdaemon/server.info \
+	test/unit.info \
+	daemons/clvmd.info \
+	daemons/dmeventd.info \
+	daemons/lvmetad.info \
+	daemons/lvmlockd.info \
+	daemons/lvmpolld.info
+
+CLEAN_TARGETS += $(LCOV_TRACES)
+
 ifneq ("$(LCOV)", "")
-.PHONY: lcov-reset lcov lcov-dated
+.PHONY: lcov-reset lcov lcov-dated $(LCOV_TRACES)
 
 ifeq ($(MAKECMDGOALS),lcov-dated)
 LCOV_REPORTS_DIR := lcov_reports-$(shell date +%Y%m%d%k%M%S)
@@ -165,22 +191,30 @@ LCOV_REPORTS_DIR := lcov_reports
 endif
 
 lcov-reset:
-	$(LCOV) --zerocounters --directory $(top_builddir)
+	$(LCOV) --zerocounters $(addprefix -d , $(basename $(LCOV_TRACES)))
+
+# maybe use subdirs processing to create tracefiles...
+$(LCOV_TRACES):
+	$(LCOV) -b $(basename $@) -d $(basename $@) \
+		--ignore-errors source -c -o - | $(SED) \
+		-e "s/\(dmeventd_lvm.[ch]\)/plugins\/lvm2\/\1/" \
+		-e "s/dmeventd_\(mirror\|snapshot\|thin\|raid\)\.c/plugins\/\1\/dmeventd_\1\.c/" \
+		>$@
 
 ifneq ("$(GENHTML)", "")
-lcov:
-	$(RM) -rf $(LCOV_REPORTS_DIR)
+lcov: $(LCOV_TRACES)
+	$(RM) -r $(LCOV_REPORTS_DIR)
 	$(MKDIR_P) $(LCOV_REPORTS_DIR)
-	$(LCOV) --capture --directory $(top_builddir) --ignore-errors source \
-		--output-file $(LCOV_REPORTS_DIR)/out.info
-	-test ! -s $(LCOV_REPORTS_DIR)/out.info || \
-		$(GENHTML) -o $(LCOV_REPORTS_DIR) --ignore-errors source \
-		$(LCOV_REPORTS_DIR)/out.info
+	for i in $(LCOV_TRACES); do \
+		test -s $$i -a $$(wc -w <$$i) -ge 100 && lc="$$lc $$i"; \
+	done; \
+	test -z "$$lc" || $(GENHTML) -p @abs_top_builddir@ \
+		-o $(LCOV_REPORTS_DIR) $$lc
 endif
 
 endif
 
-ifneq ($(shell which ctags 2>/dev/null),)
+ifneq ($(shell which ctags),)
 .PHONY: tags
 tags:
 	test -z "$(shell find $(top_srcdir) -type f -name '*.[ch]' -newer tags 2>/dev/null | head -1)" || $(RM) tags

README

@@ -1,7 +1,5 @@
 This tree contains the LVM2 and device-mapper tools and libraries.
 
-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.
 
@@ -9,6 +7,7 @@ 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:
@@ -43,9 +42,6 @@ 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 using CVS:
+The source code repository used until 7th June 2012 is accessible here:
+  http://sources.redhat.com/cgi-bin/cvsweb.cgi/LVM2/?cvsroot=lvm2.
 
-  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 @@
-2.03.11(2)-git (2020-08-09)
+2.02.186(2)-git (2019-05-13)

VERSION_DM

@@ -1 +1 @@
-1.02.175-git (2020-08-09)
+1.02.160-git (2019-05-13)

WHATS_NEW

@@ -1,199 +1,90 @@
-Version 2.03.11 - 
-==================================
-  Enhance error handling for fsadm and hanled 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.
-  Switch code base to use flexible array syntax.
-  Fix 64bit math when calculation cachevol size.
-  Preserve uint32_t for seqno handling.
-  Switch from mmap to plain read when loading regular files.
-  Update lvmvdo man page and better explain DISCARD usage.
-
-Version 2.03.10 - 09th August 2020
-==================================
-  Add writecache and integrity support to lvmdbusd.
-  Generate unique cachevol name when default required from lvcreate.
-  Converting RAID1 volume to one with same number of legs now succeeds with a
-  warning.
-  Fix conversion to raid from striped lagging type.
-  Fix conversion to 'mirrored' mirror log with larger regionsize.
-  Zero pool metadata on allocation (disable with allocation/zero_metadata=0).
-  Failure in zeroing or wiping will fail command (bypass with -Zn, -Wn).
-  Add lvcreate of new cache or writecache lv with single command.
-  Fix running out of free buffers for async writing for larger writes.
-  Add integrity with raid capability.
-  Fix support for lvconvert --repair used by foreign apps (i.e. Docker).
-
-Version 2.03.09 - 26th March 2020
-=================================
-  Fix formating of vdopool (vdo_slab_size_mb was smaller by 2 bits).
-  Fix showing of a dm kernel error when uncaching a volume with cachevol.
-
-Version 2.03.08 - 11th February 2020
-====================================
-  Prevent problematic snapshots of writecache volumes.
-  Add error handling for failing allocation in _reserve_area().
-  Fix memleak in syncing of internal cache.
-  Fix pvck dump_current_text memleak.
-  Fix lvmlockd result code on error path for _query_lock_lv().
-  Update pvck man page and help output.
-  Reject invalid writecache high/low_watermark setting.
-  Report writecache status.
-  Accept more output lines from vdo_format.
-  Prohibit reshaping of stacked raid LVs.
-  Avoid running cache input arg validation when creating vdo pool.
-  Prevent raid reshaping of stacked volumes.
-  Added VDO lvmdbusd methods for enable/disable compression & dedupe.
-  Added VDO lvmdbusd method for converting LV to VDO pool.
-
-Version 2.03.07 - 30th November 2019
-====================================
-  Subcommand in vgck for repairing headers and metadata.
-  Ensure minimum required region size on striped RaidLV creation.
-  Fix resize of thin-pool with data and metadata of different segtype.
-  Improve mirror type leg splitting.
-  Improve error path handling in daemons on shutdown.
-  Fix activation order when removing merged snapshot.
-  Experimental VDO support for lvmdbusd.
-
-Version 2.03.06 - 23rd October 2019
-===================================
-  Add _cpool suffix to cache-pool LV name when used by caching LV.
-  No longer store extra UUID for cmeta and cdata cachevol layer.
-  Enhance activation of cache devices with cachevols.
-  Add _cvol in list of protected suffixes and start use it with DM UUID.
-  Rename LV converted to cachevol to use _cvol suffix.
-  Use normal LVs for wiping of cachevols.
-  Reload cleanered cache DM only with cleaner policy.
-  Fix cmd return when zeroing of cachevol fails.
-  Extend lvs to show all VDO properties.
-  Preserve VDO write policy with vdopool.
-  Increase default vdo bio threads to 4.
-  Continue report when cache_status fails.
-  Add support for DM_DEVICE_GET_TARGET_VERSION into device_mapper.
-  Fix cmirrord usage of header files from device_mapper subdir.
-  Allow standalone activation of VDO pool just like for thin-pools.
-  Activate thin-pool layered volume as 'read-only' device.
-  Ignore crypto devices with UUID signature CRYPT-SUBDEV.
-  Enhance validation for thin and cache pool conversion and swapping.
-  Improve internal removal of cached devices.
-  Synchronize with udev when dropping snapshot.
-  Add missing device synchronization point before removing pvmove node.
-  Correctly set read_ahead for LVs when pvmove is finished.
-  Remove unsupported OPTIONS+="event_timeout" udev rule from 11-dm-lvm.rules.
-  Prevent creating VGs with PVs with different logical block sizes.
+Version 2.02.186 - 
+================================
   Fix metadata writes from corrupting with large physical block size.
-
-Version 2.03.05 - 15th June 2019
-================================
-  Fix command definition for pvchange -a.
-  Add vgck --updatemetadata command that will repair metadata problems.
-  Improve VG reading to work if one good copy of metadata is found.
-  Report/display/scan commands that read VGs will no longer write/repair.
-  Move metadata repairs from VG reading to VG writing.
-  Add config setting md_component_checks to control MD component checks.
-  Add end of device MD component checks when dev has no udev info.
-
-Version 2.03.04 - 10th June 2019
-================================
-  Remove unused_duplicate_devs from cmd causing segfault in dmeventd.
-
-Version 2.03.03 - 07th June 2019
-================================
   Report no_discard_passdown for cache LVs with lvs -o+kernel_discards.
-  Add pvck --dump option to extract metadata.
+  Prevent shared active mirror LVs with lvmlockd.
+
+Version 2.02.185 - 13th May 2019
+================================
+  Fix change of monitoring in clustered volumes.
+  Improve -lXXX%VG modifier which improves cache segment estimation.
+  Add synchronization with udev before removing cached devices.
+  Fix missing growth of _pmspare volume when extending _tmeta volume.
+  Automatically grow thin metadata, when thin data gets too big.
+  Add support for vgsplit with cached devices.
   Fix signal delivery checking race in libdaemon (lvmetad).
   Add missing Before=shutdown.target to LVM2 services to fix shutdown ordering.
-  Skip autoactivation for a PV when PV size does not match device size.
-  Remove first-pvscan-initialization which should no longer be needed.
-  Add remote refresh through lvmlockd/dlm for shared LVs after lvextend.
-  Ignore foreign and shared PVs for pvscan online files.
-  Add config setting to control fields in debug file and verbose output.
-  Add command[pid] and timestamp to debug file and verbose output.
-  Fix missing growth of _pmsmare volume when extending _tmeta volume.
-  Automatically grow thin metadata, when thin data gets too big.
-  Add synchronization with udev before removing cached devices.
-  Add support for caching VDO LVs and VDOPOOL LVs.
-  Add support for vgsplit with cached devices.
-  Query mpath device only once per command for its state.
-  Use device INFO instead of STATUS when checking for mpath device uuid.
-  Change default io_memory_size from 4 to 8 MiB.
-  Add config setting io_memory_size to set bcache size.
-  Fix pvscan autoactivation for concurrent pvscans.
+
+Version 2.02.184 - 22nd March 2019
+==================================
+  Fix (de)activation of RaidLVs with visible SubLVs
   Change scan_lvs default to 0 so LVs are not scanned for PVs.
-  Thin-pool selects power-of-2 chunk size by default.
-  Cache selects power-of-2 chunk size by default.
-  Support reszing for VDOPoolLV and VDOLV.
-  Improve -lXXX%VG modifier which improves cache segment estimation.
-  Ensure migration_threshold for cache is at least 8 chunks.
-  Restore missing man info lvcreate --zero for thin-pools.
-  Drop misleadning comment for metadata minimum_io_size for VDO segment.
-  Add device hints to reduce scanning.
-  Introduce LVM_SUPPRESS_SYSLOG to suppress syslog usage by generator.
-  Fix generator quering lvmconfig unpresent config option.
-  Fix memleak on bcache error path code.
-  Fix missing unlock on lvm2 dmeventd plugin error path initialization.
-  Improve Makefile dependency tracking.
-  Move VDO support towards V2 target (6.2) support.
-
-Version 2.03.02 - 18th December 2018
-====================================
+  Add scan_lvs config setting to control if lvm scans LVs for PVs.
   Fix missing proper initialization of pv_list struct when adding pv.
-  Fix (de)activation of RaidLVs with visible SubLVs.
-  Prohibit mirrored 'mirror' log via lvcreate and lvconvert.
+
+Version 2.02.183 - 07th December 2018
+=====================================
+  Avoid disabling lvmetad when repair does nothing.
+  Fix component detection for md version 0.90.
   Use sync io if async io_setup fails, or use_aio=0 is set in config.
-  Fix more issues reported by coverity scan.
+  Avoid opening devices to get block size by using existing open fd.
 
-Version 2.03.01 - 31st October 2018
-===================================
-
-Version 2.03.00 - 10th October 2018
-===================================
-  Add hot fix to avoiding locking collision when monitoring thin-pools.
-  Allow raid4 -> linear conversion request.
+Version 2.02.182 - 30th October 2018
+====================================
+  Fix possible write race between last metadata block and the first extent.
+  Fix filtering of md 1.0 devices so they are not seen as duplicate PVs.
   Fix lvconvert striped/raid0/raid0_meta -> raid6 regression.
-  Add 'lvm2-activation-generator:' prefix for kmsg messages logged by generator.
   Add After=rbdmap.service to {lvm2-activation-net,blk-availability}.service.
+  Fix pvs with lvmetad to avoid too many open files from filter reads.
+  Fix pvscan --cache to avoid too many open files from filter reads.
   Reduce max concurrent aios to avoid EMFILE with many devices.
   Fix lvconvert conversion attempts to linear.
   Fix lvconvert raid0/raid0_meta -> striped regression.
   Fix lvconvert --splitmirror for mirror type (2.02.178).
   Do not pair cache policy and cache metadata format.
-  lvconvert: reject conversions on raid1 LVs with split tracked SubLVs
-  lvconvert: reject conversions on raid1 split tracked SubLVs
-  Add basic creation support for VDO target.
+  Fix mirrors honoring read_only_volume_list.
+
+Version 2.02.181 - 01 August 2018
+=================================
+  Reject conversions on raid1 LVs with split tracked SubLVs.
+  Reject conversions on raid1 split tracked SubLVs.
+  Fix dmstats list failing when no regions exist.
+  Reject conversions of LVs under snapshot.
+  Limit suggested options on incorrect option for lvconvert subcommand.
+
+Version 2.02.180 - 19th July 2018
+=================================
   Never send any discard ioctl with test mode.
   Fix thin-pool alloc which needs same PV for data and metadata.
   Extend list of non-memlocked areas with newly linked libs.
   Enhance vgcfgrestore to check for active LVs in restored VG.
-  Configure supports --disable-silent-rules for verbose builds.
-  Fix unmonitoring of merging snapshots.
-  Cache can uses metadata format 2 with cleaner policy.
-  Fix check if resized PV can also fit metadata area.
-  Avoid showing internal error in lvs output or pvmoved LVs.
-  Remove clvmd
-  Remove lvmlib (api)
-  Remove lvmetad
   lvconvert: provide possible layouts between linear and striped/raid
+  Fix unmonitoring of merging snapshots.
+  Add missing -l description in fsadm man page.
+  Cache can uses metadata format 2 with cleaner policy.
+  Avoid showing internal error in lvs output or pvmoved LVs.
+  Fix check if resized PV can also fit metadata area.
+  Reopen devices RDWR only before writing to avoid udev issues.
+  Change pvresize output confusing when no resize took place.
+  Fix lvmetad hanging on shutdown.
+  Fix mem leak in clvmd and more coverity issues.
+
+Version 2.02.179 - 18th June 2018
+=================================
+  Allow forced vgchange to lock type none on clustered VG.
+  Add the report field "shared".
+  Enable automatic metadata consistency repair on a shared VG.
+  Fix pvremove force on a PV with a shared VG.
+  Fixed vgimportclone of a PV with a shared VG.
+  Enable previously disallowed thin/cache commands in shared VGs.
+  Enable metadata-related changes on LVs active with shared lock.
+  Do not continue trying to use a device that cannot be opened.
+  Fix problems opening a device that fails and returns.
   Use versionsort to fix archive file expiry beyond 100000 files.
 
+Version 2.02.178 - 13th June 2018
+=================================
+
 Version 2.02.178-rc1 - 24th May 2018
 ====================================
   Add libaio dependency for build.

WHATS_NEW_DM

@@ -1,52 +1,23 @@
-Version 1.02.175 - 
-===================================
-
-Version 1.02.173 - 09th August 2020
-===================================
-  Add support for VDO in blkdeactivate script.
-
-Version 1.02.171 - 26th March 2020
-==================================
-  Try to remove all created devices on dm preload tree error path.
-  Fix dm_list interators with gcc 10 optimization (-ftree-pta).
-  Dmeventd handles timer without looping on short intervals.
-
-Version 1.02.169 - 11th February 2020
-=====================================
-  Enhance error messages for device creation.
-
-Version 1.02.167 - 30th November 2019
-=====================================
-
-Version 1.02.165 - 23rd October 2019
-====================================
-  Add support for DM_DEVICE_GET_TARGET_VERSION.
-  Add debug of dmsetup udevcomplete with hexa print DM_COOKIE_COMPLETED.
+Version 1.02.160 - 
+================================
   Fix versioning of dm_stats_create_region and dm_stats_create_region.
-
-Version 1.02.163 - 15th June 2019
-=================================
-
-Version 1.02.161 - 10th June 2019
-=================================
-
-Version 1.02.159 - 07th June 2019
-=================================
   Parsing of cache status understand no_discard_passdown.
-  Ensure migration_threshold for cache is at least 8 chunks.
 
-Version 1.02.155 - 18th December 2018
-=====================================
-  Include correct internal header inside libdm list.c.
+Version 1.02.158 - 13th May 2019
+================================
+
+Version 1.02.156 - 22nd March 2019
+==================================
+  Ensure migration_threshold for cache is at least 8 chunks.
   Enhance ioctl flattening and add parameters only when needed.
   Add DM_DEVICE_ARM_POLL for API completness matching kernel.
+
+Version 1.02.154 - 07th December 2018
+=====================================
   Do not add parameters for RESUME with DM_DEVICE_CREATE dm task.
   Fix dmstats report printing no output.
 
-Version 1.02.153 - 31st October 2018
-====================================
-
-Version 1.02.151 - 10th October 2018
+Version 1.02.152 - 30th October 2018
 ====================================
   Add hot fix to avoiding locking collision when monitoring thin-pools.
 

aclocal.m4

@@ -1,6 +1,6 @@
-# generated automatically by aclocal 1.16.2 -*- Autoconf -*-
+# generated automatically by aclocal 1.15 -*- Autoconf -*-
 
-# Copyright (C) 1996-2020 Free Software Foundation, Inc.
+# Copyright (C) 1996-2014 Free Software Foundation, Inc.
 
 # This file is free software; the Free Software Foundation
 # gives unlimited permission to copy and/or distribute it,
@@ -13,7 +13,7 @@
 
 m4_ifndef([AC_CONFIG_MACRO_DIRS], [m4_defun([_AM_CONFIG_MACRO_DIRS], [])m4_defun([AC_CONFIG_MACRO_DIRS], [_AM_CONFIG_MACRO_DIRS($@)])])
 # ===========================================================================
-#     https://www.gnu.org/software/autoconf-archive/ax_python_module.html
+#     http://www.gnu.org/software/autoconf-archive/ax_python_module.html
 # ===========================================================================
 #
 # SYNOPSIS
@@ -37,7 +37,7 @@ m4_ifndef([AC_CONFIG_MACRO_DIRS], [m4_defun([_AM_CONFIG_MACRO_DIRS], [])m4_defun
 #   and this notice are preserved. This file is offered as-is, without any
 #   warranty.
 
-#serial 9
+#serial 8
 
 AU_ALIAS([AC_PYTHON_MODULE], [AX_PYTHON_MODULE])
 AC_DEFUN([AX_PYTHON_MODULE],[
@@ -69,9 +69,9 @@ AC_DEFUN([AX_PYTHON_MODULE],[
     fi
 ])
 
-# pkg.m4 - Macros to locate and utilise pkg-config.   -*- Autoconf -*-
-# serial 11 (pkg-config-0.29.1)
-
+dnl pkg.m4 - Macros to locate and utilise pkg-config.   -*- Autoconf -*-
+dnl serial 11 (pkg-config-0.29)
+dnl
 dnl Copyright © 2004 Scott James Remnant <scott@netsplit.com>.
 dnl Copyright © 2012-2015 Dan Nicholson <dbn.lists@gmail.com>
 dnl
@@ -112,7 +112,7 @@ dnl
 dnl See the "Since" comment for each macro you use to see what version
 dnl of the macros you require.
 m4_defun([PKG_PREREQ],
-[m4_define([PKG_MACROS_VERSION], [0.29.1])
+[m4_define([PKG_MACROS_VERSION], [0.29])
 m4_if(m4_version_compare(PKG_MACROS_VERSION, [$1]), -1,
     [m4_fatal([pkg.m4 version $1 or higher is required but ]PKG_MACROS_VERSION[ found])])
 ])dnl PKG_PREREQ
@@ -345,75 +345,7 @@ AS_VAR_COPY([$1], [pkg_cv_][$1])
 AS_VAR_IF([$1], [""], [$5], [$4])dnl
 ])dnl PKG_CHECK_VAR
 
-dnl PKG_WITH_MODULES(VARIABLE-PREFIX, MODULES,
-dnl   [ACTION-IF-FOUND],[ACTION-IF-NOT-FOUND],
-dnl   [DESCRIPTION], [DEFAULT])
-dnl ------------------------------------------
-dnl
-dnl Prepare a "--with-" configure option using the lowercase
-dnl [VARIABLE-PREFIX] name, merging the behaviour of AC_ARG_WITH and
-dnl PKG_CHECK_MODULES in a single macro.
-AC_DEFUN([PKG_WITH_MODULES],
-[
-m4_pushdef([with_arg], m4_tolower([$1]))
-
-m4_pushdef([description],
-           [m4_default([$5], [build with ]with_arg[ support])])
-
-m4_pushdef([def_arg], [m4_default([$6], [auto])])
-m4_pushdef([def_action_if_found], [AS_TR_SH([with_]with_arg)=yes])
-m4_pushdef([def_action_if_not_found], [AS_TR_SH([with_]with_arg)=no])
-
-m4_case(def_arg,
-            [yes],[m4_pushdef([with_without], [--without-]with_arg)],
-            [m4_pushdef([with_without],[--with-]with_arg)])
-
-AC_ARG_WITH(with_arg,
-     AS_HELP_STRING(with_without, description[ @<:@default=]def_arg[@:>@]),,
-    [AS_TR_SH([with_]with_arg)=def_arg])
-
-AS_CASE([$AS_TR_SH([with_]with_arg)],
-            [yes],[PKG_CHECK_MODULES([$1],[$2],$3,$4)],
-            [auto],[PKG_CHECK_MODULES([$1],[$2],
-                                        [m4_n([def_action_if_found]) $3],
-                                        [m4_n([def_action_if_not_found]) $4])])
-
-m4_popdef([with_arg])
-m4_popdef([description])
-m4_popdef([def_arg])
-
-])dnl PKG_WITH_MODULES
-
-dnl PKG_HAVE_WITH_MODULES(VARIABLE-PREFIX, MODULES,
-dnl   [DESCRIPTION], [DEFAULT])
-dnl -----------------------------------------------
-dnl
-dnl Convenience macro to trigger AM_CONDITIONAL after PKG_WITH_MODULES
-dnl check._[VARIABLE-PREFIX] is exported as make variable.
-AC_DEFUN([PKG_HAVE_WITH_MODULES],
-[
-PKG_WITH_MODULES([$1],[$2],,,[$3],[$4])
-
-AM_CONDITIONAL([HAVE_][$1],
-               [test "$AS_TR_SH([with_]m4_tolower([$1]))" = "yes"])
-])dnl PKG_HAVE_WITH_MODULES
-
-dnl PKG_HAVE_DEFINE_WITH_MODULES(VARIABLE-PREFIX, MODULES,
-dnl   [DESCRIPTION], [DEFAULT])
-dnl ------------------------------------------------------
-dnl
-dnl Convenience macro to run AM_CONDITIONAL and AC_DEFINE after
-dnl PKG_WITH_MODULES check. HAVE_[VARIABLE-PREFIX] is exported as make
-dnl and preprocessor variable.
-AC_DEFUN([PKG_HAVE_DEFINE_WITH_MODULES],
-[
-PKG_HAVE_WITH_MODULES([$1],[$2],[$3],[$4])
-
-AS_IF([test "$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) 1999-2020 Free Software Foundation, Inc.
+# Copyright (C) 1999-2014 Free Software Foundation, Inc.
 #
 # This file is free software; the Free Software Foundation
 # gives unlimited permission to copy and/or distribute it,
@@ -447,11 +379,8 @@ 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).
   m4_define_default([_AM_PYTHON_INTERPRETER_LIST],
-[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])
+[python python2 python3 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])
 
   AC_ARG_VAR([PYTHON], [the Python interpreter])
 
@@ -651,7 +580,7 @@ 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) 2001-2020 Free Software Foundation, Inc.
+# Copyright (C) 2001-2014 Free Software Foundation, Inc.
 #
 # This file is free software; the Free Software Foundation
 # gives unlimited permission to copy and/or distribute it,

base/Makefile

@@ -1,40 +0,0 @@
-# Copyright (C) 2018 Red Hat, Inc. All rights reserved.
-#
-# This file is part of the device-mapper userspace tools.
-#
-# 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
-
-# Uncomment this to build the simple radix tree.  You'll need to make clean too.
-# Comment to build the advanced radix tree.
-#base/data-struct/radix-tree.o: CFLAGS += -DSIMPLE_RADIX_TREE
-
-# NOTE: this Makefile only works as 'include' for toplevel Makefile
-#       which defined all top_* variables
-
-BASE_SOURCE=\
-	base/data-struct/hash.c \
-	base/data-struct/list.c \
-	base/data-struct/radix-tree.c
-
-BASE_TARGET = base/libbase.a
-BASE_DEPENDS = $(BASE_SOURCE:%.c=%.d)
-BASE_OBJECTS = $(BASE_SOURCE:%.c=%.o)
-CLEAN_TARGETS += $(BASE_DEPENDS) $(BASE_OBJECTS) \
-	$(BASE_SOURCE:%.c=%.gcda) \
-	$(BASE_SOURCE:%.c=%.gcno) \
-	$(BASE_TARGET)
-
-$(BASE_TARGET): $(BASE_OBJECTS)
-	@echo "    [AR] $@"
-	$(Q) $(RM) $@
-	$(Q) $(AR) rsv $@ $(BASE_OBJECTS) > /dev/null
-
-ifeq ("$(DEPENDS)","yes")
--include $(BASE_DEPENDS)
-endif

base/data-struct/hash.c

@@ -1,395 +0,0 @@
-/*
- * Copyright (C) 2001-2004 Sistina Software, Inc. All rights reserved.
- * Copyright (C) 2004-2011 Red Hat, Inc. All rights reserved.
- *
- * This file is part of the device-mapper userspace tools.
- *
- * 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 "device_mapper/misc/dmlib.h"
-#include "base/memory/zalloc.h"
-#include "hash.h"
-
-struct dm_hash_node {
-	struct dm_hash_node *next;
-	void *data;
-	unsigned data_len;
-	unsigned keylen;
-	char key[];
-};
-
-struct dm_hash_table {
-	unsigned num_nodes;
-	unsigned num_slots;
-	struct dm_hash_node **slots;
-};
-
-/* 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,
-	12, 181, 103, 70, 22, 58, 75, 78, 183, 167, 238, 157, 124, 147, 172,
-	144,
-	176, 161, 141, 86, 60, 66, 128, 83, 156, 241, 79, 46, 168, 198, 41, 254,
-	178, 85, 253, 237, 250, 154, 133, 88, 35, 206, 95, 116, 252, 192, 54,
-	221,
-	102, 218, 255, 240, 82, 106, 158, 201, 61, 3, 89, 9, 42, 155, 159, 93,
-	166, 80, 50, 34, 175, 195, 100, 99, 26, 150, 16, 145, 4, 33, 8, 189,
-	121, 64, 77, 72, 208, 245, 130, 122, 143, 55, 105, 134, 29, 164, 185,
-	194,
-	193, 239, 101, 242, 5, 171, 126, 11, 74, 59, 137, 228, 108, 191, 232,
-	139,
-	6, 24, 81, 20, 127, 17, 91, 92, 251, 151, 225, 207, 21, 98, 113, 112,
-	84, 226, 18, 214, 199, 187, 13, 32, 94, 220, 224, 212, 247, 204, 196,
-	43,
-	249, 236, 45, 244, 111, 182, 153, 136, 129, 90, 217, 202, 19, 165, 231,
-	71,
-	230, 142, 96, 227, 62, 179, 246, 114, 162, 53, 160, 215, 205, 180, 47,
-	109,
-	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 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;
-}
-
-static unsigned long _hash(const void *key, unsigned len)
-{
-	const unsigned char *str = key;
-	unsigned long h = 0, g;
-	unsigned i;
-
-	for (i = 0; i < len; i++) {
-		h <<= 4;
-		h += _nums[*str++];
-		g = h & ((unsigned long) 0xf << 16u);
-		if (g) {
-			h ^= g >> 16u;
-			h ^= g >> 5u;
-		}
-	}
-
-	return h;
-}
-
-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;
-
-	/* round size hint up to a power of two */
-	while (new_size < size_hint)
-		new_size = new_size << 1;
-
-	hc->num_slots = new_size;
-	len = sizeof(*(hc->slots)) * new_size;
-	if (!(hc->slots = zalloc(len)))
-		goto_bad;
-
-	return hc;
-
-      bad:
-	free(hc->slots);
-	free(hc);
-	return 0;
-}
-
-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++)
-		for (c = t->slots[i]; c; c = n) {
-			n = c->next;
-			free(c);
-		}
-}
-
-void dm_hash_destroy(struct dm_hash_table *t)
-{
-	_free_nodes(t);
-	free(t->slots);
-	free(t);
-}
-
-static struct dm_hash_node **_find(struct dm_hash_table *t, const void *key,
-				   uint32_t len)
-{
-	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;
-	}
-
-	return c;
-}
-
-void *dm_hash_lookup_binary(struct dm_hash_table *t, const void *key,
-			    uint32_t len)
-{
-	struct dm_hash_node **c = _find(t, key, len);
-
-	return *c ? (*c)->data : 0;
-}
-
-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);
-
-	if (*c)
-		(*c)->data = data;
-	else {
-		struct dm_hash_node *n = _create_node(key, len);
-
-		if (!n)
-			return 0;
-
-		n->data = data;
-		n->next = 0;
-		*c = n;
-		t->num_nodes++;
-	}
-
-	return 1;
-}
-
-void dm_hash_remove_binary(struct dm_hash_table *t, const void *key,
-			uint32_t len)
-{
-	struct dm_hash_node **c = _find(t, key, len);
-
-	if (*c) {
-		struct dm_hash_node *old = *c;
-		*c = (*c)->next;
-		free(old);
-		t->num_nodes--;
-	}
-}
-
-void *dm_hash_lookup(struct dm_hash_table *t, const char *key)
-{
-	return dm_hash_lookup_binary(t, key, strlen(key) + 1);
-}
-
-int dm_hash_insert(struct dm_hash_table *t, const char *key, void *data)
-{
-	return dm_hash_insert_binary(t, key, strlen(key) + 1, data);
-}
-
-void dm_hash_remove(struct dm_hash_table *t, const char *key)
-{
-	dm_hash_remove_binary(t, key, strlen(key) + 1);
-}
-
-static struct dm_hash_node **_find_str_with_val(struct dm_hash_table *t,
-					        const void *key, const void *val,
-					        uint32_t len, uint32_t val_len)
-{
-	struct dm_hash_node **c;
-	unsigned h;
-       
-	h = _hash(key, len) & (t->num_slots - 1);
-
-	for (c = &t->slots[h]; *c; c = &((*c)->next)) {
-		if ((*c)->keylen != len)
-			continue;
-
-		if (!memcmp(key, (*c)->key, len) && (*c)->data) {
-			if (((*c)->data_len == val_len) &&
-			    !memcmp(val, (*c)->data, val_len))
-				return c;
-		}
-	}
-
-	return NULL;
-}
-
-int dm_hash_insert_allow_multiple(struct dm_hash_table *t, const char *key,
-				  const void *val, uint32_t val_len)
-{
-	struct dm_hash_node *n;
-	struct dm_hash_node *first;
-	int len = strlen(key) + 1;
-	unsigned h;
-
-	n = _create_node(key, len);
-	if (!n)
-		return 0;
-
-	n->data = (void *)val;
-	n->data_len = val_len;
-
-	h = _hash(key, len) & (t->num_slots - 1);
-
-	first = t->slots[h];
-
-	if (first)
-		n->next = first;
-	else
-		n->next = 0;
-	t->slots[h] = n;
-
-	t->num_nodes++;
-	return 1;
-}
-
-/*
- * Look through multiple entries with the same key for one that has a
- * matching val and return that.  If none have maching val, return NULL.
- */
-void *dm_hash_lookup_with_val(struct dm_hash_table *t, const char *key,
-			      const void *val, uint32_t val_len)
-{
-	struct dm_hash_node **c;
-
-	c = _find_str_with_val(t, key, val, strlen(key) + 1, val_len);
-
-	return (c && *c) ? (*c)->data : 0;
-}
-
-/*
- * Look through multiple entries with the same key for one that has a
- * matching val and remove that.
- */
-void dm_hash_remove_with_val(struct dm_hash_table *t, const char *key,
-			     const void *val, uint32_t val_len)
-{
-	struct dm_hash_node **c;
-
-	c = _find_str_with_val(t, key, val, strlen(key) + 1, val_len);
-
-	if (c && *c) {
-		struct dm_hash_node *old = *c;
-		*c = (*c)->next;
-		free(old);
-		t->num_nodes--;
-	}
-}
-
-/*
- * Look up the value for a key and count how many
- * entries have the same key.
- *
- * If no entries have key, return NULL and set count to 0.
- *
- * If one entry has the key, the function returns the val,
- * and sets count to 1.
- *
- * If N entries have the key, the function returns the val
- * from the first entry, and sets count to N.
- */
-void *dm_hash_lookup_with_count(struct dm_hash_table *t, const char *key, int *count)
-{
-	struct dm_hash_node **c;
-	struct dm_hash_node **c1 = NULL;
-	uint32_t len = strlen(key) + 1;
-	unsigned h;
-
-	*count = 0;
-
-	h = _hash(key, len) & (t->num_slots - 1);
-
-	for (c = &t->slots[h]; *c; c = &((*c)->next)) {
-		if ((*c)->keylen != len)
-			continue;
-
-		if (!memcmp(key, (*c)->key, len)) {
-			(*count)++;
-			if (!c1)
-				c1 = c;
-		}
-	}
-
-	if (!c1)
-		return NULL;
-	else
-		return *c1 ? (*c1)->data : 0;
-}
-
-unsigned dm_hash_get_num_entries(struct dm_hash_table *t)
-{
-	return t->num_nodes;
-}
-
-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 (c = t->slots[i]; c; c = n) {
-			n = c->next;
-			f(c->data);
-		}
-}
-
-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;
-}
-
-char *dm_hash_get_key(struct dm_hash_table *t __attribute__((unused)),
-		      struct dm_hash_node *n)
-{
-	return n->key;
-}
-
-void *dm_hash_get_data(struct dm_hash_table *t __attribute__((unused)),
-		       struct dm_hash_node *n)
-{
-	return n->data;
-}
-
-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++)
-		c = t->slots[i];
-
-	return c;
-}
-
-struct dm_hash_node *dm_hash_get_first(struct dm_hash_table *t)
-{
-	return _next_slot(t, 0);
-}
-
-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);
-}

base/data-struct/hash.h

@@ -1,94 +0,0 @@
-#ifndef BASE_DATA_STRUCT_HASH_H
-#define BASE_DATA_STRUCT_HASH_H
-
-#include <stdint.h>
-
-//----------------------------------------------------------------
-
-struct dm_hash_table;
-struct dm_hash_node;
-
-typedef void (*dm_hash_iterate_fn) (void *data);
-
-struct dm_hash_table *dm_hash_create(unsigned size_hint)
-	__attribute__((__warn_unused_result__));
-void dm_hash_destroy(struct dm_hash_table *t);
-void dm_hash_wipe(struct dm_hash_table *t);
-
-void *dm_hash_lookup(struct dm_hash_table *t, const char *key);
-int dm_hash_insert(struct dm_hash_table *t, const char *key, void *data);
-void dm_hash_remove(struct dm_hash_table *t, const char *key);
-
-void *dm_hash_lookup_binary(struct dm_hash_table *t, const void *key, uint32_t len);
-int dm_hash_insert_binary(struct dm_hash_table *t, const void *key, uint32_t len,
-			  void *data);
-void dm_hash_remove_binary(struct dm_hash_table *t, const void *key, uint32_t len);
-
-unsigned dm_hash_get_num_entries(struct dm_hash_table *t);
-void dm_hash_iter(struct dm_hash_table *t, dm_hash_iterate_fn f);
-
-char *dm_hash_get_key(struct dm_hash_table *t, struct dm_hash_node *n);
-void *dm_hash_get_data(struct dm_hash_table *t, struct dm_hash_node *n);
-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);
-
-/*
- * dm_hash_insert() replaces the value of an existing
- * entry with a matching key if one exists.  Otherwise
- * it adds a new entry.
- *
- * dm_hash_insert_with_val() inserts a new entry if
- * another entry with the same key already exists.
- * val_len is the size of the data being inserted.
- *
- * If two entries with the same key exist,
- * (added using dm_hash_insert_allow_multiple), then:
- * . dm_hash_lookup() returns the first one it finds, and
- *   dm_hash_lookup_with_val() returns the one with a matching
- *   val_len/val.
- * . dm_hash_remove() removes the first one it finds, and
- *   dm_hash_remove_with_val() removes the one with a matching
- *   val_len/val.
- *
- * If a single entry with a given key exists, and it has
- * zero val_len, then:
- * . dm_hash_lookup() returns it
- * . dm_hash_lookup_with_val(val_len=0) returns it
- * . dm_hash_remove() removes it
- * . dm_hash_remove_with_val(val_len=0) removes it
- *
- * dm_hash_lookup_with_count() is a single call that will
- * both lookup a key's value and check if there is more
- * than one entry with the given key.
- *
- * (It is not meant to retrieve all the entries with the
- * given key.  In the common case where a single entry exists
- * for the key, it is useful to have a single call that will
- * both look up the value and indicate if multiple values
- * exist for the key.)
- *
- * dm_hash_lookup_with_count:
- * . If no entries exist, the function returns NULL, and
- *   the count is set to 0.
- * . If only one entry exists, the value of that entry is
- *   returned and count is set to 1.
- * . If N entries exists, the value of the first entry is
- *   returned and count is set to N.
- */
-
-void *dm_hash_lookup_with_val(struct dm_hash_table *t, const char *key,
-                              const void *val, uint32_t val_len);
-void dm_hash_remove_with_val(struct dm_hash_table *t, const char *key,
-                             const void *val, uint32_t val_len);
-int dm_hash_insert_allow_multiple(struct dm_hash_table *t, const char *key,
-                                  const void *val, uint32_t val_len);
-void *dm_hash_lookup_with_count(struct dm_hash_table *t, const char *key, int *count);
-
-
-#define dm_hash_iterate(v, h) \
-	for (v = dm_hash_get_first((h)); v; \
-	     v = dm_hash_get_next((h), v))
-
-//----------------------------------------------------------------
-
-#endif

base/data-struct/list.c

@@ -1,170 +0,0 @@
-/*
- * Copyright (C) 2001-2004 Sistina Software, Inc. All rights reserved.
- * Copyright (C) 2004-2010 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 "list.h"
-
-#include <assert.h>
-#include <stdlib.h>
-
-/*
- * Initialise a list before use.
- * The list head's next and previous pointers point back to itself.
- */
-void dm_list_init(struct dm_list *head)
-{
-	head->n = head->p = head;
-}
-
-/*
- * Insert an element before 'head'.
- * If 'head' is the list head, this adds an element to the end of the list.
- */
-void dm_list_add(struct dm_list *head, struct dm_list *elem)
-{
-	assert(head->n);
-
-	elem->n = head;
-	elem->p = head->p;
-
-	head->p->n = elem;
-	head->p = elem;
-}
-
-/*
- * Insert an element after 'head'.
- * If 'head' is the list head, this adds an element to the front of the list.
- */
-void dm_list_add_h(struct dm_list *head, struct dm_list *elem)
-{
-	assert(head->n);
-
-	elem->n = head->n;
-	elem->p = head;
-
-	head->n->p = elem;
-	head->n = elem;
-}
-
-/*
- * Delete an element from its list.
- * Note that this doesn't change the element itself - it may still be safe
- * to follow its pointers.
- */
-void dm_list_del(struct dm_list *elem)
-{
-	elem->n->p = elem->p;
-	elem->p->n = elem->n;
-}
-
-/*
- * Remove an element from existing list and insert before 'head'.
- */
-void dm_list_move(struct dm_list *head, struct dm_list *elem)
-{
-        dm_list_del(elem);
-        dm_list_add(head, elem);
-}
-
-/*
- * Is the list empty?
- */
-int dm_list_empty(const struct dm_list *head)
-{
-	return head->n == head;
-}
-
-/*
- * Is this the first element of the list?
- */
-int dm_list_start(const struct dm_list *head, const struct dm_list *elem)
-{
-	return elem->p == head;
-}
-
-/*
- * Is this the last element of the list?
- */
-int dm_list_end(const struct dm_list *head, const struct dm_list *elem)
-{
-	return elem->n == head;
-}
-
-/*
- * Return first element of the list or NULL if empty
- */
-struct dm_list *dm_list_first(const struct dm_list *head)
-{
-	return (dm_list_empty(head) ? NULL : head->n);
-}
-
-/*
- * Return last element of the list or NULL if empty
- */
-struct dm_list *dm_list_last(const struct dm_list *head)
-{
-	return (dm_list_empty(head) ? NULL : head->p);
-}
-
-/*
- * Return the previous element of the list, or NULL if we've reached the start.
- */
-struct dm_list *dm_list_prev(const struct dm_list *head, const struct dm_list *elem)
-{
-	return (dm_list_start(head, elem) ? NULL : elem->p);
-}
-
-/*
- * Return the next element of the list, or NULL if we've reached the end.
- */
-struct dm_list *dm_list_next(const struct dm_list *head, const struct dm_list *elem)
-{
-	return (dm_list_end(head, elem) ? NULL : elem->n);
-}
-
-/*
- * Return the number of elements in a list by walking it.
- */
-unsigned int dm_list_size(const struct dm_list *head)
-{
-	unsigned int s = 0;
-	const struct dm_list *v;
-
-	dm_list_iterate(v, head)
-	    s++;
-
-	return s;
-}
-
-/*
- * Join two lists together.
- * This moves all the elements of the list 'head1' to the end of the list
- * 'head', leaving 'head1' empty.
- */
-void dm_list_splice(struct dm_list *head, struct dm_list *head1)
-{
-	assert(head->n);
-	assert(head1->n);
-
-	if (dm_list_empty(head1))
-	    return;
-
-	head1->p->n = head;
-	head1->n->p = head->p;
-
-	head->p->n = head1->n;
-	head->p = head1->p;
-
-	dm_list_init(head1);
-}

base/data-struct/list.h

@@ -1,211 +0,0 @@
-#ifndef BASE_DATA_STRUCT_LIST_H
-#define BASE_DATA_STRUCT_LIST_H
-
-#include "base/memory/container_of.h"
-
-//----------------------------------------------------------------
-
-/*
- * A list consists of a list head plus elements.
- * Each element has 'next' and 'previous' pointers.
- * The list head's pointers point to the first and the last element.
- */
-
-struct dm_list {
-	struct dm_list *n, *p;
-};
-
-/*
- * String list.
- */
-struct dm_str_list {
-	struct dm_list list;
-	const char *str;
-};
-
-/*
- * Initialise a list before use.
- * The list head's next and previous pointers point back to itself.
- */
-#define DM_LIST_HEAD_INIT(name)	 { &(name), &(name) }
-#define DM_LIST_INIT(name)	struct dm_list name = DM_LIST_HEAD_INIT(name)
-void dm_list_init(struct dm_list *head);
-
-/*
- * Insert an element before 'head'.
- * If 'head' is the list head, this adds an element to the end of the list.
- */
-void dm_list_add(struct dm_list *head, struct dm_list *elem);
-
-/*
- * Insert an element after 'head'.
- * If 'head' is the list head, this adds an element to the front of the list.
- */
-void dm_list_add_h(struct dm_list *head, struct dm_list *elem);
-
-/*
- * Delete an element from its list.
- * Note that this doesn't change the element itself - it may still be safe
- * to follow its pointers.
- */
-void dm_list_del(struct dm_list *elem);
-
-/*
- * Remove an element from existing list and insert before 'head'.
- */
-void dm_list_move(struct dm_list *head, struct dm_list *elem);
-
-/*
- * Join 'head1' to the end of 'head'.
- */
-void dm_list_splice(struct dm_list *head, struct dm_list *head1);
-
-/*
- * Is the list empty?
- */
-int dm_list_empty(const struct dm_list *head);
-
-/*
- * Is this the first element of the list?
- */
-int dm_list_start(const struct dm_list *head, const struct dm_list *elem);
-
-/*
- * Is this the last element of the list?
- */
-int dm_list_end(const struct dm_list *head, const struct dm_list *elem);
-
-/*
- * Return first element of the list or NULL if empty
- */
-struct dm_list *dm_list_first(const struct dm_list *head);
-
-/*
- * Return last element of the list or NULL if empty
- */
-struct dm_list *dm_list_last(const struct dm_list *head);
-
-/*
- * Return the previous element of the list, or NULL if we've reached the start.
- */
-struct dm_list *dm_list_prev(const struct dm_list *head, const struct dm_list *elem);
-
-/*
- * Return the next element of the list, or NULL if we've reached the end.
- */
-struct dm_list *dm_list_next(const struct dm_list *head, const struct dm_list *elem);
-
-/*
- * Given the address v of an instance of 'struct dm_list' called 'head'
- * contained in a structure of type t, return the containing structure.
- */
-#define dm_list_struct_base(v, t, head) \
-    container_of(v, t, head)
-
-/*
- * Given the address v of an instance of 'struct dm_list list' contained in
- * a structure of type t, return the containing structure.
- */
-#define dm_list_item(v, t) dm_list_struct_base((v), t, list)
-
-/*
- * Given the address v of one known element e in a known structure of type t,
- * return another element f.
- */
-#define dm_struct_field(v, t, e, f) \
-    (((t *)((uintptr_t)(v) - offsetof(t, e)))->f)
-
-/*
- * Given the address v of a known element e in a known structure of type t,
- * return the list head 'list'
- */
-#define dm_list_head(v, t, e) dm_struct_field(v, t, e, list)
-
-/*
- * Set v to each element of a list in turn.
- */
-#define dm_list_iterate(v, head) \
-	for (v = (head)->n; v != head; v = v->n)
-
-/*
- * Set v to each element in a list in turn, starting from the element
- * in front of 'start'.
- * You can use this to 'unwind' a list_iterate and back out actions on
- * already-processed elements.
- * If 'start' is 'head' it walks the list backwards.
- */
-#define dm_list_uniterate(v, head, start) \
-	for (v = (start)->p; v != head; v = v->p)
-
-/*
- * A safe way to walk a list and delete and free some elements along
- * the way.
- * t must be defined as a temporary variable of the same type as v.
- */
-#define dm_list_iterate_safe(v, t, head) \
-	for (v = (head)->n, t = v->n; v != head; v = t, t = v->n)
-
-/*
- * Walk a list, setting 'v' in turn to the containing structure of each item.
- * The containing structure should be the same type as 'v'.
- * The 'struct dm_list' variable within the containing structure is 'field'.
- */
-#define dm_list_iterate_items_gen(v, head, field) \
-	for (v = dm_list_struct_base((head)->n, __typeof__(*v), field); \
-	     &v->field != (head); \
-	     v = dm_list_struct_base(v->field.n, __typeof__(*v), field))
-
-/*
- * Walk a list, setting 'v' in turn to the containing structure of each item.
- * The containing structure should be the same type as 'v'.
- * The list should be 'struct dm_list list' within the containing structure.
- */
-#define dm_list_iterate_items(v, head) dm_list_iterate_items_gen(v, (head), list)
-
-/*
- * Walk a list, setting 'v' in turn to the containing structure of each item.
- * The containing structure should be the same type as 'v'.
- * The 'struct dm_list' variable within the containing structure is 'field'.
- * t must be defined as a temporary variable of the same type as v.
- */
-#define dm_list_iterate_items_gen_safe(v, t, head, field) \
-	for (v = dm_list_struct_base((head)->n, __typeof__(*v), field), \
-	     t = dm_list_struct_base(v->field.n, __typeof__(*v), field); \
-	     &v->field != (head); \
-	     v = t, t = dm_list_struct_base(v->field.n, __typeof__(*v), field))
-/*
- * Walk a list, setting 'v' in turn to the containing structure of each item.
- * The containing structure should be the same type as 'v'.
- * The list should be 'struct dm_list list' within the containing structure.
- * t must be defined as a temporary variable of the same type as v.
- */
-#define dm_list_iterate_items_safe(v, t, head) \
-	dm_list_iterate_items_gen_safe(v, t, (head), list)
-
-/*
- * Walk a list backwards, setting 'v' in turn to the containing structure
- * of each item.
- * The containing structure should be the same type as 'v'.
- * The 'struct dm_list' variable within the containing structure is 'field'.
- */
-#define dm_list_iterate_back_items_gen(v, head, field) \
-	for (v = dm_list_struct_base((head)->p, __typeof__(*v), field); \
-	     &v->field != (head); \
-	     v = dm_list_struct_base(v->field.p, __typeof__(*v), field))
-
-/*
- * Walk a list backwards, setting 'v' in turn to the containing structure
- * of each item.
- * The containing structure should be the same type as 'v'.
- * The list should be 'struct dm_list list' within the containing structure.
- */
-#define dm_list_iterate_back_items(v, head) dm_list_iterate_back_items_gen(v, (head), list)
-
-/*
- * Return the number of elements in a list by walking it.
- */
-unsigned int dm_list_size(const struct dm_list *head);
-
-//----------------------------------------------------------------
-
-#endif

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

@@ -1,256 +0,0 @@
-// Copyright (C) 2018 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 "radix-tree.h"
-
-#include "base/memory/container_of.h"
-#include "base/memory/zalloc.h"
-
-#include <assert.h>
-#include <stdlib.h>
-#include <stdio.h>
-
-//----------------------------------------------------------------
-// This implementation is based around nested binary trees.  Very
-// simple (and hopefully correct).
-
-struct node {
-	struct node *left;
-	struct node *right;
-
-	uint8_t key;
-	struct node *center;
-
-	bool has_value;
-	union radix_value value;
-};
-
-struct radix_tree {
-	radix_value_dtr dtr;
-	void *dtr_context;
-
-	struct node *root;
-};
-
-struct radix_tree *
-radix_tree_create(radix_value_dtr dtr, void *dtr_context)
-{
-	struct radix_tree *rt = zalloc(sizeof(*rt));
-
-	if (rt) {
-		rt->dtr = dtr;
-		rt->dtr_context = dtr_context;
-	}
-
-	return rt;
-}
-
-// Returns the number of entries in the tree
-static unsigned _destroy_tree(struct node *n, radix_value_dtr dtr, void *context)
-{
-	unsigned r;
-
-	if (!n)
-		return 0;
-
-	r = _destroy_tree(n->left, dtr, context);
-	r += _destroy_tree(n->right, dtr, context);
-	r += _destroy_tree(n->center, dtr, context);
-
-	if (n->has_value) {
-		if (dtr)
-			dtr(context, n->value);
-		r++;
-	}
-
-	free(n);
-
-	return r;
-}
-
-void radix_tree_destroy(struct radix_tree *rt)
-{
-	_destroy_tree(rt->root, rt->dtr, rt->dtr_context);
-	free(rt);
-}
-
-static unsigned _count(struct node *n)
-{
-	unsigned r;
-
-	if (!n)
-		return 0;
-
-	r = _count(n->left);
-	r += _count(n->right);
-	r += _count(n->center);
-
-	if (n->has_value)
-		r++;
-
-	return r;
-}
-
-unsigned radix_tree_size(struct radix_tree *rt)
-{
-	return _count(rt->root);
-}
-
-static struct node **_lookup(struct node **pn, uint8_t *kb, uint8_t *ke)
-{
-	struct node *n = *pn;
-
-	if (!n || (kb == ke))
-		return pn;
-
-	if (*kb < n->key)
-		return _lookup(&n->left, kb, ke);
-
-	else if (*kb > n->key)
-		return _lookup(&n->right, kb, ke);
-
-	else
-		return _lookup(&n->center, kb + 1, ke);
-}
-
-static bool _insert(struct node **pn, uint8_t *kb, uint8_t *ke, union radix_value v)
-{
-	struct node *n = *pn;
-
-	if (!n) {
-		n = zalloc(sizeof(*n));
-		if (!n)
-			return false;
-
-		n->key = *kb;
-		*pn = n;
-	}
-
-	if (kb == ke) {
-		n->has_value = true;
-		n->value = v;
-		return true;
-	}
-
-	if (*kb < n->key)
-		return _insert(&n->left, kb, ke, v);
-
-	else if (*kb > n->key)
-		return _insert(&n->right, kb, ke, v);
-
-	else
-		return _insert(&n->center, kb + 1, ke, v);
-}
-
-bool radix_tree_insert(struct radix_tree *rt, uint8_t *kb, uint8_t *ke, union radix_value v)
-{
-	return _insert(&rt->root, kb, ke, v);
-}
-
-bool radix_tree_remove(struct radix_tree *rt, uint8_t *kb, uint8_t *ke)
-{
-	struct node **pn = _lookup(&rt->root, kb, ke);
-	struct node *n = *pn;
-
-	if (!n || !n->has_value)
-		return false;
-
-	else {
-		if (rt->dtr)
-			rt->dtr(rt->dtr_context, n->value);
-
-		if (n->left || n->center || n->right) {
-			n->has_value = false;
-			return true;
-
-		} else {
-			// FIXME: delete parent if this was the last entry
-			free(n);
-			*pn = NULL;
-		}
-
-		return true;
-	}
-}
-
-unsigned radix_tree_remove_prefix(struct radix_tree *rt, uint8_t *kb, uint8_t *ke)
-{
-	struct node **pn;
-	unsigned count;
-
-	pn = _lookup(&rt->root, kb, ke);
-
-	if (*pn) {
-		count = _destroy_tree(*pn, rt->dtr, rt->dtr_context);
-		*pn = NULL;
-	}
-
-	return count;
-}
-
-bool
-radix_tree_lookup(struct radix_tree *rt, uint8_t *kb, uint8_t *ke, union radix_value *result)
-{
-	struct node **pn = _lookup(&rt->root, kb, ke);
-	struct node *n = *pn;
-
-	if (n && n->has_value) {
-		*result = n->value;
-		return true;
-	} else
-		return false;
-}
-
-static void _iterate(struct node *n, struct radix_tree_iterator *it)
-{
-	if (!n)
-		return;
-
-	_iterate(n->left, it);
-
-	if (n->has_value)
-		// FIXME: fill out the key
-		it->visit(it, NULL, NULL, n->value);
-
-	_iterate(n->center, it);
-	_iterate(n->right, it);
-}
-
-void radix_tree_iterate(struct radix_tree *rt, uint8_t *kb, uint8_t *ke,
-                        struct radix_tree_iterator *it)
-{
-	if (kb == ke)
-		_iterate(rt->root, it);
-
-	else {
-		struct node **pn = _lookup(&rt->root, kb, ke);
-		struct node *n = *pn;
-
-		if (n) {
-			if (n->has_value)
-				it->visit(it, NULL, NULL, n->value);
-			_iterate(n->center, it);
-		}
-	}
-}
-
-bool radix_tree_is_well_formed(struct radix_tree *rt)
-{
-	return true;
-}
-
-void radix_tree_dump(struct radix_tree *rt, FILE *out)
-{
-}
-
-//----------------------------------------------------------------
-

base/data-struct/radix-tree.c

@@ -10,12 +10,853 @@
 // along with this program; if not, write to the Free Software Foundation,
 // Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 
-//----------------------------------------------------------------
+#include "radix-tree.h"
 
-#ifdef SIMPLE_RADIX_TREE
-#include "base/data-struct/radix-tree-simple.c"
-#else
-#include "base/data-struct/radix-tree-adaptive.c"
-#endif
+#include "base/memory/container_of.h"
+#include "base/memory/zalloc.h"
+
+#include <assert.h>
+#include <stdlib.h>
+#include <stdio.h>
+
+//----------------------------------------------------------------
+
+enum node_type {
+	UNSET = 0,
+	VALUE,
+	VALUE_CHAIN,
+	PREFIX_CHAIN,
+	NODE4,
+	NODE16,
+	NODE48,
+	NODE256
+};
+
+struct value {
+	enum node_type type;
+	union radix_value value;
+};
+
+// This is used for entries that have a key which is a prefix of another key.
+struct value_chain {
+	union radix_value value;
+	struct value child;
+};
+
+struct prefix_chain {
+	struct value child;
+	unsigned len;
+	uint8_t prefix[0];
+};
+
+struct node4 {
+	uint32_t nr_entries;
+	uint8_t keys[4];
+	struct value values[4];
+};
+
+struct node16 {
+	uint32_t nr_entries;
+	uint8_t keys[16];
+	struct value values[16];
+};
+
+struct node48 {
+	uint32_t nr_entries;
+	uint8_t keys[256];
+	struct value values[48];
+};
+
+struct node256 {
+        uint32_t nr_entries;
+	struct value values[256];
+};
+
+struct radix_tree {
+	unsigned nr_entries;
+	struct value root;
+	radix_value_dtr dtr;
+	void *dtr_context;
+};
+
+//----------------------------------------------------------------
+
+struct radix_tree *radix_tree_create(radix_value_dtr dtr, void *dtr_context)
+{
+	struct radix_tree *rt = malloc(sizeof(*rt));
+
+	if (rt) {
+		rt->nr_entries = 0;
+		rt->root.type = UNSET;
+		rt->dtr = dtr;
+		rt->dtr_context = dtr_context;
+	}
+
+	return rt;
+}
+
+static inline void _dtr(struct radix_tree *rt, union radix_value v)
+{
+	if (rt->dtr)
+        	rt->dtr(rt->dtr_context, v);
+}
+
+// Returns the number of values removed
+static unsigned _free_node(struct radix_tree *rt, struct value v)
+{
+	unsigned i, nr = 0;
+	struct value_chain *vc;
+	struct prefix_chain *pc;
+	struct node4 *n4;
+	struct node16 *n16;
+	struct node48 *n48;
+	struct node256 *n256;
+
+	switch (v.type) {
+	case UNSET:
+		break;
+
+	case VALUE:
+        	_dtr(rt, v.value);
+        	nr = 1;
+		break;
+
+	case VALUE_CHAIN:
+		vc = v.value.ptr;
+		_dtr(rt, vc->value);
+		nr = 1 + _free_node(rt, vc->child);
+		free(vc);
+		break;
+
+	case PREFIX_CHAIN:
+		pc = v.value.ptr;
+		nr = _free_node(rt, pc->child);
+		free(pc);
+		break;
+
+	case NODE4:
+		n4 = (struct node4 *) v.value.ptr;
+		for (i = 0; i < n4->nr_entries; i++)
+			nr += _free_node(rt, n4->values[i]);
+		free(n4);
+		break;
+
+	case NODE16:
+		n16 = (struct node16 *) v.value.ptr;
+		for (i = 0; i < n16->nr_entries; i++)
+			nr += _free_node(rt, n16->values[i]);
+		free(n16);
+		break;
+
+	case NODE48:
+		n48 = (struct node48 *) v.value.ptr;
+		for (i = 0; i < n48->nr_entries; i++)
+			nr += _free_node(rt, n48->values[i]);
+		free(n48);
+		break;
+
+	case NODE256:
+		n256 = (struct node256 *) v.value.ptr;
+		for (i = 0; i < 256; i++)
+			nr += _free_node(rt, n256->values[i]);
+		free(n256);
+		break;
+	}
+
+	return nr;
+}
+
+void radix_tree_destroy(struct radix_tree *rt)
+{
+	_free_node(rt, rt->root);
+	free(rt);
+}
+
+unsigned radix_tree_size(struct radix_tree *rt)
+{
+	return rt->nr_entries;
+}
+
+static bool _insert(struct radix_tree *rt, struct value *v, uint8_t *kb, uint8_t *ke, union radix_value rv);
+
+static bool _insert_unset(struct radix_tree *rt, struct value *v, uint8_t *kb, uint8_t *ke, union radix_value rv)
+{
+	unsigned len = ke - kb;
+
+	if (!len) {
+		// value
+		v->type = VALUE;
+		v->value = rv;
+		rt->nr_entries++;
+	} else {
+		// prefix -> value
+		struct prefix_chain *pc = zalloc(sizeof(*pc) + len);
+		if (!pc)
+			return false;
+
+		pc->child.type = VALUE;
+		pc->child.value = rv;
+		pc->len = len;
+		memcpy(pc->prefix, kb, len);
+		v->type = PREFIX_CHAIN;
+		v->value.ptr = pc;
+		rt->nr_entries++;
+	}
+
+	return true;
+}
+
+static bool _insert_value(struct radix_tree *rt, struct value *v, uint8_t *kb, uint8_t *ke, union radix_value rv)
+{
+	unsigned len = ke - kb;
+
+	if (!len)
+		// overwrite
+		v->value = rv;
+
+	else {
+		// value_chain -> value
+		struct value_chain *vc = zalloc(sizeof(*vc));
+		if (!vc)
+			return false;
+
+		vc->value = v->value;
+		if (!_insert(rt, &vc->child, kb, ke, rv)) {
+			free(vc);
+			return false;
+		}
+
+		v->type = VALUE_CHAIN;
+		v->value.ptr = vc;
+	}
+
+	return true;
+}
+
+static bool _insert_value_chain(struct radix_tree *rt, struct value *v, uint8_t *kb, uint8_t *ke, union radix_value rv)
+{
+	struct value_chain *vc = v->value.ptr;
+	return _insert(rt, &vc->child, kb, ke, rv);
+}
+
+static unsigned min(unsigned lhs, unsigned rhs)
+{
+	if (lhs <= rhs)
+		return lhs;
+	else
+		return rhs;
+}
+
+static bool _insert_prefix_chain(struct radix_tree *rt, struct value *v, uint8_t *kb, uint8_t *ke, union radix_value rv)
+{
+	struct prefix_chain *pc = v->value.ptr;
+
+	if (*kb == pc->prefix[0]) {
+		// There's a common prefix let's split the chain into two and
+		// recurse.
+		struct prefix_chain *pc2;
+		unsigned i, len = min(pc->len, ke - kb);
+
+		for (i = 0; i < len; i++)
+			if (kb[i] != pc->prefix[i])
+				break;
+
+		pc2 = zalloc(sizeof(*pc2) + pc->len - i);
+		pc2->len = pc->len - i;
+		memmove(pc2->prefix, pc->prefix + i, pc2->len);
+		pc2->child = pc->child;
+
+		// FIXME: this trashes pc so we can't back out
+		pc->child.type = PREFIX_CHAIN;
+		pc->child.value.ptr = pc2;
+		pc->len = i;
+
+		if (!_insert(rt, &pc->child, kb + i, ke, rv)) {
+			free(pc2);
+			return false;
+		}
+
+	} else {
+		// Stick an n4 in front.
+		struct node4 *n4 = zalloc(sizeof(*n4));
+		if (!n4)
+			return false;
+
+		n4->keys[0] = *kb;
+		if (!_insert(rt, n4->values, kb + 1, ke, rv)) {
+			free(n4);
+			return false;
+		}
+
+		if (pc->len) {
+			n4->keys[1] = pc->prefix[0];
+			if (pc->len == 1) {
+				n4->values[1] = pc->child;
+				free(pc);
+			} else {
+				memmove(pc->prefix, pc->prefix + 1, pc->len - 1);
+				pc->len--;
+				n4->values[1] = *v;
+			}
+			n4->nr_entries = 2;
+		} else
+			n4->nr_entries = 1;
+
+		v->type = NODE4;
+		v->value.ptr = n4;
+	}
+
+	return true;
+}
+
+static bool _insert_node4(struct radix_tree *rt, struct value *v, uint8_t *kb, uint8_t *ke, union radix_value rv)
+{
+	struct node4 *n4 = v->value.ptr;
+	if (n4->nr_entries == 4) {
+		struct node16 *n16 = zalloc(sizeof(*n16));
+		if (!n16)
+			return false;
+
+		n16->nr_entries = 5;
+		memcpy(n16->keys, n4->keys, sizeof(n4->keys));
+		memcpy(n16->values, n4->values, sizeof(n4->values));
+
+		n16->keys[4] = *kb;
+		if (!_insert(rt, n16->values + 4, kb + 1, ke, rv)) {
+			free(n16);
+			return false;
+		}
+		free(n4);
+		v->type = NODE16;
+		v->value.ptr = n16;
+	} else {
+		n4 = v->value.ptr;
+		if (!_insert(rt, n4->values + n4->nr_entries, kb + 1, ke, rv))
+			return false;
+
+		n4->keys[n4->nr_entries] = *kb;
+		n4->nr_entries++;
+	}
+	return true;
+}
+
+static bool _insert_node16(struct radix_tree *rt, struct value *v, uint8_t *kb, uint8_t *ke, union radix_value rv)
+{
+	struct node16 *n16 = v->value.ptr;
+
+	if (n16->nr_entries == 16) {
+		unsigned i;
+		struct node48 *n48 = zalloc(sizeof(*n48));
+
+		if (!n48)
+			return false;
+
+		n48->nr_entries = 17;
+		memset(n48->keys, 48, sizeof(n48->keys));
+
+		for (i = 0; i < 16; i++) {
+			n48->keys[n16->keys[i]] = i;
+			n48->values[i] = n16->values[i];
+		}
+
+		n48->keys[*kb] = 16;
+		if (!_insert(rt, n48->values + 16, kb + 1, ke, rv)) {
+			free(n48);
+			return false;
+		}
+
+		free(n16);
+		v->type = NODE48;
+		v->value.ptr = n48;
+	} else {
+		if (!_insert(rt, n16->values + n16->nr_entries, kb + 1, ke, rv))
+			return false;
+		n16->keys[n16->nr_entries] = *kb;
+		n16->nr_entries++;
+	}
+
+	return true;
+}
+
+static bool _insert_node48(struct radix_tree *rt, struct value *v, uint8_t *kb, uint8_t *ke, union radix_value rv)
+{
+	struct node48 *n48 = v->value.ptr;
+	if (n48->nr_entries == 48) {
+		unsigned i;
+		struct node256 *n256 = zalloc(sizeof(*n256));
+		if (!n256)
+			return false;
+
+		for (i = 0; i < 256; i++) {
+			if (n48->keys[i] >= 48)
+				continue;
+
+			n256->values[i] = n48->values[n48->keys[i]];
+		}
+
+		if (!_insert(rt, n256->values + *kb, kb + 1, ke, rv)) {
+			free(n256);
+			return false;
+		}
+
+		free(n48);
+		v->type = NODE256;
+		v->value.ptr = n256;
+
+	} else {
+		if (!_insert(rt, n48->values + n48->nr_entries, kb + 1, ke, rv))
+			return false;
+
+		n48->keys[*kb] = n48->nr_entries;
+		n48->nr_entries++;
+	}
+
+	return true;
+}
+
+static bool _insert_node256(struct radix_tree *rt, struct value *v, uint8_t *kb, uint8_t *ke, union radix_value rv)
+{
+	struct node256 *n256 = v->value.ptr;
+	bool was_unset = n256->values[*kb].type == UNSET;
+
+	if (!_insert(rt, n256->values + *kb, kb + 1, ke, rv))
+		return false;
+
+	if (was_unset)
+        	n256->nr_entries++;
+
+	return true;
+}
+
+// FIXME: the tree should not be touched if insert fails (eg, OOM)
+static bool _insert(struct radix_tree *rt, struct value *v, uint8_t *kb, uint8_t *ke, union radix_value rv)
+{
+	if (kb == ke) {
+		if (v->type == UNSET) {
+			v->type = VALUE;
+			v->value = rv;
+			rt->nr_entries++;
+
+		} else if (v->type == VALUE) {
+			v->value = rv;
+
+		} else {
+			struct value_chain *vc = zalloc(sizeof(*vc));
+			if (!vc)
+				return false;
+
+			vc->value = rv;
+			vc->child = *v;
+			v->type = VALUE_CHAIN;
+			v->value.ptr = vc;
+			rt->nr_entries++;
+		}
+		return true;
+	}
+
+	switch (v->type) {
+	case UNSET:
+		return _insert_unset(rt, v, kb, ke, rv);
+
+	case VALUE:
+		return _insert_value(rt, v, kb, ke, rv);
+
+	case VALUE_CHAIN:
+		return _insert_value_chain(rt, v, kb, ke, rv);
+
+	case PREFIX_CHAIN:
+		return _insert_prefix_chain(rt, v, kb, ke, rv);
+
+	case NODE4:
+		return _insert_node4(rt, v, kb, ke, rv);
+
+	case NODE16:
+		return _insert_node16(rt, v, kb, ke, rv);
+
+	case NODE48:
+		return _insert_node48(rt, v, kb, ke, rv);
+
+	case NODE256:
+		return _insert_node256(rt, v, kb, ke, rv);
+	}
+
+	// can't get here
+	return false;
+}
+
+struct lookup_result {
+	struct value *v;
+	uint8_t *kb;
+};
+
+static struct lookup_result _lookup_prefix(struct value *v, uint8_t *kb, uint8_t *ke)
+{
+	unsigned i;
+	struct value_chain *vc;
+	struct prefix_chain *pc;
+	struct node4 *n4;
+	struct node16 *n16;
+	struct node48 *n48;
+	struct node256 *n256;
+
+	if (kb == ke)
+		return (struct lookup_result) {.v = v, .kb = kb};
+
+	switch (v->type) {
+	case UNSET:
+	case VALUE:
+		break;
+
+	case VALUE_CHAIN:
+		vc = v->value.ptr;
+		return _lookup_prefix(&vc->child, kb, ke);
+
+	case PREFIX_CHAIN:
+		pc = v->value.ptr;
+		if (ke - kb < pc->len)
+			return (struct lookup_result) {.v = v, .kb = kb};
+
+		for (i = 0; i < pc->len; i++)
+			if (kb[i] != pc->prefix[i])
+				return (struct lookup_result) {.v = v, .kb = kb};
+
+		return _lookup_prefix(&pc->child, kb + pc->len, ke);
+
+	case NODE4:
+		n4 = v->value.ptr;
+		for (i = 0; i < n4->nr_entries; i++)
+			if (n4->keys[i] == *kb)
+				return _lookup_prefix(n4->values + i, kb + 1, ke);
+		break;
+
+	case NODE16:
+		// FIXME: use binary search or simd?
+		n16 = v->value.ptr;
+		for (i = 0; i < n16->nr_entries; i++)
+			if (n16->keys[i] == *kb)
+				return _lookup_prefix(n16->values + i, kb + 1, ke);
+		break;
+
+	case NODE48:
+		n48 = v->value.ptr;
+		i = n48->keys[*kb];
+		if (i < 48)
+			return _lookup_prefix(n48->values + i, kb + 1, ke);
+		break;
+
+	case NODE256:
+		n256 = v->value.ptr;
+		return _lookup_prefix(n256->values + *kb, kb + 1, ke);
+	}
+
+	return (struct lookup_result) {.v = v, .kb = kb};
+}
+
+bool radix_tree_insert(struct radix_tree *rt, uint8_t *kb, uint8_t *ke, union radix_value rv)
+{
+	struct lookup_result lr = _lookup_prefix(&rt->root, kb, ke);
+	return _insert(rt, lr.v, lr.kb, ke, rv);
+}
+
+// Note the degrade functions also free the original node.
+static void _degrade_to_n4(struct node16 *n16, struct value *result)
+{
+        struct node4 *n4 = zalloc(sizeof(*n4));
+
+        n4->nr_entries = n16->nr_entries;
+        memcpy(n4->keys, n16->keys, n16->nr_entries * sizeof(*n4->keys));
+        memcpy(n4->values, n16->values, n16->nr_entries * sizeof(*n4->values));
+        free(n16);
+
+	result->type = NODE4;
+	result->value.ptr = n4;
+}
+
+static void _degrade_to_n16(struct node48 *n48, struct value *result)
+{
+        struct node4 *n16 = zalloc(sizeof(*n16));
+
+        n16->nr_entries = n48->nr_entries;
+        memcpy(n16->keys, n48->keys, n48->nr_entries * sizeof(*n16->keys));
+        memcpy(n16->values, n48->values, n48->nr_entries * sizeof(*n16->values));
+        free(n48);
+
+	result->type = NODE16;
+	result->value.ptr = n16;
+}
+
+static void _degrade_to_n48(struct node256 *n256, struct value *result)
+{
+        unsigned i, count = 0;
+        struct node4 *n48 = zalloc(sizeof(*n48));
+
+        n48->nr_entries = n256->nr_entries;
+        for (i = 0; i < 256; i++) {
+		if (n256->values[i].type == UNSET)
+        		continue;
+
+		n48->keys[count] = i;
+		n48->values[count] = n256->values[i];
+		count++;
+        }
+        free(n256);
+
+	result->type = NODE48;
+	result->value.ptr = n48;
+}
+
+static bool _remove(struct radix_tree *rt, struct value *root, uint8_t *kb, uint8_t *ke)
+{
+	bool r;
+	unsigned i;
+	struct value_chain *vc;
+	struct prefix_chain *pc;
+	struct node4 *n4;
+	struct node16 *n16;
+	struct node48 *n48;
+	struct node256 *n256;
+
+	if (kb == ke) {
+        	if (root->type == VALUE) {
+                	root->type = UNSET;
+                	_dtr(rt, root->value);
+                	return true;
+
+                } else if (root->type == VALUE_CHAIN) {
+			vc = root->value.ptr;
+			_dtr(rt, vc->value);
+			memcpy(root, &vc->child, sizeof(*root));
+			free(vc);
+			return true;
+
+                } else
+			return false;
+	}
+
+	switch (root->type) {
+	case UNSET:
+	case VALUE:
+        	// this is a value for a prefix of the key
+        	return false;
+
+	case VALUE_CHAIN:
+		vc = root->value.ptr;
+		r = _remove(rt, &vc->child, kb, ke);
+		if (r && (vc->child.type == UNSET)) {
+			memcpy(root, &vc->child, sizeof(*root));
+			free(vc);
+		}
+		return r;
+
+	case PREFIX_CHAIN:
+		pc = root->value.ptr;
+		if (ke - kb < pc->len)
+        		return false;
+
+		for (i = 0; i < pc->len; i++)
+			if (kb[i] != pc->prefix[i])
+        			return false;
+
+		return _remove(rt, &pc->child, kb + pc->len, ke);
+
+	case NODE4:
+		n4 = root->value.ptr;
+		for (i = 0; i < n4->nr_entries; i++) {
+			if (n4->keys[i] == *kb) {
+				r = _remove(rt, n4->values + i, kb + 1, ke);
+				if (r && n4->values[i].type == UNSET) {
+        				n4->nr_entries--;
+        				if (i < n4->nr_entries)
+                				// slide the entries down
+        					memmove(n4->keys + i, n4->keys + i + 1,
+                                                       sizeof(*n4->keys) * (n4->nr_entries - i));
+					if (!n4->nr_entries)
+						root->type = UNSET;
+				}
+				return r;
+			}
+		}
+		return false;
+
+	case NODE16:
+        	n16 = root->value.ptr;
+		for (i = 0; i < n16->nr_entries; i++) {
+			if (n16->keys[i] == *kb) {
+				r = _remove(rt, n16->values + i, kb + 1, ke);
+				if (r && n16->values[i].type == UNSET) {
+        				n16->nr_entries--;
+        				if (i < n16->nr_entries)
+                				// slide the entries down
+        					memmove(n16->keys + i, n16->keys + i + 1,
+                                                        sizeof(*n16->keys) * (n16->nr_entries - i));
+					if (n16->nr_entries <= 4)
+        					_degrade_to_n4(n16, root);
+				}
+				return r;
+			}
+		}
+		return false;
+
+	case NODE48:
+		n48 = root->value.ptr;
+		i = n48->keys[*kb];
+		if (i < 48) {
+        		r = _remove(rt, n48->values + i, kb + 1, ke);
+        		if (r && n48->values[i].type == UNSET) {
+                		n48->keys[*kb] = 48;
+				n48->nr_entries--;
+				if (n48->nr_entries <= 16)
+        				_degrade_to_n16(n48, root);
+        		}
+        		return r;
+		}
+		return false;
+
+	case NODE256:
+		n256 = root->value.ptr;
+		r = _remove(rt, n256->values + (*kb), kb + 1, ke);
+		if (r && n256->values[*kb].type == UNSET) {
+			n256->nr_entries--;
+			if (n256->nr_entries <= 48)
+        			_degrade_to_n48(n256, root);
+		}
+		return r;
+	}
+
+	return false;
+}
+
+bool radix_tree_remove(struct radix_tree *rt, uint8_t *key_begin, uint8_t *key_end)
+{
+	if (_remove(rt, &rt->root, key_begin, key_end)) {
+        	rt->nr_entries--;
+        	return true;
+	}
+
+	return false;
+}
+
+static bool _prefix_chain_matches(struct lookup_result *lr, uint8_t *ke)
+{
+        // It's possible the top node is a prefix chain, and
+        // the remaining key matches part of it.
+        if (lr->v->type == PREFIX_CHAIN) {
+                unsigned i, rlen = ke - lr->kb;
+                struct prefix_chain *pc = lr->v->value.ptr;
+                if (rlen < pc->len) {
+                        for (i = 0; i < rlen; i++)
+                                if (pc->prefix[i] != lr->kb[i])
+                                        return false;
+                        return true;
+		}
+        }
+
+        return false;
+}
+
+unsigned radix_tree_remove_prefix(struct radix_tree *rt, uint8_t *kb, uint8_t *ke)
+{
+        unsigned count = 0;
+	struct lookup_result lr = _lookup_prefix(&rt->root, kb, ke);
+	if (lr.kb == ke || _prefix_chain_matches(&lr, ke)) {
+        	count = _free_node(rt, *lr.v);
+        	lr.v->type = UNSET;
+	}
+
+	rt->nr_entries -= count;
+	return count;
+}
+
+bool radix_tree_lookup(struct radix_tree *rt,
+		       uint8_t *kb, uint8_t *ke, union radix_value *result)
+{
+	struct value_chain *vc;
+	struct lookup_result lr = _lookup_prefix(&rt->root, kb, ke);
+	if (lr.kb == ke) {
+		switch (lr.v->type) {
+		case VALUE:
+			*result = lr.v->value;
+			return true;
+
+		case VALUE_CHAIN:
+			vc = lr.v->value.ptr;
+			*result = vc->value;
+			return true;
+
+		default:
+			return false;
+		}
+	}
+
+	return false;
+}
+
+// FIXME: build up the keys too
+static bool _iterate(struct value *v, struct radix_tree_iterator *it)
+{
+	unsigned i;
+	struct value_chain *vc;
+	struct prefix_chain *pc;
+	struct node4 *n4;
+	struct node16 *n16;
+	struct node48 *n48;
+	struct node256 *n256;
+
+	switch (v->type) {
+	case UNSET:
+        	// can't happen
+		break;
+
+	case VALUE:
+        	return it->visit(it, NULL, NULL, v->value);
+
+	case VALUE_CHAIN:
+		vc = v->value.ptr;
+		return it->visit(it, NULL, NULL, vc->value) && _iterate(&vc->child, it);
+
+	case PREFIX_CHAIN:
+		pc = v->value.ptr;
+		return _iterate(&pc->child, it);
+
+	case NODE4:
+		n4 = (struct node4 *) v->value.ptr;
+		for (i = 0; i < n4->nr_entries; i++)
+			if (!_iterate(n4->values + i, it))
+        			return false;
+        	return true;
+
+	case NODE16:
+		n16 = (struct node16 *) v->value.ptr;
+		for (i = 0; i < n16->nr_entries; i++)
+        		if (!_iterate(n16->values + i, it))
+        			return false;
+		return true;
+
+	case NODE48:
+		n48 = (struct node48 *) v->value.ptr;
+		for (i = 0; i < n48->nr_entries; i++)
+        		if (!_iterate(n48->values + i, it))
+        			return false;
+		return true;
+
+	case NODE256:
+		n256 = (struct node256 *) v->value.ptr;
+		for (i = 0; i < 256; i++)
+        		if (n256->values[i].type != UNSET && !_iterate(n256->values + i, it))
+        			return false;
+		return true;
+	}
+
+	// can't get here
+	return false;
+}
+
+void radix_tree_iterate(struct radix_tree *rt, uint8_t *kb, uint8_t *ke,
+                        struct radix_tree_iterator *it)
+{
+	struct lookup_result lr = _lookup_prefix(&rt->root, kb, ke);
+	if (lr.kb == ke || _prefix_chain_matches(&lr, ke))
+        	_iterate(lr.v, it);
+}
 
 //----------------------------------------------------------------

base/data-struct/radix-tree.h

@@ -15,7 +15,6 @@
 
 #include <stdbool.h>
 #include <stdint.h>
-#include <stdio.h>
 
 //----------------------------------------------------------------
 
@@ -54,11 +53,6 @@ struct radix_tree_iterator {
 void radix_tree_iterate(struct radix_tree *rt, uint8_t *kb, uint8_t *ke,
                         struct radix_tree_iterator *it);
 
-// Checks that some constraints on the shape of the tree are
-// being held.  For debug only.
-bool radix_tree_is_well_formed(struct radix_tree *rt);
-void radix_tree_dump(struct radix_tree *rt, FILE *out);
-
 //----------------------------------------------------------------
 
 #endif

base/memory/container_of.h

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

base/memory/zalloc.h

@@ -14,12 +14,16 @@
 #define BASE_MEMORY_ZALLOC_H
 
 #include <stdlib.h>
+#include <string.h>
 
 //----------------------------------------------------------------
 
 static inline void *zalloc(size_t len)
 {
-	return calloc(1, len);
+	void *ptr = malloc(len);
+	if (ptr)
+		memset(ptr, 0, len);
+	return ptr;
 }
 
 //----------------------------------------------------------------

conf/Makefile.in

@@ -1,5 +1,5 @@
 #
-# Copyright (C) 2004-2018 Red Hat, Inc. All rights reserved.
+# Copyright (C) 2004-2015 Red Hat, Inc. All rights reserved.
 #
 # This file is part of LVM2.
 #
@@ -25,7 +25,6 @@ PROFILES=$(PROFILE_TEMPLATES) \
 	$(srcdir)/cache-smq.profile \
 	$(srcdir)/thin-generic.profile \
 	$(srcdir)/thin-performance.profile \
-	$(srcdir)/vdo-small.profile \
 	$(srcdir)/lvmdbusd.profile
 
 include $(top_builddir)/make.tmpl
@@ -33,8 +32,8 @@ include $(top_builddir)/make.tmpl
 .PHONY: install_conf install_localconf install_profiles
 
 generate:
-	$(top_builddir)/tools/lvm dumpconfig --type default --unconfigured --withgeneralpreamble --withcomments --ignorelocal --withspaces > example.conf.in
-	$(top_builddir)/tools/lvm dumpconfig --type default --unconfigured --withlocalpreamble --withcomments --withspaces local > lvmlocal.conf.in
+	LD_LIBRARY_PATH=$(top_builddir)/libdm:$(LD_LIBRARY_PATH) $(top_builddir)/tools/lvm dumpconfig --type default --unconfigured --withgeneralpreamble --withcomments --ignorelocal --withspaces > example.conf.in
+	LD_LIBRARY_PATH=$(top_builddir)/libdm:$(LD_LIBRARY_PATH) $(top_builddir)/tools/lvm dumpconfig --type default --unconfigured --withlocalpreamble --withcomments --withspaces local > lvmlocal.conf.in
 
 install_conf: $(CONFSRC)
 	@if [ ! -e $(confdir)/$(CONFDEST) ]; then \
@@ -49,9 +48,8 @@ install_localconf: $(CONFLOCAL)
 	fi
 
 install_profiles: $(PROFILES)
-	@echo "    [INSTALL] $<"
-	$(Q) $(INSTALL_DIR) $(profiledir)
-	$(Q) $(INSTALL_DATA) $(PROFILES) $(profiledir)/
+	$(INSTALL_DIR) $(profiledir)
+	$(INSTALL_DATA) $(PROFILES) $(profiledir)/
 
 install_lvm2: install_conf install_localconf install_profiles
 

conf/example.conf.in

@@ -88,22 +88,6 @@ devices {
 	# 
 	external_device_info_source = "none"
 
-	# Configuration option devices/hints.
-	# Use a local file to remember which devices have PVs on them.
-	# Some commands will use this as an optimization to reduce device
-	# 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"
-
 	# Configuration option devices/preferred_names.
 	# Select which path name to display for a block device.
 	# If multiple path names exist for a block device, and LVM needs to
@@ -139,10 +123,11 @@ 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.
+	# See the use_lvmetad comment for a special case regarding filters.
 	# 
 	# Example
 	# Accept every block device:
-	# filter = [ "a|.*|" ]
+	# filter = [ "a|.*/|" ]
 	# Reject the cdrom drive:
 	# filter = [ "r|/dev/cdrom|" ]
 	# Work with just loopback devices, e.g. for testing:
@@ -150,20 +135,38 @@ devices {
 	# Accept all loop devices and ide drives except hdc:
 	# filter = [ "a|loop|", "r|/dev/hdc|", "a|/dev/ide|", "r|.*|" ]
 	# Use anchors to be very specific:
-	# filter = [ "a|^/dev/hda8$|", "r|.*|" ]
+	# filter = [ "a|^/dev/hda8$|", "r|.*/|" ]
 	# 
 	# This configuration option has an automatic default value.
-	# filter = [ "a|.*|" ]
+	# filter = [ "a|.*/|" ]
 
 	# Configuration option devices/global_filter.
 	# Limit the block devices that are used by LVM system components.
 	# Because devices/filter may be overridden from the command line, it is
-	# not suitable for system-wide device filtering, e.g. udev.
+	# not suitable for system-wide device filtering, e.g. udev and lvmetad.
 	# Use global_filter to hide devices from these LVM system components.
 	# The syntax is the same as devices/filter. Devices rejected by
 	# global_filter are not opened by LVM.
 	# This configuration option has an automatic default value.
-	# global_filter = [ "a|.*|" ]
+	# global_filter = [ "a|.*/|" ]
+
+	# Configuration option devices/cache_dir.
+	# Directory in which to store the device cache file.
+	# The results of filtering are cached on disk to avoid rescanning dud
+	# devices (which can take a very long time). By default this cache is
+	# stored in a file named .cache. It is safe to delete this file; the
+	# tools regenerate it. If obtain_device_list_from_udev is enabled, the
+	# list of devices is obtained from udev and any existing .cache file
+	# is removed.
+	cache_dir = "@DEFAULT_SYS_DIR@/@DEFAULT_CACHE_SUBDIR@"
+
+	# Configuration option devices/cache_file_prefix.
+	# A prefix used before the .cache file name. See devices/cache_dir.
+	cache_file_prefix = ""
+
+	# Configuration option devices/write_cache_state.
+	# Enable/disable writing the cache file. See devices/cache_dir.
+	write_cache_state = 1
 
 	# Configuration option devices/types.
 	# List of additional acceptable block device types.
@@ -201,34 +204,9 @@ devices {
 	multipath_component_detection = 1
 
 	# Configuration option devices/md_component_detection.
-	# Enable detection and exclusion of MD component devices.
-	# An MD component device is a block device that MD uses as part
-	# of a software RAID virtual device. When an LVM PV is created
-	# on an MD device, LVM must only use the top level MD device as
-	# the PV, and should ignore the underlying component devices.
-	# In cases where the MD superblock is located at the end of the
-	# component devices, it is more difficult for LVM to consistently
-	# identify an MD component, see the md_component_checks setting.
+	# Ignore devices that are components of software RAID (md) devices.
 	md_component_detection = 1
 
-	# 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
-	#     indications that the device is not an MD component.
-	#   start
-	#     LVM will only scan the start of devices for MD superblocks.
-	#     This does not incur extra I/O by LVM.
-	#   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"
-
 	# Configuration option devices/fw_raid_component_detection.
 	# Ignore devices that are components of firmware RAID devices.
 	# LVM must use an external_device_info_source other than none for this
@@ -236,24 +214,19 @@ devices {
 	fw_raid_component_detection = 0
 
 	# Configuration option devices/md_chunk_alignment.
-	# Align the start of a PV data area with md device's stripe-width.
+	# Align PV data blocks 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
-	# with the value detected for this setting.
-	# This setting is overriden 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
-	# option.
+	# Default alignment of the start of a PV data area in MB.
+	# If set to 0, a value of 64KiB will be used.
+	# Set to 1 for 1MiB, 2 for 2MiB, etc.
 	# This configuration option has an automatic default value.
 	# default_data_alignment = 1
 
 	# Configuration option devices/data_alignment_detection.
-	# Align the start of a PV data area with sysfs io properties.
+	# Detect PV data alignment based on sysfs device information.
 	# The start of a PV data area will be a multiple of minimum_io_size or
 	# optimal_io_size exposed in sysfs. minimum_io_size is the smallest
 	# request the device can perform without incurring a read-modify-write
@@ -261,29 +234,27 @@ 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
-	# if they are not aligned with the value detected for this setting.
-	# This setting is overriden by data_alignment and the --dataalignment
-	# option.
+	# This setting takes precedence over md_chunk_alignment.
 	data_alignment_detection = 1
 
 	# Configuration option devices/data_alignment.
-	# Align the start of a PV data area with this number of KiB.
-	# 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.
+	# Alignment of the start of a PV data area in KiB.
+	# If a PV is placed directly on an md device and md_chunk_alignment or
+	# data_alignment_detection are enabled, then this setting is ignored.
+	# Otherwise, md_chunk_alignment and data_alignment_detection are
+	# disabled if this is set. Set to 0 to use the default alignment or the
+	# page size, if larger.
 	data_alignment = 0
 
 	# Configuration option devices/data_alignment_offset_detection.
-	# Shift the start of an aligned PV data area based on sysfs information.
-	# After a PV data area is aligned, it will be shifted by the
+	# Detect PV data alignment offset based on sysfs device information.
+	# The start of a PV aligned data area will be shifted by the
 	# alignment_offset exposed in sysfs. This offset is often 0, but may
 	# be non-zero. Certain 4KiB sector drives that compensate for windows
 	# 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.
+	# pvcreate --dataalignmentoffset will skip this detection.
 	data_alignment_offset_detection = 1
 
 	# Configuration option devices/ignore_suspended_devices.
@@ -311,6 +282,14 @@ devices {
 	# different way, making them a better choice for VG stacking.
 	ignore_lvm_mirrors = 1
 
+	# Configuration option devices/disable_after_error_count.
+	# Number of I/O errors after which a device is skipped.
+	# During each LVM operation, errors received from each device are
+	# counted. If the counter of a device exceeds the limit set here,
+	# no further I/O is sent to that device for the remainder of the
+	# operation. Setting this to 0 disables the counters altogether.
+	disable_after_error_count = 0
+
 	# Configuration option devices/require_restorefile_with_uuid.
 	# Allow use of pvcreate --uuid without requiring --restorefile.
 	require_restorefile_with_uuid = 1
@@ -347,12 +326,6 @@ devices {
 	# Enabling this setting allows the VG to be used as usual even with
 	# uncertain devices.
 	allow_changes_with_duplicate_pvs = 0
-
-	# Configuration option devices/allow_mixed_block_sizes.
-	# Allow PVs in the same VG with different logical block sizes.
-	# When allowed, the user is responsible to ensure that an LV is
-	# using PVs with matching block sizes when necessary.
-	allow_mixed_block_sizes = 0
 }
 
 # Configuration section allocation.
@@ -387,7 +360,7 @@ allocation {
 	maximise_cling = 1
 
 	# Configuration option allocation/use_blkid_wiping.
-	# Use blkid to detect and erase existing signatures on new PVs and LVs.
+	# Use blkid to detect existing signatures on new PVs and LVs.
 	# The blkid library can detect more signatures than the native LVM
 	# detection code, but may take longer. LVM needs to be compiled with
 	# blkid wiping support for this setting to apply. LVM native detection
@@ -429,8 +402,7 @@ allocation {
 
 	# Configuration option allocation/cache_pool_metadata_require_separate_pvs.
 	# Cache pool metadata and data will always use different PVs.
-	# This configuration option has an automatic default value.
-	# cache_pool_metadata_require_separate_pvs = 0
+	cache_pool_metadata_require_separate_pvs = 0
 
 	# Configuration option allocation/cache_metadata_format.
 	# Sets default metadata format for new cache.
@@ -489,9 +461,8 @@ allocation {
 	# This configuration option does not have a default value defined.
 
 	# Configuration option allocation/thin_pool_metadata_require_separate_pvs.
-	# 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
+	# Thin pool metdata and data will always use different PVs.
+	thin_pool_metadata_require_separate_pvs = 0
 
 	# Configuration option allocation/thin_pool_zero.
 	# Thin pool data chunks are zeroed before they are first used.
@@ -528,11 +499,6 @@ allocation {
 	# 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,
@@ -546,154 +512,6 @@ allocation {
 	# Default physical extent size in KiB to use for new VGs.
 	# This configuration option has an automatic default value.
 	# physical_extent_size = 4096
-
-	# Configuration option allocation/vdo_use_compression.
-	# Enables or disables compression when creating a VDO volume.
-	# Compression may be disabled if necessary to maximize performance
-	# or to speed processing of data that is unlikely to compress.
-	# This configuration option has an automatic default value.
-	# vdo_use_compression = 1
-
-	# Configuration option allocation/vdo_use_deduplication.
-	# Enables or disables deduplication when creating a VDO volume.
-	# Deduplication may be disabled in instances where data is not expected
-	# to have good deduplication rates but compression is still desired.
-	# This configuration option has an automatic default value.
-	# vdo_use_deduplication = 1
-
-	# Configuration option allocation/vdo_use_metadata_hints.
-	# Enables or disables whether VDO volume should tag its latency-critical
-	# writes with the REQ_SYNC flag. Some device mapper targets such as dm-raid5
-	# process writes with this flag at a higher priority.
-	# Default is enabled.
-	# This configuration option has an automatic default value.
-	# vdo_use_metadata_hints = 1
-
-	# Configuration option allocation/vdo_minimum_io_size.
-	# The minimum IO size for VDO volume to accept, in bytes.
-	# Valid values are 512 or 4096. The recommended and default value is 4096.
-	# This configuration option has an automatic default value.
-	# vdo_minimum_io_size = 4096
-
-	# Configuration option allocation/vdo_block_map_cache_size_mb.
-	# Specifies the amount of memory in MiB allocated for caching block map
-	# pages for VDO volume. The value must be a multiple of 4096 and must be
-	# at least 128MiB and less than 16TiB. The cache must be at least 16MiB
-	# per logical thread. Note that there is a memory overhead of 15%.
-	# This configuration option has an automatic default value.
-	# vdo_block_map_cache_size_mb = 128
-
-	# Configuration option allocation/vdo_block_map_period.
-	# The speed with which the block map cache writes out modified block map pages.
-	# A smaller era length is likely to reduce the amount time spent rebuilding,
-	# at the cost of increased block map writes during normal operation.
-	# The maximum and recommended value is 16380; the minimum value is 1.
-	# This configuration option has an automatic default value.
-	# vdo_block_map_period = 16380
-
-	# Configuration option allocation/vdo_check_point_frequency.
-	# The default check point frequency for VDO volume.
-	# This configuration option has an automatic default value.
-	# vdo_check_point_frequency = 0
-
-	# Configuration option allocation/vdo_use_sparse_index.
-	# Enables sparse indexing for VDO volume.
-	# This configuration option has an automatic default value.
-	# vdo_use_sparse_index = 0
-
-	# Configuration option allocation/vdo_index_memory_size_mb.
-	# Specifies the amount of index memory in MiB for VDO volume.
-	# The value must be at least 256MiB and at most 1TiB.
-	# This configuration option has an automatic default value.
-	# vdo_index_memory_size_mb = 256
-
-	# Configuration option allocation/vdo_slab_size_mb.
-	# Specifies the size in MiB of the increment by which a VDO is grown.
-	# Using a smaller size constrains the total maximum physical size
-	# that can be accommodated. Must be a power of two between 128MiB and 32GiB.
-	# This configuration option has an automatic default value.
-	# vdo_slab_size_mb = 2048
-
-	# Configuration option allocation/vdo_ack_threads.
-	# Specifies the number of threads to use for acknowledging
-	# completion of requested VDO I/O operations.
-	# The value must be at in range [0..100].
-	# This configuration option has an automatic default value.
-	# vdo_ack_threads = 1
-
-	# Configuration option allocation/vdo_bio_threads.
-	# Specifies the number of threads to use for submitting I/O
-	# operations to the storage device of VDO volume.
-	# The value must be in range [1..100]
-	# Each additional thread after the first will use an additional 18MiB of RAM,
-	# plus 1.12 MiB of RAM per megabyte of configured read cache size.
-	# This configuration option has an automatic default value.
-	# vdo_bio_threads = 4
-
-	# Configuration option allocation/vdo_bio_rotation.
-	# Specifies the number of I/O operations to enqueue for each bio-submission
-	# thread before directing work to the next. The value must be in range [1..1024].
-	# This configuration option has an automatic default value.
-	# vdo_bio_rotation = 64
-
-	# Configuration option allocation/vdo_cpu_threads.
-	# Specifies the number of threads to use for CPU-intensive work such as
-	# hashing or compression for VDO volume. The value must be in range [1..100]
-	# This configuration option has an automatic default value.
-	# vdo_cpu_threads = 2
-
-	# Configuration option allocation/vdo_hash_zone_threads.
-	# Specifies the number of threads across which to subdivide parts of the VDO
-	# processing based on the hash value computed from the block data.
-	# The value must be at in range [0..100].
-	# vdo_hash_zone_threads, vdo_logical_threads and vdo_physical_threads must be
-	# either all zero or all non-zero.
-	# This configuration option has an automatic default value.
-	# vdo_hash_zone_threads = 1
-
-	# Configuration option allocation/vdo_logical_threads.
-	# Specifies the number of threads across which to subdivide parts of the VDO
-	# processing based on the hash value computed from the block data.
-	# A logical thread count of 9 or more will require explicitly specifying
-	# a sufficiently large block map cache size, as well.
-	# The value must be in range [0..100].
-	# vdo_hash_zone_threads, vdo_logical_threads and vdo_physical_threads must be
-	# either all zero or all non-zero.
-	# This configuration option has an automatic default value.
-	# vdo_logical_threads = 1
-
-	# Configuration option allocation/vdo_physical_threads.
-	# Specifies the number of threads across which to subdivide parts of the VDO
-	# processing based on physical block addresses.
-	# Each additional thread after the first will use an additional 10MiB of RAM.
-	# The value must be in range [0..16].
-	# vdo_hash_zone_threads, vdo_logical_threads and vdo_physical_threads must be
-	# either all zero or all non-zero.
-	# This configuration option has an automatic default value.
-	# vdo_physical_threads = 1
-
-	# Configuration option allocation/vdo_write_policy.
-	# Specifies the write policy:
-	# auto  - VDO will check the storage device and determine whether it supports flushes.
-	#         If it does, VDO will run in async mode, otherwise it will run in sync mode.
-	# sync  - Writes are acknowledged only after data is stably written.
-	#         This policy is not supported if the underlying storage is not also synchronous.
-	# async - Writes are acknowledged after data has been cached for writing to stable storage.
-	#         Data which has not been flushed is not guaranteed to persist in this mode.
-	# This configuration option has an automatic default value.
-	# vdo_write_policy = "auto"
-
-	# Configuration option allocation/vdo_max_discard.
-	# Specified te maximum size of discard bio accepted, in 4096 byte blocks.
-	# I/O requests to a VDO volume are normally split into 4096-byte blocks,
-	# and processed up to 2048 at a time. However, discard requests to a VDO volume
-	# can be automatically split to a larger size, up to <max discard> 4096-byte blocks
-	# in a single bio, and are limited to 1500 at a time.
-	# Increasing this value may provide better overall performance, at the cost of
-	# increased latency for the individual discard requests.
-	# The default and minimum is 1. The maximum is UINT_MAX / 4096.
-	# This configuration option has an automatic default value.
-	# vdo_max_discard = 1
 }
 
 # Configuration section log.
@@ -784,8 +602,7 @@ log {
 
 	# Configuration option log/indent.
 	# Indent messages according to their severity.
-	# This configuration option has an automatic default value.
-	# indent = 0
+	indent = 1
 
 	# Configuration option log/command_names.
 	# Display the command name on each line of output.
@@ -808,23 +625,9 @@ log {
 	# Select log messages by class.
 	# Some debugging messages are assigned to a class and only appear in
 	# debug output if the class is listed here. Classes currently
-	# available: memory, devices, io, activation, allocation,
+	# available: memory, devices, io, activation, allocation, lvmetad,
 	# metadata, cache, locking, lvmpolld. Use "all" to see everything.
-	debug_classes = [ "memory", "devices", "io", "activation", "allocation", "metadata", "cache", "locking", "lvmpolld", "dbus" ]
-
-	# Configuration option log/debug_file_fields.
-	# The fields included in debug output written to log file.
-	# Use "all" to include everything (the default).
-	# This configuration option is advanced.
-	# This configuration option has an automatic default value.
-	# debug_file_fields = [ "time", "command", "fileline", "message" ]
-
-	# Configuration option log/debug_output_fields.
-	# The fields included in debug output written to stderr.
-	# Use "all" to include everything (the default).
-	# This configuration option is advanced.
-	# This configuration option has an automatic default value.
-	# debug_output_fields = [ "time", "command", "fileline", "message" ]
+	debug_classes = [ "memory", "devices", "io", "activation", "allocation", "lvmetad", "metadata", "cache", "locking", "lvmpolld", "dbus" ]
 }
 
 # Configuration section backup.
@@ -912,6 +715,23 @@ global {
 	# the error messages.
 	activation = 1
 
+	# Configuration option global/fallback_to_lvm1.
+	# This setting is no longer used.
+	# This configuration option has an automatic default value.
+	# fallback_to_lvm1 = 0
+
+	# Configuration option global/format.
+	# This setting is no longer used.
+	# This configuration option has an automatic default value.
+	# format = "lvm2"
+
+	# Configuration option global/format_libraries.
+	# This setting is no longer used.
+	# This configuration option does not have a default value defined.
+
+	# Configuration option global/segment_libraries.
+	# This configuration option does not have a default value defined.
+
 	# Configuration option global/proc.
 	# Location of proc filesystem.
 	# This configuration option is advanced.
@@ -921,10 +741,57 @@ global {
 	# Location of /etc system configuration directory.
 	etc = "@CONFDIR@"
 
+	# Configuration option global/locking_type.
+	# Type of locking to use.
+	# 
+	# Accepted values:
+	#   0
+	#     Turns off locking. Warning: this risks metadata corruption if
+	#     commands run concurrently.
+	#   1
+	#     LVM uses local file-based locking, the standard mode.
+	#   2
+	#     LVM uses the external shared library locking_library.
+	#   3
+	#     LVM uses built-in clustered locking with clvmd.
+	#     This is incompatible with lvmetad. If use_lvmetad is enabled,
+	#     LVM prints a warning and disables lvmetad use.
+	#   4
+	#     LVM uses read-only locking which forbids any operations that
+	#     might change metadata.
+	#   5
+	#     Offers dummy locking for tools that do not need any locks.
+	#     You should not need to set this directly; the tools will select
+	#     when to use it instead of the configured locking_type.
+	#     Do not use lvmetad or the kernel device-mapper driver with this
+	#     locking type. It is used by the --readonly option that offers
+	#     read-only access to Volume Group metadata that cannot be locked
+	#     safely because it belongs to an inaccessible domain and might be
+	#     in use, for example a virtual machine image or a disk that is
+	#     shared by a clustered machine.
+	# 
+	locking_type = 1
+
 	# Configuration option global/wait_for_locks.
 	# When disabled, fail if a lock request would block.
 	wait_for_locks = 1
 
+	# Configuration option global/fallback_to_clustered_locking.
+	# Attempt to use built-in cluster locking if locking_type 2 fails.
+	# If using external locking (type 2) and initialisation fails, with
+	# this enabled, an attempt will be made to use the built-in clustered
+	# locking. Disable this if using a customised locking_library.
+	fallback_to_clustered_locking = 1
+
+	# Configuration option global/fallback_to_local_locking.
+	# Use locking_type 1 (local) if locking_type 2 or 3 fail.
+	# If an attempt to initialise type 2 or type 3 locking failed, perhaps
+	# because cluster components such as clvmd are not running, with this
+	# enabled, an attempt will be made to use local file-based locking
+	# (type 1). If this succeeds, only commands against local VGs will
+	# proceed. VGs marked as clustered will be ignored.
+	fallback_to_local_locking = 1
+
 	# Configuration option global/locking_dir.
 	# Directory to use for LVM command file locks.
 	# Local non-LV directory that holds file-based locks while commands are
@@ -945,6 +812,11 @@ global {
 	# Search this directory first for shared libraries.
 	# This configuration option does not have a default value defined.
 
+	# Configuration option global/locking_library.
+	# The external locking library to use for locking_type 2.
+	# This configuration option has an automatic default value.
+	# locking_library = "liblvm2clusterlock.so"
+
 	# Configuration option global/abort_on_internal_errors.
 	# Abort a command that encounters an internal error.
 	# Treat any internal errors as fatal errors, aborting the process that
@@ -985,17 +857,6 @@ global {
 	# 
 	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!
-	# 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.
 	# The --type raid10|mirror option overrides this setting.
@@ -1044,22 +905,47 @@ global {
 	# This configuration option has an automatic default value.
 	# lvdisplay_shows_full_device_path = 0
 
-	# 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.
-	# 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.
 	# This configuration option has an automatic default value.
 	# use_aio = 1
 
+	# Configuration option global/use_lvmetad.
+	# Use lvmetad to cache metadata and reduce disk scanning.
+	# When enabled (and running), lvmetad provides LVM commands with VG
+	# metadata and PV state. LVM commands then avoid reading this
+	# information from disks which can be slow. When disabled (or not
+	# running), LVM commands fall back to scanning disks to obtain VG
+	# metadata. lvmetad is kept updated via udev rules which must be set
+	# up for LVM to work correctly. (The udev rules should be installed
+	# by default.) Without a proper udev setup, changes in the system's
+	# block device configuration will be unknown to LVM, and ignored
+	# until a manual 'pvscan --cache' is run. If lvmetad was running
+	# while use_lvmetad was disabled, it must be stopped, use_lvmetad
+	# enabled, and then started. When using lvmetad, LV activation is
+	# switched to an automatic, event-based mode. In this mode, LVs are
+	# activated based on incoming udev events that inform lvmetad when
+	# PVs appear on the system. When a VG is complete (all PVs present),
+	# it is auto-activated. The auto_activation_volume_list setting
+	# controls which LVs are auto-activated (all by default.)
+	# When lvmetad is updated (automatically by udev events, or directly
+	# by pvscan --cache), devices/filter is ignored and all devices are
+	# scanned by default. lvmetad always keeps unfiltered information
+	# which is provided to LVM commands. Each LVM command then filters
+	# based on devices/filter. This does not apply to other, non-regexp,
+	# filtering settings: component filters such as multipath and MD
+	# are checked during pvscan --cache. To filter a device and prevent
+	# scanning from the LVM system entirely, including lvmetad, use
+	# devices/global_filter.
+	use_lvmetad = @DEFAULT_USE_LVMETAD@
+
+	# Configuration option global/lvmetad_update_wait_time.
+	# Number of seconds a command will wait for lvmetad update to finish.
+	# After waiting for this period, a command will not use lvmetad, and
+	# will revert to disk scanning.
+	# This configuration option has an automatic default value.
+	# lvmetad_update_wait_time = 10
+
 	# Configuration option global/use_lvmlockd.
 	# Use lvmlockd for locking among hosts using LVM on shared storage.
 	# Applicable only if LVM is compiled with lockd support in which
@@ -1184,17 +1070,6 @@ global {
 	# This configuration option has an automatic default value.
 	# cache_repair_options = [ "" ]
 
-	# Configuration option global/vdo_format_executable.
-	# The full path to the vdoformat command.
-	# LVM uses this command to initial data volume for VDO type logical volume
-	# This configuration option has an automatic default value.
-	# vdo_format_executable = "@VDO_FORMAT_CMD@"
-
-	# Configuration option global/vdo_format_options.
-	# List of options passed added to standard vdoformat command.
-	# This configuration option has an automatic default value.
-	# vdo_format_options = [ "" ]
-
 	# Configuration option global/fsadm_executable.
 	# The full path to the fsadm command.
 	# LVM uses this command to help with lvresize -r operations.
@@ -1297,8 +1172,7 @@ 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.
-	# This configuration option has an automatic default value.
-	# verify_udev_operations = 0
+	verify_udev_operations = 0
 
 	# Configuration option activation/retry_deactivation.
 	# Retry failed LV deactivation.
@@ -1323,27 +1197,23 @@ 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.
-	# This configuration option has an automatic default value.
-	# use_linear_target = 1
+	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.
-	# This configuration option has an automatic default value.
-	# reserved_stack = 64
+	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.
-	# This configuration option has an automatic default value.
-	# reserved_memory = 8192
+	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.
-	# This configuration option has an automatic default value.
-	# process_priority = -18
+	process_priority = -18
 
 	# Configuration option activation/volume_list.
 	# Only LVs selected by this list are activated.
@@ -1460,8 +1330,7 @@ activation {
 	#   auto
 	#     Use default value chosen by kernel.
 	# 
-	# This configuration option has an automatic default value.
-	# readahead = "auto"
+	readahead = "auto"
 
 	# Configuration option activation/raid_fault_policy.
 	# Defines how a device failure in a RAID LV is handled.
@@ -1584,34 +1453,6 @@ activation {
 	# 
 	thin_pool_autoextend_percent = 20
 
-	# Configuration option activation/vdo_pool_autoextend_threshold.
-	# Auto-extend a VDO pool when its usage exceeds this percent.
-	# Setting this to 100 disables automatic extension.
-	# 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
-	# 
-	# 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
-	# 8.4G, it is extended to 14.4G:
-	# This configuration option has an automatic default value.
-	# vdo_pool_autoextend_percent = 20
-
 	# Configuration option activation/mlock_filter.
 	# Do not mlock these memory areas.
 	# While activating devices, I/O to devices being (re)configured is
@@ -1634,8 +1475,7 @@ 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.
-	# This configuration option has an automatic default value.
-	# use_mlockall = 0
+	use_mlockall = 0
 
 	# Configuration option activation/monitoring.
 	# Monitor LVs that are activated.
@@ -1650,8 +1490,7 @@ 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.
-	# This configuration option has an automatic default value.
-	# polling_interval = 15
+	polling_interval = 15
 
 	# Configuration option activation/auto_set_activation_skip.
 	# Set the activation skip flag on new thin snapshot LVs.
@@ -1759,19 +1598,13 @@ activation {
 	# vgmetadatacopies = 0
 
 	# Configuration option metadata/pvmetadatasize.
-	# The default size of the metadata area in units of 512 byte sectors.
-	# The metadata area begins at an offset of the page size from the start
-	# of the device. The first PE is by default at 1 MiB from the start of
-	# the device. The space between these is the default metadata area size.
-	# The actual size of the metadata area may be larger than what is set
-	# here due to default_data_alignment making the first PE a MiB multiple.
-	# The metadata area begins with a 512 byte header and is followed by a
-	# circular buffer used for VG metadata text. The maximum size of the VG
-	# metadata is about half the size of the metadata buffer. VGs with large
-	# numbers of PVs or LVs, or VGs containing complex LV structures, may need
-	# additional space for VG metadata. The --metadatasize option overrides
-	# this setting.
-	# This configuration option does not have a default value defined.
+	# Approximate number of sectors to use for each metadata copy.
+	# VGs with large numbers of PVs or LVs, or VGs containing complex LV
+	# structures, may need additional space for VG metadata. The metadata
+	# areas are treated as circular buffers, so unused space becomes filled
+	# with an archive of the most recent previous versions of the metadata.
+	# This configuration option has an automatic default value.
+	# pvmetadatasize = 255
 
 	# Configuration option metadata/pvmetadataignore.
 	# Ignore metadata areas on a new PV.
@@ -1786,6 +1619,24 @@ activation {
 	# This configuration option is advanced.
 	# This configuration option has an automatic default value.
 	# stripesize = 64
+
+	# Configuration option metadata/dirs.
+	# Directories holding live copies of text format metadata.
+	# These directories must not be on logical volumes!
+	# It's possible to use LVM with a couple of directories here,
+	# preferably on different (non-LV) filesystems, and with no other
+	# on-disk metadata (pvmetadatacopies = 0). Or this can be in addition
+	# to on-disk metadata areas. The feature was originally added to
+	# simplify testing and is not supported under low memory situations -
+	# the machine could lock up. Never edit any files in these directories
+	# by hand unless you are absolutely sure you know what you are doing!
+	# Use the supplied toolset to make changes (e.g. vgcfgrestore).
+	# 
+	# Example
+	# dirs = [ "/etc/lvm/metadata", "/mnt/disk2/lvm/metadata2" ]
+	# 
+	# This configuration option is advanced.
+	# This configuration option does not have a default value defined.
 # }
 
 # Configuration section report.
@@ -2207,8 +2058,7 @@ 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.
-	# This configuration option has an automatic default value.
-	# mirror_library = "libdevmapper-event-lvm2mirror.so"
+	mirror_library = "libdevmapper-event-lvm2mirror.so"
 
 	# Configuration option dmeventd/raid_library.
 	# This configuration option has an automatic default value.
@@ -2219,16 +2069,14 @@ 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.
-	# This configuration option has an automatic default value.
-	# snapshot_library = "libdevmapper-event-lvm2snapshot.so"
+	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.
-	# This configuration option has an automatic default value.
-	# thin_library = "libdevmapper-event-lvm2thin.so"
+	thin_library = "libdevmapper-event-lvm2thin.so"
 
 	# Configuration option dmeventd/thin_command.
 	# The plugin runs command with each 5% increment when thin-pool data volume
@@ -2239,23 +2087,6 @@ dmeventd {
 	# This configuration option has an automatic default value.
 	# thin_command = "lvm lvextend --use-policies"
 
-	# Configuration option dmeventd/vdo_library.
-	# The library dmeventd uses when monitoring a VDO pool device.
-	# libdevmapper-event-lvm2vdo.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.
-	# This configuration option has an automatic default value.
-	# vdo_library = "libdevmapper-event-lvm2vdo.so"
-
-	# Configuration option dmeventd/vdo_command.
-	# The plugin runs command with each 5% increment when VDO pool volume
-	# gets above 50%.
-	# Command which starts with 'lvm ' prefix is internal lvm command.
-	# You can write your own handler to customise behaviour in more details.
-	# User handler is specified with the full path starting with '/'.
-	# This configuration option has an automatic default value.
-	# vdo_command = "lvm lvextend --use-policies"
-
 	# Configuration option dmeventd/executable.
 	# The full path to the dmeventd binary.
 	# This configuration option has an automatic default value.

conf/vdo-small.profile

@@ -1,24 +0,0 @@
-# Demo configuration for 'VDO' using less memory.
-# ~lvmconfig --type full | grep vdo
-
-allocation {
-	vdo_use_compression=1
-	vdo_use_deduplication=1
-	vdo_use_metadata_hints=1
-	vdo_minimum_io_size=4096
-	vdo_block_map_cache_size_mb=128
-	vdo_block_map_period=16380
-	vdo_check_point_frequency=0
-	vdo_use_sparse_index=0
-	vdo_index_memory_size_mb=256
-	vdo_slab_size_mb=2048
-	vdo_ack_threads=1
-	vdo_bio_threads=1
-	vdo_bio_rotation=64
-	vdo_cpu_threads=2
-	vdo_hash_zone_threads=1
-	vdo_logical_threads=1
-	vdo_physical_threads=1
-	vdo_write_policy="auto"
-	vdo_max_discard=1
-}

configure.ac

@@ -30,7 +30,7 @@ AC_CANONICAL_TARGET([])
 AS_IF([test -z "$CFLAGS"], [COPTIMISE_FLAG="-O2"])
 case "$host_os" in
 	linux*)
-		CLDFLAGS="${CLDFLAGS-"$LDFLAGS"} -Wl,--version-script,.export.sym"
+		CLDFLAGS="$CLDFLAGS -Wl,--version-script,.export.sym"
 		# equivalent to -rdynamic
 		ELDFLAGS="-Wl,--export-dynamic"
 		# FIXME Generate list and use --dynamic-list=.dlopen.sym
@@ -39,19 +39,20 @@ case "$host_os" in
 		LDDEPS="$LDDEPS .export.sym"
 		LIB_SUFFIX=so
 		DEVMAPPER=yes
+		BUILD_LVMETAD=no
 		BUILD_LVMPOLLD=no
 		LOCKDSANLOCK=no
 		LOCKDDLM=no
-		LOCKDDLM_CONTROL=no
 		ODIRECT=yes
 		DM_IOCTLS=yes
 		SELINUX=yes
+		CLUSTER=internal
 		FSADM=yes
 		BLKDEACTIVATE=yes
 		;;
 	darwin*)
 		CFLAGS="$CFLAGS -no-cpp-precomp -fno-common"
-		CLDFLAGS="${CLDFLAGS-"$LDFLAGS"}"
+		CLDFLAGS="$CLDFLAGS"
 		ELDFLAGS=
 		CLDWHOLEARCHIVE="-all_load"
 		CLDNOWHOLEARCHIVE=
@@ -60,12 +61,10 @@ case "$host_os" in
 		ODIRECT=no
 		DM_IOCTLS=no
 		SELINUX=no
+		CLUSTER=none
 		FSADM=no
 		BLKDEACTIVATE=no
 		;;
-	*)
-		CLDFLAGS="${CLDFLAGS-"$LDFLAGS"}"
-		;;
 esac
 
 ################################################################################
@@ -143,12 +142,6 @@ AC_TYPE_UINT16_T
 AC_TYPE_UINT32_T
 AC_TYPE_UINT64_T
 AX_GCC_BUILTIN([__builtin_clz])
-AX_GCC_BUILTIN([__builtin_clzll])
-
-
-AC_DEFINE([_GNU_SOURCE], 1, [Define to get access to GNU/Linux extension])
-AC_DEFINE([_REENTRANT], 1, [Define to use re-entrant thread safe versions])
-
 
 ################################################################################
 dnl -- Check for functions
@@ -156,7 +149,6 @@ AC_CHECK_FUNCS([ftruncate gethostname getpagesize gettimeofday localtime_r \
   memchr memset mkdir mkfifo munmap nl_langinfo pselect realpath rmdir setenv \
   setlocale strcasecmp strchr strcspn strdup strerror strncasecmp strndup \
   strrchr strspn strstr strtol strtoul uname], , [AC_MSG_ERROR(bailing out)])
-AC_CHECK_FUNCS([prlimit])
 AC_FUNC_ALLOCA
 AC_FUNC_CLOSEDIR_VOID
 AC_FUNC_CHOWN
@@ -180,15 +172,6 @@ AC_ARG_ENABLE(dependency-tracking,
 	      USE_TRACKING=$enableval, USE_TRACKING=yes)
 AC_MSG_RESULT($USE_TRACKING)
 
-################################################################################
-dnl -- Disable silence rules
-AC_MSG_CHECKING(whether to build silently)
-AC_ARG_ENABLE(silent-rules,
-	      AC_HELP_STRING([--disable-silent-rules], [disable silent building]),
-	      SILENT_RULES=$enableval, SILENT_RULES=yes)
-AC_MSG_RESULT($SILENT_RULES)
-
-
 ################################################################################
 dnl -- Enables statically-linked tools
 AC_MSG_CHECKING(whether to use static linking)
@@ -299,6 +282,22 @@ esac
 AC_MSG_RESULT($MANGLING)
 AC_DEFINE_UNQUOTED([DEFAULT_DM_NAME_MANGLING], $mangling, [Define default name mangling behaviour])
 
+################################################################################
+dnl -- cluster_locking inclusion type
+AC_MSG_CHECKING(whether to include support for cluster locking)
+AC_ARG_WITH(cluster,
+	    AC_HELP_STRING([--with-cluster=TYPE],
+			   [cluster LVM locking support: internal/shared/none [internal]]),
+	    CLUSTER=$withval)
+AC_MSG_RESULT($CLUSTER)
+
+case "$CLUSTER" in
+  none|shared) ;;
+  internal) AC_DEFINE([CLUSTER_LOCKING_INTERNAL], 1,
+		      [Define to 1 to include built-in support for clustered LVM locking.]) ;;
+  *) AC_MSG_ERROR([--with-cluster parameter invalid]) ;;
+esac
+
 ################################################################################
 dnl -- snapshots inclusion type
 AC_MSG_CHECKING(whether to include snapshots)
@@ -601,89 +600,6 @@ AC_DEFINE_UNQUOTED([CACHE_REPAIR_CMD], ["$CACHE_REPAIR_CMD"],
 AC_DEFINE_UNQUOTED([CACHE_RESTORE_CMD], ["$CACHE_RESTORE_CMD"],
 		   [The path to 'cache_restore', if available.])
 
-################################################################################
-dnl -- cache inclusion type
-AC_MSG_CHECKING(whether to include vdo)
-AC_ARG_WITH(vdo,
-	    AC_HELP_STRING([--with-vdo=TYPE],
-			   [vdo support: internal/none [internal]]),
-			   VDO=$withval, VDO="internal")
-
-AC_MSG_RESULT($VDO)
-
-AC_ARG_WITH(vdo-format,
-	    AC_HELP_STRING([--with-vdo-format=PATH],
-			   [vdoformat tool: [autodetect]]),
-			   VDO_FORMAT_CMD=$withval, VDO_FORMAT_CMD="autodetect")
-case "$VDO" in
- 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])
-		if test -z "$VDO_FORMAT_CMD"; then
-			AC_MSG_WARN([vdoformat not found in path $PATH])
-			VDO_FORMAT_CMD=/usr/bin/vdoformat
-			VDO_CONFIGURE_WARN=y
-		fi
-	fi
-	;;
- *) AC_MSG_ERROR([--with-vdo parameter invalid]) ;;
-esac
-
-AC_DEFINE_UNQUOTED([VDO_FORMAT_CMD], ["$VDO_FORMAT_CMD"],
-		   [The path to 'vdoformat', if available.])
-#
-# Do we need to use the API??
-# Do we want to link lvm2 with a big library for vdoformating ?
-#
-#AC_ARG_WITH(vdo-include,
-#	    AC_HELP_STRING([--with-vdo-include=PATH],
-#			   [vdo support: Path to utils headers: [/usr/include/vdo/utils]]),
-#			   VDO_INCLUDE=$withval, VDO_INCLUDE="/usr/include/vdo/utils")
-#AC_MSG_RESULT($VDO_INCLUDE)
-#
-#AC_ARG_WITH(vdo-lib,
-#            AC_HELP_STRING([--with-vdo-lib=PATH],
-#                           [vdo support: Path to utils lib: [/usr/lib]]),
-#                           VDO_LIB=$withval, VDO_LIB="/usr/lib") 
-#AC_MSG_RESULT($VDO_LIB)
-
-################################################################################
-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 [internal]]),
-			   WRITECACHE=$withval, WRITECACHE="internal")
-
-AC_MSG_RESULT($WRITECACHE)
-
-case "$WRITECACHE" in
- none) ;;
- internal) 
-	AC_DEFINE([WRITECACHE_INTERNAL], 1, [Define to 1 to include built-in support for writecache.])
-	;;
- *) AC_MSG_ERROR([--with-writecache parameter invalid]) ;;
-esac
-
-################################################################################
-dnl -- integrity inclusion type
-AC_MSG_CHECKING(whether to include integrity)
-AC_ARG_WITH(integrity,
-	    AC_HELP_STRING([--with-integrity=TYPE],
-			   [integrity support: internal/none [internal]]),
-			   INTEGRITY=$withval, INTEGRITY="internal")
-
-AC_MSG_RESULT($INTEGRITY)
-
-case "$INTEGRITY" in
- none) ;;
- internal)
-	AC_DEFINE([INTEGRITY_INTERNAL], 1, [Define to 1 to include built-in support for integrity.])
-	;;
- *) AC_MSG_ERROR([--with-integrity parameter invalid]) ;;
-esac
 
 ################################################################################
 dnl -- Disable readline
@@ -691,12 +607,6 @@ 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=$enableval, EDITLINE=no)
-
 ################################################################################
 dnl -- Disable realtime clock support
 AC_MSG_CHECKING(whether to enable realtime support)
@@ -740,7 +650,7 @@ dnl -- Set up pidfile and run directory
 AH_TEMPLATE(DEFAULT_PID_DIR)
 AC_ARG_WITH(default-pid-dir,
 	    AC_HELP_STRING([--with-default-pid-dir=PID_DIR],
-			   [default directory to keep PID files in [autodetect]]),
+			   [Default directory to keep PID files in. [autodetect]]),
 	    DEFAULT_PID_DIR="$withval", DEFAULT_PID_DIR=$RUN_DIR)
 AC_DEFINE_UNQUOTED(DEFAULT_PID_DIR, ["$DEFAULT_PID_DIR"],
 		   [Default directory to keep PID files in.])
@@ -748,7 +658,7 @@ 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.])
@@ -756,11 +666,246 @@ 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.])
 
+################################################################################
+dnl -- Build cluster LVM daemon
+AC_MSG_CHECKING(whether to build cluster LVM daemon)
+AC_ARG_WITH(clvmd,
+  [  --with-clvmd=TYPE       build cluster LVM Daemon
+                          The following cluster manager combinations are valid:
+                           * cman                  (RHEL5 or equivalent)
+                           * cman,corosync,openais (or selection of them)
+                           * singlenode            (localhost only)
+                           * all                   (autodetect)
+                           * none                  (disable build)
+                          [[none]]],
+	    CLVMD=$withval, CLVMD=none)
+test "$CLVMD" = yes && CLVMD=all
+AC_MSG_RESULT($CLVMD)
+
+dnl -- If clvmd enabled without cluster locking, automagically include it
+test "$CLVMD" != none -a "$CLUSTER" = none && CLUSTER=internal
+
+dnl -- init pkgconfig if required
+test "$CLVMD" != none && pkg_config_init
+
+dnl -- Express clvmd init script Required-Start / Required-Stop
+CLVMD_CMANAGERS=""
+dnl -- On RHEL4/RHEL5, qdiskd is started from a separate init script.
+dnl -- Enable if we are build for cman.
+CLVMD_NEEDS_QDISKD=no
+
+dnl -- define build types
+if [[ `expr x"$CLVMD" : '.*gulm.*'` != 0 ]]; then
+	AC_MSG_ERROR([Since version 2.02.87 GULM locking is no longer supported.]);
+fi
+if [[ `expr x"$CLVMD" : '.*cman.*'` != 0 ]]; then
+	BUILDCMAN=yes
+	CLVMD_CMANAGERS="$CLVMD_CMANAGERS cman"
+	CLVMD_NEEDS_QDISKD=yes
+fi
+if [[ `expr x"$CLVMD" : '.*corosync.*'` != 0 ]]; then
+	BUILDCOROSYNC=yes
+	CLVMD_CMANAGERS="$CLVMD_CMANAGERS corosync"
+fi
+if [[ `expr x"$CLVMD" : '.*openais.*'` != 0 ]]; then
+	BUILDOPENAIS=yes
+	CLVMD_CMANAGERS="$CLVMD_CMANAGERS openais"
+fi
+test "$CLVMD_NEEDS_QDISKD" != no && CLVMD_CMANAGERS="$CLVMD_CMANAGERS qdiskd"
+
+dnl -- define a soft bailout if we are autodetecting
+soft_bailout() {
+	NOTFOUND=1
+}
+
+hard_bailout() {
+	AC_MSG_ERROR([bailing out])
+}
+
+dnl -- if clvmd=all then set soft_bailout (we do not want to error)
+dnl -- and set all builds to yes. We need to do this here
+dnl -- to skip the openais|corosync sanity check above.
+if test "$CLVMD" = all; then
+	bailout=soft_bailout
+	BUILDCMAN=yes
+	BUILDCOROSYNC=yes
+	BUILDOPENAIS=yes
+else
+	bailout=hard_bailout
+fi
+
+dnl -- helper macro to check libs without adding them to LIBS
+check_lib_no_libs() {
+	lib_no_libs_arg1=$1
+	shift
+	lib_no_libs_arg2=$1
+	shift
+	lib_no_libs_args=$@
+	AC_CHECK_LIB([$lib_no_libs_arg1],
+		     [$lib_no_libs_arg2],,
+		     [$bailout],
+		     [$lib_no_libs_args])
+	LIBS=$ac_check_lib_save_LIBS
+}
+
+dnl -- Look for cman libraries if required.
+if test "$BUILDCMAN" = yes; then
+	PKG_CHECK_MODULES(CMAN, libcman, [HAVE_CMAN=yes],
+		[NOTFOUND=0
+		AC_CHECK_HEADERS(libcman.h,,$bailout)
+		check_lib_no_libs cman cman_init
+		if test $NOTFOUND = 0; then
+			AC_MSG_RESULT([no pkg for libcman, using -lcman])
+			CMAN_LIBS="-lcman"
+			HAVE_CMAN=yes
+		fi])
+	CHECKCONFDB=yes
+	CHECKDLM=yes
+fi
+
+dnl -- Look for corosync that is required also for openais build
+dnl -- only enough recent version of corosync ship pkg-config files.
+dnl -- We can safely rely on that to detect the correct bits.
+if test "$BUILDCOROSYNC" = yes -o "$BUILDOPENAIS" = yes; then
+	PKG_CHECK_MODULES(COROSYNC, corosync, [HAVE_COROSYNC=yes], $bailout)
+	CHECKCONFDB=yes
+	CHECKCMAP=yes
+fi
+
+dnl -- Look for corosync libraries if required.
+if test "$BUILDCOROSYNC" = yes; then
+	PKG_CHECK_MODULES(QUORUM, libquorum, [HAVE_QUORUM=yes], $bailout)
+	CHECKCPG=yes
+	CHECKDLM=yes
+fi
+
+dnl -- Look for openais libraries if required.
+if test "$BUILDOPENAIS" = yes; then
+	PKG_CHECK_MODULES(SALCK, libSaLck, [HAVE_SALCK=yes], $bailout)
+	CHECKCPG=yes
+fi
+
+dnl -- Below are checks for libraries common to more than one build.
+
+dnl -- Check confdb library.
+dnl -- mandatory for corosync < 2.0 build.
+dnl -- optional for openais/cman build.
+
+if test "$CHECKCONFDB" = yes; then
+	PKG_CHECK_MODULES(CONFDB, libconfdb,
+			  [HAVE_CONFDB=yes], [HAVE_CONFDB=no])
+
+	AC_CHECK_HEADERS([corosync/confdb.h],
+			 [HAVE_CONFDB_H=yes], [HAVE_CONFDB_H=no])
+
+	if test "$HAVE_CONFDB" != yes -a "$HAVE_CONFDB_H" = yes; then
+		check_lib_no_libs confdb confdb_initialize
+		AC_MSG_RESULT([no pkg for confdb, using -lconfdb])
+		CONFDB_LIBS="-lconfdb"
+		HAVE_CONFDB=yes
+	fi
+fi
+
+dnl -- Check cmap library
+dnl -- mandatory for corosync >= 2.0 build.
+
+if test "$CHECKCMAP" = yes; then
+	PKG_CHECK_MODULES(CMAP, libcmap,
+			  [HAVE_CMAP=yes], [HAVE_CMAP=no])
+
+	AC_CHECK_HEADERS([corosync/cmap.h],
+			 [HAVE_CMAP_H=yes], [HAVE_CMAP_H=no])
+
+	if test "$HAVE_CMAP" != yes -a "$HAVE_CMAP_H" = yes; then
+		check_lib_no_libs cmap cmap_initialize
+		AC_MSG_RESULT([no pkg for cmap, using -lcmap])
+		CMAP_LIBS="-lcmap"
+		HAVE_CMAP=yes
+	fi
+fi
+
+if test "$BUILDCOROSYNC" = yes -a \
+	"$HAVE_CMAP" != yes -a "$HAVE_CONFDB" != yes -a "$CLVMD" != all; then
+	AC_MSG_ERROR([bailing out... cmap (corosync >= 2.0) or confdb (corosync < 2.0) library is required])
+fi
+
+dnl -- Check cpg library.
+if test "$CHECKCPG" = yes; then
+	PKG_CHECK_MODULES(CPG, libcpg, [HAVE_CPG=yes], [$bailout])
+fi
+
+dnl -- Check dlm library.
+if test "$CHECKDLM" = yes; then
+	PKG_CHECK_MODULES(DLM, libdlm, [HAVE_DLM=yes],
+		[NOTFOUND=0
+		AC_CHECK_HEADERS(libdlm.h,,[$bailout])
+		check_lib_no_libs dlm dlm_lock -lpthread
+		if test $NOTFOUND = 0; then
+			AC_MSG_RESULT([no pkg for libdlm, using -ldlm])
+			DLM_LIBS="-ldlm -lpthread"
+			HAVE_DLM=yes
+		fi])
+fi
+
+dnl -- If we are autodetecting, we need to re-create
+dnl -- the depedencies checks and set a proper CLVMD,
+dnl -- together with init script Required-Start/Stop entries.
+if test "$CLVMD" = all; then
+	CLVMD=none
+	CLVMD_CMANAGERS=""
+	CLVMD_NEEDS_QDISKD=no
+	if test "$HAVE_CMAN" = yes -a \
+		"$HAVE_DLM" = yes; then
+		AC_MSG_RESULT([Enabling clvmd cman cluster manager])
+		CLVMD="$CLVMD,cman"
+		CLVMD_CMANAGERS="$CLVMD_CMANAGERS cman"
+		CLVMD_NEEDS_QDISKD=yes
+	fi
+	if test "$HAVE_COROSYNC" = yes -a \
+		"$HAVE_QUORUM" = yes -a \
+		"$HAVE_CPG" = yes -a \
+		"$HAVE_DLM" = yes; then
+	   if test "$HAVE_CONFDB" = yes -o "$HAVE_CMAP" = yes; then
+		AC_MSG_RESULT([Enabling clvmd corosync cluster manager])
+		CLVMD="$CLVMD,corosync"
+		CLVMD_CMANAGERS="$CLVMD_CMANAGERS corosync"
+	   fi
+	fi
+	if test "$HAVE_COROSYNC" = yes -a \
+		"$HAVE_CPG" = yes -a \
+		"$HAVE_SALCK" = yes; then
+		AC_MSG_RESULT([Enabling clvmd openais cluster manager])
+		CLVMD="$CLVMD,openais"
+		CLVMD_CMANAGERS="$CLVMD_CMANAGERS openais"
+	fi
+	test "$CLVMD_NEEDS_QDISKD" != no && CLVMD_CMANAGERS="$CLVMD_CMANAGERS qdiskd"
+	test "$CLVMD" = none && AC_MSG_RESULT([Disabling clvmd build. No cluster manager detected.])
+fi
+
+dnl -- Fixup CLVMD_CMANAGERS with new corosync
+dnl -- clvmd built with corosync >= 2.0 needs dlm (either init or systemd service)
+dnl -- to be started.
+if [[ `expr x"$CLVMD" : '.*corosync.*'` != 0 ]]; then
+   test "$HAVE_CMAP" = yes && CLVMD_CMANAGERS="$CLVMD_CMANAGERS dlm"
+fi
+
+################################################################################
+dnl -- clvmd pidfile
+if test "$CLVMD" != none; then
+	AC_ARG_WITH(clvmd-pidfile,
+		    AC_HELP_STRING([--with-clvmd-pidfile=PATH],
+				   [clvmd pidfile [PID_DIR/clvmd.pid]]),
+		    CLVMD_PIDFILE=$withval,
+		    CLVMD_PIDFILE="$DEFAULT_PID_DIR/clvmd.pid")
+	AC_DEFINE_UNQUOTED(CLVMD_PIDFILE, ["$CLVMD_PIDFILE"],
+			   [Path to clvmd pidfile.])
+fi
+
 ################################################################################
 dnl -- Build cluster mirror log daemon
 AC_MSG_CHECKING(whether to build cluster mirror log daemon)
@@ -789,6 +934,11 @@ dnl -- Look for corosync libraries if required.
 if [[ "$BUILD_CMIRRORD" = yes ]]; then
 	pkg_config_init
 
+	AC_DEFINE([CMIRROR_HAS_CHECKPOINT], 1, [Define to 1 to include libSaCkpt.])
+	PKG_CHECK_MODULES(SACKPT, libSaCkpt, [HAVE_SACKPT=yes],
+		[AC_MSG_RESULT([no libSaCkpt, compiling without it])
+		AC_DEFINE([CMIRROR_HAS_CHECKPOINT], 0, [Define to 0 to exclude libSaCkpt.])])
+
 	if test "$HAVE_CPG" != yes; then
 		PKG_CHECK_MODULES(CPG, libcpg)
 	fi
@@ -894,6 +1044,16 @@ if test "$DEVMAPPER" = yes; then
 	AC_DEFINE([DEVMAPPER_SUPPORT], 1, [Define to 1 to enable LVM2 device-mapper interaction.])
 fi
 
+################################################################################
+dnl -- Build lvmetad
+AC_MSG_CHECKING(whether to build LVMetaD)
+AC_ARG_ENABLE(lvmetad,
+	      AC_HELP_STRING([--enable-lvmetad],
+			     [enable the LVM Metadata Daemon]),
+	      LVMETAD=$enableval)
+test -n "$LVMETAD" && BUILD_LVMETAD=$LVMETAD
+AC_MSG_RESULT($BUILD_LVMETAD)
+
 ################################################################################
 dnl -- Build lvmpolld
 AC_MSG_CHECKING(whether to build lvmpolld)
@@ -942,24 +1102,6 @@ if test "$BUILD_LOCKDDLM" = yes; then
 	BUILD_LVMLOCKD=yes
 fi
 
-################################################################################
-dnl -- Build lvmlockddlmcontrol
-AC_MSG_CHECKING(whether to build lvmlockddlmcontrol)
-AC_ARG_ENABLE(lvmlockd-dlmcontrol,
-	      AC_HELP_STRING([--enable-lvmlockd-dlmcontrol],
-			     [enable lvmlockd remote refresh using libdlmcontrol]),
-	      LOCKDDLM_CONTROL=$enableval)
-AC_MSG_RESULT($LOCKDDLM_CONTROL)
-
-BUILD_LOCKDDLM_CONTROL=$LOCKDDLM_CONTROL
-
-dnl -- Look for libdlmcontrol libraries
-if test "$BUILD_LOCKDDLM_CONTROL" = yes; then
-	PKG_CHECK_MODULES(LOCKD_DLM_CONTROL, libdlmcontrol >= 3.2, [HAVE_LOCKD_DLM_CONTROL=yes], $bailout)
-	AC_DEFINE([LOCKDDLM_CONTROL_SUPPORT], 1, [Define to 1 to include code that uses lvmlockd dlm control option.])
-	BUILD_LVMLOCKD=yes
-fi
-
 ################################################################################
 dnl -- Build lvmlockd
 AC_MSG_CHECKING(whether to build lvmlockd)
@@ -967,7 +1109,9 @@ AC_MSG_RESULT($BUILD_LVMLOCKD)
 
 if test "$BUILD_LVMLOCKD" = yes; then
 	AS_IF([test "$LVMPOLLD" = no], [AC_MSG_ERROR([cannot build lvmlockd with --disable-lvmpolld.])])
+	AS_IF([test "$LVMETAD" = no], [AC_MSG_ERROR([cannot build lvmlockd with --disable-lvmetad.])])
 	AS_IF([test "$BUILD_LVMPOLLD" = no], [BUILD_LVMPOLLD=yes; AC_MSG_WARN([Enabling lvmpolld - required by lvmlockd.])])
+	AS_IF([test "$BUILD_LVMETAD" = no], [BUILD_LVMETAD=yes; AC_MSG_WARN([Enabling lvmetad - required by lvmlockd.])])
 	AC_MSG_CHECKING([defaults for use_lvmlockd])
 	AC_ARG_ENABLE(use_lvmlockd,
 		      AC_HELP_STRING([--disable-use-lvmlockd],
@@ -992,6 +1136,33 @@ fi
 AC_DEFINE_UNQUOTED(DEFAULT_USE_LVMLOCKD, [$DEFAULT_USE_LVMLOCKD],
 		   [Use lvmlockd by default.])
 
+################################################################################
+dnl -- Check lvmetad
+if test "$BUILD_LVMETAD" = yes; then
+	AC_MSG_CHECKING([defaults for use_lvmetad])
+	AC_ARG_ENABLE(use_lvmetad,
+		      AC_HELP_STRING([--disable-use-lvmetad],
+				     [disable usage of LVM Metadata Daemon]),
+		      [case ${enableval} in
+		       yes) DEFAULT_USE_LVMETAD=1 ;;
+		       *) DEFAULT_USE_LVMETAD=0 ;;
+		       esac], DEFAULT_USE_LVMETAD=1)
+	AC_MSG_RESULT($DEFAULT_USE_LVMETAD)
+	AC_DEFINE([LVMETAD_SUPPORT], 1, [Define to 1 to include code that uses lvmetad.])
+
+	AC_ARG_WITH(lvmetad-pidfile,
+		    AC_HELP_STRING([--with-lvmetad-pidfile=PATH],
+				   [lvmetad pidfile [PID_DIR/lvmetad.pid]]),
+		    LVMETAD_PIDFILE=$withval,
+		    LVMETAD_PIDFILE="$DEFAULT_PID_DIR/lvmetad.pid")
+	AC_DEFINE_UNQUOTED(LVMETAD_PIDFILE, ["$LVMETAD_PIDFILE"],
+			   [Path to lvmetad pidfile.])
+else
+	DEFAULT_USE_LVMETAD=0
+fi
+AC_DEFINE_UNQUOTED(DEFAULT_USE_LVMETAD, [$DEFAULT_USE_LVMETAD],
+		   [Use lvmetad by default.])
+
 ################################################################################
 dnl -- Check lvmpolld
 if test "$BUILD_LVMPOLLD" = yes; then
@@ -1195,6 +1366,20 @@ if test "$ODIRECT" = yes; then
 	AC_DEFINE([O_DIRECT_SUPPORT], 1, [Define to 1 to enable O_DIRECT support.])
 fi
 
+################################################################################
+dnl -- Enable liblvm2app.so
+AC_MSG_CHECKING(whether to build liblvm2app.so application library)
+AC_ARG_ENABLE(applib,
+	      AC_HELP_STRING([--enable-applib], [build application library]),
+	      APPLIB=$enableval, APPLIB=no)
+AC_MSG_RESULT($APPLIB)
+AC_SUBST([LVM2APP_LIB])
+test "$APPLIB" = yes \
+  && LVM2APP_LIB=-llvm2app \
+  || LVM2APP_LIB=
+AS_IF([test "$APPLIB"],
+      [AC_MSG_WARN([liblvm2app is deprecated. Use D-Bus API])])
+
 ################################################################################
 dnl -- Enable cmdlib
 AC_MSG_CHECKING(whether to compile liblvm2cmd.so)
@@ -1218,15 +1403,48 @@ AS_IF([test "$NOTIFYDBUS_SUPPORT" = yes && test "BUILD_LVMDBUSD" = yes],
       [AC_MSG_WARN([Building D-Bus support without D-Bus notifications.])])
 
 ################################################################################
-dnl -- Enable Python dbus library
+dnl -- Enable Python liblvm2app bindings
+AC_MSG_CHECKING(whether to build Python wrapper for liblvm2app.so)
+AC_ARG_ENABLE(python_bindings,
+	      AC_HELP_STRING([--enable-python_bindings], [build default Python applib bindings]),
+	      PYTHON_BINDINGS=$enableval, PYTHON_BINDINGS=no)
+AC_MSG_RESULT($PYTHON_BINDINGS)
 
-if test "$BUILD_LVMDBUSD" = yes; then
+AC_MSG_CHECKING(whether to build Python2 wrapper for liblvm2app.so)
+AC_ARG_ENABLE(python2_bindings,
+	      AC_HELP_STRING([--enable-python2_bindings], [build Python2 applib bindings]),
+	      PYTHON2_BINDINGS=$enableval, PYTHON2_BINDINGS=no)
+AC_MSG_RESULT($PYTHON2_BINDINGS)
+
+
+AC_MSG_CHECKING(whether to build Python3 wrapper for liblvm2app.so)
+AC_ARG_ENABLE(python3_bindings,
+	      AC_HELP_STRING([--enable-python3_bindings], [build Python3 applib bindings]),
+	      PYTHON3_BINDINGS=$enableval, PYTHON3_BINDINGS=no)
+AC_MSG_RESULT($PYTHON3_BINDINGS)
+
+if test "$PYTHON_BINDINGS" = yes; then
+	AC_MSG_ERROR([--enable-python-bindings is replaced by --enable-python2-bindings and --enable-python3-bindings])
+fi
+
+if test "$PYTHON2_BINDINGS" = yes; then
+	AM_PATH_PYTHON([2])
+	AC_PATH_TOOL(PYTHON2, python2)
+	test -z "$PYTHON2" && AC_MSG_ERROR([python2 is required for --enable-python2_bindings but cannot be found])
+	AC_PATH_TOOL(PYTHON2_CONFIG, python2-config)
+	test -z "$PYTHON2_CONFIG" && AC_PATH_TOOL(PYTHON2_CONFIG, python-config)
+	test -z "$PYTHON2_CONFIG" && AC_MSG_ERROR([python headers are required for --enable-python2_bindings but cannot be found])
+	PYTHON2_INCDIRS=`"$PYTHON2_CONFIG" --includes`
+	PYTHON2_LIBDIRS=`"$PYTHON2_CONFIG" --libs`
+	PYTHON2DIR=$pythondir
+	PYTHON_BINDINGS=yes
+fi
+	
+if test "$PYTHON3_BINDINGS" = yes -o "$BUILD_LVMDBUSD" = yes; then
+	unset PYTHON PYTHON_CONFIG
 	unset am_cv_pathless_PYTHON ac_cv_path_PYTHON am_cv_python_platform
 	unset am_cv_python_pythondir am_cv_python_version am_cv_python_pyexecdir
 	unset ac_cv_path_PYTHON_CONFIG ac_cv_path_ac_pt_PYTHON_CONFIG
-	m4_define_default([_AM_PYTHON_INTERPRETER_LIST],[ python3 python2 python dnl
-	python3.9 python3.8 python3.7 python3.6 python3.5 python3.4 python3.3 python3.2 python3.1 python3.0 dnl
-	python2.7 python2.6 python2.5 python2.4 python2.3 python2.2 python2.1 python2.0 ])
 	AM_PATH_PYTHON([3])
 	PYTHON3=$PYTHON
 	test -z "$PYTHON3" && AC_MSG_ERROR([python3 is required for --enable-python3_bindings or --enable-dbus-service but cannot be found])
@@ -1236,12 +1454,19 @@ if test "$BUILD_LVMDBUSD" = yes; then
 	PYTHON3_LIBDIRS=`"$PYTHON3_CONFIG" --libs`
 	PYTHON3DIR=$pythondir
 	test "$PYTHON3_BINDINGS" = yes && PYTHON_BINDINGS=yes
+fi
 
+if test "$BUILD_LVMDBUSD" = yes; then
 	# To get this macro, install autoconf-archive package then run autoreconf
 	AC_PYTHON_MODULE([pyudev], [Required], python3)
 	AC_PYTHON_MODULE([dbus], [Required], python3)
 fi
 
+if test "$PYTHON_BINDINGS" = yes -o "$PYTHON2_BINDINGS" = yes -o "$PYTHON3_BINDINGS" = yes; then
+	AC_MSG_WARN([Python bindings are deprecated. Use D-Bus API])
+	test "$APPLIB" != yes && AC_MSG_ERROR([Python_bindings require --enable-applib])
+fi
+
 ################################################################################
 dnl -- Enable pkg-config
 AC_ARG_ENABLE(pkgconfig,
@@ -1313,7 +1538,7 @@ AC_CHECK_LIB(dl, dlopen,
 
 ################################################################################
 dnl -- Check for shared/static conflicts
-if [[ \( "$LVM1" = shared -o "$POOL" = shared \
+if [[ \( "$LVM1" = shared -o "$POOL" = shared -o "$CLUSTER" = shared \
       \) -a "$STATIC_LINK" = yes ]]; then
 	AC_MSG_ERROR([Features cannot be 'shared' when building statically])
 fi
@@ -1354,33 +1579,6 @@ if test "$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=
@@ -1414,16 +1612,6 @@ AC_IF_YES(ac_cv_stat_st_ctim,
 dnl -- Check for getopt
 AC_CHECK_HEADERS(getopt.h, AC_DEFINE([HAVE_GETOPTLONG], 1, [Define to 1 if getopt_long is available.]))
 
-################################################################################
-dnl -- Check for editline
-if test "$EDITLINE" == yes; then
-	PKG_CHECK_MODULES([EDITLINE], [libedit], [
-		AC_DEFINE([EDITLINE_SUPPORT], 1,
-			[Define to 1 to include the LVM editline shell.])], AC_MSG_ERROR(
-[libedit could not be found which is required for the --enable-readline option.])
-	)
-fi
-
 ################################################################################
 dnl -- Check for readline (Shamelessly copied from parted 1.4.17)
 if test "$READLINE" != no; then
@@ -1556,12 +1744,6 @@ fi
 AC_MSG_CHECKING(whether to enable readline)
 AC_MSG_RESULT($READLINE)
 
-if test "$EDITLINE" = yes; then
-	AC_CHECK_HEADERS(editline/readline.h editline/history.h,,hard_bailout)
-fi
-AC_MSG_CHECKING(whether to enable editline)
-AC_MSG_RESULT($EDITLINE)
-
 if test "$BUILD_CMIRRORD" = yes; then
 	AC_CHECK_FUNCS(atexit,,hard_bailout)
 fi
@@ -1576,6 +1758,18 @@ if test "$BUILD_LVMPOLLD" = yes; then
 	AC_FUNC_STRERROR_R
 fi
 
+if test "$CLVMD" != none; then
+	AC_CHECK_HEADERS(mntent.h netdb.h netinet/in.h pthread.h search.h sys/mount.h sys/socket.h sys/uio.h sys/un.h utmpx.h,,AC_MSG_ERROR(bailing out))
+	AC_CHECK_FUNCS(dup2 getmntent memmove select socket,,hard_bailout)
+	AC_FUNC_GETMNTENT
+	AC_FUNC_SELECT_ARGTYPES
+fi
+
+if test "$CLUSTER" != none; then
+	AC_CHECK_HEADERS(sys/socket.h sys/un.h,,hard_bailout)
+	AC_CHECK_FUNCS(socket,,hard_bailout)
+fi
+
 if test "$BUILD_DMEVENTD" = yes; then
 	AC_CHECK_HEADERS(arpa/inet.h,,hard_bailout)
 fi
@@ -1609,10 +1803,9 @@ SBINDIR="$(eval echo $(eval echo $sbindir))"
 LVM_PATH="$SBINDIR/lvm"
 AC_DEFINE_UNQUOTED(LVM_PATH, ["$LVM_PATH"], [Path to lvm binary.])
 
-LVMCONFIG_PATH="$SBINDIR/lvmconfig"
-AC_DEFINE_UNQUOTED(LVMCONFIG_PATH, ["$LVMCONFIG_PATH"], [Path to lvmconfig binary.])
-
 USRSBINDIR="$(eval echo $(eval echo $usrsbindir))"
+CLVMD_PATH="$USRSBINDIR/clvmd"
+AC_DEFINE_UNQUOTED(CLVMD_PATH, ["$CLVMD_PATH"], [Path to clvmd binary.])
 
 FSADM_PATH="$SBINDIR/fsadm"
 AC_DEFINE_UNQUOTED(FSADM_PATH, ["$FSADM_PATH"], [Path to fsadm binary.])
@@ -1692,6 +1885,15 @@ AC_ARG_WITH(default-locking-dir,
 AC_DEFINE_UNQUOTED(DEFAULT_LOCK_DIR, ["$DEFAULT_LOCK_DIR"],
 		   [Name of default locking directory.])
 
+################################################################################
+dnl -- Setup default data alignment
+AC_ARG_WITH(default-data-alignment,
+	    AC_HELP_STRING([--with-default-data-alignment=NUM],
+			   [set the default data alignment in MiB [1]]),
+	    DEFAULT_DATA_ALIGNMENT=$withval, DEFAULT_DATA_ALIGNMENT=1)
+AC_DEFINE_UNQUOTED(DEFAULT_DATA_ALIGNMENT, [$DEFAULT_DATA_ALIGNMENT],
+		   [Default data alignment.])
+
 ################################################################################
 dnl -- which kernel interface to use (ioctl only)
 AC_MSG_CHECKING(for kernel interface choice)
@@ -1723,16 +1925,17 @@ LVM_LIBAPI=`echo "$VER" | $AWK -F '[[()]]' '{print $2}'`
 AC_DEFINE_UNQUOTED(LVM_CONFIGURE_LINE, "$CONFIGURE_LINE", [configure command line used])
 
 ################################################################################
+AC_SUBST(APPLIB)
 AC_SUBST(AWK)
 AC_SUBST(BLKID_PC)
 AC_SUBST(BUILD_CMIRRORD)
 AC_SUBST(BUILD_DMEVENTD)
 AC_SUBST(BUILD_LVMDBUSD)
+AC_SUBST(BUILD_LVMETAD)
 AC_SUBST(BUILD_LVMPOLLD)
 AC_SUBST(BUILD_LVMLOCKD)
 AC_SUBST(BUILD_LOCKDSANLOCK)
 AC_SUBST(BUILD_LOCKDDLM)
-AC_SUBST(BUILD_LOCKDDLM_CONTROL)
 AC_SUBST(BUILD_DMFILEMAPD)
 AC_SUBST(CACHE)
 AC_SUBST(CFLAGS)
@@ -1741,6 +1944,14 @@ AC_SUBST(CHMOD)
 AC_SUBST(CLDFLAGS)
 AC_SUBST(CLDNOWHOLEARCHIVE)
 AC_SUBST(CLDWHOLEARCHIVE)
+AC_SUBST(CLUSTER)
+AC_SUBST(CLVMD)
+AC_SUBST(CLVMD_CMANAGERS)
+AC_SUBST(CLVMD_PATH)
+AC_SUBST(CMAN_CFLAGS)
+AC_SUBST(CMAN_LIBS)
+AC_SUBST(CMAP_CFLAGS)
+AC_SUBST(CMAP_LIBS)
 AC_SUBST(CMDLIB)
 AC_SUBST(CONFDB_CFLAGS)
 AC_SUBST(CONFDB_LIBS)
@@ -1753,6 +1964,7 @@ AC_SUBST(DEBUG)
 AC_SUBST(DEFAULT_ARCHIVE_SUBDIR)
 AC_SUBST(DEFAULT_BACKUP_SUBDIR)
 AC_SUBST(DEFAULT_CACHE_SUBDIR)
+AC_SUBST(DEFAULT_DATA_ALIGNMENT)
 AC_SUBST(DEFAULT_DM_RUN_DIR)
 AC_SUBST(DEFAULT_LOCK_DIR)
 AC_SUBST(DEFAULT_MIRROR_SEGTYPE)
@@ -1764,6 +1976,7 @@ AC_SUBST(DEFAULT_SPARSE_SEGTYPE)
 AC_SUBST(DEFAULT_SYS_DIR)
 AC_SUBST(DEFAULT_SYS_LOCK_DIR)
 AC_SUBST(DEFAULT_USE_BLKID_WIPING)
+AC_SUBST(DEFAULT_USE_LVMETAD)
 AC_SUBST(DEFAULT_USE_LVMPOLLD)
 AC_SUBST(DEFAULT_USE_LVMLOCKD)
 AC_SUBST(DEVMAPPER)
@@ -1817,7 +2030,6 @@ 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)
@@ -1848,17 +2060,14 @@ AC_SUBST(UDEV_SYSTEMD_BACKGROUND_JOBS)
 AC_SUBST(UDEV_RULE_EXEC_DETECTION)
 AC_SUBST(UDEV_HAS_BUILTIN_BLKID)
 AC_SUBST(USE_TRACKING)
-AC_SUBST(SILENT_RULES)
 AC_SUBST(USRSBINDIR)
 AC_SUBST(VALGRIND_POOL)
-AC_SUBST(VDO)
-AC_SUBST(VDO_FORMAT_CMD)
-AC_SUBST(VDO_INCLUDE)
-AC_SUBST(VDO_LIB)
 AC_SUBST(WRITE_INSTALL)
 AC_SUBST(DMEVENTD_PIDFILE)
+AC_SUBST(LVMETAD_PIDFILE)
 AC_SUBST(LVMPOLLD_PIDFILE)
 AC_SUBST(LVMLOCKD_PIDFILE)
+AC_SUBST(CLVMD_PIDFILE)
 AC_SUBST(CMIRRORD_PIDFILE)
 AC_SUBST(interface)
 AC_SUBST(kerneldir)
@@ -1879,8 +2088,8 @@ dnl -- keep utility scripts running properly
 AC_CONFIG_FILES([
 Makefile
 make.tmpl
-libdm/make.tmpl
 daemons/Makefile
+daemons/clvmd/Makefile
 daemons/cmirrord/Makefile
 daemons/dmeventd/Makefile
 daemons/dmeventd/libdevmapper-event.pc
@@ -1891,50 +2100,68 @@ daemons/dmeventd/plugins/mirror/Makefile
 daemons/dmeventd/plugins/snapshot/Makefile
 daemons/dmeventd/plugins/thin/Makefile
 daemons/dmeventd/plugins/vdo/Makefile
+daemons/dmfilemapd/Makefile
 daemons/lvmdbusd/Makefile
 daemons/lvmdbusd/lvmdbusd
 daemons/lvmdbusd/lvmdb.py
 daemons/lvmdbusd/lvm_shell_proxy.py
 daemons/lvmdbusd/path.py
+daemons/lvmetad/Makefile
 daemons/lvmpolld/Makefile
 daemons/lvmlockd/Makefile
+device_mapper/Makefile
 conf/Makefile
 conf/example.conf
 conf/lvmlocal.conf
 conf/command_profile_template.profile
 conf/metadata_profile_template.profile
+include/.symlinks
 include/Makefile
 lib/Makefile
+lib/locking/Makefile
 include/lvm-version.h
 libdaemon/Makefile
 libdaemon/client/Makefile
 libdaemon/server/Makefile
 libdm/Makefile
-libdm/dm-tools/Makefile
 libdm/libdevmapper.pc
+liblvm/Makefile
+liblvm/liblvm2app.pc
 man/Makefile
 po/Makefile
-scripts/lvm2-pvscan.service
+python/Makefile
+python/setup.py
 scripts/blkdeactivate.sh
 scripts/blk_availability_init_red_hat
 scripts/blk_availability_systemd_red_hat.service
+scripts/clvmd_init_red_hat
 scripts/cmirrord_init_red_hat
 scripts/com.redhat.lvmdbus1.service
 scripts/dm_event_systemd_red_hat.service
 scripts/dm_event_systemd_red_hat.socket
+scripts/lvm2_cluster_activation_red_hat.sh
+scripts/lvm2_cluster_activation_systemd_red_hat.service
+scripts/lvm2_clvmd_systemd_red_hat.service
 scripts/lvm2_cmirrord_systemd_red_hat.service
 scripts/lvm2_lvmdbusd_systemd_red_hat.service
+scripts/lvm2_lvmetad_init_red_hat
+scripts/lvm2_lvmetad_systemd_red_hat.service
+scripts/lvm2_lvmetad_systemd_red_hat.socket
 scripts/lvm2_lvmpolld_init_red_hat
 scripts/lvm2_lvmpolld_systemd_red_hat.service
 scripts/lvm2_lvmpolld_systemd_red_hat.socket
-scripts/lvmlockd.service
-scripts/lvmlocks.service
+scripts/lvm2_lvmlockd_systemd_red_hat.service
+scripts/lvm2_lvmlocking_systemd_red_hat.service
 scripts/lvm2_monitoring_init_red_hat
 scripts/lvm2_monitoring_systemd_red_hat.service
+scripts/lvm2_pvscan_systemd_red_hat@.service
 scripts/lvm2_tmpfiles_red_hat.conf
 scripts/lvmdump.sh
 scripts/Makefile
 test/Makefile
+test/api/Makefile
+test/api/python_lvm_unit.py
+test/unit/Makefile
 tools/Makefile
 udev/Makefile
 ])
@@ -1952,9 +2179,6 @@ AS_IF([test -n "$CACHE_CONFIGURE_WARN"],
 AS_IF([test -n "$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!])])
-
 
 AS_IF([test "$ODIRECT" != yes],
       [AC_MSG_WARN([O_DIRECT disabled: low-memory pvmove may lock up])])

coverity/coverity_model.c

@@ -46,7 +46,6 @@ 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)
@@ -54,7 +53,6 @@ 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/Makefile.in

@@ -15,7 +15,11 @@ srcdir = @srcdir@
 top_srcdir = @top_srcdir@
 top_builddir = @top_builddir@
 
-.PHONY: dmeventd cmirrord lvmpolld lvmlockd
+.PHONY: dmeventd clvmd cmirrord lvmetad lvmpolld lvmlockd
+
+ifneq ("@CLVMD@", "none")
+  SUBDIRS += clvmd
+endif
 
 ifeq ("@BUILD_CMIRRORD@", "yes")
   SUBDIRS += cmirrord
@@ -28,6 +32,10 @@ daemons.cflow: dmeventd.cflow
 endif
 endif
 
+ifeq ("@BUILD_LVMETAD@", "yes")
+  SUBDIRS += lvmetad
+endif
+
 ifeq ("@BUILD_LVMPOLLD@", "yes")
   SUBDIRS += lvmpolld
 endif
@@ -40,8 +48,12 @@ ifeq ("@BUILD_LVMDBUSD@", "yes")
   SUBDIRS += lvmdbusd
 endif
 
+ifeq ("@BUILD_DMFILEMAPD@", "yes")
+  SUBDIRS += dmfilemapd
+endif
+
 ifeq ($(MAKECMDGOALS),distclean)
-  SUBDIRS = cmirrord dmeventd lvmpolld lvmlockd lvmdbusd
+  SUBDIRS = clvmd cmirrord dmeventd lvmetad lvmpolld lvmlockd lvmdbusd dmfilemapd
 endif
 
 include $(top_builddir)/make.tmpl

daemons/clvmd/.gitignore

@@ -0,0 +1 @@
+clvmd

daemons/clvmd/Makefile.in

@@ -0,0 +1,94 @@
+#
+# Copyright (C) 2004 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 General Public License v.2.
+#
+# You should have received a copy of the GNU 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
+
+srcdir = @srcdir@
+top_srcdir = @top_srcdir@
+top_builddir = @top_builddir@
+
+CMAN_LIBS = @CMAN_LIBS@
+CMAN_CFLAGS = @CMAN_CFLAGS@
+CMAP_LIBS = @CMAP_LIBS@
+CMAP_CFLAGS = @CMAP_CFLAGS@
+CONFDB_LIBS = @CONFDB_LIBS@
+CONFDB_CFLAGS = @CONFDB_CFLAGS@
+CPG_LIBS = @CPG_LIBS@
+CPG_CFLAGS = @CPG_CFLAGS@
+DLM_LIBS = @DLM_LIBS@
+DLM_CFLAGS = @DLM_CFLAGS@
+QUORUM_LIBS = @QUORUM_LIBS@
+QUORUM_CFLAGS = @QUORUM_CFLAGS@
+SALCK_LIBS = @SALCK_LIBS@
+SALCK_CFLAGS = @SALCK_CFLAGS@
+
+SOURCES = \
+	clvmd-command.c\
+	clvmd.c\
+	lvm-functions.c\
+	refresh_clvmd.c
+
+ifneq (,$(findstring cman,, "@CLVMD@,"))
+	SOURCES += clvmd-cman.c
+	LMLIBS += $(CMAN_LIBS) $(CONFDB_LIBS) $(DLM_LIBS)
+	CFLAGS += $(CMAN_CFLAGS) $(CONFDB_CFLAGS) $(DLM_CFLAGS)
+	DEFS += -DUSE_CMAN
+endif
+
+ifneq (,$(findstring openais,, "@CLVMD@,"))
+	SOURCES += clvmd-openais.c
+	LMLIBS += $(CONFDB_LIBS) $(CPG_LIBS) $(SALCK_LIBS)
+	CFLAGS += $(CONFDB_CFLAGS) $(CPG_CFLAGS) $(SALCK_CFLAGS)
+	DEFS += -DUSE_OPENAIS
+endif
+
+ifneq (,$(findstring corosync,, "@CLVMD@,"))
+	SOURCES += clvmd-corosync.c
+	LMLIBS += $(CMAP_LIBS) $(CONFDB_LIBS) $(CPG_LIBS) $(DLM_LIBS) $(QUORUM_LIBS)
+	CFLAGS += $(CMAP_CFLAGS) $(CONFDB_CFLAGS) $(CPG_CFLAGS) $(DLM_CFLAGS) $(QUORUM_CFLAGS)
+	DEFS += -DUSE_COROSYNC
+endif
+
+ifneq (,$(findstring singlenode,, "@CLVMD@,"))
+	SOURCES += clvmd-singlenode.c
+	DEFS += -DUSE_SINGLENODE
+endif
+
+ifeq ($(MAKECMDGOALS),distclean)
+	SOURCES += clvmd-cman.c
+	SOURCES += clvmd-openais.c
+	SOURCES += clvmd-corosync.c
+	SOURCES += clvmd-singlenode.c
+endif
+
+TARGETS = \
+	clvmd
+
+include $(top_builddir)/make.tmpl
+
+LIBS += $(LVMINTERNAL_LIBS) -ldevmapper $(PTHREAD_LIBS) -laio
+CFLAGS += -fno-strict-aliasing $(EXTRA_EXEC_CFLAGS)
+
+INSTALL_TARGETS = \
+	install_clvmd
+
+clvmd: $(OBJECTS) $(top_builddir)/lib/liblvm-internal.a
+	$(CC) $(CFLAGS) $(LDFLAGS) $(EXTRA_EXEC_LDFLAGS) $(ELDFLAGS) \
+	      -o clvmd $(OBJECTS) $(LMLIBS) $(LIBS)
+
+.PHONY: install_clvmd
+
+install_clvmd: $(TARGETS)
+	$(INSTALL_PROGRAM) -D clvmd $(usrsbindir)/clvmd
+
+install: $(INSTALL_TARGETS)
+
+install_cluster: $(INSTALL_TARGETS)

daemons/clvmd/clvm.h

@@ -0,0 +1,85 @@
+/*
+ * Copyright (C) 2002-2004 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 General Public License v.2.
+ *
+ * You should have received a copy of the GNU 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
+ */
+
+/* Definitions for CLVMD server and clients */
+
+/*
+ * The protocol spoken over the cluster and across the local socket.
+ */
+
+#ifndef _CLVM_H
+#define _CLVM_H
+
+#include "configure.h"
+#include <inttypes.h>
+
+struct clvm_header {
+	uint8_t  cmd;	        /* See below */
+	uint8_t  flags;	        /* See below */
+	uint16_t xid;	        /* Transaction ID */
+	uint32_t clientid;	/* Only used in Daemon->Daemon comms */
+	int32_t  status;	/* For replies, whether request succeeded */
+	uint32_t arglen;	/* Length of argument below.
+				   If >1500 then it will be passed
+				   around the cluster in the system LV */
+	char node[1];		/* Actually a NUL-terminated string, node name.
+				   If this is empty then the command is
+				   forwarded to all cluster nodes unless
+				   FLAG_LOCAL or FLAG_REMOTE is also set. */
+	char args[1];		/* Arguments for the command follow the
+				   node name, This member is only
+				   valid if the node name is empty */
+} __attribute__ ((packed));
+
+/* Flags */
+#define CLVMD_FLAG_LOCAL	1	/* Only do this on the local node */
+#define CLVMD_FLAG_SYSTEMLV	2	/* Data in system LV under my node name */
+#define CLVMD_FLAG_NODEERRS	4	/* Reply has errors in node-specific portion */
+#define CLVMD_FLAG_REMOTE	8	/* Do this on all nodes except for the local node */
+
+/* Name of the local socket to communicate between lvm and clvmd */
+#define CLVMD_SOCKNAME		DEFAULT_RUN_DIR "/clvmd.sock"
+
+/* Internal commands & replies */
+#define CLVMD_CMD_REPLY    1
+#define CLVMD_CMD_VERSION  2	/* Send version around cluster when we start */
+#define CLVMD_CMD_GOAWAY   3	/* Die if received this - we are running
+				   an incompatible version */
+#define CLVMD_CMD_TEST     4	/* Just for mucking about */
+
+#define CLVMD_CMD_LOCK              30
+#define CLVMD_CMD_UNLOCK            31
+
+/* Lock/Unlock commands */
+#define CLVMD_CMD_LOCK_LV           50
+#define CLVMD_CMD_LOCK_VG           51
+#define CLVMD_CMD_LOCK_QUERY	    52
+
+/* Misc functions */
+#define CLVMD_CMD_REFRESH	    40
+#define CLVMD_CMD_GET_CLUSTERNAME   41
+#define CLVMD_CMD_SET_DEBUG	    42
+#define CLVMD_CMD_VG_BACKUP	    43
+#define CLVMD_CMD_RESTART	    44
+#define CLVMD_CMD_SYNC_NAMES	    45
+
+/* Used internally by some callers, but not part of the protocol.*/
+#ifndef NODE_ALL
+#  define NODE_ALL	"*"
+#  define NODE_LOCAL	"."
+#  define NODE_REMOTE	"^"
+#endif
+
+#endif

daemons/clvmd/clvmd-cman.c

@@ -0,0 +1,505 @@
+/*
+ * Copyright (C) 2002-2004 Sistina Software, Inc. All rights reserved.
+ * Copyright (C) 2004 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 General Public License v.2.
+ *
+ * You should have received a copy of the GNU 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
+ */
+
+/*
+ * CMAN communication layer for clvmd.
+ */
+
+#include "clvmd-common.h"
+
+#include <pthread.h>
+
+#include "clvmd-comms.h"
+#include "clvm.h"
+#include "clvmd.h"
+#include "lvm-functions.h"
+
+#include <libdlm.h>
+
+#include <syslog.h>
+
+#define LOCKSPACE_NAME "clvmd"
+
+struct clvmd_node
+{
+	struct cman_node *node;
+	int clvmd_up;
+};
+
+static int num_nodes;
+static struct cman_node *nodes = NULL;
+static struct cman_node this_node;
+static int count_nodes; /* size of allocated nodes array */
+static struct dm_hash_table *node_updown_hash;
+static dlm_lshandle_t *lockspace;
+static cman_handle_t c_handle;
+
+static void count_clvmds_running(void);
+static void get_members(void);
+static int nodeid_from_csid(const char *csid);
+static int name_from_nodeid(int nodeid, char *name);
+static void event_callback(cman_handle_t handle, void *private, int reason, int arg);
+static void data_callback(cman_handle_t handle, void *private,
+			  char *buf, int len, uint8_t port, int nodeid);
+
+struct lock_wait {
+	pthread_cond_t cond;
+	pthread_mutex_t mutex;
+	struct dlm_lksb lksb;
+};
+
+static int _init_cluster(void)
+{
+	node_updown_hash = dm_hash_create(100);
+
+	/* Open the cluster communication socket */
+	c_handle = cman_init(NULL);
+	if (!c_handle) {
+		syslog(LOG_ERR, "Can't open cluster manager socket: %m");
+		return -1;
+	}
+	DEBUGLOG("Connected to CMAN\n");
+
+	if (cman_start_recv_data(c_handle, data_callback, CLUSTER_PORT_CLVMD)) {
+		syslog(LOG_ERR, "Can't bind cluster socket: %m");
+		return -1;
+	}
+
+	if (cman_start_notification(c_handle, event_callback)) {
+		syslog(LOG_ERR, "Can't start cluster event listening");
+		return -1;
+	}
+
+	/* Get the cluster members list */
+	get_members();
+	count_clvmds_running();
+
+	DEBUGLOG("CMAN initialisation complete\n");
+
+	/* Create a lockspace for LV & VG locks to live in */
+	lockspace = dlm_open_lockspace(LOCKSPACE_NAME);
+	if (!lockspace) {
+		lockspace = dlm_create_lockspace(LOCKSPACE_NAME, 0600);
+		if (!lockspace) {
+			syslog(LOG_ERR, "Unable to create DLM lockspace for CLVM: %m");
+			return -1;
+		}
+		DEBUGLOG("Created DLM lockspace for CLVMD.\n");
+	} else
+		DEBUGLOG("Opened existing DLM lockspace for CLVMD.\n");
+
+	dlm_ls_pthread_init(lockspace);
+	DEBUGLOG("DLM initialisation complete\n");
+	return 0;
+}
+
+static void _cluster_init_completed(void)
+{
+	clvmd_cluster_init_completed();
+}
+
+static int _get_main_cluster_fd(void)
+{
+	return cman_get_fd(c_handle);
+}
+
+static int _get_num_nodes(void)
+{
+	int i;
+	int nnodes = 0;
+
+	/* return number of ACTIVE nodes */
+	for (i=0; i<num_nodes; i++) {
+		if (nodes[i].cn_member && nodes[i].cn_nodeid)
+			nnodes++;
+	}
+	return nnodes;
+}
+
+/* send_message with the fd check removed */
+static int _cluster_send_message(const void *buf, int msglen, const char *csid,
+				 const char *errtext)
+{
+	int nodeid = 0;
+
+	if (csid)
+		memcpy(&nodeid, csid, CMAN_MAX_CSID_LEN);
+
+	if (cman_send_data(c_handle, buf, msglen, 0, CLUSTER_PORT_CLVMD, nodeid) <= 0)
+	{
+		log_error("%s", errtext);
+	}
+	return msglen;
+}
+
+static void _get_our_csid(char *csid)
+{
+	if (this_node.cn_nodeid == 0) {
+		cman_get_node(c_handle, 0, &this_node);
+	}
+	memcpy(csid, &this_node.cn_nodeid, CMAN_MAX_CSID_LEN);
+}
+
+/* Call a callback routine for each node is that known (down means not running a clvmd) */
+static int _cluster_do_node_callback(struct local_client *client,
+				     void (*callback) (struct local_client *,
+						       const char *,
+						       int))
+{
+	int i;
+	int somedown = 0;
+
+	for (i = 0; i < _get_num_nodes(); i++) {
+		if (nodes[i].cn_member && nodes[i].cn_nodeid) {
+			int up = (int)(long)dm_hash_lookup_binary(node_updown_hash, (char *)&nodes[i].cn_nodeid, sizeof(int));
+
+			callback(client, (char *)&nodes[i].cn_nodeid, up);
+			if (!up)
+				somedown = -1;
+		}
+	}
+	return somedown;
+}
+
+/* Process OOB messages from the cluster socket */
+static void event_callback(cman_handle_t handle, void *private, int reason, int arg)
+{
+	char namebuf[MAX_CLUSTER_MEMBER_NAME_LEN];
+
+	switch (reason) {
+        case CMAN_REASON_PORTCLOSED:
+		name_from_nodeid(arg, namebuf);
+		log_notice("clvmd on node %s has died\n", namebuf);
+		DEBUGLOG("Got port closed message, removing node %s\n", namebuf);
+
+		dm_hash_insert_binary(node_updown_hash, (char *)&arg, sizeof(int), (void *)0);
+		break;
+
+	case CMAN_REASON_STATECHANGE:
+		DEBUGLOG("Got state change message, re-reading members list\n");
+		get_members();
+		break;
+
+#if defined(LIBCMAN_VERSION) && LIBCMAN_VERSION >= 2
+	case CMAN_REASON_PORTOPENED:
+		/* Ignore this, wait for startup message from clvmd itself */
+		break;
+
+	case CMAN_REASON_TRY_SHUTDOWN:
+		DEBUGLOG("Got try shutdown, sending OK\n");
+		cman_replyto_shutdown(c_handle, 1);
+		break;
+#endif
+	default:
+		/* ERROR */
+		DEBUGLOG("Got unknown event callback message: %d\n", reason);
+		break;
+	}
+}
+
+static struct local_client *cman_client;
+static int _cluster_fd_callback(struct local_client *fd, char *buf, int len,
+				const char *csid,
+				struct local_client **new_client)
+{
+
+	/* Save this for data_callback */
+	cman_client = fd;
+
+	/* We never return a new client */
+	*new_client = NULL;
+
+	return cman_dispatch(c_handle, 0);
+}
+
+
+static void data_callback(cman_handle_t handle, void *private,
+			  char *buf, int len, uint8_t port, int nodeid)
+{
+	/* Ignore looped back messages */
+	if (nodeid == this_node.cn_nodeid)
+		return;
+	process_message(cman_client, buf, len, (char *)&nodeid);
+}
+
+static void _add_up_node(const char *csid)
+{
+	/* It's up ! */
+	int nodeid = nodeid_from_csid(csid);
+
+	dm_hash_insert_binary(node_updown_hash, (char *)&nodeid, sizeof(int), (void *)1);
+	DEBUGLOG("Added new node %d to updown list\n", nodeid);
+}
+
+static void _cluster_closedown(void)
+{
+	dlm_release_lockspace(LOCKSPACE_NAME, lockspace, 1);
+	cman_finish(c_handle);
+}
+
+static int is_listening(int nodeid)
+{
+	int status;
+
+	do {
+		status = cman_is_listening(c_handle, nodeid, CLUSTER_PORT_CLVMD);
+		if (status < 0 && errno == EBUSY) {	/* Don't busywait */
+			sleep(1);
+			errno = EBUSY;	/* In case sleep trashes it */
+		}
+	}
+	while (status < 0 && errno == EBUSY);
+
+	return status;
+}
+
+/* Populate the list of CLVMDs running.
+   called only at startup time */
+static void count_clvmds_running(void)
+{
+	int i;
+
+	for (i = 0; i < num_nodes; i++) {
+		int nodeid = nodes[i].cn_nodeid;
+
+		if (is_listening(nodeid) == 1)
+			dm_hash_insert_binary(node_updown_hash, (void *)&nodeid, sizeof(int), (void*)1);
+		else
+			dm_hash_insert_binary(node_updown_hash, (void *)&nodeid, sizeof(int), (void*)0);
+	}
+}
+
+/* Get a list of active cluster members */
+static void get_members(void)
+{
+	int retnodes;
+	int status;
+	int i;
+	int high_nodeid = 0;
+
+	num_nodes = cman_get_node_count(c_handle);
+	if (num_nodes == -1) {
+		log_error("Unable to get node count");
+		return;
+	}
+
+	/* Not enough room for new nodes list ? */
+	if (num_nodes > count_nodes && nodes) {
+		free(nodes);
+		nodes = NULL;
+	}
+
+	if (nodes == NULL) {
+		count_nodes = num_nodes + 10; /* Overallocate a little */
+		nodes = malloc(count_nodes * sizeof(struct cman_node));
+		if (!nodes) {
+			log_error("Unable to allocate nodes array\n");
+			exit(5);
+		}
+	}
+
+	status = cman_get_nodes(c_handle, count_nodes, &retnodes, nodes);
+	if (status < 0) {
+		log_error("Unable to get node details");
+		exit(6);
+	}
+
+	/* Get the highest nodeid */
+	for (i=0; i<retnodes; i++) {
+		if (nodes[i].cn_nodeid > high_nodeid)
+			high_nodeid = nodes[i].cn_nodeid;
+	}
+}
+
+
+/* Convert a node name to a CSID */
+static int _csid_from_name(char *csid, const char *name)
+{
+	int i;
+
+	for (i = 0; i < num_nodes; i++) {
+		if (strcmp(name, nodes[i].cn_name) == 0) {
+			memcpy(csid, &nodes[i].cn_nodeid, CMAN_MAX_CSID_LEN);
+			return 0;
+		}
+	}
+	return -1;
+}
+
+/* Convert a CSID to a node name */
+static int _name_from_csid(const char *csid, char *name)
+{
+	int i;
+
+	for (i = 0; i < num_nodes; i++) {
+		if (memcmp(csid, &nodes[i].cn_nodeid, CMAN_MAX_CSID_LEN) == 0) {
+			strcpy(name, nodes[i].cn_name);
+			return 0;
+		}
+	}
+	/* Who?? */
+	strcpy(name, "Unknown");
+	return -1;
+}
+
+/* Convert a node ID to a node name */
+static int name_from_nodeid(int nodeid, char *name)
+{
+	int i;
+
+	for (i = 0; i < num_nodes; i++) {
+		if (nodeid == nodes[i].cn_nodeid) {
+			strcpy(name, nodes[i].cn_name);
+			return 0;
+		}
+	}
+	/* Who?? */
+	strcpy(name, "Unknown");
+	return -1;
+}
+
+/* Convert a CSID to a node ID */
+static int nodeid_from_csid(const char *csid)
+{
+        int nodeid;
+
+	memcpy(&nodeid, csid, CMAN_MAX_CSID_LEN);
+
+	return nodeid;
+}
+
+static int _is_quorate(void)
+{
+	return cman_is_quorate(c_handle);
+}
+
+static void sync_ast_routine(void *arg)
+{
+	struct lock_wait *lwait = arg;
+
+	pthread_mutex_lock(&lwait->mutex);
+	pthread_cond_signal(&lwait->cond);
+	pthread_mutex_unlock(&lwait->mutex);
+}
+
+static int _sync_lock(const char *resource, int mode, int flags, int *lockid)
+{
+	int status;
+	struct lock_wait lwait;
+
+	if (!lockid) {
+		errno = EINVAL;
+		return -1;
+	}
+
+	DEBUGLOG("sync_lock: '%s' mode:%d flags=%d\n", resource,mode,flags);
+	/* Conversions need the lockid in the LKSB */
+	if (flags & LKF_CONVERT)
+		lwait.lksb.sb_lkid = *lockid;
+
+	pthread_cond_init(&lwait.cond, NULL);
+	pthread_mutex_init(&lwait.mutex, NULL);
+	pthread_mutex_lock(&lwait.mutex);
+
+	status = dlm_ls_lock(lockspace,
+			     mode,
+			     &lwait.lksb,
+			     flags,
+			     resource,
+			     strlen(resource),
+			     0, sync_ast_routine, &lwait, NULL, NULL);
+	if (status)
+		return status;
+
+	/* Wait for it to complete */
+	pthread_cond_wait(&lwait.cond, &lwait.mutex);
+	pthread_mutex_unlock(&lwait.mutex);
+
+	*lockid = lwait.lksb.sb_lkid;
+
+	errno = lwait.lksb.sb_status;
+	DEBUGLOG("sync_lock: returning lkid %x\n", *lockid);
+	if (lwait.lksb.sb_status)
+		return -1;
+	else
+		return 0;
+}
+
+static int _sync_unlock(const char *resource /* UNUSED */, int lockid)
+{
+	int status;
+	struct lock_wait lwait;
+
+	DEBUGLOG("sync_unlock: '%s' lkid:%x\n", resource, lockid);
+
+	pthread_cond_init(&lwait.cond, NULL);
+	pthread_mutex_init(&lwait.mutex, NULL);
+	pthread_mutex_lock(&lwait.mutex);
+
+	status = dlm_ls_unlock(lockspace, lockid, 0, &lwait.lksb, &lwait);
+
+	if (status)
+		return status;
+
+	/* Wait for it to complete */
+	pthread_cond_wait(&lwait.cond, &lwait.mutex);
+	pthread_mutex_unlock(&lwait.mutex);
+
+	errno = lwait.lksb.sb_status;
+	if (lwait.lksb.sb_status != EUNLOCK)
+		return -1;
+	else
+		return 0;
+
+}
+
+static int _get_cluster_name(char *buf, int buflen)
+{
+	cman_cluster_t cluster_info;
+	int status;
+
+	status = cman_get_cluster(c_handle, &cluster_info);
+	if (!status) {
+		strncpy(buf, cluster_info.ci_name, buflen);
+	}
+	return status;
+}
+
+static struct cluster_ops _cluster_cman_ops = {
+	.name                     = "cman",
+	.cluster_init_completed   = _cluster_init_completed,
+	.cluster_send_message     = _cluster_send_message,
+	.name_from_csid           = _name_from_csid,
+	.csid_from_name           = _csid_from_name,
+	.get_num_nodes            = _get_num_nodes,
+	.cluster_fd_callback      = _cluster_fd_callback,
+	.get_main_cluster_fd      = _get_main_cluster_fd,
+	.cluster_do_node_callback = _cluster_do_node_callback,
+	.is_quorate               = _is_quorate,
+	.get_our_csid             = _get_our_csid,
+	.add_up_node              = _add_up_node,
+	.cluster_closedown        = _cluster_closedown,
+	.get_cluster_name         = _get_cluster_name,
+	.sync_lock                = _sync_lock,
+	.sync_unlock              = _sync_unlock,
+};
+
+struct cluster_ops *init_cman_cluster(void)
+{
+	if (!_init_cluster())
+		return &_cluster_cman_ops;
+	else
+		return NULL;
+}

daemons/clvmd/clvmd-command.c

@@ -0,0 +1,415 @@
+/*
+ * Copyright (C) 2002-2004 Sistina Software, Inc. All rights reserved.
+ * Copyright (C) 2004-2011 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 General Public License v.2.
+ *
+ * You should have received a copy of the GNU 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
+ */
+
+/*
+
+  CLVMD Cluster LVM daemon command processor.
+
+  To add commands to the daemon simply add a processor in do_command and return
+  and messages back in buf and the length in *retlen. The initial value of
+  buflen is the maximum size of the buffer. if buf is not large enough then it
+  may be reallocated by the functions in here to a suitable size bearing in
+  mind that anything larger than the passed-in size will have to be returned
+  using the system LV and so performance will suffer.
+
+  The status return will be negated and passed back to the originating node.
+
+  pre- and post- command routines are called only on the local node. The
+  purpose is primarily to get and release locks, though the pre- routine should
+  also do any other local setups required by the command (if any) and can
+  return a failure code that prevents the command from being distributed around
+  the cluster
+
+  The pre- and post- routines are run in their own thread so can block as long
+  they like, do_command is run in the main clvmd thread so should not block for
+  too long. If the pre-command returns an error code (!=0) then the command
+  will not be propogated around the cluster but the post-command WILL be called
+
+  Also note that the pre and post routine are *always* called on the local
+  node, even if the command to be executed was only requested to run on a
+  remote node. It may peek inside the client structure to check the status of
+  the command.
+
+  The clients of the daemon must, naturally, understand the return messages and
+  codes.
+
+  Routines in here may only READ the values in the client structure passed in
+  apart from client->private which they are free to do what they like with.
+
+*/
+
+#include "clvmd-common.h"
+#include "clvmd-comms.h"
+#include "clvm.h"
+#include "clvmd.h"
+#include "lvm-globals.h"
+#include "lvm-functions.h"
+
+#include "locking.h"
+
+#include <sys/utsname.h>
+
+extern struct cluster_ops *clops;
+static int restart_clvmd(void);
+
+/* This is where all the real work happens:
+   NOTE: client will be NULL when this is executed on a remote node */
+int do_command(struct local_client *client, struct clvm_header *msg, int msglen,
+	       char **buf, int buflen, int *retlen)
+{
+	char *args = msg->node + strlen(msg->node) + 1;
+	int arglen = msglen - sizeof(struct clvm_header) - strlen(msg->node);
+	int status = 0;
+	char *lockname;
+	const char *locktype;
+	struct utsname nodeinfo;
+	unsigned char lock_cmd;
+	unsigned char lock_flags;
+
+	/* Do the command */
+	switch (msg->cmd) {
+		/* Just a test message */
+	case CLVMD_CMD_TEST:
+		if (arglen > buflen) {
+			char *new_buf;
+			buflen = arglen + 200;
+			new_buf = realloc(*buf, buflen);
+			if (new_buf == NULL) {
+				status = errno;
+				free (*buf);
+			}
+			*buf = new_buf;
+		}
+		if (*buf) {
+			if (uname(&nodeinfo))
+				memset(&nodeinfo, 0, sizeof(nodeinfo));
+
+			*retlen = 1 + dm_snprintf(*buf, buflen,
+						  "TEST from %s: %s v%s",
+						  nodeinfo.nodename, args,
+						  nodeinfo.release);
+		}
+		break;
+
+	case CLVMD_CMD_LOCK_VG:
+		lock_cmd = args[0];
+		lock_flags = args[1];
+		lockname = &args[2];
+		/* Check to see if the VG is in use by LVM1 */
+		do_lock_vg(lock_cmd, lock_flags, lockname);
+		break;
+
+	case CLVMD_CMD_LOCK_LV:
+		/* This is the biggie */
+		lock_cmd = args[0];
+		lock_flags = args[1];
+		lockname = &args[2];
+		status = do_lock_lv(lock_cmd, lock_flags, lockname);
+		/* Replace EIO with something less scary */
+		if (status == EIO) {
+			*retlen = 1 + dm_snprintf(*buf, buflen, "%s",
+						  get_last_lvm_error());
+			return EIO;
+		}
+		break;
+
+	case CLVMD_CMD_LOCK_QUERY:
+		lockname = &args[2];
+		if (buflen < 3)
+			return EIO;
+		if ((locktype = do_lock_query(lockname)))
+			*retlen = 1 + dm_snprintf(*buf, buflen, "%s", locktype);
+		break;
+
+	case CLVMD_CMD_REFRESH:
+		do_refresh_cache();
+		break;
+
+	case CLVMD_CMD_SYNC_NAMES:
+		lvm_do_fs_unlock();
+		break;
+
+	case CLVMD_CMD_SET_DEBUG:
+		clvmd_set_debug((debug_t) args[0]);
+		break;
+
+	case CLVMD_CMD_RESTART:
+		status = restart_clvmd();
+		break;
+
+	case CLVMD_CMD_GET_CLUSTERNAME:
+		status = clops->get_cluster_name(*buf, buflen);
+		if (!status)
+			*retlen = strlen(*buf)+1;
+		break;
+
+	case CLVMD_CMD_VG_BACKUP:
+		/*
+		 * Do not run backup on local node, caller should do that.
+		 */
+		if (!client)
+			lvm_do_backup(&args[2]);
+		break;
+
+	default:
+		/* Won't get here because command is validated in pre_command */
+		break;
+	}
+
+	/* Check the status of the command and return the error text */
+	if (status) {
+		if (*buf)
+			*retlen = dm_snprintf(*buf, buflen, "%s", strerror(status)) + 1;
+		else
+			*retlen = 0;
+	}
+
+	return status;
+}
+
+static int lock_vg(struct local_client *client)
+{
+	struct dm_hash_table *lock_hash;
+	struct clvm_header *header =
+		(struct clvm_header *) client->bits.localsock.cmd;
+	unsigned char lock_cmd;
+	int lock_mode;
+	char *args = header->node + strlen(header->node) + 1;
+	int lkid;
+	int status;
+	char *lockname;
+
+	/*
+	 * Keep a track of VG locks in our own hash table. In current
+	 * practice there should only ever be more than two VGs locked
+	 * if a user tries to merge lots of them at once
+	 */
+	if (!client->bits.localsock.private) {
+		if (!(lock_hash = dm_hash_create(3)))
+			return ENOMEM;
+		client->bits.localsock.private = (void *) lock_hash;
+	} else
+		lock_hash = (struct dm_hash_table *) client->bits.localsock.private;
+
+	lock_cmd = args[0] & (LCK_NONBLOCK | LCK_HOLD | LCK_SCOPE_MASK | LCK_TYPE_MASK);
+	lock_mode = ((int) lock_cmd & LCK_TYPE_MASK);
+	/* lock_flags = args[1]; */
+	lockname = &args[2];
+	DEBUGLOG("(%p) doing PRE command LOCK_VG '%s' at %x\n", client, lockname, lock_cmd);
+
+	if (lock_mode == LCK_UNLOCK) {
+		if (!(lkid = (int) (long) dm_hash_lookup(lock_hash, lockname)))
+			return EINVAL;
+
+		if ((status = sync_unlock(lockname, lkid)))
+			status = errno;
+		else
+			dm_hash_remove(lock_hash, lockname);
+	} else {
+		/* Read locks need to be PR; other modes get passed through */
+		if (lock_mode == LCK_READ)
+			lock_mode = LCK_PREAD;
+
+		if ((status = sync_lock(lockname, lock_mode, (lock_cmd & LCK_NONBLOCK) ? LCKF_NOQUEUE : 0, &lkid)))
+			status = errno;
+		else if (!dm_hash_insert(lock_hash, lockname, (void *) (long) lkid))
+			return ENOMEM;
+	}
+
+	return status;
+}
+
+
+/* Pre-command is a good place to get locks that are needed only for the duration
+   of the commands around the cluster (don't forget to free them in post-command),
+   and to sanity check the command arguments */
+int do_pre_command(struct local_client *client)
+{
+	struct clvm_header *header =
+	    (struct clvm_header *) client->bits.localsock.cmd;
+	unsigned char lock_cmd;
+	unsigned char lock_flags;
+	char *args = header->node + strlen(header->node) + 1;
+	int lockid = 0;
+	int status = 0;
+	char *lockname;
+
+	switch (header->cmd) {
+	case CLVMD_CMD_TEST:
+		status = sync_lock("CLVMD_TEST", LCK_EXCL, 0, &lockid);
+		client->bits.localsock.private = (void *)(long)lockid;
+		break;
+
+	case CLVMD_CMD_LOCK_VG:
+		lockname = &args[2];
+		/* We take out a real lock unless LCK_CACHE was set */
+		if (!strncmp(lockname, "V_", 2) ||
+		    !strncmp(lockname, "P_#", 3))
+			status = lock_vg(client);
+		break;
+
+	case CLVMD_CMD_LOCK_LV:
+		lock_cmd = args[0];
+		lock_flags = args[1];
+		lockname = &args[2];
+		status = pre_lock_lv(lock_cmd, lock_flags, lockname);
+		break;
+
+	case CLVMD_CMD_REFRESH:
+	case CLVMD_CMD_GET_CLUSTERNAME:
+	case CLVMD_CMD_SET_DEBUG:
+	case CLVMD_CMD_VG_BACKUP:
+	case CLVMD_CMD_SYNC_NAMES:
+	case CLVMD_CMD_LOCK_QUERY:
+	case CLVMD_CMD_RESTART:
+		break;
+
+	default:
+		log_error("Unknown command %d received\n", header->cmd);
+		status = EINVAL;
+	}
+	return status;
+}
+
+/* Note that the post-command routine is called even if the pre-command or the real command
+   failed */
+int do_post_command(struct local_client *client)
+{
+	struct clvm_header *header =
+	    (struct clvm_header *) client->bits.localsock.cmd;
+	int status = 0;
+	unsigned char lock_cmd;
+	unsigned char lock_flags;
+	char *args = header->node + strlen(header->node) + 1;
+	char *lockname;
+
+	switch (header->cmd) {
+	case CLVMD_CMD_TEST:
+		status = sync_unlock("CLVMD_TEST", (int) (long) client->bits.localsock.private);
+		client->bits.localsock.private = NULL;
+		break;
+
+	case CLVMD_CMD_LOCK_LV:
+		lock_cmd = args[0];
+		lock_flags = args[1];
+		lockname = &args[2];
+		status = post_lock_lv(lock_cmd, lock_flags, lockname);
+		break;
+
+	default:
+		/* Nothing to do here */
+		break;
+	}
+	return status;
+}
+
+
+/* Called when the client is about to be deleted */
+void cmd_client_cleanup(struct local_client *client)
+{
+	struct dm_hash_node *v;
+	struct dm_hash_table *lock_hash;
+	int lkid;
+	char *lockname;
+
+	DEBUGLOG("(%p) Client thread cleanup\n", client);
+	if (!client->bits.localsock.private)
+		return;
+
+	lock_hash = (struct dm_hash_table *)client->bits.localsock.private;
+
+	dm_hash_iterate(v, lock_hash) {
+		lkid = (int)(long)dm_hash_get_data(lock_hash, v);
+		lockname = dm_hash_get_key(lock_hash, v);
+		DEBUGLOG("(%p) Cleanup: Unlocking lock %s %x\n", client, lockname, lkid);
+		(void) sync_unlock(lockname, lkid);
+	}
+
+	dm_hash_destroy(lock_hash);
+	client->bits.localsock.private = NULL;
+}
+
+static int restart_clvmd(void)
+{
+	const char **argv;
+	char *lv_name;
+	int argc = 0, max_locks = 0;
+	struct dm_hash_node *hn = NULL;
+	char debug_arg[16];
+	const char *clvmd = getenv("LVM_CLVMD_BINARY") ? : CLVMD_PATH;
+
+	DEBUGLOG("clvmd restart requested\n");
+
+	/* Count exclusively-open LVs */
+	do {
+		hn = get_next_excl_lock(hn, &lv_name);
+		if (lv_name) {
+			max_locks++;
+			if (!*lv_name)
+				break; /* FIXME: Is this error ? */
+		}
+	} while (hn);
+
+	/* clvmd + locks (-E uuid) + debug (-d X) + NULL */
+	if (!(argv = malloc((max_locks * 2 + 6) * sizeof(*argv))))
+		goto_out;
+
+	/*
+	 * Build the command-line
+	 */
+	argv[argc++] = "clvmd";
+
+	/* Propagate debug options */
+	if (clvmd_get_debug()) {
+		if (dm_snprintf(debug_arg, sizeof(debug_arg), "-d%u", clvmd_get_debug()) < 0)
+			goto_out;
+		argv[argc++] = debug_arg;
+	}
+
+	/* Propagate foreground options */
+	if (clvmd_get_foreground())
+		argv[argc++] = "-f";
+
+	argv[argc++] = "-I";
+	argv[argc++] = clops->name;
+
+	/* Now add the exclusively-open LVs */
+	hn = NULL;
+	do {
+		hn = get_next_excl_lock(hn, &lv_name);
+		if (lv_name) {
+			if (!*lv_name)
+				break; /* FIXME: Is this error ? */
+			argv[argc++] = "-E";
+			argv[argc++] = lv_name;
+			DEBUGLOG("excl lock: %s\n", lv_name);
+		}
+	} while (hn);
+	argv[argc] = NULL;
+
+	/* Exec new clvmd */
+	DEBUGLOG("--- Restarting %s ---\n", clvmd);
+	for (argc = 1; argv[argc]; argc++) DEBUGLOG("--- %d: %s\n", argc, argv[argc]);
+
+	/* NOTE: This will fail when downgrading! */
+	execvp(clvmd, (char **)argv);
+out:
+	/* We failed */
+	DEBUGLOG("Restart of clvmd failed.\n");
+
+	free(argv);
+
+	return EIO;
+}

daemons/clvmd/clvmd-common.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2010 Red Hat, Inc. All rights reserved.
  *
  * This file is part of LVM2.
  *
@@ -12,11 +12,16 @@
  * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
-#ifndef _LIBDM_KDEV_H
-#define _LIBDM_KDEV_H
+/*
+ * This file must be included first by every clvmd source file.
+ */
+#ifndef _LVM_CLVMD_COMMON_H
+#define _LVM_CLVMD_COMMON_H
 
-#define MAJOR(dev)      ((dev & 0xfff00) >> 8)
-#define MINOR(dev)      ((dev & 0xff) | ((dev >> 12) & 0xfff00))
-#define MKDEV(ma,mi)    (((dev_t)mi & 0xff) | ((dev_t)ma << 8) | (((dev_t)mi & ~0xff) << 12))
+#define _REENTRANT
+
+#include "tool.h"
+
+#include "lvm-logging.h"
 
 #endif

daemons/clvmd/clvmd-comms.h

@@ -0,0 +1,119 @@
+/*
+ * Copyright (C) 2002-2004 Sistina Software, Inc. All rights reserved.
+ * Copyright (C) 2004-2011 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 General Public License v.2.
+ *
+ * You should have received a copy of the GNU 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
+ */
+
+/*
+ * Abstraction layer for clvmd cluster communications
+ */
+
+#ifndef _CLVMD_COMMS_H
+#define _CLVMD_COMMS_H
+
+struct local_client;
+
+struct cluster_ops {
+	const char *name;
+	void (*cluster_init_completed) (void);
+
+	int (*cluster_send_message) (const void *buf, int msglen,
+				     const char *csid,
+				     const char *errtext);
+	int (*name_from_csid) (const char *csid, char *name);
+	int (*csid_from_name) (char *csid, const char *name);
+	int (*get_num_nodes) (void);
+	int (*cluster_fd_callback) (struct local_client *fd, char *buf, int len,
+				    const char *csid,
+				    struct local_client **new_client);
+	int (*get_main_cluster_fd) (void);	/* gets accept FD or cman cluster socket */
+	int (*cluster_do_node_callback) (struct local_client *client,
+					 void (*callback) (struct local_client *,
+							   const char *csid,
+							   int node_up));
+	int (*is_quorate) (void);
+
+	void (*get_our_csid) (char *csid);
+	void (*add_up_node) (const char *csid);
+	void (*reread_config) (void);
+	void (*cluster_closedown) (void);
+
+	int (*get_cluster_name)(char *buf, int buflen);
+
+	int (*sync_lock) (const char *resource, int mode,
+			  int flags, int *lockid);
+	int (*sync_unlock) (const char *resource, int lockid);
+
+};
+
+#ifdef USE_CMAN
+#  include <netinet/in.h>
+#  include "libcman.h"
+#  define CMAN_MAX_CSID_LEN 4
+#  ifndef MAX_CSID_LEN
+#    define MAX_CSID_LEN CMAN_MAX_CSID_LEN
+#  endif
+#  undef MAX_CLUSTER_MEMBER_NAME_LEN
+#  define MAX_CLUSTER_MEMBER_NAME_LEN   CMAN_MAX_NODENAME_LEN
+#  define CMAN_MAX_CLUSTER_MESSAGE 1500
+#  define CLUSTER_PORT_CLVMD 11
+struct cluster_ops *init_cman_cluster(void);
+#endif
+
+#ifdef USE_OPENAIS
+#  include <openais/saAis.h>
+#  include <corosync/totem/totem.h>
+#  define OPENAIS_CSID_LEN (sizeof(int))
+#  define OPENAIS_MAX_CLUSTER_MESSAGE         MESSAGE_SIZE_MAX
+#  define OPENAIS_MAX_CLUSTER_MEMBER_NAME_LEN SA_MAX_NAME_LENGTH
+#  ifndef MAX_CLUSTER_MEMBER_NAME_LEN
+#    define MAX_CLUSTER_MEMBER_NAME_LEN       SA_MAX_NAME_LENGTH
+#  endif
+#  ifndef CMAN_MAX_CLUSTER_MESSAGE
+#    define CMAN_MAX_CLUSTER_MESSAGE          MESSAGE_SIZE_MAX
+#  endif
+#  ifndef MAX_CSID_LEN
+#    define MAX_CSID_LEN sizeof(int)
+#  endif
+struct cluster_ops *init_openais_cluster(void);
+#endif
+
+#ifdef USE_COROSYNC
+#  include <corosync/corotypes.h>
+#  define COROSYNC_CSID_LEN (sizeof(int))
+#  define COROSYNC_MAX_CLUSTER_MESSAGE         65535
+#  define COROSYNC_MAX_CLUSTER_MEMBER_NAME_LEN CS_MAX_NAME_LENGTH
+#  ifndef MAX_CLUSTER_MEMBER_NAME_LEN
+#    define MAX_CLUSTER_MEMBER_NAME_LEN       CS_MAX_NAME_LENGTH
+#  endif
+#  ifndef CMAN_MAX_CLUSTER_MESSAGE
+#    define CMAN_MAX_CLUSTER_MESSAGE          65535
+#  endif
+#  ifndef MAX_CSID_LEN
+#    define MAX_CSID_LEN sizeof(int)
+#  endif
+struct cluster_ops *init_corosync_cluster(void);
+#endif
+
+#ifdef USE_SINGLENODE
+#  define SINGLENODE_CSID_LEN (sizeof(int))
+#  ifndef MAX_CLUSTER_MEMBER_NAME_LEN
+#    define MAX_CLUSTER_MEMBER_NAME_LEN       64
+#  endif
+#  define SINGLENODE_MAX_CLUSTER_MESSAGE          65535
+#  ifndef MAX_CSID_LEN
+#    define MAX_CSID_LEN sizeof(int)
+#  endif
+struct cluster_ops *init_singlenode_cluster(void);
+#endif
+
+#endif

daemons/clvmd/clvmd-corosync.c

@@ -0,0 +1,662 @@
+/*
+ * Copyright (C) 2009-2012 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
+ */
+
+/*
+ * This provides the interface between clvmd and corosync/DLM as the cluster
+ * and lock manager.
+ */
+
+#include "clvmd-common.h"
+
+#include <pthread.h>
+
+#include "clvm.h"
+#include "clvmd-comms.h"
+#include "clvmd.h"
+#include "lvm-functions.h"
+
+#include "locking.h"
+
+#include <corosync/cpg.h>
+#include <corosync/quorum.h>
+
+#ifdef HAVE_COROSYNC_CONFDB_H
+#  include <corosync/confdb.h>
+#elif defined HAVE_COROSYNC_CMAP_H
+#  include <corosync/cmap.h>
+#else
+#  error "Either HAVE_COROSYNC_CONFDB_H or HAVE_COROSYNC_CMAP_H must be defined."
+#endif
+
+#include <libdlm.h>
+
+#include <syslog.h>
+
+/* Timeout value for several corosync calls */
+#define LOCKSPACE_NAME "clvmd"
+
+static void corosync_cpg_deliver_callback (cpg_handle_t handle,
+				  const struct cpg_name *groupName,
+				  uint32_t nodeid,
+				  uint32_t pid,
+				  void *msg,
+				  size_t msg_len);
+static void corosync_cpg_confchg_callback(cpg_handle_t handle,
+				 const struct cpg_name *groupName,
+				 const struct cpg_address *member_list, size_t member_list_entries,
+				 const struct cpg_address *left_list, size_t left_list_entries,
+				 const struct cpg_address *joined_list, size_t joined_list_entries);
+static void _cluster_closedown(void);
+
+/* Hash list of nodes in the cluster */
+static struct dm_hash_table *node_hash;
+
+/* Number of active nodes */
+static int num_nodes;
+static unsigned int our_nodeid;
+
+static struct local_client *cluster_client;
+
+/* Corosync handles */
+static cpg_handle_t cpg_handle;
+static quorum_handle_t quorum_handle;
+
+/* DLM Handle */
+static dlm_lshandle_t *lockspace;
+
+static struct cpg_name cpg_group_name;
+
+/* Corosync callback structs */
+cpg_callbacks_t corosync_cpg_callbacks = {
+	.cpg_deliver_fn =            corosync_cpg_deliver_callback,
+	.cpg_confchg_fn =            corosync_cpg_confchg_callback,
+};
+
+quorum_callbacks_t quorum_callbacks = {
+	.quorum_notify_fn = NULL,
+};
+
+struct node_info
+{
+	enum {NODE_DOWN, NODE_CLVMD} state;
+	int nodeid;
+};
+
+
+/* Set errno to something approximating the right value and return 0 or -1 */
+static int cs_to_errno(cs_error_t err)
+{
+	switch(err)
+	{
+	case CS_OK:
+		return 0;
+        case CS_ERR_LIBRARY:
+		errno = EINVAL;
+		break;
+        case CS_ERR_VERSION:
+		errno = EINVAL;
+		break;
+        case CS_ERR_INIT:
+		errno = EINVAL;
+		break;
+        case CS_ERR_TIMEOUT:
+		errno = ETIME;
+		break;
+        case CS_ERR_TRY_AGAIN:
+		errno = EAGAIN;
+		break;
+        case CS_ERR_INVALID_PARAM:
+		errno = EINVAL;
+		break;
+        case CS_ERR_NO_MEMORY:
+		errno = ENOMEM;
+		break;
+        case CS_ERR_BAD_HANDLE:
+		errno = EINVAL;
+		break;
+        case CS_ERR_BUSY:
+		errno = EBUSY;
+		break;
+        case CS_ERR_ACCESS:
+		errno = EPERM;
+		break;
+        case CS_ERR_NOT_EXIST:
+		errno = ENOENT;
+		break;
+        case CS_ERR_NAME_TOO_LONG:
+		errno = ENAMETOOLONG;
+		break;
+        case CS_ERR_EXIST:
+		errno = EEXIST;
+		break;
+        case CS_ERR_NO_SPACE:
+		errno = ENOSPC;
+		break;
+        case CS_ERR_INTERRUPT:
+		errno = EINTR;
+		break;
+	case CS_ERR_NAME_NOT_FOUND:
+		errno = ENOENT;
+		break;
+        case CS_ERR_NO_RESOURCES:
+		errno = ENOMEM;
+		break;
+        case CS_ERR_NOT_SUPPORTED:
+		errno = EOPNOTSUPP;
+		break;
+        case CS_ERR_BAD_OPERATION:
+		errno = EINVAL;
+		break;
+        case CS_ERR_FAILED_OPERATION:
+		errno = EIO;
+		break;
+        case CS_ERR_MESSAGE_ERROR:
+		errno = EIO;
+		break;
+        case CS_ERR_QUEUE_FULL:
+		errno = EXFULL;
+		break;
+        case CS_ERR_QUEUE_NOT_AVAILABLE:
+		errno = EINVAL;
+		break;
+        case CS_ERR_BAD_FLAGS:
+		errno = EINVAL;
+		break;
+        case CS_ERR_TOO_BIG:
+		errno = E2BIG;
+		break;
+        case CS_ERR_NO_SECTIONS:
+		errno = ENOMEM;
+		break;
+	default:
+		errno = EINVAL;
+		break;
+	}
+	return -1;
+}
+
+static char *print_corosync_csid(const char *csid)
+{
+	static char buf[128];
+	int id;
+
+	memcpy(&id, csid, sizeof(int));
+	sprintf(buf, "%d", id);
+	return buf;
+}
+
+static void corosync_cpg_deliver_callback (cpg_handle_t handle,
+				  const struct cpg_name *groupName,
+				  uint32_t nodeid,
+				  uint32_t pid,
+				  void *msg,
+				  size_t msg_len)
+{
+	int target_nodeid;
+
+	memcpy(&target_nodeid, msg, COROSYNC_CSID_LEN);
+
+	DEBUGLOG("%u got message from nodeid %d for %d. len %zd\n",
+		 our_nodeid, nodeid, target_nodeid, msg_len-4);
+
+	if (nodeid != our_nodeid)
+		if (target_nodeid == our_nodeid || target_nodeid == 0)
+			process_message(cluster_client, (char *)msg+COROSYNC_CSID_LEN,
+					msg_len-COROSYNC_CSID_LEN, (char*)&nodeid);
+}
+
+static void corosync_cpg_confchg_callback(cpg_handle_t handle,
+				 const struct cpg_name *groupName,
+				 const struct cpg_address *member_list, size_t member_list_entries,
+				 const struct cpg_address *left_list, size_t left_list_entries,
+				 const struct cpg_address *joined_list, size_t joined_list_entries)
+{
+	int i;
+	struct node_info *ninfo;
+
+	DEBUGLOG("confchg callback. %zd joined, %zd left, %zd members\n",
+		 joined_list_entries, left_list_entries, member_list_entries);
+
+	for (i=0; i<joined_list_entries; i++) {
+		ninfo = dm_hash_lookup_binary(node_hash,
+					      (char *)&joined_list[i].nodeid,
+					      COROSYNC_CSID_LEN);
+		if (!ninfo) {
+			ninfo = malloc(sizeof(struct node_info));
+			if (!ninfo) {
+				break;
+			}
+			else {
+				ninfo->nodeid = joined_list[i].nodeid;
+				dm_hash_insert_binary(node_hash,
+						      (char *)&ninfo->nodeid,
+						      COROSYNC_CSID_LEN, ninfo);
+			}
+		}
+		ninfo->state = NODE_CLVMD;
+	}
+
+	for (i=0; i<left_list_entries; i++) {
+		ninfo = dm_hash_lookup_binary(node_hash,
+					      (char *)&left_list[i].nodeid,
+					      COROSYNC_CSID_LEN);
+		if (ninfo)
+			ninfo->state = NODE_DOWN;
+	}
+
+	num_nodes = member_list_entries;
+}
+
+static int _init_cluster(void)
+{
+	cs_error_t err;
+
+#ifdef QUORUM_SET	/* corosync/quorum.h */
+	uint32_t quorum_type;
+#endif
+
+	node_hash = dm_hash_create(100);
+
+	err = cpg_initialize(&cpg_handle,
+			     &corosync_cpg_callbacks);
+	if (err != CS_OK) {
+		syslog(LOG_ERR, "Cannot initialise Corosync CPG service: %d",
+		       err);
+		DEBUGLOG("Cannot initialise Corosync CPG service: %d", err);
+		return cs_to_errno(err);
+	}
+
+#ifdef QUORUM_SET
+	err = quorum_initialize(&quorum_handle,
+				&quorum_callbacks,
+				&quorum_type);
+
+	if (quorum_type != QUORUM_SET) {
+		syslog(LOG_ERR, "Corosync quorum service is not configured");
+		DEBUGLOG("Corosync quorum service is not configured");
+		return EINVAL;
+	}
+#else
+	err = quorum_initialize(&quorum_handle,
+				&quorum_callbacks);
+#endif
+
+	if (err != CS_OK) {
+		syslog(LOG_ERR, "Cannot initialise Corosync quorum service: %d",
+		       err);
+		DEBUGLOG("Cannot initialise Corosync quorum service: %d", err);
+		return cs_to_errno(err);
+	}
+
+	/* Create a lockspace for LV & VG locks to live in */
+	lockspace = dlm_open_lockspace(LOCKSPACE_NAME);
+	if (!lockspace) {
+		lockspace = dlm_create_lockspace(LOCKSPACE_NAME, 0600);
+		if (!lockspace) {
+			syslog(LOG_ERR, "Unable to create DLM lockspace for CLVM: %m");
+			return -1;
+		}
+		DEBUGLOG("Created DLM lockspace for CLVMD.\n");
+	} else
+		DEBUGLOG("Opened existing DLM lockspace for CLVMD.\n");
+
+	dlm_ls_pthread_init(lockspace);
+	DEBUGLOG("DLM initialisation complete\n");
+
+	/* Connect to the clvmd group */
+	strcpy((char *)cpg_group_name.value, "clvmd");
+	cpg_group_name.length = strlen((char *)cpg_group_name.value);
+	err = cpg_join(cpg_handle, &cpg_group_name);
+	if (err != CS_OK) {
+		cpg_finalize(cpg_handle);
+		quorum_finalize(quorum_handle);
+		dlm_release_lockspace(LOCKSPACE_NAME, lockspace, 1);
+		syslog(LOG_ERR, "Cannot join clvmd process group");
+		DEBUGLOG("Cannot join clvmd process group: %d\n", err);
+		return cs_to_errno(err);
+	}
+
+	err = cpg_local_get(cpg_handle,
+			    &our_nodeid);
+	if (err != CS_OK) {
+		cpg_finalize(cpg_handle);
+		quorum_finalize(quorum_handle);
+		dlm_release_lockspace(LOCKSPACE_NAME, lockspace, 1);
+		syslog(LOG_ERR, "Cannot get local node id\n");
+		return cs_to_errno(err);
+	}
+	DEBUGLOG("Our local node id is %d\n", our_nodeid);
+
+	DEBUGLOG("Connected to Corosync\n");
+
+	return 0;
+}
+
+static void _cluster_closedown(void)
+{
+	dlm_release_lockspace(LOCKSPACE_NAME, lockspace, 1);
+	cpg_finalize(cpg_handle);
+	quorum_finalize(quorum_handle);
+}
+
+static void _get_our_csid(char *csid)
+{
+	memcpy(csid, &our_nodeid, sizeof(int));
+}
+
+/* Corosync doesn't really have nmode names so we
+   just use the node ID in hex instead */
+static int _csid_from_name(char *csid, const char *name)
+{
+	int nodeid;
+	struct node_info *ninfo;
+
+	if (sscanf(name, "%x", &nodeid) == 1) {
+		ninfo = dm_hash_lookup_binary(node_hash, csid, COROSYNC_CSID_LEN);
+		if (ninfo)
+			return nodeid;
+	}
+	return -1;
+}
+
+static int _name_from_csid(const char *csid, char *name)
+{
+	struct node_info *ninfo;
+
+	ninfo = dm_hash_lookup_binary(node_hash, csid, COROSYNC_CSID_LEN);
+	if (!ninfo)
+	{
+		sprintf(name, "UNKNOWN %s", print_corosync_csid(csid));
+		return -1;
+	}
+
+	sprintf(name, "%x", ninfo->nodeid);
+	return 0;
+}
+
+static int _get_num_nodes(void)
+{
+	DEBUGLOG("num_nodes = %d\n", num_nodes);
+	return num_nodes;
+}
+
+/* Node is now known to be running a clvmd */
+static void _add_up_node(const char *csid)
+{
+	struct node_info *ninfo;
+
+	ninfo = dm_hash_lookup_binary(node_hash, csid, COROSYNC_CSID_LEN);
+	if (!ninfo) {
+		DEBUGLOG("corosync_add_up_node no node_hash entry for csid %s\n",
+			 print_corosync_csid(csid));
+		return;
+	}
+
+	DEBUGLOG("corosync_add_up_node %d\n", ninfo->nodeid);
+
+	ninfo->state = NODE_CLVMD;
+
+	return;
+}
+
+/* Call a callback for each node, so the caller knows whether it's up or down */
+static int _cluster_do_node_callback(struct local_client *master_client,
+				     void (*callback)(struct local_client *,
+						      const char *csid, int node_up))
+{
+	struct dm_hash_node *hn;
+	struct node_info *ninfo;
+
+	dm_hash_iterate(hn, node_hash)
+	{
+		char csid[COROSYNC_CSID_LEN];
+
+		ninfo = dm_hash_get_data(node_hash, hn);
+		memcpy(csid, dm_hash_get_key(node_hash, hn), COROSYNC_CSID_LEN);
+
+		DEBUGLOG("down_callback. node %d, state = %d\n", ninfo->nodeid,
+			 ninfo->state);
+
+		if (ninfo->state == NODE_CLVMD)
+			callback(master_client, csid, 1);
+	}
+	return 0;
+}
+
+/* Real locking */
+static int _lock_resource(const char *resource, int mode, int flags, int *lockid)
+{
+	struct dlm_lksb lksb;
+	int err;
+
+	DEBUGLOG("lock_resource '%s', flags=%d, mode=%d\n", resource, flags, mode);
+
+	if (flags & LKF_CONVERT)
+		lksb.sb_lkid = *lockid;
+
+	err = dlm_ls_lock_wait(lockspace,
+			       mode,
+			       &lksb,
+			       flags,
+			       resource,
+			       strlen(resource),
+			       0,
+			       NULL, NULL, NULL);
+
+	if (err != 0)
+	{
+		DEBUGLOG("dlm_ls_lock returned %d\n", errno);
+		return err;
+	}
+	if (lksb.sb_status != 0)
+	{
+		DEBUGLOG("dlm_ls_lock returns lksb.sb_status %d\n", lksb.sb_status);
+		errno = lksb.sb_status;
+		return -1;
+	}
+
+	DEBUGLOG("lock_resource returning %d, lock_id=%x\n", err, lksb.sb_lkid);
+
+	*lockid = lksb.sb_lkid;
+
+	return 0;
+}
+
+
+static int _unlock_resource(const char *resource, int lockid)
+{
+	struct dlm_lksb lksb;
+	int err;
+
+	DEBUGLOG("unlock_resource: %s lockid: %x\n", resource, lockid);
+	lksb.sb_lkid = lockid;
+
+	err = dlm_ls_unlock_wait(lockspace,
+				 lockid,
+				 0,
+				 &lksb);
+	if (err != 0)
+	{
+		DEBUGLOG("Unlock returned %d\n", err);
+		return err;
+	}
+	if (lksb.sb_status != EUNLOCK)
+	{
+		DEBUGLOG("dlm_ls_unlock_wait returns lksb.sb_status: %d\n", lksb.sb_status);
+		errno = lksb.sb_status;
+		return -1;
+	}   
+
+
+	return 0;
+}
+
+static int _is_quorate(void)
+{
+	int quorate;
+	if (quorum_getquorate(quorum_handle, &quorate) == CS_OK)
+		return quorate;
+	else
+		return 0;
+}
+
+static int _get_main_cluster_fd(void)
+{
+	int select_fd;
+
+	cpg_fd_get(cpg_handle, &select_fd);
+	return select_fd;
+}
+
+static int _cluster_fd_callback(struct local_client *fd, char *buf, int len,
+				const char *csid,
+				struct local_client **new_client)
+{
+	cluster_client = fd;
+	*new_client = NULL;
+	cpg_dispatch(cpg_handle, CS_DISPATCH_ONE);
+	return 1;
+}
+
+static int _cluster_send_message(const void *buf, int msglen, const char *csid,
+				 const char *errtext)
+{
+	static pthread_mutex_t _mutex = PTHREAD_MUTEX_INITIALIZER;
+	struct iovec iov[2];
+	cs_error_t err;
+	int target_node;
+
+	if (csid)
+		memcpy(&target_node, csid, COROSYNC_CSID_LEN);
+	else
+		target_node = 0;
+
+	iov[0].iov_base = &target_node;
+	iov[0].iov_len = sizeof(int);
+	iov[1].iov_base = (char *)buf;
+	iov[1].iov_len = msglen;
+
+	pthread_mutex_lock(&_mutex);
+	err = cpg_mcast_joined(cpg_handle, CPG_TYPE_AGREED, iov, 2);
+	pthread_mutex_unlock(&_mutex);
+
+	return cs_to_errno(err);
+}
+
+#ifdef HAVE_COROSYNC_CONFDB_H
+/*
+ * We are not necessarily connected to a Red Hat Cluster system,
+ * but if we are, this returns the cluster name from cluster.conf.
+ * I've used confdb rather than ccs to reduce the inter-package
+ * dependancies as well as to allow people to set a cluster name
+ * for themselves even if they are not running on RH cluster.
+ */
+static int _get_cluster_name(char *buf, int buflen)
+{
+	confdb_handle_t handle;
+	int result;
+	size_t namelen = buflen;
+	hdb_handle_t cluster_handle;
+	confdb_callbacks_t callbacks = {
+		.confdb_key_change_notify_fn = NULL,
+		.confdb_object_create_change_notify_fn = NULL,
+		.confdb_object_delete_change_notify_fn = NULL
+	};
+
+	/* This is a default in case everything else fails */
+	strncpy(buf, "Corosync", buflen);
+
+	/* Look for a cluster name in confdb */
+	result = confdb_initialize (&handle, &callbacks);
+        if (result != CS_OK)
+		return 0;
+
+        result = confdb_object_find_start(handle, OBJECT_PARENT_HANDLE);
+	if (result != CS_OK)
+		goto out;
+
+        result = confdb_object_find(handle, OBJECT_PARENT_HANDLE, (void *)"cluster", strlen("cluster"), &cluster_handle);
+        if (result != CS_OK)
+		goto out;
+
+        result = confdb_key_get(handle, cluster_handle, (void *)"name", strlen("name"), buf, &namelen);
+        if (result != CS_OK)
+		goto out;
+
+	buf[namelen] = '\0';
+
+out:
+	confdb_finalize(handle);
+	return 0;
+}
+
+#elif defined HAVE_COROSYNC_CMAP_H
+
+static int _get_cluster_name(char *buf, int buflen)
+{
+	cmap_handle_t cmap_handle = 0;
+	int result;
+	char *name = NULL;
+
+	/* This is a default in case everything else fails */
+	strncpy(buf, "Corosync", buflen);
+
+	/* Look for a cluster name in cmap */
+	result = cmap_initialize(&cmap_handle);
+	if (result != CS_OK)
+		return 0;
+
+	result = cmap_get_string(cmap_handle, "totem.cluster_name", &name);
+	if (result != CS_OK)
+		goto out;
+
+	memset(buf, 0, buflen);
+	strncpy(buf, name, buflen - 1);
+
+out:
+	if (name)
+		free(name);
+	cmap_finalize(cmap_handle);
+	return 0;
+}
+
+#endif
+
+static struct cluster_ops _cluster_corosync_ops = {
+	.name                     = "corosync",
+	.cluster_init_completed   = NULL,
+	.cluster_send_message     = _cluster_send_message,
+	.name_from_csid           = _name_from_csid,
+	.csid_from_name           = _csid_from_name,
+	.get_num_nodes            = _get_num_nodes,
+	.cluster_fd_callback      = _cluster_fd_callback,
+	.get_main_cluster_fd      = _get_main_cluster_fd,
+	.cluster_do_node_callback = _cluster_do_node_callback,
+	.is_quorate               = _is_quorate,
+	.get_our_csid             = _get_our_csid,
+	.add_up_node              = _add_up_node,
+	.reread_config            = NULL,
+	.cluster_closedown        = _cluster_closedown,
+	.get_cluster_name         = _get_cluster_name,
+	.sync_lock                = _lock_resource,
+	.sync_unlock              = _unlock_resource,
+};
+
+struct cluster_ops *init_corosync_cluster(void)
+{
+	if (!_init_cluster())
+		return &_cluster_corosync_ops;
+	else
+		return NULL;
+}

daemons/clvmd/clvmd-openais.c

@@ -0,0 +1,687 @@
+/*
+ * Copyright (C) 2007-2009 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
+ */
+
+/*
+ * This provides the interface between clvmd and OpenAIS as the cluster
+ * and lock manager.
+ */
+
+#include "clvmd-common.h"
+
+#include <pthread.h>
+#include <fcntl.h>
+#include <syslog.h>
+
+#include <openais/saAis.h>
+#include <openais/saLck.h>
+
+#include <corosync/corotypes.h>
+#include <corosync/cpg.h>
+
+#include "locking.h"
+#include "clvm.h"
+#include "clvmd-comms.h"
+#include "lvm-functions.h"
+#include "clvmd.h"
+
+/* Timeout value for several openais calls */
+#define TIMEOUT 10
+
+static void openais_cpg_deliver_callback (cpg_handle_t handle,
+				  const struct cpg_name *groupName,
+				  uint32_t nodeid,
+				  uint32_t pid,
+				  void *msg,
+				  size_t msg_len);
+static void openais_cpg_confchg_callback(cpg_handle_t handle,
+				 const struct cpg_name *groupName,
+				 const struct cpg_address *member_list, size_t member_list_entries,
+				 const struct cpg_address *left_list, size_t left_list_entries,
+				 const struct cpg_address *joined_list, size_t joined_list_entries);
+
+static void _cluster_closedown(void);
+
+/* Hash list of nodes in the cluster */
+static struct dm_hash_table *node_hash;
+
+/* For associating lock IDs & resource handles */
+static struct dm_hash_table *lock_hash;
+
+/* Number of active nodes */
+static int num_nodes;
+static unsigned int our_nodeid;
+
+static struct local_client *cluster_client;
+
+/* OpenAIS handles */
+static cpg_handle_t cpg_handle;
+static SaLckHandleT lck_handle;
+
+static struct cpg_name cpg_group_name;
+
+/* Openais callback structs */
+cpg_callbacks_t openais_cpg_callbacks = {
+	.cpg_deliver_fn =            openais_cpg_deliver_callback,
+	.cpg_confchg_fn =            openais_cpg_confchg_callback,
+};
+
+struct node_info
+{
+	enum {NODE_UNKNOWN, NODE_DOWN, NODE_UP, NODE_CLVMD} state;
+	int nodeid;
+};
+
+struct lock_info
+{
+	SaLckResourceHandleT res_handle;
+	SaLckLockIdT         lock_id;
+	SaNameT              lock_name;
+};
+
+/* Set errno to something approximating the right value and return 0 or -1 */
+static int ais_to_errno(SaAisErrorT err)
+{
+	switch(err)
+	{
+	case SA_AIS_OK:
+		return 0;
+        case SA_AIS_ERR_LIBRARY:
+		errno = EINVAL;
+		break;
+        case SA_AIS_ERR_VERSION:
+		errno = EINVAL;
+		break;
+        case SA_AIS_ERR_INIT:
+		errno = EINVAL;
+		break;
+        case SA_AIS_ERR_TIMEOUT:
+		errno = ETIME;
+		break;
+        case SA_AIS_ERR_TRY_AGAIN:
+		errno = EAGAIN;
+		break;
+        case SA_AIS_ERR_INVALID_PARAM:
+		errno = EINVAL;
+		break;
+        case SA_AIS_ERR_NO_MEMORY:
+		errno = ENOMEM;
+		break;
+        case SA_AIS_ERR_BAD_HANDLE:
+		errno = EINVAL;
+		break;
+        case SA_AIS_ERR_BUSY:
+		errno = EBUSY;
+		break;
+        case SA_AIS_ERR_ACCESS:
+		errno = EPERM;
+		break;
+        case SA_AIS_ERR_NOT_EXIST:
+		errno = ENOENT;
+		break;
+        case SA_AIS_ERR_NAME_TOO_LONG:
+		errno = ENAMETOOLONG;
+		break;
+        case SA_AIS_ERR_EXIST:
+		errno = EEXIST;
+		break;
+        case SA_AIS_ERR_NO_SPACE:
+		errno = ENOSPC;
+		break;
+        case SA_AIS_ERR_INTERRUPT:
+		errno = EINTR;
+		break;
+	case SA_AIS_ERR_NAME_NOT_FOUND:
+		errno = ENOENT;
+		break;
+        case SA_AIS_ERR_NO_RESOURCES:
+		errno = ENOMEM;
+		break;
+        case SA_AIS_ERR_NOT_SUPPORTED:
+		errno = EOPNOTSUPP;
+		break;
+        case SA_AIS_ERR_BAD_OPERATION:
+		errno = EINVAL;
+		break;
+        case SA_AIS_ERR_FAILED_OPERATION:
+		errno = EIO;
+		break;
+        case SA_AIS_ERR_MESSAGE_ERROR:
+		errno = EIO;
+		break;
+        case SA_AIS_ERR_QUEUE_FULL:
+		errno = EXFULL;
+		break;
+        case SA_AIS_ERR_QUEUE_NOT_AVAILABLE:
+		errno = EINVAL;
+		break;
+        case SA_AIS_ERR_BAD_FLAGS:
+		errno = EINVAL;
+		break;
+        case SA_AIS_ERR_TOO_BIG:
+		errno = E2BIG;
+		break;
+        case SA_AIS_ERR_NO_SECTIONS:
+		errno = ENOMEM;
+		break;
+	default:
+		errno = EINVAL;
+		break;
+	}
+	return -1;
+}
+
+static char *print_openais_csid(const char *csid)
+{
+	static char buf[128];
+	int id;
+
+	memcpy(&id, csid, sizeof(int));
+	sprintf(buf, "%d", id);
+	return buf;
+}
+
+static int add_internal_client(int fd, fd_callback_t callback)
+{
+	struct local_client *client;
+
+	DEBUGLOG("Add_internal_client, fd = %d\n", fd);
+
+	if (!(client = dm_zalloc(sizeof(*client)))) {
+		DEBUGLOG("malloc failed\n");
+		return -1;
+	}
+
+	client->fd = fd;
+	client->type = CLUSTER_INTERNAL;
+	client->callback = callback;
+	add_client(client);
+
+	/* Set Close-on-exec */
+	fcntl(fd, F_SETFD, 1);
+
+	return 0;
+}
+
+static void openais_cpg_deliver_callback (cpg_handle_t handle,
+				  const struct cpg_name *groupName,
+				  uint32_t nodeid,
+				  uint32_t pid,
+				  void *msg,
+				  size_t msg_len)
+{
+	int target_nodeid;
+
+	memcpy(&target_nodeid, msg, OPENAIS_CSID_LEN);
+
+	DEBUGLOG("%u got message from nodeid %d for %d. len %" PRIsize_t "\n",
+		 our_nodeid, nodeid, target_nodeid, msg_len-4);
+
+	if (nodeid != our_nodeid)
+		if (target_nodeid == our_nodeid || target_nodeid == 0)
+			process_message(cluster_client, (char *)msg+OPENAIS_CSID_LEN,
+					msg_len-OPENAIS_CSID_LEN, (char*)&nodeid);
+}
+
+static void openais_cpg_confchg_callback(cpg_handle_t handle,
+				 const struct cpg_name *groupName,
+				 const struct cpg_address *member_list, size_t member_list_entries,
+				 const struct cpg_address *left_list, size_t left_list_entries,
+				 const struct cpg_address *joined_list, size_t joined_list_entries)
+{
+	int i;
+	struct node_info *ninfo;
+
+	DEBUGLOG("confchg callback. %" PRIsize_t " joined, "
+		 FMTsize_t " left, %" PRIsize_t " members\n",
+		 joined_list_entries, left_list_entries, member_list_entries);
+
+	for (i=0; i<joined_list_entries; i++) {
+		ninfo = dm_hash_lookup_binary(node_hash,
+					      (char *)&joined_list[i].nodeid,
+					      OPENAIS_CSID_LEN);
+		if (!ninfo) {
+			ninfo = malloc(sizeof(struct node_info));
+			if (!ninfo) {
+				break;
+			}
+			else {
+				ninfo->nodeid = joined_list[i].nodeid;
+				dm_hash_insert_binary(node_hash,
+						      (char *)&ninfo->nodeid,
+						      OPENAIS_CSID_LEN, ninfo);
+			}
+		}
+		ninfo->state = NODE_CLVMD;
+	}
+
+	for (i=0; i<left_list_entries; i++) {
+		ninfo = dm_hash_lookup_binary(node_hash,
+					      (char *)&left_list[i].nodeid,
+					      OPENAIS_CSID_LEN);
+		if (ninfo)
+			ninfo->state = NODE_DOWN;
+	}
+
+	for (i=0; i<member_list_entries; i++) {
+		if (member_list[i].nodeid == 0) continue;
+		ninfo = dm_hash_lookup_binary(node_hash,
+				(char *)&member_list[i].nodeid,
+				OPENAIS_CSID_LEN);
+		if (!ninfo) {
+			ninfo = malloc(sizeof(struct node_info));
+			if (!ninfo) {
+				break;
+			}
+			else {
+				ninfo->nodeid = member_list[i].nodeid;
+				dm_hash_insert_binary(node_hash,
+						(char *)&ninfo->nodeid,
+						OPENAIS_CSID_LEN, ninfo);
+			}
+		}
+		ninfo->state = NODE_CLVMD;
+	}
+
+	num_nodes = member_list_entries;
+}
+
+static int lck_dispatch(struct local_client *client, char *buf, int len,
+			const char *csid, struct local_client **new_client)
+{
+	*new_client = NULL;
+	saLckDispatch(lck_handle, SA_DISPATCH_ONE);
+	return 1;
+}
+
+static int _init_cluster(void)
+{
+	SaAisErrorT err;
+	SaVersionT  ver = { 'B', 1, 1 };
+	int select_fd;
+
+	node_hash = dm_hash_create(100);
+	lock_hash = dm_hash_create(10);
+
+	err = cpg_initialize(&cpg_handle,
+			     &openais_cpg_callbacks);
+	if (err != SA_AIS_OK) {
+		syslog(LOG_ERR, "Cannot initialise OpenAIS CPG service: %d",
+		       err);
+		DEBUGLOG("Cannot initialise OpenAIS CPG service: %d", err);
+		return ais_to_errno(err);
+	}
+
+	err = saLckInitialize(&lck_handle,
+					NULL,
+			      &ver);
+	if (err != SA_AIS_OK) {
+		cpg_initialize(&cpg_handle, &openais_cpg_callbacks);
+		syslog(LOG_ERR, "Cannot initialise OpenAIS lock service: %d",
+		       err);
+		DEBUGLOG("Cannot initialise OpenAIS lock service: %d\n\n", err);
+		return ais_to_errno(err);
+	}
+
+	/* Connect to the clvmd group */
+	strcpy((char *)cpg_group_name.value, "clvmd");
+	cpg_group_name.length = strlen((char *)cpg_group_name.value);
+	err = cpg_join(cpg_handle, &cpg_group_name);
+	if (err != SA_AIS_OK) {
+		cpg_finalize(cpg_handle);
+		saLckFinalize(lck_handle);
+		syslog(LOG_ERR, "Cannot join clvmd process group");
+		DEBUGLOG("Cannot join clvmd process group: %d\n", err);
+		return ais_to_errno(err);
+	}
+
+	err = cpg_local_get(cpg_handle,
+			    &our_nodeid);
+	if (err != SA_AIS_OK) {
+		cpg_finalize(cpg_handle);
+		saLckFinalize(lck_handle);
+		syslog(LOG_ERR, "Cannot get local node id\n");
+		return ais_to_errno(err);
+	}
+	DEBUGLOG("Our local node id is %d\n", our_nodeid);
+
+	saLckSelectionObjectGet(lck_handle, (SaSelectionObjectT *)&select_fd);
+	add_internal_client(select_fd, lck_dispatch);
+
+	DEBUGLOG("Connected to OpenAIS\n");
+
+	return 0;
+}
+
+static void _cluster_closedown(void)
+{
+	saLckFinalize(lck_handle);
+	cpg_finalize(cpg_handle);
+}
+
+static void _get_our_csid(char *csid)
+{
+	memcpy(csid, &our_nodeid, sizeof(int));
+}
+
+/* OpenAIS doesn't really have nmode names so we
+   just use the node ID in hex instead */
+static int _csid_from_name(char *csid, const char *name)
+{
+	int nodeid;
+	struct node_info *ninfo;
+
+	if (sscanf(name, "%x", &nodeid) == 1) {
+		ninfo = dm_hash_lookup_binary(node_hash, csid, OPENAIS_CSID_LEN);
+		if (ninfo)
+			return nodeid;
+	}
+	return -1;
+}
+
+static int _name_from_csid(const char *csid, char *name)
+{
+	struct node_info *ninfo;
+
+	ninfo = dm_hash_lookup_binary(node_hash, csid, OPENAIS_CSID_LEN);
+	if (!ninfo)
+	{
+		sprintf(name, "UNKNOWN %s", print_openais_csid(csid));
+		return -1;
+	}
+
+	sprintf(name, "%x", ninfo->nodeid);
+	return 0;
+}
+
+static int _get_num_nodes()
+{
+	DEBUGLOG("num_nodes = %d\n", num_nodes);
+	return num_nodes;
+}
+
+/* Node is now known to be running a clvmd */
+static void _add_up_node(const char *csid)
+{
+	struct node_info *ninfo;
+
+	ninfo = dm_hash_lookup_binary(node_hash, csid, OPENAIS_CSID_LEN);
+	if (!ninfo) {
+		DEBUGLOG("openais_add_up_node no node_hash entry for csid %s\n",
+			 print_openais_csid(csid));
+		return;
+	}
+
+	DEBUGLOG("openais_add_up_node %d\n", ninfo->nodeid);
+
+	ninfo->state = NODE_CLVMD;
+}
+
+/* Call a callback for each node, so the caller knows whether it's up or down */
+static int _cluster_do_node_callback(struct local_client *master_client,
+				     void (*callback)(struct local_client *,
+						      const char *csid, int node_up))
+{
+	struct dm_hash_node *hn;
+	struct node_info *ninfo;
+	int somedown = 0;
+
+	dm_hash_iterate(hn, node_hash)
+	{
+		char csid[OPENAIS_CSID_LEN];
+
+		ninfo = dm_hash_get_data(node_hash, hn);
+		memcpy(csid, dm_hash_get_key(node_hash, hn), OPENAIS_CSID_LEN);
+
+		DEBUGLOG("down_callback. node %d, state = %d\n", ninfo->nodeid,
+			 ninfo->state);
+
+		if (ninfo->state != NODE_DOWN)
+			callback(master_client, csid, ninfo->state == NODE_CLVMD);
+		if (ninfo->state != NODE_CLVMD)
+			somedown = -1;
+	}
+	return somedown;
+}
+
+/* Real locking */
+static int _lock_resource(char *resource, int mode, int flags, int *lockid)
+{
+	struct lock_info *linfo;
+	SaLckResourceHandleT res_handle;
+	SaAisErrorT err;
+	SaLckLockIdT lock_id;
+	SaLckLockStatusT lockStatus;
+
+	/* This needs to be converted from DLM/LVM2 value for OpenAIS LCK */
+	if (flags & LCK_NONBLOCK) flags = SA_LCK_LOCK_NO_QUEUE;
+
+	linfo = malloc(sizeof(struct lock_info));
+	if (!linfo)
+		return -1;
+
+	DEBUGLOG("lock_resource '%s', flags=%d, mode=%d\n", resource, flags, mode);
+
+	linfo->lock_name.length = strlen(resource)+1;
+	strcpy((char *)linfo->lock_name.value, resource);
+
+	err = saLckResourceOpen(lck_handle, &linfo->lock_name,
+				SA_LCK_RESOURCE_CREATE, TIMEOUT, &res_handle);
+	if (err != SA_AIS_OK)
+	{
+		DEBUGLOG("ResourceOpen returned %d\n", err);
+		free(linfo);
+		return ais_to_errno(err);
+	}
+
+	err = saLckResourceLock(
+			res_handle,
+			&lock_id,
+			mode,
+			flags,
+			0,
+			SA_TIME_END,
+			&lockStatus);
+	if (err != SA_AIS_OK && lockStatus != SA_LCK_LOCK_GRANTED)
+	{
+		free(linfo);
+		saLckResourceClose(res_handle);
+		return ais_to_errno(err);
+	}
+
+	/* Wait for it to complete */
+
+	DEBUGLOG("lock_resource returning %d, lock_id=%" PRIx64 "\n",
+		 err, lock_id);
+
+	linfo->lock_id = lock_id;
+	linfo->res_handle = res_handle;
+
+	dm_hash_insert(lock_hash, resource, linfo);
+
+	return ais_to_errno(err);
+}
+
+
+static int _unlock_resource(char *resource, int lockid)
+{
+	SaAisErrorT err;
+	struct lock_info *linfo;
+
+	DEBUGLOG("unlock_resource %s\n", resource);
+	linfo = dm_hash_lookup(lock_hash, resource);
+	if (!linfo)
+		return 0;
+
+	DEBUGLOG("unlock_resource: lockid: %" PRIx64 "\n", linfo->lock_id);
+	err = saLckResourceUnlock(linfo->lock_id, SA_TIME_END);
+	if (err != SA_AIS_OK)
+	{
+		DEBUGLOG("Unlock returned %d\n", err);
+		return ais_to_errno(err);
+	}
+
+	/* Release the resource */
+	dm_hash_remove(lock_hash, resource);
+	saLckResourceClose(linfo->res_handle);
+	free(linfo);
+
+	return ais_to_errno(err);
+}
+
+static int _sync_lock(const char *resource, int mode, int flags, int *lockid)
+{
+	int status;
+	char lock1[strlen(resource)+3];
+	char lock2[strlen(resource)+3];
+
+	snprintf(lock1, sizeof(lock1), "%s-1", resource);
+	snprintf(lock2, sizeof(lock2), "%s-2", resource);
+
+	switch (mode)
+	{
+	case LCK_EXCL:
+		status = _lock_resource(lock1, SA_LCK_EX_LOCK_MODE, flags, lockid);
+		if (status)
+			goto out;
+
+		/* If we can't get this lock too then bail out */
+		status = _lock_resource(lock2, SA_LCK_EX_LOCK_MODE, LCK_NONBLOCK,
+					lockid);
+		if (status == SA_LCK_LOCK_NOT_QUEUED)
+		{
+			_unlock_resource(lock1, *lockid);
+			status = -1;
+			errno = EAGAIN;
+		}
+		break;
+
+	case LCK_PREAD:
+	case LCK_READ:
+		status = _lock_resource(lock1, SA_LCK_PR_LOCK_MODE, flags, lockid);
+		if (status)
+			goto out;
+		_unlock_resource(lock2, *lockid);
+		break;
+
+	case LCK_WRITE:
+		status = _lock_resource(lock2, SA_LCK_EX_LOCK_MODE, flags, lockid);
+		if (status)
+			goto out;
+		_unlock_resource(lock1, *lockid);
+		break;
+
+	default:
+		status = -1;
+		errno = EINVAL;
+		break;
+	}
+out:
+	*lockid = mode;
+	return status;
+}
+
+static int _sync_unlock(const char *resource, int lockid)
+{
+	int status = 0;
+	char lock1[strlen(resource)+3];
+	char lock2[strlen(resource)+3];
+
+	snprintf(lock1, sizeof(lock1), "%s-1", resource);
+	snprintf(lock2, sizeof(lock2), "%s-2", resource);
+
+	_unlock_resource(lock1, lockid);
+	_unlock_resource(lock2, lockid);
+
+	return status;
+}
+
+/* We are always quorate ! */
+static int _is_quorate()
+{
+	return 1;
+}
+
+static int _get_main_cluster_fd(void)
+{
+	int select_fd;
+
+	cpg_fd_get(cpg_handle, &select_fd);
+	return select_fd;
+}
+
+static int _cluster_fd_callback(struct local_client *fd, char *buf, int len,
+				const char *csid,
+				struct local_client **new_client)
+{
+	cluster_client = fd;
+	*new_client = NULL;
+	cpg_dispatch(cpg_handle, SA_DISPATCH_ONE);
+	return 1;
+}
+
+static int _cluster_send_message(const void *buf, int msglen, const char *csid,
+				 const char *errtext)
+{
+	struct iovec iov[2];
+	SaAisErrorT err;
+	int target_node;
+
+	if (csid)
+		memcpy(&target_node, csid, OPENAIS_CSID_LEN);
+	else
+		target_node = 0;
+
+	iov[0].iov_base = &target_node;
+	iov[0].iov_len = sizeof(int);
+	iov[1].iov_base = (char *)buf;
+	iov[1].iov_len = msglen;
+
+	err = cpg_mcast_joined(cpg_handle, CPG_TYPE_AGREED, iov, 2);
+	return ais_to_errno(err);
+}
+
+/* We don't have a cluster name to report here */
+static int _get_cluster_name(char *buf, int buflen)
+{
+	strncpy(buf, "OpenAIS", buflen);
+	return 0;
+}
+
+static struct cluster_ops _cluster_openais_ops = {
+	.name                     = "openais",
+	.cluster_init_completed   = NULL,
+	.cluster_send_message     = _cluster_send_message,
+	.name_from_csid           = _name_from_csid,
+	.csid_from_name           = _csid_from_name,
+	.get_num_nodes            = _get_num_nodes,
+	.cluster_fd_callback      = _cluster_fd_callback,
+	.get_main_cluster_fd      = _get_main_cluster_fd,
+	.cluster_do_node_callback = _cluster_do_node_callback,
+	.is_quorate               = _is_quorate,
+	.get_our_csid             = _get_our_csid,
+	.add_up_node              = _add_up_node,
+	.reread_config            = NULL,
+	.cluster_closedown        = _cluster_closedown,
+	.get_cluster_name         = _get_cluster_name,
+	.sync_lock                = _sync_lock,
+	.sync_unlock              = _sync_unlock,
+};
+
+struct cluster_ops *init_openais_cluster(void)
+{
+	if (!_init_cluster())
+		return &_cluster_openais_ops;
+
+	return NULL;
+}

daemons/clvmd/clvmd-singlenode.c

@@ -0,0 +1,382 @@
+/*
+ * Copyright (C) 2009-2013 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 "clvmd-common.h"
+
+#include <pthread.h>
+
+#include "locking.h"
+#include "clvm.h"
+#include "clvmd-comms.h"
+#include "clvmd.h"
+
+#include <sys/un.h>
+#include <sys/socket.h>
+#include <fcntl.h>
+
+static const char SINGLENODE_CLVMD_SOCKNAME[] = DEFAULT_RUN_DIR "/clvmd_singlenode.sock";
+static int listen_fd = -1;
+
+static struct dm_hash_table *_locks;
+static int _lockid;
+
+static pthread_mutex_t _lock_mutex = PTHREAD_MUTEX_INITIALIZER;
+/* Using one common condition for all locks for simplicity */
+static pthread_cond_t _lock_cond = PTHREAD_COND_INITIALIZER;
+
+struct lock {
+	struct dm_list list;
+	int lockid;
+	int mode;
+};
+
+static void close_comms(void)
+{
+	if (listen_fd != -1 && close(listen_fd))
+		stack;
+	(void)unlink(SINGLENODE_CLVMD_SOCKNAME);
+	listen_fd = -1;
+}
+
+static int init_comms(void)
+{
+	mode_t old_mask;
+	struct sockaddr_un addr = { .sun_family = AF_UNIX };
+
+	if (!dm_strncpy(addr.sun_path, SINGLENODE_CLVMD_SOCKNAME,
+			sizeof(addr.sun_path))) {
+		DEBUGLOG("%s: singlenode socket name too long.",
+			 SINGLENODE_CLVMD_SOCKNAME);
+		return -1;
+	}
+
+	close_comms();
+
+	(void) dm_prepare_selinux_context(SINGLENODE_CLVMD_SOCKNAME, S_IFSOCK);
+	old_mask = umask(0077);
+
+	listen_fd = socket(PF_UNIX, SOCK_STREAM, 0);
+	if (listen_fd < 0) {
+		DEBUGLOG("Can't create local socket: %s\n", strerror(errno));
+		goto error;
+	}
+	/* Set Close-on-exec */
+	if (fcntl(listen_fd, F_SETFD, 1)) {
+		DEBUGLOG("Setting CLOEXEC on client fd failed: %s\n", strerror(errno));
+		goto error;
+	}
+
+	if (bind(listen_fd, (struct sockaddr *)&addr, sizeof(addr)) < 0) {
+		DEBUGLOG("Can't bind local socket: %s\n", strerror(errno));
+		goto error;
+	}
+	if (listen(listen_fd, 10) < 0) {
+		DEBUGLOG("Can't listen local socket: %s\n", strerror(errno));
+		goto error;
+	}
+
+	umask(old_mask);
+	(void) dm_prepare_selinux_context(NULL, 0);
+	return 0;
+error:
+	umask(old_mask);
+	(void) dm_prepare_selinux_context(NULL, 0);
+	close_comms();
+	return -1;
+}
+
+static int _init_cluster(void)
+{
+	int r;
+
+	if (!(_locks = dm_hash_create(128))) {
+		DEBUGLOG("Failed to allocate single-node hash table.\n");
+		return 1;
+	}
+
+	r = init_comms();
+	if (r) {
+		dm_hash_destroy(_locks);
+		_locks = NULL;
+		return r;
+	}
+
+	DEBUGLOG("Single-node cluster initialised.\n");
+	return 0;
+}
+
+static void _cluster_closedown(void)
+{
+	close_comms();
+
+	/* If there is any awaited resource, kill it softly */
+	pthread_mutex_lock(&_lock_mutex);
+	dm_hash_destroy(_locks);
+	_locks = NULL;
+	_lockid = 0;
+	pthread_cond_broadcast(&_lock_cond); /* wakeup waiters */
+	pthread_mutex_unlock(&_lock_mutex);
+}
+
+static void _get_our_csid(char *csid)
+{
+	int nodeid = 1;
+	memcpy(csid, &nodeid, sizeof(int));
+}
+
+static int _csid_from_name(char *csid, const char *name)
+{
+	return 1;
+}
+
+static int _name_from_csid(const char *csid, char *name)
+{
+	strcpy(name, "SINGLENODE");
+	return 0;
+}
+
+static int _get_num_nodes(void)
+{
+	return 1;
+}
+
+/* Node is now known to be running a clvmd */
+static void _add_up_node(const char *csid)
+{
+}
+
+/* Call a callback for each node, so the caller knows whether it's up or down */
+static int _cluster_do_node_callback(struct local_client *master_client,
+				     void (*callback)(struct local_client *,
+				     const char *csid, int node_up))
+{
+	return 0;
+}
+
+int _lock_file(const char *file, uint32_t flags);
+
+static const char *_get_mode(int mode)
+{
+	switch (mode) {
+	case LCK_NULL: return "NULL";
+	case LCK_READ: return "READ";
+	case LCK_PREAD: return "PREAD";
+	case LCK_WRITE: return "WRITE";
+	case LCK_EXCL: return "EXCLUSIVE";
+	case LCK_UNLOCK: return "UNLOCK";
+	default: return "????";
+	}
+}
+
+/* Real locking */
+static int _lock_resource(const char *resource, int mode, int flags, int *lockid)
+{
+	/* DLM table of allowed transition states */
+	static const int _dlm_table[6][6] = {
+	/* Mode	   NL	CR	CW	PR	PW	EX */
+	/* NL */ { 1,	 1,	 1,	 1,	 1,	 1},
+	/* CR */ { 1,	 1,	 1,	 1,	 1,	 0},
+	/* CW */ { 1,	 1,	 1,	 0,	 0,	 0},
+	/* PR */ { 1,	 1,	 0,	 1,	 0,	 0},
+	/* PW */ { 1,	 1,	 0,	 0,	 0,	 0},
+	/* EX */ { 1,	 0,	 0,	 0,	 0,	 0}
+	};
+
+	struct lock *lck = NULL, *lckt;
+	struct dm_list *head;
+
+	DEBUGLOG("Locking resource %s, flags=0x%02x (%s%s%s), mode=%s (%d)\n",
+		 resource, flags,
+		 (flags & LCKF_NOQUEUE) ? "NOQUEUE" : "",
+		 ((flags & (LCKF_NOQUEUE | LCKF_CONVERT)) ==
+		  (LCKF_NOQUEUE | LCKF_CONVERT)) ? "|" : "",
+		 (flags & LCKF_CONVERT) ? "CONVERT" : "",
+		 _get_mode(mode), mode);
+
+	mode &= LCK_TYPE_MASK;
+	pthread_mutex_lock(&_lock_mutex);
+
+retry:
+	if (!(head = dm_hash_lookup(_locks, resource))) {
+		if (flags & LCKF_CONVERT) {
+			/* In real DLM, lock is identified only by lockid, resource is not used */
+			DEBUGLOG("Unlocked resource %s cannot be converted\n", resource);
+			goto_bad;
+		}
+		/* Add new locked resource */
+		if (!(head = dm_malloc(sizeof(struct dm_list))) ||
+		    !dm_hash_insert(_locks, resource, head)) {
+			dm_free(head);
+			goto_bad;
+		}
+
+		dm_list_init(head);
+	} else	/* Update/convert locked resource */
+		dm_list_iterate_items(lck, head) {
+			/* Check is all locks are compatible with requested lock */
+			if (flags & LCKF_CONVERT) {
+				if (lck->lockid != *lockid)
+					continue;
+
+				DEBUGLOG("Converting resource %s lockid=%d mode:%s -> %s...\n",
+					 resource, lck->lockid, _get_mode(lck->mode), _get_mode(mode));
+				dm_list_iterate_items(lckt, head) {
+					if ((lckt->lockid != *lockid) &&
+					    !_dlm_table[mode][lckt->mode]) {
+						if (!(flags & LCKF_NOQUEUE) &&
+						    /* TODO: Real dlm uses here conversion queues */
+						    !pthread_cond_wait(&_lock_cond, &_lock_mutex) &&
+						    _locks) /* End of the game? */
+							goto retry;
+						goto bad;
+					}
+				}
+				lck->mode = mode; /* Lock is now converted */
+				goto out;
+			} else if (!_dlm_table[mode][lck->mode]) {
+				DEBUGLOG("Resource %s already locked lockid=%d, mode:%s\n",
+					 resource, lck->lockid, _get_mode(lck->mode));
+				if (!(flags & LCKF_NOQUEUE) &&
+				    !pthread_cond_wait(&_lock_cond, &_lock_mutex) &&
+				    _locks) { /* End of the game? */
+					DEBUGLOG("Resource %s retrying lock in mode:%s...\n",
+						 resource, _get_mode(mode));
+					goto retry;
+				}
+				goto bad;
+			}
+		}
+
+	if (!(flags & LCKF_CONVERT)) {
+		if (!(lck = dm_malloc(sizeof(struct lock))))
+			goto_bad;
+
+		*lockid = lck->lockid = ++_lockid;
+		lck->mode = mode;
+		dm_list_add(head, &lck->list);
+	}
+out:
+	pthread_cond_broadcast(&_lock_cond); /* to wakeup waiters */
+	pthread_mutex_unlock(&_lock_mutex);
+	DEBUGLOG("Locked resource %s, lockid=%d, mode=%s\n",
+		 resource, lck->lockid, _get_mode(lck->mode));
+
+	return 0;
+bad:
+	pthread_cond_broadcast(&_lock_cond); /* to wakeup waiters */
+	pthread_mutex_unlock(&_lock_mutex);
+	DEBUGLOG("Failed to lock resource %s\n", resource);
+
+	return 1; /* fail */
+}
+
+static int _unlock_resource(const char *resource, int lockid)
+{
+	struct lock *lck;
+	struct dm_list *head;
+	int r = 1;
+
+	if (lockid < 0) {
+		DEBUGLOG("Not tracking unlock of lockid -1: %s, lockid=%d\n",
+			 resource, lockid);
+		return 1;
+	}
+
+	DEBUGLOG("Unlocking resource %s, lockid=%d\n", resource, lockid);
+	pthread_mutex_lock(&_lock_mutex);
+	pthread_cond_broadcast(&_lock_cond); /* wakeup waiters */
+
+	if (!(head = dm_hash_lookup(_locks, resource))) {
+		pthread_mutex_unlock(&_lock_mutex);
+		DEBUGLOG("Resource %s is not locked.\n", resource);
+		return 1;
+	}
+
+	dm_list_iterate_items(lck, head)
+		if (lck->lockid == lockid) {
+			dm_list_del(&lck->list);
+			dm_free(lck);
+			r = 0;
+			goto out;
+		}
+
+	DEBUGLOG("Resource %s has wrong lockid %d.\n", resource, lockid);
+out:
+	if (dm_list_empty(head)) {
+		//DEBUGLOG("Resource %s is no longer hashed (lockid=%d).\n", resource, lockid);
+		dm_hash_remove(_locks, resource);
+		dm_free(head);
+	}
+
+	pthread_mutex_unlock(&_lock_mutex);
+
+	return r;
+}
+
+static int _is_quorate(void)
+{
+	return 1;
+}
+
+static int _get_main_cluster_fd(void)
+{
+	return listen_fd;
+}
+
+static int _cluster_fd_callback(struct local_client *fd, char *buf, int len,
+				const char *csid,
+				struct local_client **new_client)
+{
+	return 1;
+}
+
+static int _cluster_send_message(const void *buf, int msglen,
+				 const char *csid,
+				 const char *errtext)
+{
+	return 0;
+}
+
+static int _get_cluster_name(char *buf, int buflen)
+{
+	return dm_strncpy(buf, "localcluster", buflen) ? 0 : 1;
+}
+
+static struct cluster_ops _cluster_singlenode_ops = {
+	.name                     = "singlenode",
+	.cluster_init_completed   = NULL,
+	.cluster_send_message     = _cluster_send_message,
+	.name_from_csid           = _name_from_csid,
+	.csid_from_name           = _csid_from_name,
+	.get_num_nodes            = _get_num_nodes,
+	.cluster_fd_callback      = _cluster_fd_callback,
+	.get_main_cluster_fd      = _get_main_cluster_fd,
+	.cluster_do_node_callback = _cluster_do_node_callback,
+	.is_quorate               = _is_quorate,
+	.get_our_csid             = _get_our_csid,
+	.add_up_node              = _add_up_node,
+	.reread_config            = NULL,
+	.cluster_closedown        = _cluster_closedown,
+	.get_cluster_name         = _get_cluster_name,
+	.sync_lock                = _lock_resource,
+	.sync_unlock              = _unlock_resource,
+};
+
+struct cluster_ops *init_singlenode_cluster(void)
+{
+	if (!_init_cluster())
+		return &_cluster_singlenode_ops;
+
+	return NULL;
+}

daemons/clvmd/clvmd.h

@@ -0,0 +1,126 @@
+/*
+ * Copyright (C) 2002-2004 Sistina Software, Inc. All rights reserved.
+ * Copyright (C) 2004 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 General Public License v.2.
+ *
+ * You should have received a copy of the GNU 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 _CLVMD_H
+#define _CLVMD_H
+
+#define CLVMD_MAJOR_VERSION 0
+#define CLVMD_MINOR_VERSION 2
+#define CLVMD_PATCH_VERSION 1
+
+/* Default time (in seconds) we will wait for all remote commands to execute
+   before declaring them dead */
+#define DEFAULT_CMD_TIMEOUT 60
+
+/* One of these for each reply we get from command execution on a node */
+struct node_reply {
+	char node[MAX_CLUSTER_MEMBER_NAME_LEN];
+	char *replymsg;
+	int status;
+	struct node_reply *next;
+};
+
+typedef enum {DEBUG_OFF, DEBUG_STDERR, DEBUG_SYSLOG} debug_t;
+
+/*
+ * These exist for the use of local sockets only when we are
+ * collecting responses from all cluster nodes
+ */
+struct localsock_bits {
+	struct node_reply *replies;
+	int num_replies;
+	int expected_replies;
+	time_t sent_time;	/* So we can check for timeouts */
+	int in_progress;	/* Only execute one cmd at a time per client */
+	int sent_out;		/* Flag to indicate that a command was sent
+				   to remote nodes */
+	void *private;		/* Private area for command processor use */
+	void *cmd;		/* Whole command as passed down local socket */
+	int cmd_len;		/* Length of above */
+	int pipe;		/* Pipe to send PRE completion status down */
+	int finished;		/* Flag to tell subthread to exit */
+	int all_success;	/* Set to 0 if any node (or the pre_command)
+				   failed */
+	int cleanup_needed;     /* helper for cleanup_zombie */
+	struct local_client *pipe_client;
+	pthread_t threadid;
+	enum { PRE_COMMAND, POST_COMMAND } state;
+	pthread_mutex_t mutex;	/* Main thread and worker synchronisation */
+	pthread_cond_t cond;
+};
+
+/* Entries for PIPE clients */
+struct pipe_bits {
+	struct local_client *client;	/* Actual (localsock) client */
+	pthread_t threadid;		/* Our own copy of the thread id */
+};
+
+/* Entries for Network socket clients */
+struct netsock_bits {
+	void *private;
+	int flags;
+};
+
+typedef int (*fd_callback_t) (struct local_client * fd, char *buf, int len,
+			      const char *csid,
+			      struct local_client ** new_client);
+
+/* One of these for each fd we are listening on */
+struct local_client {
+	int fd;
+	enum { CLUSTER_MAIN_SOCK, CLUSTER_DATA_SOCK, LOCAL_RENDEZVOUS,
+		    LOCAL_SOCK, THREAD_PIPE, CLUSTER_INTERNAL } type;
+	struct local_client *next;
+	unsigned short xid;
+	fd_callback_t callback;
+	uint8_t removeme;
+
+	union {
+		struct localsock_bits localsock;
+		struct pipe_bits pipe;
+		struct netsock_bits net;
+	} bits;
+};
+
+#define DEBUGLOG(fmt, args...) debuglog(fmt, ## args)
+
+#ifndef max
+#define max(a,b) ((a)>(b)?(a):(b))
+#endif
+
+/* The real command processor is in clvmd-command.c */
+extern int do_command(struct local_client *client, struct clvm_header *msg,
+		      int msglen, char **buf, int buflen, int *retlen);
+
+/* Pre and post command routines are called only on the local node */
+extern int do_pre_command(struct local_client *client);
+extern int do_post_command(struct local_client *client);
+extern void cmd_client_cleanup(struct local_client *client);
+extern int add_client(struct local_client *new_client);
+
+extern void clvmd_cluster_init_completed(void);
+extern void process_message(struct local_client *client, char *buf,
+			    int len, const char *csid);
+extern void debuglog(const char *fmt, ... )
+  __attribute__ ((format(printf, 1, 2)));
+
+void clvmd_set_debug(debug_t new_de);
+debug_t clvmd_get_debug(void);
+int clvmd_get_foreground(void);
+
+int sync_lock(const char *resource, int mode, int flags, int *lockid);
+int sync_unlock(const char *resource, int lockid);
+
+#endif

daemons/clvmd/lvm-functions.c

@@ -0,0 +1,927 @@
+/*
+ * Copyright (C) 2002-2004 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 General Public License v.2.
+ *
+ * You should have received a copy of the GNU 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 "clvmd-common.h"
+
+#include <pthread.h>
+
+#include "clvm.h"
+#include "clvmd-comms.h"
+#include "clvmd.h"
+#include "lvm-functions.h"
+
+/* LVM2 headers */
+#include "toolcontext.h"
+#include "lvmcache.h"
+#include "lvm-globals.h"
+#include "activate.h"
+#include "archiver.h"
+#include "memlock.h"
+
+#include <syslog.h>
+
+static struct cmd_context *cmd = NULL;
+static struct dm_hash_table *lv_hash = NULL;
+static pthread_mutex_t lv_hash_lock;
+static pthread_mutex_t lvm_lock;
+static char last_error[1024];
+
+struct lv_info {
+	int lock_id;
+	int lock_mode;
+};
+
+static const char *decode_full_locking_cmd(uint32_t cmdl)
+{
+	static char buf[128];
+	const char *type;
+	const char *scope;
+	const char *command;
+
+	switch (cmdl & LCK_TYPE_MASK) {
+	case LCK_NULL:
+		type = "NULL";
+		break;
+	case LCK_READ:
+		type = "READ";
+		break;
+	case LCK_PREAD:
+		type = "PREAD";
+		break;
+	case LCK_WRITE:
+		type = "WRITE";
+		break;
+	case LCK_EXCL:
+		type = "EXCL";
+		break;
+	case LCK_UNLOCK:
+		type = "UNLOCK";
+		break;
+	default:
+		type = "unknown";
+		break;
+	}
+
+	switch (cmdl & LCK_SCOPE_MASK) {
+	case LCK_VG:
+		scope = "VG";
+		command = "LCK_VG";
+		break;
+	case LCK_LV:
+		scope = "LV";
+		switch (cmdl & LCK_MASK) {
+		case LCK_LV_EXCLUSIVE & LCK_MASK:
+			command = "LCK_LV_EXCLUSIVE";
+			break;
+		case LCK_LV_SUSPEND & LCK_MASK:
+			command = "LCK_LV_SUSPEND";
+			break;
+		case LCK_LV_RESUME & LCK_MASK:
+			command = "LCK_LV_RESUME";
+			break;
+		case LCK_LV_ACTIVATE & LCK_MASK:
+			command = "LCK_LV_ACTIVATE";
+			break;
+		case LCK_LV_DEACTIVATE & LCK_MASK:
+			command = "LCK_LV_DEACTIVATE";
+			break;
+		default:
+			command = "unknown";
+			break;
+		}
+		break;
+	default:
+		scope = "unknown";
+		command = "unknown";
+		break;
+	}
+
+	sprintf(buf, "0x%x %s (%s|%s%s%s%s%s)", cmdl, command, type, scope,
+		cmdl & LCK_NONBLOCK   ? "|NONBLOCK" : "",
+		cmdl & LCK_HOLD       ? "|HOLD" : "",
+		cmdl & LCK_CLUSTER_VG ? "|CLUSTER_VG" : "",
+		cmdl & LCK_CACHE      ? "|CACHE" : "");
+
+	return buf;
+}
+
+/*
+ * Only processes 8 bits: excludes LCK_CACHE.
+ */
+static const char *decode_locking_cmd(unsigned char cmdl)
+{
+	return decode_full_locking_cmd((uint32_t) cmdl);
+}
+
+static const char *decode_flags(unsigned char flags)
+{
+	static char buf[128];
+	int len;
+
+	len = sprintf(buf, "0x%x ( %s%s%s%s%s%s%s%s)", flags,
+		flags & LCK_PARTIAL_MODE	  ? "PARTIAL_MODE|" : "",
+		flags & LCK_MIRROR_NOSYNC_MODE	  ? "MIRROR_NOSYNC|" : "",
+		flags & LCK_DMEVENTD_MONITOR_MODE ? "DMEVENTD_MONITOR|" : "",
+		flags & LCK_ORIGIN_ONLY_MODE ? "ORIGIN_ONLY|" : "",
+		flags & LCK_TEST_MODE ? "TEST|" : "",
+		flags & LCK_CONVERT_MODE ? "CONVERT|" : "",
+		flags & LCK_DMEVENTD_MONITOR_IGNORE ? "DMEVENTD_MONITOR_IGNORE|" : "",
+		flags & LCK_REVERT_MODE ? "REVERT|" : "");
+
+	if (len > 1)
+		buf[len - 2] = ' ';
+	else
+		buf[0] = '\0';
+
+	return buf;
+}
+
+char *get_last_lvm_error(void)
+{
+	return last_error;
+}
+
+/*
+ * Hash lock info helpers
+ */
+static struct lv_info *lookup_info(const char *resource)
+{
+	struct lv_info *lvi;
+
+	pthread_mutex_lock(&lv_hash_lock);
+	lvi = dm_hash_lookup(lv_hash, resource);
+	pthread_mutex_unlock(&lv_hash_lock);
+
+	return lvi;
+}
+
+static int insert_info(const char *resource, struct lv_info *lvi)
+{
+	int ret;
+
+	pthread_mutex_lock(&lv_hash_lock);
+	ret = dm_hash_insert(lv_hash, resource, lvi);
+	pthread_mutex_unlock(&lv_hash_lock);
+
+	return ret;
+}
+
+static void remove_info(const char *resource)
+{
+	int num_open;
+
+	pthread_mutex_lock(&lv_hash_lock);
+	dm_hash_remove(lv_hash, resource);
+
+	/* When last lock is remove, validate there are not left opened devices */
+	if (!dm_hash_get_first(lv_hash)) {
+		if (critical_section())
+			log_error(INTERNAL_ERROR "No volumes are locked however clvmd is in activation mode critical section.");
+		if ((num_open = dev_cache_check_for_open_devices()))
+			log_error(INTERNAL_ERROR "No volumes are locked however %d devices are still open.", num_open);
+	}
+
+	pthread_mutex_unlock(&lv_hash_lock);
+}
+
+/*
+ * Return the mode a lock is currently held at (or -1 if not held)
+ */
+static int get_current_lock(char *resource)
+{
+	struct lv_info *lvi;
+
+	if ((lvi = lookup_info(resource)))
+		return lvi->lock_mode;
+
+	return -1;
+}
+
+
+void init_lvhash(void)
+{
+	/* Create hash table for keeping LV locks & status */
+	lv_hash = dm_hash_create(1024);
+	pthread_mutex_init(&lv_hash_lock, NULL);
+	pthread_mutex_init(&lvm_lock, NULL);
+}
+
+/* Called at shutdown to tidy the lockspace */
+void destroy_lvhash(void)
+{
+	struct dm_hash_node *v;
+	struct lv_info *lvi;
+	char *resource;
+	int status;
+
+	pthread_mutex_lock(&lv_hash_lock);
+
+	dm_hash_iterate(v, lv_hash) {
+		lvi = dm_hash_get_data(lv_hash, v);
+		resource = dm_hash_get_key(lv_hash, v);
+
+		if ((status = sync_unlock(resource, lvi->lock_id)))
+			DEBUGLOG("unlock_all. unlock failed(%d): %s\n",
+				 status,  strerror(errno));
+		dm_free(lvi);
+	}
+
+	dm_hash_destroy(lv_hash);
+	lv_hash = NULL;
+
+	pthread_mutex_unlock(&lv_hash_lock);
+}
+
+/* Gets a real lock and keeps the info in the hash table */
+static int hold_lock(char *resource, int mode, int flags)
+{
+	int status;
+	int saved_errno;
+	struct lv_info *lvi;
+
+	/* Mask off invalid options */
+	flags &= LCKF_NOQUEUE | LCKF_CONVERT;
+
+	lvi = lookup_info(resource);
+
+	if (lvi) {
+		if (lvi->lock_mode == mode) {
+			DEBUGLOG("hold_lock, lock mode %d already held\n",
+				 mode);
+			return 0;
+		}
+		if ((lvi->lock_mode == LCK_EXCL) && (mode == LCK_WRITE)) {
+			DEBUGLOG("hold_lock, lock already held LCK_EXCL, "
+				 "ignoring LCK_WRITE request\n");
+			return 0;
+		}
+	}
+
+	/* Only allow explicit conversions */
+	if (lvi && !(flags & LCKF_CONVERT)) {
+		errno = EBUSY;
+		return -1;
+	}
+	if (lvi) {
+		/* Already exists - convert it */
+		status = sync_lock(resource, mode, flags, &lvi->lock_id);
+		saved_errno = errno;
+		if (!status)
+			lvi->lock_mode = mode;
+		else
+			DEBUGLOG("hold_lock. convert to %d failed: %s\n", mode,
+				 strerror(errno));
+		errno = saved_errno;
+	} else {
+		if (!(lvi = dm_malloc(sizeof(struct lv_info)))) {
+			errno = ENOMEM;
+			return -1;
+		}
+
+		lvi->lock_mode = mode;
+		lvi->lock_id = 0;
+		status = sync_lock(resource, mode, flags & ~LCKF_CONVERT, &lvi->lock_id);
+		saved_errno = errno;
+		if (status) {
+			dm_free(lvi);
+			DEBUGLOG("hold_lock. lock at %d failed: %s\n", mode,
+				 strerror(errno));
+		} else
+			if (!insert_info(resource, lvi)) {
+				errno = ENOMEM;
+				return -1;
+			}
+
+		errno = saved_errno;
+	}
+	return status;
+}
+
+/* Unlock and remove it from the hash table */
+static int hold_unlock(char *resource)
+{
+	struct lv_info *lvi;
+	int status;
+	int saved_errno;
+
+	if (!(lvi = lookup_info(resource))) {
+		DEBUGLOG("hold_unlock, lock not already held\n");
+		return 0;
+	}
+
+	status = sync_unlock(resource, lvi->lock_id);
+	saved_errno = errno;
+	if (!status) {
+		remove_info(resource);
+		dm_free(lvi);
+	} else {
+		DEBUGLOG("hold_unlock. unlock failed(%d): %s\n", status,
+			 strerror(errno));
+	}
+
+	errno = saved_errno;
+	return status;
+}
+
+/* Watch the return codes here.
+   liblvm API functions return 1(true) for success, 0(false) for failure and don't set errno.
+   libdlm API functions return 0 for success, -1 for failure and do set errno.
+   These functions here return 0 for success or >0 for failure (where the retcode is errno)
+*/
+
+/* Activate LV exclusive or non-exclusive */
+static int do_activate_lv(char *resource, unsigned char command, unsigned char lock_flags, int mode)
+{
+	int oldmode;
+	int status;
+	int activate_lv;
+	int exclusive = 0;
+	struct lvinfo lvi;
+
+	/* Is it already open ? */
+	oldmode = get_current_lock(resource);
+	if (oldmode == mode && (command & LCK_CLUSTER_VG)) {
+		DEBUGLOG("do_activate_lv, lock already held at %d\n", oldmode);
+		return 0;	/* Nothing to do */
+	}
+
+	/* Does the config file want us to activate this LV ? */
+	if (!lv_activation_filter(cmd, resource, &activate_lv, NULL))
+		return EIO;
+
+	if (!activate_lv)
+		return 0;	/* Success, we did nothing! */
+
+	/* Do we need to activate exclusively? */
+	if ((activate_lv == 2) || (mode == LCK_EXCL)) {
+		exclusive = 1;
+		mode = LCK_EXCL;
+	}
+
+	/*
+	 * Try to get the lock if it's a clustered volume group.
+	 * Use lock conversion only if requested, to prevent implicit conversion
+	 * of exclusive lock to shared one during activation.
+	 */
+	if (!test_mode() && command & LCK_CLUSTER_VG) {
+		status = hold_lock(resource, mode, LCKF_NOQUEUE | ((lock_flags & LCK_CONVERT_MODE) ? LCKF_CONVERT:0));
+		if (status) {
+			/* Return an LVM-sensible error for this.
+			 * Forcing EIO makes the upper level return this text
+			 * rather than the strerror text for EAGAIN.
+			 */
+			if (errno == EAGAIN) {
+				sprintf(last_error, "Volume is busy on another node");
+				errno = EIO;
+			}
+			return errno;
+		}
+	}
+
+	/* If it's suspended then resume it */
+	if (!lv_info_by_lvid(cmd, resource, 0, &lvi, 0, 0))
+		goto error;
+
+	if (lvi.suspended) {
+		critical_section_inc(cmd, "resuming");
+		if (!lv_resume(cmd, resource, 0, NULL)) {
+			critical_section_dec(cmd, "resumed");
+			goto error;
+		}
+	}
+
+	/* Now activate it */
+	if (!lv_activate(cmd, resource, exclusive, 0, 0, NULL))
+		goto error;
+
+	return 0;
+
+error:
+	if (!test_mode() && (oldmode == -1 || oldmode != mode))
+		(void)hold_unlock(resource);
+	return EIO;
+}
+
+/* Resume the LV if it was active */
+static int do_resume_lv(char *resource, unsigned char command, unsigned char lock_flags)
+{
+	int oldmode, origin_only, exclusive, revert;
+
+	/* Is it open ? */
+	oldmode = get_current_lock(resource);
+	if (oldmode == -1 && (command & LCK_CLUSTER_VG)) {
+		DEBUGLOG("do_resume_lv, lock not already held\n");
+		return 0;	/* We don't need to do anything */
+	}
+	origin_only = (lock_flags & LCK_ORIGIN_ONLY_MODE) ? 1 : 0;
+	exclusive = (oldmode == LCK_EXCL) ? 1 : 0;
+	revert = (lock_flags & LCK_REVERT_MODE) ? 1 : 0;
+
+	if (!lv_resume_if_active(cmd, resource, origin_only, exclusive, revert, NULL))
+		return EIO;
+
+	return 0;
+}
+
+/* Suspend the device if active */
+static int do_suspend_lv(char *resource, unsigned char command, unsigned char lock_flags)
+{
+	int oldmode;
+	unsigned origin_only = (lock_flags & LCK_ORIGIN_ONLY_MODE) ? 1 : 0;
+	unsigned exclusive;
+
+	/* Is it open ? */
+	oldmode = get_current_lock(resource);
+	if (oldmode == -1 && (command & LCK_CLUSTER_VG)) {
+		DEBUGLOG("do_suspend_lv, lock not already held\n");
+		return 0; /* Not active, so it's OK */
+	}
+
+	exclusive = (oldmode == LCK_EXCL) ? 1 : 0;
+
+	/* Always call lv_suspend to read commited and precommited data */
+	if (!lv_suspend_if_active(cmd, resource, origin_only, exclusive, NULL, NULL))
+		return EIO;
+
+	return 0;
+}
+
+static int do_deactivate_lv(char *resource, unsigned char command, unsigned char lock_flags)
+{
+	int oldmode;
+	int status;
+
+	/* Is it open ? */
+	oldmode = get_current_lock(resource);
+	if (oldmode == -1 && (command & LCK_CLUSTER_VG)) {
+		DEBUGLOG("do_deactivate_lock, lock not already held\n");
+		return 0;	/* We don't need to do anything */
+	}
+
+	if (!lv_deactivate(cmd, resource, NULL))
+		return EIO;
+
+	if (!test_mode() && command & LCK_CLUSTER_VG) {
+		status = hold_unlock(resource);
+		if (status)
+			return errno;
+	}
+
+	return 0;
+}
+
+const char *do_lock_query(char *resource)
+{
+	int mode;
+	const char *type;
+
+	mode = get_current_lock(resource);
+	switch (mode) {
+	case LCK_NULL: type = "NL"; break;
+	case LCK_READ: type = "CR"; break;
+	case LCK_PREAD:type = "PR"; break;
+	case LCK_WRITE:type = "PW"; break;
+	case LCK_EXCL: type = "EX"; break;
+	default: type = NULL;
+	}
+
+	DEBUGLOG("do_lock_query: resource '%s', mode %i (%s)\n", resource, mode, type ?: "--");
+
+	return type;
+}
+
+/* This is the LOCK_LV part that happens on all nodes in the cluster -
+   it is responsible for the interaction with device-mapper and LVM */
+int do_lock_lv(unsigned char command, unsigned char lock_flags, char *resource)
+{
+	int status = 0;
+
+	DEBUGLOG("do_lock_lv: resource '%s', cmd = %s, flags = %s, critical_section = %d\n",
+		 resource, decode_locking_cmd(command), decode_flags(lock_flags), critical_section());
+
+	if (!cmd->initialized.config || config_files_changed(cmd)) {
+		/* Reinitialise various settings inc. logging, filters */
+		if (do_refresh_cache()) {
+			log_error("Updated config file invalid. Aborting.");
+			return EINVAL;
+		}
+	}
+
+	pthread_mutex_lock(&lvm_lock);
+	init_test((lock_flags & LCK_TEST_MODE) ? 1 : 0);
+
+	if (lock_flags & LCK_MIRROR_NOSYNC_MODE)
+		init_mirror_in_sync(1);
+
+	if (lock_flags & LCK_DMEVENTD_MONITOR_IGNORE)
+		init_dmeventd_monitor(DMEVENTD_MONITOR_IGNORE);
+	else {
+		if (lock_flags & LCK_DMEVENTD_MONITOR_MODE)
+			init_dmeventd_monitor(1);
+		else
+			init_dmeventd_monitor(0);
+	}
+
+	cmd->partial_activation = (lock_flags & LCK_PARTIAL_MODE) ? 1 : 0;
+
+	/* clvmd should never try to read suspended device */
+	init_ignore_suspended_devices(1);
+
+	switch (command & LCK_MASK) {
+	case LCK_LV_EXCLUSIVE:
+		status = do_activate_lv(resource, command, lock_flags, LCK_EXCL);
+		break;
+
+	case LCK_LV_SUSPEND:
+		status = do_suspend_lv(resource, command, lock_flags);
+		break;
+
+	case LCK_UNLOCK:
+	case LCK_LV_RESUME:	/* if active */
+		status = do_resume_lv(resource, command, lock_flags);
+		break;
+
+	case LCK_LV_ACTIVATE:
+		status = do_activate_lv(resource, command, lock_flags, LCK_READ);
+		break;
+
+	case LCK_LV_DEACTIVATE:
+		status = do_deactivate_lv(resource, command, lock_flags);
+		break;
+
+	default:
+		DEBUGLOG("Invalid LV command 0x%x\n", command);
+		status = EINVAL;
+		break;
+	}
+
+	if (lock_flags & LCK_MIRROR_NOSYNC_MODE)
+		init_mirror_in_sync(0);
+
+	cmd->partial_activation = 0;
+
+	/* clean the pool for another command */
+	dm_pool_empty(cmd->mem);
+	init_test(0);
+	pthread_mutex_unlock(&lvm_lock);
+
+	DEBUGLOG("Command return is %d, critical_section is %d\n", status, critical_section());
+	return status;
+}
+
+/* Functions to do on the local node only BEFORE the cluster-wide stuff above happens */
+int pre_lock_lv(unsigned char command, unsigned char lock_flags, char *resource)
+{
+	/* Nearly all the stuff happens cluster-wide. Apart from SUSPEND. Here we get the
+	   lock out on this node (because we are the node modifying the metadata)
+	   before suspending cluster-wide.
+	   LCKF_CONVERT is used always, local node is going to modify metadata
+	 */
+	if ((command & (LCK_SCOPE_MASK | LCK_TYPE_MASK)) == LCK_LV_SUSPEND &&
+	    (command & LCK_CLUSTER_VG)) {
+		DEBUGLOG("pre_lock_lv: resource '%s', cmd = %s, flags = %s\n",
+			 resource, decode_locking_cmd(command), decode_flags(lock_flags));
+
+		if (!(lock_flags & LCK_TEST_MODE) &&
+		    hold_lock(resource, LCK_WRITE, LCKF_NOQUEUE | LCKF_CONVERT))
+			return errno;
+	}
+	return 0;
+}
+
+/* Functions to do on the local node only AFTER the cluster-wide stuff above happens */
+int post_lock_lv(unsigned char command, unsigned char lock_flags,
+		 char *resource)
+{
+	int status;
+	unsigned origin_only = (lock_flags & LCK_ORIGIN_ONLY_MODE) ? 1 : 0;
+
+	/* Opposite of above, done on resume after a metadata update */
+	if ((command & (LCK_SCOPE_MASK | LCK_TYPE_MASK)) == LCK_LV_RESUME &&
+	    (command & LCK_CLUSTER_VG)) {
+		int oldmode;
+
+		DEBUGLOG("post_lock_lv: resource '%s', cmd = %s, flags = %s\n",
+			 resource, decode_locking_cmd(command), decode_flags(lock_flags));
+
+		/* If the lock state is PW then restore it to what it was */
+		oldmode = get_current_lock(resource);
+		if (oldmode == LCK_WRITE) {
+			struct lvinfo lvi;
+
+			pthread_mutex_lock(&lvm_lock);
+			status = lv_info_by_lvid(cmd, resource, origin_only, &lvi, 0, 0);
+			pthread_mutex_unlock(&lvm_lock);
+			if (!status)
+				return EIO;
+
+			if (!(lock_flags & LCK_TEST_MODE)) {
+				if (lvi.exists) {
+					if (hold_lock(resource, LCK_READ, LCKF_CONVERT))
+						return errno;
+				} else if (hold_unlock(resource))
+					return errno;
+			}
+		}
+	}
+	return 0;
+}
+
+int do_refresh_cache(void)
+{
+	DEBUGLOG("Refreshing context\n");
+	log_notice("Refreshing context");
+
+	pthread_mutex_lock(&lvm_lock);
+
+	if (!refresh_toolcontext(cmd)) {
+		pthread_mutex_unlock(&lvm_lock);
+		return -1;
+	}
+
+	init_ignore_suspended_devices(1);
+	lvmcache_label_scan(cmd);
+	label_scan_destroy(cmd); /* destroys bcache (to close devs), keeps lvmcache */
+	dm_pool_empty(cmd->mem);
+
+	pthread_mutex_unlock(&lvm_lock);
+
+	return 0;
+}
+
+/*
+ * Handle VG lock - drop metadata or update lvmcache state
+ */
+void do_lock_vg(unsigned char command, unsigned char lock_flags, char *resource)
+{
+	uint32_t lock_cmd = command;
+	char *vgname = resource + 2;
+
+	lock_cmd &= (LCK_SCOPE_MASK | LCK_TYPE_MASK | LCK_HOLD);
+
+	/*
+	 * Check if LCK_CACHE should be set. All P_ locks except # are cache related.
+	 */
+	if (strncmp(resource, "P_#", 3) && !strncmp(resource, "P_", 2))
+		lock_cmd |= LCK_CACHE;
+
+	DEBUGLOG("do_lock_vg: resource '%s', cmd = %s, flags = %s, critical_section = %d\n",
+		 resource, decode_full_locking_cmd(lock_cmd), decode_flags(lock_flags), critical_section());
+
+	/* P_#global causes a full cache refresh */
+	if (!strcmp(resource, "P_" VG_GLOBAL)) {
+		do_refresh_cache();
+		return;
+	}
+
+	pthread_mutex_lock(&lvm_lock);
+	init_test((lock_flags & LCK_TEST_MODE) ? 1 : 0);
+
+	switch (lock_cmd) {
+		case LCK_VG_COMMIT:
+			DEBUGLOG("vg_commit notification for VG %s\n", vgname);
+			lvmcache_commit_metadata(vgname);
+			break;
+		case LCK_VG_REVERT:
+			DEBUGLOG("vg_revert notification for VG %s\n", vgname);
+			lvmcache_drop_metadata(vgname, 1);
+			break;
+		case LCK_VG_DROP_CACHE:
+		default:
+			DEBUGLOG("Invalidating cached metadata for VG %s\n", vgname);
+			lvmcache_drop_metadata(vgname, 0);
+	}
+
+	init_test(0);
+	pthread_mutex_unlock(&lvm_lock);
+}
+
+/*
+ * Ideally, clvmd should be started before any LVs are active
+ * but this may not be the case...
+ * I suppose this also comes in handy if clvmd crashes, not that it would!
+ */
+static int get_initial_state(struct dm_hash_table *excl_uuid)
+{
+	int lock_mode;
+	char lv[65], vg[65], flags[26], vg_flags[26]; /* with space for '\0' */
+	char uuid[65];
+	char line[255];
+	char *lvs_cmd;
+	const char *lvm_binary = getenv("LVM_BINARY") ? : LVM_PATH;
+	FILE *lvs;
+
+	if (dm_asprintf(&lvs_cmd, "%s lvs  --config 'log{command_names=0 prefix=\"\"}' "
+			"--nolocking --noheadings -o vg_uuid,lv_uuid,lv_attr,vg_attr",
+			lvm_binary) < 0)
+		return_0;
+
+	/* FIXME: Maybe link and use liblvm2cmd directly instead of fork */
+	if (!(lvs = popen(lvs_cmd, "r"))) {
+		dm_free(lvs_cmd);
+		return 0;
+	}
+
+	while (fgets(line, sizeof(line), lvs)) {
+	        if (sscanf(line, "%64s %64s %25s %25s\n", vg, lv, flags, vg_flags) == 4) {
+
+			/* States: s:suspended a:active S:dropped snapshot I:invalid snapshot */
+		        if (strlen(vg) == 38 &&                         /* is is a valid UUID ? */
+			    (flags[4] == 'a' || flags[4] == 's') &&	/* is it active or suspended? */
+			    vg_flags[5] == 'c') {			/* is it clustered ? */
+				/* Convert hyphen-separated UUIDs into one */
+				memcpy(&uuid[0], &vg[0], 6);
+				memcpy(&uuid[6], &vg[7], 4);
+				memcpy(&uuid[10], &vg[12], 4);
+				memcpy(&uuid[14], &vg[17], 4);
+				memcpy(&uuid[18], &vg[22], 4);
+				memcpy(&uuid[22], &vg[27], 4);
+				memcpy(&uuid[26], &vg[32], 6);
+				memcpy(&uuid[32], &lv[0], 6);
+				memcpy(&uuid[38], &lv[7], 4);
+				memcpy(&uuid[42], &lv[12], 4);
+				memcpy(&uuid[46], &lv[17], 4);
+				memcpy(&uuid[50], &lv[22], 4);
+				memcpy(&uuid[54], &lv[27], 4);
+				memcpy(&uuid[58], &lv[32], 6);
+				uuid[64] = '\0';
+
+				/* Look for this lock in the list of EX locks
+				   we were passed on the command-line */
+				lock_mode = (dm_hash_lookup(excl_uuid, uuid)) ?
+					LCK_EXCL : LCK_READ;
+
+				DEBUGLOG("getting initial lock for %s\n", uuid);
+				if (hold_lock(uuid, lock_mode, LCKF_NOQUEUE))
+					DEBUGLOG("Failed to hold lock %s\n", uuid);
+			}
+		}
+	}
+	if (pclose(lvs))
+		DEBUGLOG("lvs pclose failed: %s\n", strerror(errno));
+
+	dm_free(lvs_cmd);
+
+	return 1;
+}
+
+static void lvm2_log_fn(int level, const char *file, int line, int dm_errno,
+			const char *message)
+{
+
+	/* Send messages to the normal LVM2 logging system too,
+	   so we get debug output when it's asked for.
+ 	   We need to NULL the function ptr otherwise it will just call
+	   back into here! */
+	init_log_fn(NULL);
+	print_log(level, file, line, dm_errno, "%s", message);
+	init_log_fn(lvm2_log_fn);
+
+	/*
+	 * Ignore non-error messages, but store the latest one for returning
+	 * to the user.
+	 */
+	if (level != _LOG_ERR && level != _LOG_FATAL)
+		return;
+
+	(void) dm_strncpy(last_error, message, sizeof(last_error));
+}
+
+/* This checks some basic cluster-LVM configuration stuff */
+static void check_config(void)
+{
+	int locking_type;
+
+	locking_type = find_config_tree_int(cmd, global_locking_type_CFG, NULL);
+
+	if (locking_type == 3) /* compiled-in cluster support */
+		return;
+
+	if (locking_type == 2) { /* External library, check name */
+		const char *libname;
+
+		libname = find_config_tree_str(cmd, global_locking_library_CFG, NULL);
+		if (libname && strstr(libname, "liblvm2clusterlock.so"))
+			return;
+
+		log_error("Incorrect LVM locking library specified in lvm.conf, cluster operations may not work.");
+		return;
+	}
+	log_error("locking_type not set correctly in lvm.conf, cluster operations will not work.");
+}
+
+/* Backups up the LVM metadata if it's changed */
+void lvm_do_backup(const char *vgname)
+{
+	struct volume_group * vg;
+	int consistent = 0;
+
+	DEBUGLOG("Triggering backup of VG metadata for %s.\n", vgname);
+
+	pthread_mutex_lock(&lvm_lock);
+
+	vg = vg_read_internal(cmd, vgname, NULL /*vgid*/, 0, 0, WARN_PV_READ, &consistent);
+
+	if (vg && consistent)
+		check_current_backup(vg);
+	else
+		log_error("Error backing up metadata, can't find VG for group %s", vgname);
+
+	release_vg(vg);
+	dm_pool_empty(cmd->mem);
+
+	pthread_mutex_unlock(&lvm_lock);
+}
+
+struct dm_hash_node *get_next_excl_lock(struct dm_hash_node *v, char **name)
+{
+	struct lv_info *lvi;
+
+	*name = NULL;
+	if (!v)
+		v = dm_hash_get_first(lv_hash);
+
+	do {
+		if (v) {
+			lvi = dm_hash_get_data(lv_hash, v);
+			DEBUGLOG("Looking for EX locks. found %x mode %d\n", lvi->lock_id, lvi->lock_mode);
+
+			if (lvi->lock_mode == LCK_EXCL) {
+				*name = dm_hash_get_key(lv_hash, v);
+			}
+			v = dm_hash_get_next(lv_hash, v);
+		}
+	} while (v && !*name);
+
+	if (*name)
+		DEBUGLOG("returning EXclusive UUID %s\n", *name);
+	return v;
+}
+
+void lvm_do_fs_unlock(void)
+{
+	pthread_mutex_lock(&lvm_lock);
+	DEBUGLOG("Syncing device names\n");
+	fs_unlock();
+	pthread_mutex_unlock(&lvm_lock);
+}
+
+/* Called to initialise the LVM context of the daemon */
+int init_clvm(struct dm_hash_table *excl_uuid)
+{
+	/* Use LOG_DAEMON for syslog messages instead of LOG_USER */
+	init_syslog(LOG_DAEMON);
+	openlog("clvmd", LOG_PID, LOG_DAEMON);
+
+	/* Initialise already held locks */
+	if (!get_initial_state(excl_uuid))
+		log_error("Cannot load initial lock states.");
+
+	if (!udev_init_library_context())
+		stack;
+
+	if (!(cmd = create_toolcontext(1, NULL, 0, 1, 1, 1))) {
+		log_error("Failed to allocate command context");
+		udev_fin_library_context();
+		return 0;
+	}
+
+	if (stored_errno()) {
+		destroy_toolcontext(cmd);
+		return 0;
+	}
+
+	cmd->cmd_line = "clvmd";
+
+	/* Check lvm.conf is setup for cluster-LVM */
+	check_config();
+	init_ignore_suspended_devices(1);
+
+	/* Trap log messages so we can pass them back to the user */
+	init_log_fn(lvm2_log_fn);
+	memlock_inc_daemon(cmd);
+
+	return 1;
+}
+
+void destroy_lvm(void)
+{
+	if (cmd) {
+		memlock_dec_daemon(cmd);
+		destroy_toolcontext(cmd);
+		udev_fin_library_context();
+		cmd = NULL;
+	}
+}

daemons/clvmd/lvm-functions.h

@@ -0,0 +1,40 @@
+/*
+ * Copyright (C) 2002-2004 Sistina Software, Inc. All rights reserved.
+ * Copyright (C) 2004-2010 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 General Public License v.2.
+ *
+ * You should have received a copy of the GNU 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
+ */
+
+/* Functions in lvm-functions.c */
+
+#ifndef _LVM_FUNCTIONS_H
+#define _LVM_FUNCTIONS_H
+
+extern int pre_lock_lv(unsigned char lock_cmd, unsigned char lock_flags,
+		       char *resource);
+extern int do_lock_lv(unsigned char lock_cmd, unsigned char lock_flags,
+		      char *resource);
+extern const char *do_lock_query(char *resource);
+extern int post_lock_lv(unsigned char lock_cmd, unsigned char lock_flags,
+			char *resource);
+extern int do_refresh_cache(void);
+extern int init_clvm(struct dm_hash_table *excl_uuid);
+extern void destroy_lvm(void);
+extern void init_lvhash(void);
+extern void destroy_lvhash(void);
+extern void lvm_do_backup(const char *vgname);
+extern char *get_last_lvm_error(void);
+extern void do_lock_vg(unsigned char command, unsigned char lock_flags,
+		      char *resource);
+extern struct dm_hash_node *get_next_excl_lock(struct dm_hash_node *v, char **name);
+void lvm_do_fs_unlock(void);
+
+#endif

daemons/clvmd/refresh_clvmd.c

@@ -0,0 +1,382 @@
+/*
+ * Copyright (C) 2002-2004 Sistina Software, Inc. All rights reserved.
+ * Copyright (C) 2004-2010 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 General Public License v.2.
+ *
+ * You should have received a copy of the GNU 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
+ */
+
+/* FIXME Remove duplicated functions from this file. */
+
+/*
+ * Send a command to a running clvmd from the command-line
+ */
+
+#include "clvmd-common.h"
+
+#include "clvm.h"
+#include "refresh_clvmd.h"
+
+#include <stddef.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+
+typedef struct lvm_response {
+	char node[255];
+	char *response;
+	int status;
+	int len;
+} lvm_response_t;
+
+/*
+ * This gets stuck at the start of memory we allocate so we
+ * can sanity-check it at deallocation time
+ */
+#define LVM_SIGNATURE 0x434C564D
+
+static int _clvmd_sock = -1;
+
+/* Open connection to the clvm daemon */
+static int _open_local_sock(void)
+{
+	int local_socket;
+	struct sockaddr_un sockaddr = { .sun_family = AF_UNIX };
+
+	if (!dm_strncpy(sockaddr.sun_path, CLVMD_SOCKNAME, sizeof(sockaddr.sun_path))) {
+		fprintf(stderr, "%s: clvmd socket name too long.", CLVMD_SOCKNAME);
+		return -1;
+	}
+
+	/* Open local socket */
+	if ((local_socket = socket(PF_UNIX, SOCK_STREAM, 0)) < 0) {
+		fprintf(stderr, "Local socket creation failed: %s", strerror(errno));
+		return -1;
+	}
+
+	if (connect(local_socket,(struct sockaddr *) &sockaddr,
+		    sizeof(sockaddr))) {
+		int saved_errno = errno;
+
+		fprintf(stderr, "connect() failed on local socket: %s\n",
+			  strerror(errno));
+		if (close(local_socket))
+			return -1;
+
+		errno = saved_errno;
+		return -1;
+	}
+
+	return local_socket;
+}
+
+/* Send a request and return the status */
+static int _send_request(const char *inbuf, int inlen, char **retbuf, int no_response)
+{
+	char outbuf[PIPE_BUF];
+	struct clvm_header *outheader = (struct clvm_header *) outbuf;
+	int len;
+	unsigned off;
+	int buflen;
+	int err;
+
+	/* Send it to CLVMD */
+ rewrite:
+	if ( (err = write(_clvmd_sock, inbuf, inlen)) != inlen) {
+	        if (err == -1 && errno == EINTR)
+		        goto rewrite;
+		fprintf(stderr, "Error writing data to clvmd: %s", strerror(errno));
+		return 0;
+	}
+	if (no_response)
+		return 1;
+
+	/* Get the response */
+ reread:
+	if ((len = read(_clvmd_sock, outbuf, sizeof(struct clvm_header))) < 0) {
+	        if (errno == EINTR)
+		        goto reread;
+		fprintf(stderr, "Error reading data from clvmd: %s", strerror(errno));
+		return 0;
+	}
+
+	if (len == 0) {
+		fprintf(stderr, "EOF reading CLVMD");
+		errno = ENOTCONN;
+		return 0;
+	}
+
+	/* Allocate buffer */
+	buflen = len + outheader->arglen;
+	*retbuf = dm_malloc(buflen);
+	if (!*retbuf) {
+		errno = ENOMEM;
+		return 0;
+	}
+
+	/* Copy the header */
+	memcpy(*retbuf, outbuf, len);
+	outheader = (struct clvm_header *) *retbuf;
+
+	/* Read the returned values */
+	off = 1;		/* we've already read the first byte */
+	while (off <= outheader->arglen && len > 0) {
+		len = read(_clvmd_sock, outheader->args + off,
+			   buflen - off - offsetof(struct clvm_header, args));
+		if (len > 0)
+			off += len;
+	}
+
+	/* Was it an error ? */
+	if (outheader->status != 0) {
+		errno = outheader->status;
+
+		/* Only return an error here if there are no node-specific
+		   errors present in the message that might have more detail */
+		if (!(outheader->flags & CLVMD_FLAG_NODEERRS)) {
+			fprintf(stderr, "cluster request failed: %s\n", strerror(errno));
+			return 0;
+		}
+
+	}
+
+	return 1;
+}
+
+/* Build the structure header and parse-out wildcard node names */
+static void _build_header(struct clvm_header *head, int cmd, const char *node,
+			  unsigned int len)
+{
+	head->cmd = cmd;
+	head->status = 0;
+	head->flags = 0;
+	head->xid = 0;
+	head->clientid = 0;
+	if (len)
+		/* 1 byte is used from struct clvm_header.args[1], so -> len - 1 */
+		head->arglen = len - 1;
+	else {
+		head->arglen = 0;
+		*head->args = '\0';
+	}
+
+	/*
+	 * Translate special node names.
+	 */
+	if (!node || !strcmp(node, NODE_ALL))
+		head->node[0] = '\0';
+	else if (!strcmp(node, NODE_LOCAL)) {
+		head->node[0] = '\0';
+		head->flags = CLVMD_FLAG_LOCAL;
+	} else
+		strcpy(head->node, node);
+}
+
+/*
+ * Send a message to a(or all) node(s) in the cluster and wait for replies
+ */
+static int _cluster_request(char cmd, const char *node, void *data, int len,
+			    lvm_response_t ** response, int *num, int no_response)
+{
+	char outbuf[sizeof(struct clvm_header) + len + strlen(node) + 1];
+	char *inptr;
+	char *retbuf = NULL;
+	int status;
+	int i;
+	int num_responses = 0;
+	struct clvm_header *head = (struct clvm_header *) outbuf;
+	lvm_response_t *rarray;
+
+	*num = 0;
+
+	if (_clvmd_sock == -1)
+		_clvmd_sock = _open_local_sock();
+
+	if (_clvmd_sock == -1)
+		return 0;
+
+	_build_header(head, cmd, node, len);
+	if (len)
+		memcpy(head->node + strlen(head->node) + 1, data, len);
+
+	status = _send_request(outbuf, sizeof(struct clvm_header) +
+			       strlen(head->node) + len, &retbuf, no_response);
+	if (!status || no_response)
+		goto out;
+
+	/* Count the number of responses we got */
+	head = (struct clvm_header *) retbuf;
+	inptr = head->args;
+	while (inptr[0]) {
+		num_responses++;
+		inptr += strlen(inptr) + 1;
+		inptr += sizeof(int);
+		inptr += strlen(inptr) + 1;
+	}
+
+	/*
+	 * Allocate response array.
+	 * With an extra pair of INTs on the front to sanity
+	 * check the pointer when we are given it back to free
+	 */
+	*response = NULL;
+	if (!(rarray = dm_malloc(sizeof(lvm_response_t) * num_responses +
+				 sizeof(int) * 2))) {
+		errno = ENOMEM;
+		status = 0;
+		goto out;
+	}
+
+	/* Unpack the response into an lvm_response_t array */
+	inptr = head->args;
+	i = 0;
+	while (inptr[0]) {
+		strcpy(rarray[i].node, inptr);
+		inptr += strlen(inptr) + 1;
+
+		memcpy(&rarray[i].status, inptr, sizeof(int));
+		inptr += sizeof(int);
+
+		rarray[i].response = dm_malloc(strlen(inptr) + 1);
+		if (rarray[i].response == NULL) {
+			/* Free up everything else and return error */
+			int j;
+			for (j = 0; j < i; j++)
+				dm_free(rarray[i].response);
+			dm_free(rarray);
+			errno = ENOMEM;
+			status = 0;
+			goto out;
+		}
+
+		strcpy(rarray[i].response, inptr);
+		rarray[i].len = strlen(inptr);
+		inptr += strlen(inptr) + 1;
+		i++;
+	}
+	*num = num_responses;
+	*response = rarray;
+
+      out:
+	dm_free(retbuf);
+
+	return status;
+}
+
+/* Free reply array */
+static int _cluster_free_request(lvm_response_t * response, int num)
+{
+	int i;
+
+	for (i = 0; i < num; i++) {
+		dm_free(response[i].response);
+	}
+
+	dm_free(response);
+
+	return 1;
+}
+
+int refresh_clvmd(int all_nodes)
+{
+	int num_responses;
+	char args[1]; // No args really.
+	lvm_response_t *response = NULL;
+	int saved_errno;
+	int status;
+	int i;
+
+	status = _cluster_request(CLVMD_CMD_REFRESH, all_nodes ? NODE_ALL : NODE_LOCAL, args, 0, &response, &num_responses, 0);
+
+	/* If any nodes were down then display them and return an error */
+	for (i = 0; i < num_responses; i++) {
+		if (response[i].status == EHOSTDOWN) {
+			fprintf(stderr, "clvmd not running on node %s",
+				  response[i].node);
+			status = 0;
+			errno = response[i].status;
+		} else if (response[i].status) {
+			fprintf(stderr, "Error resetting node %s: %s",
+				  response[i].node,
+				  response[i].response[0] ?
+				  	response[i].response :
+				  	strerror(response[i].status));
+			status = 0;
+			errno = response[i].status;
+		}
+	}
+
+	saved_errno = errno;
+	_cluster_free_request(response, num_responses);
+	errno = saved_errno;
+
+	return status;
+}
+
+int restart_clvmd(int all_nodes)
+{
+	int dummy, status;
+
+	status = _cluster_request(CLVMD_CMD_RESTART, all_nodes ? NODE_ALL : NODE_LOCAL, NULL, 0, NULL, &dummy, 1);
+
+	/*
+	 * FIXME: we cannot receive response, clvmd re-exec before it.
+	 *        but also should not close socket too early (the whole rq is dropped then).
+	 * FIXME: This should be handled this way:
+	 *  - client waits for RESTART ack (and socket close)
+	 *  - server restarts
+	 *  - client checks that server is ready again (VERSION command?)
+	 */
+	usleep(500000);
+
+	return status;
+}
+
+int debug_clvmd(int level, int clusterwide)
+{
+	int num_responses;
+	char args[1];
+	const char *nodes;
+	lvm_response_t *response = NULL;
+	int saved_errno;
+	int status;
+	int i;
+
+	args[0] = level;
+	if (clusterwide)
+		nodes = NODE_ALL;
+	else
+		nodes = NODE_LOCAL;
+
+	status = _cluster_request(CLVMD_CMD_SET_DEBUG, nodes, args, 1, &response, &num_responses, 0);
+
+	/* If any nodes were down then display them and return an error */
+	for (i = 0; i < num_responses; i++) {
+		if (response[i].status == EHOSTDOWN) {
+			fprintf(stderr, "clvmd not running on node %s",
+				  response[i].node);
+			status = 0;
+			errno = response[i].status;
+		} else if (response[i].status) {
+			fprintf(stderr, "Error setting debug on node %s: %s",
+				  response[i].node,
+				  response[i].response[0] ?
+				  	response[i].response :
+				  	strerror(response[i].status));
+			status = 0;
+			errno = response[i].status;
+		}
+	}
+
+	saved_errno = errno;
+	_cluster_free_request(response, num_responses);
+	errno = saved_errno;
+
+	return status;
+}

daemons/clvmd/refresh_clvmd.h

@@ -0,0 +1,19 @@
+/*
+ * Copyright (C) 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 General Public License v.2.
+ *
+ * You should have received a copy of the GNU 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
+ */
+
+
+int refresh_clvmd(int all_nodes);
+int restart_clvmd(int all_nodes);
+int debug_clvmd(int level, int clusterwide);
+

daemons/cmirrord/Makefile.in

@@ -17,6 +17,8 @@ top_builddir = @top_builddir@
 
 CPG_LIBS = @CPG_LIBS@
 CPG_CFLAGS = @CPG_CFLAGS@
+SACKPT_LIBS = @SACKPT_LIBS@
+SACKPT_CFLAGS = @SACKPT_CFLAGS@
 
 SOURCES = clogd.c cluster.c compat.c functions.c link_mon.c local.c logging.c
 
@@ -24,15 +26,14 @@ TARGETS = cmirrord
 
 include $(top_builddir)/make.tmpl
 
-LMLIBS += $(CPG_LIBS)
-CFLAGS += $(CPG_CFLAGS) $(EXTRA_EXEC_CFLAGS)
+LIBS += -ldevmapper
+LMLIBS += $(CPG_LIBS) $(SACKPT_LIBS)
+CFLAGS += $(CPG_CFLAGS) $(SACKPT_CFLAGS) $(EXTRA_EXEC_CFLAGS)
 LDFLAGS += $(EXTRA_EXEC_LDFLAGS) $(ELDFLAGS)
 
-cmirrord: $(OBJECTS)
-	@echo "    [CC] $@"
-	$(Q) $(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJECTS) \
-		$(LMLIBS) -L$(top_builddir)/libdm -ldevmapper $(LIBS)
+cmirrord: $(OBJECTS) $(top_builddir)/lib/liblvm-internal.a
+	$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJECTS) \
+		$(LVMLIBS) $(LMLIBS) $(LIBS)
 
 install: $(TARGETS)
-	@echo "    [INSTALL] $<"
-	$(Q) $(INSTALL_PROGRAM) -D cmirrord $(usrsbindir)/cmirrord
+	$(INSTALL_PROGRAM) -D cmirrord $(usrsbindir)/cmirrord

daemons/cmirrord/cluster.c

@@ -16,11 +16,7 @@
 #include "functions.h"
 #include "link_mon.h"
 #include "local.h"
-#include "lib/mm/xlate.h"
-#include "base/memory/zalloc.h"
-
-/* FIXME: remove this and the code */
-#define CMIRROR_HAS_CHECKPOINT 0
+#include "xlate.h"
 
 #include <corosync/cpg.h>
 #include <errno.h>
@@ -403,12 +399,13 @@ static struct checkpoint_data *prepare_checkpoint(struct clog_cpg *entry,
 		return NULL;
 	}
 
-	new = zalloc(sizeof(*new));
+	new = malloc(sizeof(*new));
 	if (!new) {
 		LOG_ERROR("Unable to create checkpoint data for %u",
 			  cp_requester);
 		return NULL;
 	}
+	memset(new, 0, sizeof(*new));
 	new->requester = cp_requester;
 	strncpy(new->uuid, entry->name.value, entry->name.length);
 
@@ -643,12 +640,13 @@ static int export_checkpoint(struct checkpoint_data *cp)
 	rq_size += RECOVERING_REGION_SECTION_SIZE;
 	rq_size += cp->bitmap_size * 2; /* clean|sync_bits */
 
-	rq = zalloc(rq_size);
+	rq = malloc(rq_size);
 	if (!rq) {
 		LOG_ERROR("export_checkpoint: "
 			  "Unable to allocate transfer structs");
 		return -ENOMEM;
 	}
+	memset(rq, 0, rq_size);
 
 	dm_list_init(&rq->u.list);
 	rq->u_rq.request_type = DM_ULOG_CHECKPOINT_READY;
@@ -1620,11 +1618,12 @@ int create_cluster_cpg(char *uuid, uint64_t luid)
 			return -EEXIST;
 		}
 
-	new = zalloc(sizeof(*new));
+	new = malloc(sizeof(*new));
 	if (!new) {
 		LOG_ERROR("Unable to allocate memory for clog_cpg");
 		return -ENOMEM;
 	}
+	memset(new, 0, sizeof(*new));
 	dm_list_init(&new->list);
 	new->lowest_id = 0xDEAD;
 	dm_list_init(&new->startup_list);

daemons/cmirrord/cluster.h

@@ -12,8 +12,8 @@
 #ifndef _LVM_CLOG_CLUSTER_H
 #define _LVM_CLOG_CLUSTER_H
 
-#include "libdm/libdevmapper.h"
-#include "libdm/misc/dm-log-userspace.h"
+#include "dm-log-userspace.h"
+#include "libdevmapper.h"
 
 #define DM_ULOG_RESPONSE 0x1000U /* in last byte of 32-bit value */
 #define DM_ULOG_CHECKPOINT_READY 21

daemons/cmirrord/compat.c

@@ -8,7 +8,7 @@
 #include "logging.h"
 #include "cluster.h"
 #include "compat.h"
-#include "lib/mm/xlate.h"
+#include "xlate.h"
 
 #include <errno.h>
 

daemons/cmirrord/functions.c

@@ -11,7 +11,6 @@
  */
 #include "logging.h"
 #include "functions.h"
-#include "base/memory/zalloc.h"
 
 #include <sys/sysmacros.h>
 #include <dirent.h>
@@ -436,7 +435,7 @@ static int _clog_ctr(char *uuid, uint64_t luid,
 			block_on_error = 1;
 	}
 
-	lc = zalloc(sizeof(*lc));
+	lc = dm_zalloc(sizeof(*lc));
 	if (!lc) {
 		LOG_ERROR("Unable to allocate cluster log context");
 		r = -ENOMEM;
@@ -533,9 +532,9 @@ fail:
 			LOG_ERROR("Close device error, %s: %s",
 				  disk_path, strerror(errno));
 		free(lc->disk_buffer);
-		free(lc->sync_bits);
-		free(lc->clean_bits);
-		free(lc);
+		dm_free(lc->sync_bits);
+		dm_free(lc->clean_bits);
+		dm_free(lc);
 	}
 	return r;
 }
@@ -660,9 +659,9 @@ static int clog_dtr(struct dm_ulog_request *rq)
 			  strerror(errno));
 	if (lc->disk_buffer)
 		free(lc->disk_buffer);
-	free(lc->clean_bits);
-	free(lc->sync_bits);
-	free(lc);
+	dm_free(lc->clean_bits);
+	dm_free(lc->sync_bits);
+	dm_free(lc);
 
 	return 0;
 }

daemons/cmirrord/functions.h

@@ -12,8 +12,7 @@
 #ifndef _LVM_CLOG_FUNCTIONS_H
 #define _LVM_CLOG_FUNCTIONS_H
 
-#include "libdm/libdevmapper.h"
-#include "libdm/misc/dm-log-userspace.h"
+#include "dm-log-userspace.h"
 #include "cluster.h"
 
 #define LOG_RESUMED   1

daemons/cmirrord/logging.h

@@ -13,6 +13,9 @@
 #ifndef _LVM_CLOG_LOGGING_H
 #define _LVM_CLOG_LOGGING_H
 
+#define _GNU_SOURCE
+
+#include "configure.h"
 #include <stdio.h>
 #include <stdint.h>
 #include <syslog.h>

daemons/dmeventd/Makefile.in

@@ -57,16 +57,14 @@ all: device-mapper
 device-mapper: $(TARGETS)
 
 CFLAGS_dmeventd.o += $(EXTRA_EXEC_CFLAGS)
-LIBS += $(PTHREAD_LIBS) -L$(top_builddir)/libdm -ldevmapper
+LIBS += -ldevmapper $(PTHREAD_LIBS)
 
 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
+	$(CC) $(CFLAGS) -L. $(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 \
+dmeventd.static: $(LIB_STATIC) dmeventd.o $(interfacebuilddir)/libdevmapper.a
+	$(CC) $(CFLAGS) $(LDFLAGS) -static -L. -L$(interfacebuilddir) dmeventd.o \
 		-o $@ $(DL_LIBS) $(DMEVENT_LIBS) $(LIBS) $(STATIC_LIBS)
 
 ifeq ("@PKGCONFIG@", "yes")
@@ -75,6 +73,7 @@ endif
 
 ifneq ("$(CFLOW_CMD)", "")
 CFLOW_SOURCES = $(addprefix $(srcdir)/, $(SOURCES))
+-include $(top_builddir)/libdm/libdevmapper.cflow
 -include $(top_builddir)/lib/liblvm-internal.cflow
 -include $(top_builddir)/lib/liblvm2cmd.cflow
 -include $(top_builddir)/daemons/dmeventd/$(LIB_NAME).cflow
@@ -82,28 +81,23 @@ CFLOW_SOURCES = $(addprefix $(srcdir)/, $(SOURCES))
 endif
 
 install_include: $(srcdir)/libdevmapper-event.h
-	@echo "    [INSTALL] $<"
-	$(Q) $(INSTALL_DATA) -D $< $(includedir)/$(<F)
+	$(INSTALL_DATA) -D $< $(includedir)/$(<F)
 
 install_pkgconfig: libdevmapper-event.pc
-	@echo "    [INSTALL] $<"
-	$(Q) $(INSTALL_DATA) -D $< $(pkgconfigdir)/devmapper-event.pc
+	$(INSTALL_DATA) -D $< $(pkgconfigdir)/devmapper-event.pc
 
 install_lib_dynamic: install_lib_shared
 
 install_lib_static: $(LIB_STATIC)
-	@echo "    [INSTALL] $<"
-	$(Q) $(INSTALL_DATA) -D $< $(usrlibdir)/$(<F)
+	$(INSTALL_DATA) -D $< $(usrlibdir)/$(<F)
 
 install_lib: $(INSTALL_LIB_TARGETS)
 
 install_dmeventd_dynamic: dmeventd
-	@echo "    [INSTALL] $<"
-	$(Q) $(INSTALL_PROGRAM) -D $< $(sbindir)/$(<F)
+	$(INSTALL_PROGRAM) -D $< $(sbindir)/$(<F)
 
 install_dmeventd_static: dmeventd.static
-	@echo "    [INSTALL] $<"
-	$(Q) $(INSTALL_PROGRAM) -D $< $(staticdir)/$(<F)
+	$(INSTALL_PROGRAM) -D $< $(staticdir)/$(<F)
 
 install_dmeventd: $(INSTALL_DMEVENTD_TARGETS)
 

daemons/dmeventd/dmeventd.c

@@ -16,12 +16,12 @@
  * dmeventd - dm event daemon to monitor active mapped devices
  */
 
+#include "dm-logging.h"
 
 #include "libdevmapper-event.h"
 #include "dmeventd.h"
 
-#include "libdm/misc/dm-logging.h"
-#include "base/memory/zalloc.h"
+#include "tool.h"
 
 #include <dlfcn.h>
 #include <pthread.h>
@@ -33,8 +33,6 @@
 #include <signal.h>
 #include <arpa/inet.h>		/* for htonl, ntohl */
 #include <fcntl.h>		/* for musl libc */
-#include <unistd.h>
-#include <syslog.h>
 
 #ifdef __linux__
 /*
@@ -62,6 +60,8 @@
 
 #endif
 
+#include <syslog.h>
+
 #define DM_SIGNALED_EXIT  1
 #define DM_SCHEDULED_EXIT 2
 static volatile sig_atomic_t _exit_now = 0;	/* set to '1' when signal is given to exit */
@@ -264,19 +264,19 @@ static pthread_cond_t _timeout_cond = PTHREAD_COND_INITIALIZER;
 /* DSO data allocate/free. */
 static void _free_dso_data(struct dso_data *data)
 {
-	free(data->dso_name);
-	free(data);
+	dm_free(data->dso_name);
+	dm_free(data);
 }
 
 static struct dso_data *_alloc_dso_data(struct message_data *data)
 {
-	struct dso_data *ret = (typeof(ret)) zalloc(sizeof(*ret));
+	struct dso_data *ret = (typeof(ret)) dm_zalloc(sizeof(*ret));
 
 	if (!ret)
 		return_NULL;
 
-	if (!(ret->dso_name = strdup(data->dso_name))) {
-		free(ret);
+	if (!(ret->dso_name = dm_strdup(data->dso_name))) {
+		dm_free(ret);
 		return_NULL;
 	}
 
@@ -397,9 +397,9 @@ static void _free_thread_status(struct thread_status *thread)
 	_lib_put(thread->dso_data);
 	if (thread->wait_task)
 		dm_task_destroy(thread->wait_task);
-	free(thread->device.uuid);
-	free(thread->device.name);
-	free(thread);
+	dm_free(thread->device.uuid);
+	dm_free(thread->device.name);
+	dm_free(thread);
 }
 
 /* Note: events_field must not be 0, ensured by caller */
@@ -408,7 +408,7 @@ static struct thread_status *_alloc_thread_status(const struct message_data *dat
 {
 	struct thread_status *thread;
 
-	if (!(thread = zalloc(sizeof(*thread)))) {
+	if (!(thread = dm_zalloc(sizeof(*thread)))) {
 		log_error("Cannot create new thread, out of memory.");
 		return NULL;
 	}
@@ -422,11 +422,11 @@ static struct thread_status *_alloc_thread_status(const struct message_data *dat
 	if (!dm_task_set_uuid(thread->wait_task, data->device_uuid))
 		goto_out;
 
-	if (!(thread->device.uuid = strdup(data->device_uuid)))
+	if (!(thread->device.uuid = dm_strdup(data->device_uuid)))
 		goto_out;
 
 	/* Until real name resolved, use UUID */
-	if (!(thread->device.name = strdup(data->device_uuid)))
+	if (!(thread->device.name = dm_strdup(data->device_uuid)))
 		goto_out;
 
 	/* runs ioctl and may register lvm2 pluging */
@@ -515,7 +515,7 @@ static int _fetch_string(char **ptr, char **src, const int delimiter)
 	if ((p = strchr(*src, delimiter))) {
 		if (*src < p) {
 			*p = 0; /* Temporary exit with \0 */
-			if (!(*ptr = strdup(*src))) {
+			if (!(*ptr = dm_strdup(*src))) {
 				log_error("Failed to fetch item %s.", *src);
 				ret = 0; /* Allocation fail */
 			}
@@ -525,7 +525,7 @@ static int _fetch_string(char **ptr, char **src, const int delimiter)
 		(*src)++; /* Skip delmiter, next field */
 	} else if ((len = strlen(*src))) {
 		/* No delimiter, item ends with '\0' */
-		if (!(*ptr = strdup(*src))) {
+		if (!(*ptr = dm_strdup(*src))) {
 			log_error("Failed to fetch last item %s.", *src);
 			ret = 0; /* Fail */
 		}
@@ -538,11 +538,11 @@ out:
 /* Free message memory. */
 static void _free_message(struct message_data *message_data)
 {
-	free(message_data->id);
-	free(message_data->dso_name);
-	free(message_data->device_uuid);
-	free(message_data->events_str);
-	free(message_data->timeout_str);
+	dm_free(message_data->id);
+	dm_free(message_data->dso_name);
+	dm_free(message_data->device_uuid);
+	dm_free(message_data->events_str);
+	dm_free(message_data->timeout_str);
 }
 
 /* Parse a register message from the client. */
@@ -574,7 +574,7 @@ static int _parse_message(struct message_data *message_data)
 		ret = 1;
 	}
 
-	free(msg->data);
+	dm_free(msg->data);
 	msg->data = NULL;
 
 	return ret;
@@ -608,8 +608,8 @@ static int _fill_device_data(struct thread_status *ts)
 	if (!dm_task_run(dmt))
 		goto fail;
 
-	free(ts->device.name);
-	if (!(ts->device.name = strdup(dm_task_get_name(dmt))))
+	dm_free(ts->device.name);
+	if (!(ts->device.name = dm_strdup(dm_task_get_name(dmt))))
 		goto fail;
 
 	if (!dm_task_get_info(dmt, &dmi))
@@ -696,8 +696,8 @@ static int _get_status(struct message_data *message_data)
 
 	len = strlen(message_data->id);
 	msg->size = size + len + 1;
-	free(msg->data);
-	if (!(msg->data = malloc(msg->size)))
+	dm_free(msg->data);
+	if (!(msg->data = dm_malloc(msg->size)))
 		goto out;
 
 	memcpy(msg->data, message_data->id, len);
@@ -712,7 +712,7 @@ static int _get_status(struct message_data *message_data)
 	ret = 0;
  out:
 	for (j = 0; j < i; ++j)
-		free(buffers[j]);
+		dm_free(buffers[j]);
 
 	return ret;
 }
@@ -721,7 +721,7 @@ static int _get_parameters(struct message_data *message_data) {
 	struct dm_event_daemon_message *msg = message_data->msg;
 	int size;
 
-	free(msg->data);
+	dm_free(msg->data);
 	if ((size = dm_asprintf(&msg->data, "%s pid=%d daemon=%s exec_method=%s",
 				message_data->id, getpid(),
 				_foreground ? "no" : "yes",
@@ -752,7 +752,7 @@ static void _exit_timeout(void *unused __attribute__((unused)))
 static void *_timeout_thread(void *unused __attribute__((unused)))
 {
 	struct thread_status *thread;
-	struct timespec timeout, real_time;
+	struct timespec timeout;
 	time_t curr_time;
 	int ret;
 
@@ -763,16 +763,7 @@ static void *_timeout_thread(void *unused __attribute__((unused)))
 	while (!dm_list_empty(&_timeout_registry)) {
 		timeout.tv_sec = 0;
 		timeout.tv_nsec = 0;
-#ifndef HAVE_REALTIME
 		curr_time = time(NULL);
-#else
-		if (clock_gettime(CLOCK_REALTIME, &real_time)) {
-			log_error("Failed to read clock_gettime().");
-			break;
-		}
-		/* 10ms back to the future */
-		curr_time = real_time.tv_sec + ((real_time.tv_nsec > (1000000000 - 10000000)) ? 1 : 0);
-#endif
 
 		dm_list_iterate_items_gen(thread, &_timeout_registry, timeout_list) {
 			if (thread->next_time <= curr_time) {
@@ -1234,7 +1225,7 @@ static int _registered_device(struct message_data *message_data,
 	int r;
 	struct dm_event_daemon_message *msg = message_data->msg;
 
-	free(msg->data);
+	dm_free(msg->data);
 
 	if ((r = dm_asprintf(&(msg->data), "%s %s %s %u",
 			     message_data->id,
@@ -1374,7 +1365,7 @@ static int _get_timeout(struct message_data *message_data)
 	if (!thread)
 		return -ENODEV;
 
-	free(msg->data);
+	dm_free(msg->data);
 	msg->size = dm_asprintf(&(msg->data), "%s %" PRIu32,
 				message_data->id, thread->timeout);
 
@@ -1494,34 +1485,37 @@ static int _client_read(struct dm_event_fifos *fifos,
 		t.tv_usec = 0;
 		ret = select(fifos->client + 1, &fds, NULL, NULL, &t);
 
-		if (!ret && bytes)
-			continue; /* trying to finish read */
+		if (!ret && !bytes)	/* nothing to read */
+			return 0;
 
-		if (ret <= 0)	/* nothing to read */
-			goto bad;
+		if (!ret)	/* trying to finish read */
+			continue;
+
+		if (ret < 0)	/* error */
+			return 0;
 
 		ret = read(fifos->client, buf + bytes, size - bytes);
 		bytes += ret > 0 ? ret : 0;
-		if (!msg->data && (bytes == 2 * sizeof(uint32_t))) {
+		if (header && (bytes == 2 * sizeof(uint32_t))) {
 			msg->cmd = ntohl(header[0]);
+			size = msg->size = ntohl(header[1]);
 			bytes = 0;
-
-			if (!(size = msg->size = ntohl(header[1])))
-				break;
-
-			if (!(buf = msg->data = malloc(msg->size)))
-				goto bad;
+			if (!size)
+				break; /* No data -> error */
+			buf = msg->data = dm_malloc(msg->size);
+			if (!buf)
+				break; /* No mem -> error */
+			header = 0;
 		}
 	}
 
-	if (bytes == size)
-		return 1;
+	if (bytes != size) {
+		dm_free(msg->data);
+		msg->data = NULL;
+		return 0;
+	}
 
-bad:
-	free(msg->data);
-	msg->data = NULL;
-
-	return 0;
+	return 1;
 }
 
 /*
@@ -1536,7 +1530,7 @@ static int _client_write(struct dm_event_fifos *fifos,
 	fd_set fds;
 
 	size_t size = 2 * sizeof(uint32_t) + ((msg->data) ? msg->size : 0);
-	uint32_t *header = malloc(size);
+	uint32_t *header = dm_malloc(size);
 	char *buf = (char *)header;
 
 	if (!header) {
@@ -1566,7 +1560,7 @@ static int _client_write(struct dm_event_fifos *fifos,
 	}
 
 	if (header != temp)
-		free(header);
+		dm_free(header);
 
 	return (bytes == size);
 }
@@ -1628,7 +1622,7 @@ static int _do_process_request(struct dm_event_daemon_message *msg)
 			msg->size = dm_asprintf(&(msg->data), "%s %s %d", answer,
 						(msg->cmd == DM_EVENT_CMD_DIE) ? "DYING" : "HELLO",
 						DM_EVENT_PROTOCOL_VERSION);
-			free(answer);
+			dm_free(answer);
 		}
 	} else if (msg->cmd != DM_EVENT_CMD_ACTIVE && !_parse_message(&message_data)) {
 		stack;
@@ -1670,7 +1664,7 @@ static void _process_request(struct dm_event_fifos *fifos)
 
 	DEBUGLOG("<<< CMD:%s (0x%x) completed (result %d).", decode_cmd(cmd), cmd, msg.cmd);
 
-	free(msg.data);
+	dm_free(msg.data);
 
 	if (cmd == DM_EVENT_CMD_DIE) {
 		if (unlink(DMEVENTD_PIDFILE))
@@ -1751,8 +1745,7 @@ static void _init_thread_signals(void)
 	sigdelset(&my_sigset, SIGHUP);
 	sigdelset(&my_sigset, SIGQUIT);
 
-	if (pthread_sigmask(SIG_BLOCK, &my_sigset, NULL))
-		log_sys_error("pthread_sigmask", "SIG_BLOCK");
+	pthread_sigmask(SIG_BLOCK, &my_sigset, NULL);
 }
 
 /*
@@ -1982,7 +1975,7 @@ static int _reinstate_registrations(struct dm_event_fifos *fifos)
 	int i, ret;
 
 	ret = daemon_talk(fifos, &msg, DM_EVENT_CMD_HELLO, NULL, NULL, 0, 0);
-	free(msg.data);
+	dm_free(msg.data);
 	msg.data = NULL;
 
 	if (ret) {
@@ -2028,8 +2021,8 @@ static int _reinstate_registrations(struct dm_event_fifos *fifos)
 static void _restart_dmeventd(void)
 {
 	struct dm_event_fifos fifos = {
-		.client = -1,
 		.server = -1,
+		.client = -1,
 		/* FIXME Make these either configurable or depend directly on dmeventd_path */
 		.client_path = DM_EVENT_FIFO_CLIENT,
 		.server_path = DM_EVENT_FIFO_SERVER
@@ -2068,13 +2061,13 @@ static void _restart_dmeventd(void)
 			++count;
 		}
 
-	if (!(_initial_registrations = malloc(sizeof(char*) * (count + 1)))) {
+	if (!(_initial_registrations = dm_malloc(sizeof(char*) * (count + 1)))) {
 		fprintf(stderr, "Memory allocation registration failed.\n");
 		goto bad;
 	}
 
 	for (i = 0; i < count; ++i) {
-		if (!(_initial_registrations[i] = strdup(message))) {
+		if (!(_initial_registrations[i] = dm_strdup(message))) {
 			fprintf(stderr, "Memory allocation for message failed.\n");
 			goto bad;
 		}
@@ -2243,8 +2236,7 @@ int main(int argc, char *argv[])
 
 	_init_thread_signals();
 
-	if (pthread_mutex_init(&_global_mutex, NULL))
-		exit(EXIT_FAILURE);
+	pthread_mutex_init(&_global_mutex, NULL);
 
 	if (!_systemd_activation && !_open_fifos(&fifos))
 		exit(EXIT_FIFO_FAILURE);

daemons/dmeventd/libdevmapper-event.c

@@ -12,12 +12,10 @@
  * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
+#include "dm-logging.h"
+#include "dmlib.h"
 #include "libdevmapper-event.h"
 #include "dmeventd.h"
-#include "libdm/misc/dm-logging.h"
-#include "base/memory/zalloc.h"
-
-#include "lib/misc/intl.h"
 
 #include <fcntl.h>
 #include <sys/file.h>
@@ -27,7 +25,6 @@
 #include <arpa/inet.h>		/* for htonl, ntohl */
 #include <pthread.h>
 #include <syslog.h>
-#include <unistd.h>
 
 static int _debug_level = 0;
 static int _use_syslog = 0;
@@ -50,8 +47,8 @@ struct dm_event_handler {
 
 static void _dm_event_handler_clear_dev_info(struct dm_event_handler *dmevh)
 {
-	free(dmevh->dev_name);
-	free(dmevh->uuid);
+	dm_free(dmevh->dev_name);
+	dm_free(dmevh->uuid);
 	dmevh->dev_name = dmevh->uuid = NULL;
 	dmevh->major = dmevh->minor = 0;
 }
@@ -60,7 +57,7 @@ struct dm_event_handler *dm_event_handler_create(void)
 {
 	struct dm_event_handler *dmevh;
 
-	if (!(dmevh = zalloc(sizeof(*dmevh)))) {
+	if (!(dmevh = dm_zalloc(sizeof(*dmevh)))) {
 		log_error("Failed to allocate event handler.");
 		return NULL;
 	}
@@ -71,9 +68,9 @@ struct dm_event_handler *dm_event_handler_create(void)
 void dm_event_handler_destroy(struct dm_event_handler *dmevh)
 {
 	_dm_event_handler_clear_dev_info(dmevh);
-	free(dmevh->dso);
-	free(dmevh->dmeventd_path);
-	free(dmevh);
+	dm_free(dmevh->dso);
+	dm_free(dmevh->dmeventd_path);
+	dm_free(dmevh);
 }
 
 int dm_event_handler_set_dmeventd_path(struct dm_event_handler *dmevh, const char *dmeventd_path)
@@ -81,9 +78,9 @@ int dm_event_handler_set_dmeventd_path(struct dm_event_handler *dmevh, const cha
 	if (!dmeventd_path) /* noop */
 		return 0;
 
-	free(dmevh->dmeventd_path);
+	dm_free(dmevh->dmeventd_path);
 
-	if (!(dmevh->dmeventd_path = strdup(dmeventd_path)))
+	if (!(dmevh->dmeventd_path = dm_strdup(dmeventd_path)))
 		return -ENOMEM;
 
 	return 0;
@@ -94,9 +91,9 @@ int dm_event_handler_set_dso(struct dm_event_handler *dmevh, const char *path)
 	if (!path) /* noop */
 		return 0;
 
-	free(dmevh->dso);
+	dm_free(dmevh->dso);
 
-	if (!(dmevh->dso = strdup(path)))
+	if (!(dmevh->dso = dm_strdup(path)))
 		return -ENOMEM;
 
 	return 0;
@@ -109,7 +106,7 @@ int dm_event_handler_set_dev_name(struct dm_event_handler *dmevh, const char *de
 
 	_dm_event_handler_clear_dev_info(dmevh);
 
-	if (!(dmevh->dev_name = strdup(dev_name)))
+	if (!(dmevh->dev_name = dm_strdup(dev_name)))
 		return -ENOMEM;
 
 	return 0;
@@ -122,7 +119,7 @@ int dm_event_handler_set_uuid(struct dm_event_handler *dmevh, const char *uuid)
 
 	_dm_event_handler_clear_dev_info(dmevh);
 
-	if (!(dmevh->uuid = strdup(uuid)))
+	if (!(dmevh->uuid = dm_strdup(uuid)))
 		return -ENOMEM;
 
 	return 0;
@@ -237,16 +234,16 @@ static int _daemon_read(struct dm_event_fifos *fifos,
 			ret = select(fifos->server + 1, &fds, NULL, NULL, &tval);
 			if (ret < 0 && errno != EINTR) {
 				log_error("Unable to read from event server.");
-				goto bad;
+				return 0;
 			}
 			if ((ret == 0) && (i > 4) && !bytes) {
 				log_error("No input from event server.");
-				goto bad;
+				return 0;
 			}
 		}
 		if (ret < 1) {
 			log_error("Unable to read from event server.");
-			goto bad;
+			return 0;
 		}
 
 		ret = read(fifos->server, buf + bytes, size);
@@ -255,32 +252,25 @@ static int _daemon_read(struct dm_event_fifos *fifos,
 				continue;
 
 			log_error("Unable to read from event server.");
-			goto bad;
+			return 0;
 		}
 
 		bytes += ret;
-		if (!msg->data && (bytes == 2 * sizeof(uint32_t))) {
+		if (header && (bytes == 2 * sizeof(uint32_t))) {
 			msg->cmd = ntohl(header[0]);
+			msg->size = ntohl(header[1]);
+			buf = msg->data = dm_malloc(msg->size);
+			size = msg->size;
 			bytes = 0;
-
-			if (!(size = msg->size = ntohl(header[1])))
-				break;
-
-			if (!(buf = msg->data = malloc(msg->size))) {
-				log_error("Unable to allocate message data.");
-				return 0;
-			}
+			header = 0;
 		}
 	}
 
-	if (bytes == size)
-		return 1;
-
-bad:
-	free(msg->data);
-	msg->data = NULL;
-
-	return 0;
+	if (bytes != size) {
+		dm_free(msg->data);
+		msg->data = NULL;
+	}
+	return bytes == size;
 }
 
 /* Write message to daemon. */
@@ -380,13 +370,13 @@ int daemon_talk(struct dm_event_fifos *fifos,
 	 */
 	if (!_daemon_write(fifos, msg)) {
 		stack;
-		free(msg->data);
+		dm_free(msg->data);
 		msg->data = NULL;
 		return -EIO;
 	}
 
 	do {
-		free(msg->data);
+		dm_free(msg->data);
 		msg->data = NULL;
 
 		if (!_daemon_read(fifos, msg)) {
@@ -615,8 +605,8 @@ static int _do_event(int cmd, char *dmeventd_path, struct dm_event_daemon_messag
 {
 	int ret;
 	struct dm_event_fifos fifos = {
-		.client = -1,
 		.server = -1,
+		.client = -1,
 		/* FIXME Make these either configurable or depend directly on dmeventd_path */
 		.client_path = DM_EVENT_FIFO_CLIENT,
 		.server_path = DM_EVENT_FIFO_SERVER
@@ -629,7 +619,7 @@ static int _do_event(int cmd, char *dmeventd_path, struct dm_event_daemon_messag
 
 	ret = daemon_talk(&fifos, msg, DM_EVENT_CMD_HELLO, NULL, NULL, 0, 0);
 
-	free(msg->data);
+	dm_free(msg->data);
 	msg->data = 0;
 
 	if (!ret)
@@ -670,7 +660,7 @@ int dm_event_register_handler(const struct dm_event_handler *dmevh)
 		ret = 0;
 	}
 
-	free(msg.data);
+	dm_free(msg.data);
 
 	dm_task_destroy(dmt);
 
@@ -697,7 +687,7 @@ int dm_event_unregister_handler(const struct dm_event_handler *dmevh)
 		ret = 0;
 	}
 
-	free(msg.data);
+	dm_free(msg.data);
 
 	dm_task_destroy(dmt);
 
@@ -713,7 +703,7 @@ static char *_fetch_string(char **src, const int delimiter)
 	if ((p = strchr(*src, delimiter)))
 		*p = 0;
 
-	if ((ret = strdup(*src)))
+	if ((ret = dm_strdup(*src)))
 		*src += strlen(ret) + 1;
 
 	if (p)
@@ -733,11 +723,11 @@ static int _parse_message(struct dm_event_daemon_message *msg, char **dso_name,
 	    (*dso_name = _fetch_string(&p, ' ')) &&
 	    (*uuid = _fetch_string(&p, ' '))) {
 		*evmask = atoi(p);
-		free(id);
+		dm_free(id);
 		return 0;
 	}
 
-	free(id);
+	dm_free(id);
 	return -ENOMEM;
 }
 
@@ -779,7 +769,7 @@ int dm_event_get_registered_device(struct dm_event_handler *dmevh, int next)
 	dm_task_destroy(dmt);
 	dmt = NULL;
 
-	free(msg.data);
+	dm_free(msg.data);
 	msg.data = NULL;
 
 	_dm_event_handler_clear_dev_info(dmevh);
@@ -788,7 +778,7 @@ int dm_event_get_registered_device(struct dm_event_handler *dmevh, int next)
 		goto fail;
 	}
 
-	if (!(dmevh->uuid = strdup(reply_uuid))) {
+	if (!(dmevh->uuid = dm_strdup(reply_uuid))) {
 		ret = -ENOMEM;
 		goto fail;
 	}
@@ -801,13 +791,13 @@ int dm_event_get_registered_device(struct dm_event_handler *dmevh, int next)
 	dm_event_handler_set_dso(dmevh, reply_dso);
 	dm_event_handler_set_event_mask(dmevh, reply_mask);
 
-	free(reply_dso);
+	dm_free(reply_dso);
 	reply_dso = NULL;
 
-	free(reply_uuid);
+	dm_free(reply_uuid);
 	reply_uuid = NULL;
 
-	if (!(dmevh->dev_name = strdup(dm_task_get_name(dmt)))) {
+	if (!(dmevh->dev_name = dm_strdup(dm_task_get_name(dmt)))) {
 		ret = -ENOMEM;
 		goto fail;
 	}
@@ -825,9 +815,9 @@ int dm_event_get_registered_device(struct dm_event_handler *dmevh, int next)
 	return ret;
 
  fail:
-	free(msg.data);
-	free(reply_dso);
-	free(reply_uuid);
+	dm_free(msg.data);
+	dm_free(reply_dso);
+	dm_free(reply_uuid);
 	_dm_event_handler_clear_dev_info(dmevh);
 	if (dmt)
 		dm_task_destroy(dmt);
@@ -992,12 +982,12 @@ int dm_event_get_timeout(const char *device_path, uint32_t *timeout)
 		if (!p) {
 			log_error("Malformed reply from dmeventd '%s'.",
 				  msg.data);
-			free(msg.data);
+			dm_free(msg.data);
 			return -EIO;
 		}
 		*timeout = atoi(p);
 	}
-	free(msg.data);
+	dm_free(msg.data);
 
 	return ret;
 }

daemons/dmeventd/libdevmapper-event.h

@@ -21,7 +21,6 @@
 #ifndef LIB_DMEVENT_H
 #define LIB_DMEVENT_H
 
-#include <stdarg.h>
 #include <stdint.h>
 
 /*

daemons/dmeventd/libdevmapper-event.pc.in

@@ -8,3 +8,4 @@ Description: device-mapper event library
 Version: @DM_LIB_PATCHLEVEL@
 Cflags: -I${includedir}
 Libs: -L${libdir} -ldevmapper-event
+Requires.private: devmapper

daemons/dmeventd/plugins/lvm2/Makefile.in

@@ -16,7 +16,6 @@ top_srcdir = @top_srcdir@
 top_builddir = @top_builddir@
 
 CLDFLAGS += -L$(top_builddir)/tools
-LIBS += $(DMEVENT_LIBS) $(PTHREAD_LIBS) @LVM2CMD_LIB@
 
 SOURCES = dmeventd_lvm.c
 
@@ -25,6 +24,8 @@ LIB_VERSION = $(LIB_VERSION_LVM)
 
 include $(top_builddir)/make.tmpl
 
+LIBS += @LVM2CMD_LIB@ -ldevmapper $(PTHREAD_LIBS)
+
 install_lvm2: install_lib_shared
 
 install: install_lvm2

daemons/dmeventd/plugins/lvm2/dmeventd_lvm.c

@@ -12,10 +12,10 @@
  * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
-#include "lib/misc/lib.h"
+#include "lib.h"
 #include "dmeventd_lvm.h"
-#include "daemons/dmeventd/libdevmapper-event.h"
-#include "tools/lvm2cmd.h"
+#include "libdevmapper-event.h"
+#include "lvm2cmd.h"
 
 #include <pthread.h>
 
@@ -71,7 +71,7 @@ int dmeventd_lvm2_init(void)
 	if (!_lvm_handle) {
 		lvm2_log_fn(_lvm2_print_log);
 
-		if (!(_lvm_handle = lvm2_init_threaded()))
+		if (!(_lvm_handle = lvm2_init()))
 			goto out;
 
 		/*

daemons/dmeventd/plugins/mirror/Makefile.in

@@ -16,8 +16,8 @@ srcdir = @srcdir@
 top_srcdir = @top_srcdir@
 top_builddir = @top_builddir@
 
+INCLUDES += -I$(top_srcdir)/daemons/dmeventd/plugins/lvm2
 CLDFLAGS += -L$(top_builddir)/daemons/dmeventd/plugins/lvm2
-LIBS += -ldevmapper-event-lvm2
 
 SOURCES = dmeventd_mirror.c
 
@@ -30,6 +30,8 @@ CFLOW_LIST_TARGET = $(LIB_NAME).cflow
 
 include $(top_builddir)/make.tmpl
 
+LIBS += -ldevmapper-event-lvm2 -ldevmapper
+
 install_lvm2: install_dm_plugin
 
 install: install_lvm2

daemons/dmeventd/plugins/mirror/dmeventd_mirror.c

@@ -12,10 +12,10 @@
  * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
-#include "lib/misc/lib.h"
-#include "daemons/dmeventd/plugins/lvm2/dmeventd_lvm.h"
-#include "daemons/dmeventd/libdevmapper-event.h"
-#include "lib/activate/activate.h"
+#include "lib.h"
+#include "libdevmapper-event.h"
+#include "dmeventd_lvm.h"
+#include "activate.h"	/* For TARGET_NAME* */
 
 /* FIXME Reformat to 80 char lines. */
 

daemons/dmeventd/plugins/raid/Makefile.in

@@ -15,8 +15,8 @@ srcdir = @srcdir@
 top_srcdir = @top_srcdir@
 top_builddir = @top_builddir@
 
+INCLUDES += -I$(top_srcdir)/daemons/dmeventd/plugins/lvm2
 CLDFLAGS += -L$(top_builddir)/daemons/dmeventd/plugins/lvm2
-LIBS += -ldevmapper-event-lvm2
 
 SOURCES = dmeventd_raid.c
 
@@ -29,6 +29,8 @@ CFLOW_LIST_TARGET = $(LIB_NAME).cflow
 
 include $(top_builddir)/make.tmpl
 
+LIBS += -ldevmapper-event-lvm2 -ldevmapper
+
 install_lvm2: install_dm_plugin
 
 install: install_lvm2

daemons/dmeventd/plugins/raid/dmeventd_raid.c

@@ -12,10 +12,10 @@
  * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
-#include "lib/misc/lib.h"
-#include "daemons/dmeventd/plugins/lvm2/dmeventd_lvm.h"
-#include "daemons/dmeventd/libdevmapper-event.h"
-#include "lib/config/defaults.h"
+#include "lib.h"
+#include "defaults.h"
+#include "dmeventd_lvm.h"
+#include "libdevmapper-event.h"
 
 /* Hold enough elements for the mximum number of RAID images */
 #define	RAID_DEVS_ELEMS	((DEFAULT_RAID_MAX_IMAGES + 63) / 64)
@@ -76,17 +76,14 @@ 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.
-		 *
-		 * We presume lvconvert to do pre-repair
-		 * checks to avoid bloat in this plugin.
-		 */
-		if (!state->warned && status->insync_regions < status->total_regions) {
-			state->warned = 1;
-			log_warn("WARNING: waiting for resynchronization to finish "
-				 "before initiating repair on RAID device %s.", device);
-			/* Fall through to allow lvconvert to run. */
+		if (status->insync_regions < status->total_regions) {
+			if (!state->warned) {
+				state->warned = 1;
+				log_warn("WARNING: waiting for resynchronization to finish "
+					 "before initiating repair on RAID device %s.", device);
+			}
+
+			goto out; /* Not yet done syncing with accessible devices */
 		}
 
 		if (state->failed)

daemons/dmeventd/plugins/snapshot/Makefile.in

@@ -16,8 +16,8 @@ srcdir = @srcdir@
 top_srcdir = @top_srcdir@
 top_builddir = @top_builddir@
 
+INCLUDES += -I$(top_srcdir)/daemons/dmeventd/plugins/lvm2
 CLDFLAGS += -L$(top_builddir)/daemons/dmeventd/plugins/lvm2
-LIBS += -ldevmapper-event-lvm2
 
 SOURCES = dmeventd_snapshot.c
 
@@ -26,6 +26,8 @@ LIB_VERSION = $(LIB_VERSION_LVM)
 
 include $(top_builddir)/make.tmpl
 
+LIBS += -ldevmapper-event-lvm2 -ldevmapper
+
 install_lvm2: install_dm_plugin
 
 install: install_lvm2

daemons/dmeventd/plugins/snapshot/dmeventd_snapshot.c

@@ -12,9 +12,9 @@
  * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
-#include "lib/misc/lib.h"
-#include "daemons/dmeventd/plugins/lvm2/dmeventd_lvm.h"
-#include "daemons/dmeventd/libdevmapper-event.h"
+#include "lib.h"
+#include "dmeventd_lvm.h"
+#include "libdevmapper-event.h"
 
 #include <sys/sysmacros.h>
 #include <sys/wait.h>
@@ -175,7 +175,6 @@ void process_event(struct dm_task *dmt,
 	const char *device = dm_task_get_name(dmt);
 	int percent;
 	struct dm_info info;
-	int ret;
 
 	/* No longer monitoring, waiting for remove */
 	if (!state->percent_check)
@@ -206,8 +205,7 @@ void process_event(struct dm_task *dmt,
 		/* Maybe configurable ? */
 		_remove(dm_task_get_uuid(dmt));
 #endif
-		if ((ret = pthread_kill(pthread_self(), SIGALRM)) && (ret != ESRCH))
-			log_sys_error("pthread_kill", "self");
+		pthread_kill(pthread_self(), SIGALRM);
 		goto out;
 	}
 
@@ -215,8 +213,7 @@ void process_event(struct dm_task *dmt,
 		/* TODO eventually recognize earlier when room is enough */
 		log_info("Dropping monitoring of fully provisioned snapshot %s.",
 			 device);
-		if ((ret = pthread_kill(pthread_self(), SIGALRM)) && (ret != ESRCH))
-			log_sys_error("pthread_kill", "self");
+		pthread_kill(pthread_self(), SIGALRM);
 		goto out;
 	}
 

daemons/dmeventd/plugins/thin/Makefile.in

@@ -15,8 +15,8 @@ srcdir = @srcdir@
 top_srcdir = @top_srcdir@
 top_builddir = @top_builddir@
 
+INCLUDES += -I$(top_srcdir)/daemons/dmeventd/plugins/lvm2
 CLDFLAGS += -L$(top_builddir)/daemons/dmeventd/plugins/lvm2
-LIBS += -ldevmapper-event-lvm2
 
 SOURCES = dmeventd_thin.c
 
@@ -29,6 +29,8 @@ CFLOW_LIST_TARGET = $(LIB_NAME).cflow
 
 include $(top_builddir)/make.tmpl
 
+LIBS += -ldevmapper-event-lvm2 -ldevmapper
+
 install_lvm2: install_dm_plugin
 
 install: install_lvm2

daemons/dmeventd/plugins/thin/dmeventd_thin.c

@@ -12,16 +12,16 @@
  * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
-#include "lib/misc/lib.h"
-#include "daemons/dmeventd/plugins/lvm2/dmeventd_lvm.h"
-#include "daemons/dmeventd/libdevmapper-event.h"
+#include "lib.h"	/* using here lvm log */
+#include "dmeventd_lvm.h"
+#include "libdevmapper-event.h"
 
 #include <sys/wait.h>
 #include <stdarg.h>
 
 /* TODO - move this mountinfo code into library to be reusable */
 #ifdef __linux__
-#  include "libdm/misc/kdev_t.h"
+#  include "kdev_t.h"
 #else
 #  define MAJOR(x) major((x))
 #  define MINOR(x) minor((x))
@@ -286,7 +286,7 @@ void process_event(struct dm_task *dmt,
 		if (state->fails++ <= state->max_fails) {
 			log_debug("Postponing frequently failing policy (%u <= %u).",
 				  state->fails - 1, state->max_fails);
-			goto out;
+			return;
 		}
 		if (state->max_fails < MAX_FAILS)
 			state->max_fails <<= 1;

daemons/dmeventd/plugins/vdo/Makefile.in

@@ -15,8 +15,8 @@ srcdir = @srcdir@
 top_srcdir = @top_srcdir@
 top_builddir = @top_builddir@
 
+INCLUDES += -I$(top_srcdir)/daemons/dmeventd/plugins/lvm2
 CLDFLAGS += -L$(top_builddir)/daemons/dmeventd/plugins/lvm2
-LIBS += -ldevmapper-event-lvm2
 
 SOURCES = dmeventd_vdo.c
 
@@ -29,6 +29,8 @@ CFLOW_LIST_TARGET = $(LIB_NAME).cflow
 
 include $(top_builddir)/make.tmpl
 
+LIBS += -ldevmapper-event-lvm2 $(INTERNAL_LIBS)
+
 install_lvm2: install_dm_plugin
 
 install: install_lvm2

daemons/dmeventd/plugins/vdo/dmeventd_vdo.c

@@ -12,17 +12,9 @@
  * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
-#include "lib/misc/lib.h"
-#include "daemons/dmeventd/plugins/lvm2/dmeventd_lvm.h"
-#include "daemons/dmeventd/libdevmapper-event.h"
-
-/*
- * Use parser from new device_mapper library.
- * Although during compilation we can see dm_vdo_status_parse()
- * in runtime we are linked agains systems libdm 'older' library
- * which does not provide this symbol and plugin fails to load
- */
-#include "device_mapper/vdo/status.c"
+#include "lib.h"
+#include "dmeventd_lvm.h"
+#include "libdevmapper-event.h"
 
 #include <sys/wait.h>
 #include <stdarg.h>
@@ -53,6 +45,23 @@ struct dso_state {
 	const char *name;
 };
 
+struct vdo_status {
+	uint64_t used_blocks;
+	uint64_t total_blocks;
+};
+
+static int _vdo_status_parse(const char *params, struct vdo_status *status)
+{
+	if (sscanf(params, "%*s %*s %*s %*s %*s %" PRIu64 " %" PRIu64,
+		   &status->used_blocks,
+		   &status->total_blocks) < 2) {
+		log_error("Failed to parse vdo params: %s.", params);
+		return 0;
+	}
+
+	return 1;
+}
+
 DM_EVENT_LOG_FN("vdo")
 
 static int _run_command(struct dso_state *state)
@@ -156,7 +165,7 @@ void process_event(struct dm_task *dmt,
 	char *params;
 	int needs_policy = 0;
 	struct dm_task *new_dmt = NULL;
-	struct dm_vdo_status_parse_result vdop = { .status = NULL };
+	struct vdo_status status;
 
 #if VDO_DEBUG
 	log_debug("Watch for VDO %s:%.2f%%.", state->name,
@@ -202,24 +211,24 @@ void process_event(struct dm_task *dmt,
 		goto out;
 	}
 
-	if (!dm_vdo_status_parse(state->mem, params, &vdop)) {
+	if (!_vdo_status_parse(params, &status)) {
 		log_error("Failed to parse status.");
 		goto out;
 	}
 
-	state->percent = dm_make_percent(vdop.status->used_blocks,
-					 vdop.status->total_blocks);
+	state->percent = dm_make_percent(status.used_blocks,
+					 status.total_blocks);
 
 #if VDO_DEBUG
 	log_debug("VDO %s status  %.2f%% " FMTu64 "/" FMTu64 ".",
 		  state->name, dm_percent_to_round_float(state->percent, 2),
-		  vdop.status->used_blocks, vdop.status->total_blocks);
+		  status.used_blocks, status.total_blocks);
 #endif
 
 	/* VDO pool size had changed. Clear the threshold. */
-	if (state->known_data_size != vdop.status->total_blocks) {
+	if (state->known_data_size != status.total_blocks) {
 		state->percent_check = CHECK_MINIMUM;
-		state->known_data_size = vdop.status->total_blocks;
+		state->known_data_size = status.total_blocks;
 		state->fails = 0;
 	}
 
@@ -252,7 +261,7 @@ void process_event(struct dm_task *dmt,
 		if (state->fails++ <= state->max_fails) {
 			log_debug("Postponing frequently failing policy (%u <= %u).",
 				  state->fails - 1, state->max_fails);
-			goto out;
+			return;
 		}
 		if (state->max_fails < MAX_FAILS)
 			state->max_fails <<= 1;
@@ -260,12 +269,10 @@ void process_event(struct dm_task *dmt,
 	} else
 		state->max_fails = 1; /* Reset on success */
 
-	if (needs_policy)
+	/* FIXME: ATM nothing can be done, drop 0, once it becomes useful */
+	if (0 && needs_policy)
 		_use_policy(dmt, state);
 out:
-	if (vdop.status)
-		dm_pool_free(state->mem, vdop.status);
-
 	if (new_dmt)
 		dm_task_destroy(new_dmt);
 }

daemons/dmfilemapd/.gitignore

@@ -1,2 +1 @@
-dmsetup
 dmfilemapd

daemons/dmfilemapd/Makefile.in

@@ -0,0 +1,66 @@
+#
+# Copyright (C) 2016 Red Hat, Inc. All rights reserved.
+#
+# This file is part of the device-mapper userspace tools.
+#
+# 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
+
+srcdir = @srcdir@
+top_srcdir = @top_srcdir@
+top_builddir = @top_builddir@
+
+SOURCES = dmfilemapd.c
+
+TARGETS = dmfilemapd
+
+.PHONY: install_dmfilemapd install_dmfilemapd_static
+
+INSTALL_DMFILEMAPD_TARGETS = install_dmfilemapd_dynamic
+
+CLEAN_TARGETS = dmfilemapd.static
+
+CFLOW_LIST = $(SOURCES)
+CFLOW_LIST_TARGET = $(LIB_NAME).cflow
+CFLOW_TARGET = dmfilemapd
+
+include $(top_builddir)/make.tmpl
+
+all: device-mapper
+device-mapper: $(TARGETS)
+
+CFLAGS_dmfilemapd.o += $(EXTRA_EXEC_CFLAGS)
+LIBS += -ldevmapper
+
+dmfilemapd: $(LIB_SHARED) dmfilemapd.o
+	$(CC) $(CFLAGS) $(LDFLAGS) $(EXTRA_EXEC_LDFLAGS) $(ELDFLAGS) \
+		-o $@ dmfilemapd.o $(DL_LIBS) $(LIBS)
+
+dmfilemapd.static: $(LIB_STATIC) dmfilemapd.o $(interfacebuilddir)/libdevmapper.a
+	$(CC) $(CFLAGS) $(LDFLAGS) $(ELDFLAGS) -static -L$(interfacebuilddir) \
+		-o $@ dmfilemapd.o $(DL_LIBS) $(LIBS) $(STATIC_LIBS)
+
+ifneq ("$(CFLOW_CMD)", "")
+CFLOW_SOURCES = $(addprefix $(srcdir)/, $(SOURCES))
+-include $(top_builddir)/libdm/libdevmapper.cflow
+-include $(top_builddir)/lib/liblvm-internal.cflow
+-include $(top_builddir)/lib/liblvm2cmd.cflow
+-include $(top_builddir)/daemons/dmfilemapd/$(LIB_NAME).cflow
+endif
+
+install_dmfilemapd_dynamic: dmfilemapd
+	$(INSTALL_PROGRAM) -D $< $(sbindir)/$(<F)
+
+install_dmfilemapd_static: dmfilemapd.static
+	$(INSTALL_PROGRAM) -D $< $(staticdir)/$(<F)
+
+install_dmfilemapd: $(INSTALL_DMFILEMAPD_TARGETS)
+
+install: install_dmfilemapd
+
+install_device-mapper: install_dmfilemapd

daemons/dmfilemapd/dmfilemapd.c

@@ -14,8 +14,11 @@
  * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
-#include "util.h"
-#include "libdm/misc/dm-logging.h"
+#include "tool.h"
+
+#include "dm-logging.h"
+
+#include "defaults.h"
 
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -26,15 +29,13 @@
 #include <ctype.h>
 
 #ifdef __linux__
-#  include "libdm/misc/kdev_t.h"
+#  include "kdev_t.h"
 #else
 #  define MAJOR(x) major((x))
 #  define MINOR(x) minor((x))
-#  define MKDEV(x,y) makedev((x),(y))
+#  define MKDEV(x,y) makedev((dev_t)(x),(dev_t)(y))
 #endif
 
-#define DEFAULT_PROC_DIR "/proc"
-
 /* limit to two updates/sec */
 #define FILEMAPD_WAIT_USECS 500000
 
@@ -310,7 +311,7 @@ static int _parse_args(int argc, char **argv, struct filemap_monitor *fm)
 		return 0;
 	}
 
-	fm->path = strdup(argv[0]);
+	fm->path = dm_strdup(argv[0]);
 	if (!fm->path) {
 		_early_log("Could not allocate memory for path argument.");
 		return 0;
@@ -537,8 +538,8 @@ static void _filemap_monitor_destroy(struct filemap_monitor *fm)
 		_filemap_monitor_end_notify(fm);
 		_filemap_monitor_close_fd(fm);
 	}
-	free((void *) fm->program_id);
-	free(fm->path);
+	dm_free((void *) fm->program_id);
+	dm_free(fm->path);
 }
 
 static int _filemap_monitor_check_same_file(int fd1, int fd2)
@@ -698,7 +699,7 @@ static int _update_regions(struct dm_stats *dms, struct filemap_monitor *fm)
 			 fm->group_id, regions[0]);
 		fm->group_id = regions[0];
 	}
-	free(regions);
+	dm_free(regions);
 	fm->nr_regions = nr_regions;
 	return 1;
 }
@@ -740,7 +741,7 @@ static int _dmfilemapd(struct filemap_monitor *fm)
 	 */
 	program_id = dm_stats_get_region_program_id(dms, fm->group_id);
 	if (program_id)
-		fm->program_id = strdup(program_id);
+		fm->program_id = dm_strdup(program_id);
 	else
 		fm->program_id = NULL;
 	dm_stats_set_program_id(dms, 1, program_id);
@@ -816,7 +817,7 @@ int main(int argc, char **argv)
 	memset(&fm, 0, sizeof(fm));
 
 	if (!_parse_args(argc, argv, &fm)) {
-		free(fm.path);
+		dm_free(fm.path);
 		return 1;
 	}
 
@@ -827,7 +828,7 @@ int main(int argc, char **argv)
 		 _mode_names[fm.mode], fm.path);
 
 	if (!_foreground && !_daemonise(&fm)) {
-		free(fm.path);
+		dm_free(fm.path);
 		return 1;
 	}
 

daemons/lvmdbusd/Makefile.in

@@ -23,10 +23,11 @@ LVMDBUS_SRCDIR_FILES = \
 	cfg.py \
 	cmdhandler.py \
 	fetch.py \
+	__init__.py \
 	job.py \
 	loader.py \
-	lv.py \
 	main.py \
+	lv.py \
 	manager.py \
 	objectmanager.py \
 	pv.py \
@@ -34,8 +35,7 @@ LVMDBUS_SRCDIR_FILES = \
 	state.py \
 	udevwatch.py \
 	utils.py \
-	vg.py \
-	__init__.py
+	vg.py
 
 LVMDBUS_BUILDDIR_FILES = \
 	lvmdb.py \
@@ -51,18 +51,17 @@ include $(top_builddir)/make.tmpl
 .PHONY: install_lvmdbusd
 
 all:
-	$(Q) test -x $(LVMDBUSD) || chmod 755 $(LVMDBUSD)
+	test -x $(LVMDBUSD) || chmod 755 $(LVMDBUSD)
 
 install_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]
+	$(INSTALL_DIR) $(sbindir)
+	$(INSTALL_SCRIPT) $(LVMDBUSD) $(sbindir)
+	$(INSTALL_DIR) $(DESTDIR)$(lvmdbusdir)
+	(cd $(srcdir); $(INSTALL_DATA) $(LVMDBUS_SRCDIR_FILES) $(DESTDIR)$(lvmdbusdir))
+	$(INSTALL_DATA) $(LVMDBUS_BUILDDIR_FILES) $(DESTDIR)$(lvmdbusdir)
+	PYTHON=$(PYTHON3) $(PYCOMPILE) --destdir "$(DESTDIR)" --basedir "$(lvmdbusdir)" $(LVMDBUS_SRCDIR_FILES) $(LVMDBUS_BUILDDIR_FILES)
+	$(CHMOD) 755 $(DESTDIR)$(lvmdbusdir)/__pycache__
+	$(CHMOD) 444 $(DESTDIR)$(lvmdbusdir)/__pycache__/*.py[co]
 
 install_lvm2: install_lvmdbusd
 

daemons/lvmdbusd/automatedproperties.py

@@ -155,7 +155,7 @@ class AutomatedProperties(dbus.service.Object):
 		# through all dbus objects as some don't have a search method, like
 		# 'Manager' object.
 		if not self._ap_search_method:
-			return 0
+			return
 
 		search = self.lvm_id
 		if search_key:

daemons/lvmdbusd/cfg.py

@@ -47,11 +47,9 @@ BUS_NAME = os.getenv('LVM_DBUS_NAME', 'com.redhat.lvmdbus1')
 BASE_INTERFACE = 'com.redhat.lvmdbus1'
 PV_INTERFACE = BASE_INTERFACE + '.Pv'
 VG_INTERFACE = BASE_INTERFACE + '.Vg'
-VG_VDO_INTERFACE = BASE_INTERFACE + '.VgVdo'
 LV_INTERFACE = BASE_INTERFACE + '.Lv'
 LV_COMMON_INTERFACE = BASE_INTERFACE + '.LvCommon'
 THIN_POOL_INTERFACE = BASE_INTERFACE + '.ThinPool'
-VDO_POOL_INTERFACE = BASE_INTERFACE + '.VdoPool'
 CACHE_POOL_INTERFACE = BASE_INTERFACE + '.CachePool'
 LV_CACHED = BASE_INTERFACE + '.CachedLv'
 SNAPSHOT_INTERFACE = BASE_INTERFACE + '.Snapshot'
@@ -63,7 +61,6 @@ PV_OBJ_PATH = BASE_OBJ_PATH + '/Pv'
 VG_OBJ_PATH = BASE_OBJ_PATH + '/Vg'
 LV_OBJ_PATH = BASE_OBJ_PATH + '/Lv'
 THIN_POOL_PATH = BASE_OBJ_PATH + "/ThinPool"
-VDO_POOL_PATH = BASE_OBJ_PATH + "/VdoPool"
 CACHE_POOL_PATH = BASE_OBJ_PATH + "/CachePool"
 HIDDEN_LV_PATH = BASE_OBJ_PATH + "/HiddenLv"
 MANAGER_OBJ_PATH = BASE_OBJ_PATH + '/Manager'
@@ -74,7 +71,6 @@ pv_id = itertools.count()
 vg_id = itertools.count()
 lv_id = itertools.count()
 thin_id = itertools.count()
-vdo_id = itertools.count()
 cache_pool_id = itertools.count()
 job_id = itertools.count()
 hidden_lv = itertools.count()
@@ -83,9 +79,6 @@ hidden_lv = itertools.count()
 load = None
 event = None
 
-# Boolean to denote if lvm supports VDO integration
-vdo_support = False
-
 # Global cached state
 db = None
 
@@ -94,13 +87,3 @@ blackbox = None
 
 # RequestEntry ctor
 create_request_entry = None
-
-
-def exit_daemon():
-    """
-    Exit the daemon cleanly
-    :return:
-    """
-    if run and loop:
-        run.value = 0
-        loop.quit()

daemons/lvmdbusd/cmdhandler.py

@@ -67,7 +67,7 @@ class LvmFlightRecorder(object):
 		with cmd_lock:
 			if len(self.queue):
 				log_error("LVM dbus flight recorder START")
-				for c in reversed(self.queue):
+				for c in self.queue:
 					log_error(str(c))
 				log_error("LVM dbus flight recorder END")
 
@@ -217,10 +217,7 @@ def options_to_cli_args(options):
 		else:
 			rc.append("--%s" % k)
 		if v != "":
-			if isinstance(v, int):
-				rc.append(str(int(v)))
-			else:
-				rc.append(str(v))
+			rc.append(str(v))
 	return rc
 
 
@@ -266,10 +263,10 @@ def lv_tag(lv_name, add, rm, tag_options):
 	return _tag('lvchange', lv_name, add, rm, tag_options)
 
 
-def vg_rename(vg_uuid, new_name, rename_options):
+def vg_rename(vg, new_name, rename_options):
 	cmd = ['vgrename']
 	cmd.extend(options_to_cli_args(rename_options))
-	cmd.extend([vg_uuid, new_name])
+	cmd.extend([vg, new_name])
 	return call(cmd)
 
 
@@ -283,7 +280,7 @@ def vg_remove(vg_name, remove_options):
 def vg_lv_create(vg_name, create_options, name, size_bytes, pv_dests):
 	cmd = ['lvcreate']
 	cmd.extend(options_to_cli_args(create_options))
-	cmd.extend(['--size', '%dB' % size_bytes])
+	cmd.extend(['--size', str(size_bytes) + 'B'])
 	cmd.extend(['--name', name, vg_name, '--yes'])
 	pv_dest_ranges(cmd, pv_dests)
 	return call(cmd)
@@ -295,7 +292,7 @@ def vg_lv_snapshot(vg_name, snapshot_options, name, size_bytes):
 	cmd.extend(["-s"])
 
 	if size_bytes != 0:
-		cmd.extend(['--size', '%dB' % size_bytes])
+		cmd.extend(['--size', str(size_bytes) + 'B'])
 
 	cmd.extend(['--name', name, vg_name])
 	return call(cmd)
@@ -306,9 +303,9 @@ def _vg_lv_create_common_cmd(create_options, size_bytes, thin_pool):
 	cmd.extend(options_to_cli_args(create_options))
 
 	if not thin_pool:
-		cmd.extend(['--size', '%dB' % size_bytes])
+		cmd.extend(['--size', str(size_bytes) + 'B'])
 	else:
-		cmd.extend(['--thin', '--size', '%dB' % size_bytes])
+		cmd.extend(['--thin', '--size', str(size_bytes) + 'B'])
 
 	cmd.extend(['--yes'])
 	return cmd
@@ -323,10 +320,10 @@ def vg_lv_create_linear(vg_name, create_options, name, size_bytes, thin_pool):
 def vg_lv_create_striped(vg_name, create_options, name, size_bytes,
 							num_stripes, stripe_size_kb, thin_pool):
 	cmd = _vg_lv_create_common_cmd(create_options, size_bytes, thin_pool)
-	cmd.extend(['--stripes', str(int(num_stripes))])
+	cmd.extend(['--stripes', str(num_stripes)])
 
 	if stripe_size_kb != 0:
-		cmd.extend(['--stripesize', str(int(stripe_size_kb))])
+		cmd.extend(['--stripesize', str(stripe_size_kb)])
 
 	cmd.extend(['--name', name, vg_name])
 	return call(cmd)
@@ -339,13 +336,13 @@ def _vg_lv_create_raid(vg_name, create_options, name, raid_type, size_bytes,
 	cmd.extend(options_to_cli_args(create_options))
 
 	cmd.extend(['--type', raid_type])
-	cmd.extend(['--size', '%dB' % size_bytes])
+	cmd.extend(['--size', str(size_bytes) + 'B'])
 
 	if num_stripes != 0:
-		cmd.extend(['--stripes', str(int(num_stripes))])
+		cmd.extend(['--stripes', str(num_stripes)])
 
 	if stripe_size_kb != 0:
-		cmd.extend(['--stripesize', str(int(stripe_size_kb))])
+		cmd.extend(['--stripesize', str(stripe_size_kb)])
 
 	cmd.extend(['--name', name, vg_name, '--yes'])
 	return call(cmd)
@@ -366,8 +363,8 @@ def vg_lv_create_mirror(
 	cmd.extend(options_to_cli_args(create_options))
 
 	cmd.extend(['--type', 'mirror'])
-	cmd.extend(['--mirrors', str(int(num_copies))])
-	cmd.extend(['--size', '%dB' % size_bytes])
+	cmd.extend(['--mirrors', str(num_copies)])
+	cmd.extend(['--size', str(size_bytes) + 'B'])
 	cmd.extend(['--name', name, vg_name, '--yes'])
 	return call(cmd)
 
@@ -388,24 +385,6 @@ def vg_create_thin_pool(md_full_name, data_full_name, create_options):
 	return call(cmd)
 
 
-def vg_create_vdo_pool_lv_and_lv(vg_name, pool_name, lv_name, data_size,
-									virtual_size, create_options):
-	cmd = ['lvcreate']
-	cmd.extend(options_to_cli_args(create_options))
-	cmd.extend(['-y', '--type', 'vdo', '-n', lv_name,
-				'-L', '%dB' % data_size, '-V', '%dB' % virtual_size,
-				"%s/%s" % (vg_name, pool_name)])
-	return call(cmd)
-
-
-def vg_create_vdo_pool(pool_full_name, lv_name, virtual_size, create_options):
-	cmd = ['lvconvert']
-	cmd.extend(options_to_cli_args(create_options))
-	cmd.extend(['--type', 'vdo-pool', '-n', lv_name, '--force', '-y',
-				'-V', '%dB' % virtual_size, pool_full_name])
-	return call(cmd)
-
-
 def lv_remove(lv_path, remove_options):
 	cmd = ['lvremove']
 	cmd.extend(options_to_cli_args(remove_options))
@@ -439,7 +418,7 @@ def lv_resize(lv_full_name, size_change, pv_dests,
 def lv_lv_create(lv_full_name, create_options, name, size_bytes):
 	cmd = ['lvcreate']
 	cmd.extend(options_to_cli_args(create_options))
-	cmd.extend(['--virtualsize', '%dB' % size_bytes, '-T'])
+	cmd.extend(['--virtualsize', str(size_bytes) + 'B', '-T'])
 	cmd.extend(['--name', name, lv_full_name, '--yes'])
 	return call(cmd)
 
@@ -453,15 +432,6 @@ 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:
@@ -477,28 +447,6 @@ def lv_detach_cache(lv_full_name, detach_options, destroy_cache):
 	return call(cmd)
 
 
-def lv_vdo_compression(lv_path, enable, comp_options):
-	cmd = ['lvchange', '--compression']
-	if enable:
-		cmd.append('y')
-	else:
-		cmd.append('n')
-	cmd.extend(options_to_cli_args(comp_options))
-	cmd.append(lv_path)
-	return call(cmd)
-
-
-def lv_vdo_deduplication(lv_path, enable, dedup_options):
-	cmd = ['lvchange', '--deduplication']
-	if enable:
-		cmd.append('y')
-	else:
-		cmd.append('n')
-	cmd.extend(options_to_cli_args(dedup_options))
-	cmd.append(lv_path)
-	return call(cmd)
-
-
 def supports_json():
 	cmd = ['help']
 	rc, out, err = call(cmd)
@@ -511,16 +459,6 @@ def supports_json():
 	return False
 
 
-def supports_vdo():
-	cmd = ['segtypes']
-	rc, out, err = call(cmd)
-	if rc == 0:
-		if "vdo" in out:
-			log_debug("We have VDO support")
-			return True
-	return False
-
-
 def lvm_full_report_json():
 	pv_columns = ['pv_name', 'pv_uuid', 'pv_fmt', 'pv_size', 'pv_free',
 					'pv_used', 'dev_size', 'pv_mda_size', 'pv_mda_free',
@@ -548,22 +486,6 @@ def lvm_full_report_json():
 
 	lv_seg_columns = ['seg_pe_ranges', 'segtype', 'lv_uuid']
 
-	if cfg.vdo_support:
-		lv_columns.extend(
-			['vdo_operating_mode', 'vdo_compression_state', 'vdo_index_state',
-				'vdo_used_size', 'vdo_saving_percent']
-		)
-
-		lv_seg_columns.extend(
-			['vdo_compression', 'vdo_deduplication',
-				'vdo_use_metadata_hints', 'vdo_minimum_io_size',
-				'vdo_block_map_cache_size', 'vdo_block_map_era_length',
-				'vdo_use_sparse_index', 'vdo_index_memory_size',
-				'vdo_slab_size', 'vdo_ack_threads', 'vdo_bio_threads',
-				'vdo_bio_rotation', 'vdo_cpu_threads', 'vdo_hash_zone_threads',
-				'vdo_logical_threads', 'vdo_physical_threads',
-				'vdo_max_discard', 'vdo_write_policy', 'vdo_header_size'])
-
 	cmd = _dc('fullreport', [
 		'-a',		# Need hidden too
 		'--configreport', 'pv', '-o', ','.join(pv_columns),
@@ -575,8 +497,7 @@ def lvm_full_report_json():
 	])
 
 	rc, out, err = call(cmd)
-	# When we have an exported vg the exit code of lvs or fullreport will be 5
-	if rc == 0 or rc == 5:
+	if rc == 0:
 		# With the current implementation, if we are using the shell then we
 		# are using JSON and JSON is returned back to us as it was parsed to
 		# figure out if we completed OK or not
@@ -634,7 +555,7 @@ def pv_resize(device, size_bytes, create_options):
 	cmd.extend(options_to_cli_args(create_options))
 
 	if size_bytes != 0:
-		cmd.extend(['--yes', '--setphysicalvolumesize', '%dB' % size_bytes])
+		cmd.extend(['--yes', '--setphysicalvolumesize', str(size_bytes) + 'B'])
 
 	cmd.extend([device])
 	return call(cmd)
@@ -730,12 +651,12 @@ def vg_allocation_policy(vg_name, policy, policy_options):
 
 
 def vg_max_pv(vg_name, number, max_options):
-	return _vg_value_set(vg_name, ['--maxphysicalvolumes', str(int(number))],
+	return _vg_value_set(vg_name, ['--maxphysicalvolumes', str(number)],
 							max_options)
 
 
 def vg_max_lv(vg_name, number, max_options):
-	return _vg_value_set(vg_name, ['-l', str(int(number))], max_options)
+	return _vg_value_set(vg_name, ['-l', str(number)], max_options)
 
 
 def vg_uuid_gen(vg_name, ignore, options):
@@ -777,7 +698,6 @@ def activate_deactivate(op, name, activate, control_flags, options):
 		op += 'n'
 
 	cmd.append(op)
-	cmd.append("-y")
 	cmd.append(name)
 	return call(cmd)
 

daemons/lvmdbusd/fetch.py

@@ -14,7 +14,6 @@ from . import cfg
 from .utils import MThreadRunner, log_debug, log_error
 import threading
 import queue
-import time
 import traceback
 
 
@@ -29,26 +28,11 @@ def _main_thread_load(refresh=True, emit_signal=True):
 		refresh=refresh,
 		emit_signal=emit_signal,
 		cache_refresh=False)[1]
-
-	lv_changes = load_lvs(
+	num_total_changes += load_lvs(
 		refresh=refresh,
 		emit_signal=emit_signal,
 		cache_refresh=False)[1]
 
-	num_total_changes += lv_changes
-
-	# When the LVs change it can cause another change in the VGs which is
-	# missed if we don't scan through the VGs again.  We could achieve this
-	# the other way and re-scan the LVs, but in general there are more LVs than
-	# VGs, thus this should be more efficient.  This happens when a LV interface
-	# changes causing the dbus object representing it to be removed and
-	# recreated.
-	if refresh and lv_changes > 0:
-		num_total_changes += load_vgs(
-			refresh=refresh,
-			emit_signal=emit_signal,
-			cache_refresh=False)[1]
-
 	return num_total_changes
 
 
@@ -98,8 +82,6 @@ class StateUpdate(object):
 
 	@staticmethod
 	def update_thread(obj):
-		exception_count = 0
-
 		queued_requests = []
 		while cfg.run.value != 0:
 			# noinspection PyBroadException
@@ -154,26 +136,12 @@ class StateUpdate(object):
 				# wake up if we get an exception
 				queued_requests = []
 
-				# We retrieved OK, clear exception count
-				exception_count = 0
-
 			except queue.Empty:
 				pass
-			except Exception as e:
+			except Exception:
 				st = traceback.format_exc()
 				log_error("update_thread exception: \n%s" % st)
 				cfg.blackbox.dump()
-				exception_count += 1
-				if exception_count >= 5:
-					for i in queued_requests:
-						i.set_result(e)
-
-					log_error("Too many errors in update_thread, exiting daemon")
-					cfg.exit_daemon()
-
-				else:
-					# Slow things down when encountering errors
-					time.sleep(1)
 
 	def __init__(self):
 		self.lock = threading.RLock()

daemons/lvmdbusd/lv.py

@@ -10,22 +10,20 @@
 from .automatedproperties import AutomatedProperties
 
 from . import utils
-from .utils import vg_obj_path_generate, log_error, _handle_execute
+from .utils import vg_obj_path_generate
 import dbus
 from . import cmdhandler
 from . import cfg
 from .cfg import LV_INTERFACE, THIN_POOL_INTERFACE, SNAPSHOT_INTERFACE, \
-	LV_COMMON_INTERFACE, CACHE_POOL_INTERFACE, LV_CACHED, VDO_POOL_INTERFACE
+	LV_COMMON_INTERFACE, CACHE_POOL_INTERFACE, LV_CACHED
 from .request import RequestEntry
-from .utils import n, n32, d
+from .utils import n, n32
 from .loader import common
 from .state import State
 from . import background
 from .utils import round_size, mt_remove_dbus_objects
 from .job import JobState
 
-import traceback
-
 
 # Try and build a key for a LV, so that we sort the LVs with least dependencies
 # first.  This may be error prone because of the flexibility LVM
@@ -74,66 +72,23 @@ def lvs_state_retrieve(selection, cache_refresh=True):
 	lvs = sorted(cfg.db.fetch_lvs(selection), key=get_key)
 
 	for l in lvs:
-		if cfg.vdo_support:
-			rc.append(LvStateVdo(
-				l['lv_uuid'], l['lv_name'],
-				l['lv_path'], n(l['lv_size']),
-				l['vg_name'],
-				l['vg_uuid'], l['pool_lv_uuid'],
-				l['pool_lv'], l['origin_uuid'], l['origin'],
-				n32(l['data_percent']), l['lv_attr'],
-				l['lv_tags'], l['lv_active'], l['data_lv'],
-				l['metadata_lv'], l['segtype'], l['lv_role'],
-				l['lv_layout'],
-				n32(l['snap_percent']),
-				n32(l['metadata_percent']),
-				n32(l['copy_percent']),
-				n32(l['sync_percent']),
-				n(l['lv_metadata_size']),
-				l['move_pv'],
-				l['move_pv_uuid'],
-				l['vdo_operating_mode'],
-				l['vdo_compression_state'],
-				l['vdo_index_state'],
-				n(l['vdo_used_size']),
-				d(l['vdo_saving_percent']),
-				l['vdo_compression'],
-				l['vdo_deduplication'],
-				l['vdo_use_metadata_hints'],
-				n32(l['vdo_minimum_io_size']),
-				n(l['vdo_block_map_cache_size']),
-				n32(l['vdo_block_map_era_length']),
-				l['vdo_use_sparse_index'],
-				n(l['vdo_index_memory_size']),
-				n(l['vdo_slab_size']),
-				n32(l['vdo_ack_threads']),
-				n32(l['vdo_bio_threads']),
-				n32(l['vdo_bio_rotation']),
-				n32(l['vdo_cpu_threads']),
-				n32(l['vdo_hash_zone_threads']),
-				n32(l['vdo_logical_threads']),
-				n32(l['vdo_physical_threads']),
-				n32(l['vdo_max_discard']),
-				l['vdo_write_policy'],
-				n32(l['vdo_header_size'])))
-		else:
-			rc.append(LvState(
-				l['lv_uuid'], l['lv_name'],
-				l['lv_path'], n(l['lv_size']),
-				l['vg_name'],
-				l['vg_uuid'], l['pool_lv_uuid'],
-				l['pool_lv'], l['origin_uuid'], l['origin'],
-				n32(l['data_percent']), l['lv_attr'],
-				l['lv_tags'], l['lv_active'], l['data_lv'],
-				l['metadata_lv'], l['segtype'], l['lv_role'],
-				l['lv_layout'],
-				n32(l['snap_percent']),
-				n32(l['metadata_percent']),
-				n32(l['copy_percent']),
-				n32(l['sync_percent']),
-				n(l['lv_metadata_size']),
-				l['move_pv'],
-				l['move_pv_uuid']))
+		rc.append(LvState(
+			l['lv_uuid'], l['lv_name'],
+			l['lv_path'], n(l['lv_size']),
+			l['vg_name'],
+			l['vg_uuid'], l['pool_lv_uuid'],
+			l['pool_lv'], l['origin_uuid'], l['origin'],
+			n32(l['data_percent']), l['lv_attr'],
+			l['lv_tags'], l['lv_active'], l['data_lv'],
+			l['metadata_lv'], l['segtype'], l['lv_role'],
+			l['lv_layout'],
+			n32(l['snap_percent']),
+			n32(l['metadata_percent']),
+			n32(l['copy_percent']),
+			n32(l['sync_percent']),
+			n(l['lv_metadata_size']),
+			l['move_pv'],
+			l['move_pv_uuid']))
 	return rc
 
 
@@ -237,8 +192,6 @@ class LvState(State):
 	def _object_type_create(self):
 		if self.Attr[0] == 't':
 			return LvThinPool
-		elif self.Attr[0] == 'd':
-			return LvVdoPool
 		elif self.Attr[0] == 'C':
 			if 'pool' in self.layout:
 				return LvCachePool
@@ -265,34 +218,6 @@ class LvState(State):
 		return (klass, path_method)
 
 
-class LvStateVdo(LvState):
-
-	def __init__(self, Uuid, Name, Path, SizeBytes,
-					vg_name, vg_uuid, pool_lv_uuid, PoolLv,
-					origin_uuid, OriginLv, DataPercent, Attr, Tags, active,
-					data_lv, metadata_lv, segtypes, role, layout, SnapPercent,
-					MetaDataPercent, CopyPercent, SyncPercent,
-					MetaDataSizeBytes, move_pv, move_pv_uuid,
-					vdo_operating_mode, vdo_compression_state, vdo_index_state,
-					vdo_used_size,vdo_saving_percent,vdo_compression,
-					vdo_deduplication,vdo_use_metadata_hints,
-					vdo_minimum_io_size,vdo_block_map_cache_size,
-					vdo_block_map_era_length,vdo_use_sparse_index,
-					vdo_index_memory_size,vdo_slab_size,vdo_ack_threads,
-					vdo_bio_threads,vdo_bio_rotation,vdo_cpu_threads,
-					vdo_hash_zone_threads,vdo_logical_threads,
-					vdo_physical_threads,vdo_max_discard,
-					vdo_write_policy,vdo_header_size):
-		super(LvStateVdo, self).__init__(Uuid, Name, Path, SizeBytes,
-					vg_name, vg_uuid, pool_lv_uuid, PoolLv,
-					origin_uuid, OriginLv, DataPercent, Attr, Tags, active,
-					data_lv, metadata_lv, segtypes, role, layout, SnapPercent,
-					MetaDataPercent, CopyPercent, SyncPercent,
-					MetaDataSizeBytes, move_pv, move_pv_uuid)
-
-		utils.init_class_from_arguments(self, "vdo_", snake_to_pascal=True)
-
-
 # noinspection PyPep8Naming
 @utils.dbus_property(LV_COMMON_INTERFACE, 'Uuid', 's')
 @utils.dbus_property(LV_COMMON_INTERFACE, 'Name', 's')
@@ -348,7 +273,13 @@ class LvCommon(AutomatedProperties):
 
 	@staticmethod
 	def handle_execute(rc, out, err):
-		_handle_execute(rc, out, err, LV_INTERFACE)
+		if rc == 0:
+			cfg.load()
+		else:
+			# Need to work on error handling, need consistent
+			raise dbus.exceptions.DBusException(
+				LV_INTERFACE,
+				'Exit code %s, stderr = %s' % (str(rc), err))
 
 	@staticmethod
 	def validate_dbus_object(lv_uuid, lv_name):
@@ -360,22 +291,6 @@ class LvCommon(AutomatedProperties):
 				(lv_uuid, lv_name))
 		return dbo
 
-	def attr_struct(self, index, type_map, default='undisclosed'):
-		try:
-			if self.state.Attr[index] not in type_map:
-				log_error("LV %s %s with lv_attr %s, lv_attr[%d] = "
-					"'%s' is not known" %
-					(self.Uuid, self.Name, self.Attr, index,
-					self.state.Attr[index]))
-
-			return dbus.Struct((self.state.Attr[index],
-				type_map.get(self.state.Attr[index], default)),
-								signature="(ss)")
-		except BaseException:
-			st = traceback.format_exc()
-			log_error("attr_struct: \n%s" % st)
-			return dbus.Struct(('?', 'Unavailable'), signature="(ss)")
-
 	@property
 	def VolumeType(self):
 		type_map = {'C': 'Cache', 'm': 'mirrored',
@@ -388,16 +303,17 @@ 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', 'g': 'integrity',
 					'-': 'Unspecified'}
-		return self.attr_struct(0, type_map)
+		return dbus.Struct((self.state.Attr[0], type_map[self.state.Attr[0]]),
+						signature="as")
 
 	@property
 	def Permissions(self):
 		type_map = {'w': 'writable', 'r': 'read-only',
 					'R': 'Read-only activation of non-read-only volume',
 					'-': 'Unspecified'}
-		return self.attr_struct(1, type_map)
+		return dbus.Struct((self.state.Attr[1], type_map[self.state.Attr[1]]),
+						signature="(ss)")
 
 	@property
 	def AllocationPolicy(self):
@@ -406,7 +322,8 @@ class LvCommon(AutomatedProperties):
 					'i': 'inherited', 'I': 'inherited locked',
 					'l': 'cling', 'L': 'cling locked',
 					'n': 'normal', 'N': 'normal locked', '-': 'Unspecified'}
-		return self.attr_struct(2, type_map)
+		return dbus.Struct((self.state.Attr[2], type_map[self.state.Attr[2]]),
+						signature="(ss)")
 
 	@property
 	def FixedMinor(self):
@@ -414,20 +331,15 @@ class LvCommon(AutomatedProperties):
 
 	@property
 	def State(self):
-		type_map = {'a': 'active',
-					's': 'suspended',
-					'I': 'Invalid snapshot',
+		type_map = {'a': 'active', 's': 'suspended', 'I': 'Invalid snapshot',
 					'S': 'invalid Suspended snapshot',
 					'm': 'snapshot merge failed',
 					'M': 'suspended snapshot (M)erge failed',
 					'd': 'mapped device present without  tables',
 					'i': 'mapped device present with inactive table',
-					'h': 'historical',
-					'c': 'check needed suspended thin-pool',
-					'C': 'check needed',
-					'X': 'unknown',
-					'-': 'Unspecified'}
-		return self.attr_struct(4, type_map)
+					'X': 'unknown', '-': 'Unspecified'}
+		return dbus.Struct((self.state.Attr[4], type_map[self.state.Attr[4]]),
+						signature="(ss)")
 
 	@property
 	def TargetType(self):
@@ -443,18 +355,11 @@ class LvCommon(AutomatedProperties):
 
 	@property
 	def Health(self):
-		type_map = {'p': 'partial',
-					'r': 'refresh needed',
-					'm': 'mismatches',
-					'w': 'writemostly',
-					'X': 'unknown',
-					'-': 'unspecified',
-					's': 'reshaping',
-					'F': 'failed',
-					'D': 'Data space',
-					'R': 'Remove',
-					'M': 'Metadata'}
-		return self.attr_struct(8, type_map)
+		type_map = {'p': 'partial', 'r': 'refresh',
+					'm': 'mismatches', 'w': 'writemostly',
+					'X': 'X unknown', '-': 'Unspecified'}
+		return dbus.Struct((self.state.Attr[8], type_map[self.state.Attr[8]]),
+					signature="(ss)")
 
 	@property
 	def SkipActivation(self):
@@ -524,7 +429,8 @@ class Lv(LvCommon):
 		# Make sure we have a dbus object representing it
 		LvCommon.validate_dbus_object(lv_uuid, lv_name)
 		# Remove the LV, if successful then remove from the model
-		LvCommon.handle_execute(*cmdhandler.lv_remove(lv_name, remove_options))
+		rc, out, err = cmdhandler.lv_remove(lv_name, remove_options)
+		LvCommon.handle_execute(rc, out, err)
 		return '/'
 
 	@dbus.service.method(
@@ -544,8 +450,9 @@ class Lv(LvCommon):
 		# Make sure we have a dbus object representing it
 		LvCommon.validate_dbus_object(lv_uuid, lv_name)
 		# Rename the logical volume
-		LvCommon.handle_execute(*cmdhandler.lv_rename(lv_name, new_name,
-												rename_options))
+		rc, out, err = cmdhandler.lv_rename(lv_name, new_name,
+											rename_options)
+		LvCommon.handle_execute(rc, out, err)
 		return '/'
 
 	@dbus.service.method(
@@ -594,11 +501,13 @@ class Lv(LvCommon):
 				remainder = space % 512
 				optional_size = space + 512 - remainder
 
-		LvCommon.handle_execute(*cmdhandler.vg_lv_snapshot(
-			lv_name, snapshot_options,name, optional_size))
+		rc, out, err = cmdhandler.vg_lv_snapshot(
+			lv_name, snapshot_options, name, optional_size)
+		LvCommon.handle_execute(rc, out, err)
 		full_name = "%s/%s" % (dbo.vg_name_lookup(), name)
 		return cfg.om.get_object_path_by_lvm_id(full_name)
 
+
 	@dbus.service.method(
 		dbus_interface=LV_INTERFACE,
 		in_signature='stia{sv}',
@@ -634,8 +543,9 @@ class Lv(LvCommon):
 				pv_dests.append((pv_dbus_obj.lvm_id, pr[1], pr[2]))
 
 		size_change = new_size_bytes - dbo.SizeBytes
-		LvCommon.handle_execute(*cmdhandler.lv_resize(
-			dbo.lvm_id, size_change,pv_dests, resize_options))
+		rc, out, err = cmdhandler.lv_resize(dbo.lvm_id, size_change,
+											pv_dests, resize_options)
+		LvCommon.handle_execute(rc, out, err)
 		return "/"
 
 	@dbus.service.method(
@@ -670,8 +580,9 @@ class Lv(LvCommon):
 								options):
 		# Make sure we have a dbus object representing it
 		LvCommon.validate_dbus_object(uuid, lv_name)
-		LvCommon.handle_execute(*cmdhandler.activate_deactivate(
-			'lvchange', lv_name, activate, control_flags, options))
+		rc, out, err = cmdhandler.activate_deactivate(
+			'lvchange', lv_name, activate, control_flags, options)
+		LvCommon.handle_execute(rc, out, err)
 		return '/'
 
 	@dbus.service.method(
@@ -705,8 +616,9 @@ class Lv(LvCommon):
 	def _add_rm_tags(uuid, lv_name, tags_add, tags_del, tag_options):
 		# Make sure we have a dbus object representing it
 		LvCommon.validate_dbus_object(uuid, lv_name)
-		LvCommon.handle_execute(*cmdhandler.lv_tag(
-			lv_name, tags_add, tags_del, tag_options))
+		rc, out, err = cmdhandler.lv_tag(
+			lv_name, tags_add, tags_del, tag_options)
+		LvCommon.handle_execute(rc, out, err)
 		return '/'
 
 	@dbus.service.method(
@@ -743,152 +655,6 @@ 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')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'IndexState', 's')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'UsedSize', 't')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'SavingPercent', 'd')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'Compression', 's')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'Deduplication', 's')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'UseMetadataHints', 's')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'MinimumIoSize', 'u')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'BlockMapCacheSize', "t")
-@utils.dbus_property(VDO_POOL_INTERFACE, 'BlockMapEraLength', 'u')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'UseSparseIndex', 's')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'IndexMemorySize', 't')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'SlabSize', 't')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'AckThreads', 'u')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'BioThreads', 'u')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'BioRotation', 'u')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'CpuThreads', 'u')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'HashZoneThreads', 'u')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'LogicalThreads', 'u')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'PhysicalThreads', 'u')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'MaxDiscard', 'u')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'WritePolicy', 's')
-@utils.dbus_property(VDO_POOL_INTERFACE, 'HeaderSize', 'u')
-class LvVdoPool(Lv):
-	_DataLv_meta = ("o", VDO_POOL_INTERFACE)
-
-	def __init__(self, object_path, object_state):
-		super(LvVdoPool, self).__init__(object_path, object_state)
-		self.set_interface(VDO_POOL_INTERFACE)
-		self._data_lv, _ = self._get_data_meta()
-
-	@property
-	def DataLv(self):
-		return dbus.ObjectPath(self._data_lv)
-
-	@staticmethod
-	def _enable_disable_compression(pool_uuid, pool_name, enable, comp_options):
-		# Make sure we have a dbus object representing it
-		LvCommon.validate_dbus_object(pool_uuid, pool_name)
-		# Rename the logical volume
-		LvCommon.handle_execute(*cmdhandler.lv_vdo_compression(
-			pool_name, enable, comp_options))
-		return '/'
-
-	@dbus.service.method(
-		dbus_interface=VDO_POOL_INTERFACE,
-		in_signature='ia{sv}',
-		out_signature='o',
-		async_callbacks=('cb', 'cbe'))
-	def EnableCompression(self, tmo, comp_options, cb, cbe):
-		r = RequestEntry(
-			tmo, LvVdoPool._enable_disable_compression,
-			(self.Uuid, self.lvm_id, True, comp_options),
-			cb, cbe, False)
-		cfg.worker_q.put(r)
-
-	@dbus.service.method(
-	dbus_interface=VDO_POOL_INTERFACE,
-	in_signature='ia{sv}',
-	out_signature='o',
-	async_callbacks=('cb', 'cbe'))
-	def DisableCompression(self, tmo, comp_options, cb, cbe):
-		r = RequestEntry(
-			tmo, LvVdoPool._enable_disable_compression,
-			(self.Uuid, self.lvm_id, False, comp_options),
-			cb, cbe, False)
-		cfg.worker_q.put(r)
-
-	@staticmethod
-	def _enable_disable_deduplication(pool_uuid, pool_name, enable, dedup_options):
-		# Make sure we have a dbus object representing it
-		LvCommon.validate_dbus_object(pool_uuid, pool_name)
-		# Rename the logical volume
-		LvCommon.handle_execute(*cmdhandler.lv_vdo_deduplication(
-			pool_name, enable, dedup_options))
-		return '/'
-
-	@dbus.service.method(
-		dbus_interface=VDO_POOL_INTERFACE,
-		in_signature='ia{sv}',
-		out_signature='o',
-		async_callbacks=('cb', 'cbe'))
-	def EnableDeduplication(self, tmo, dedup_options, cb, cbe):
-		r = RequestEntry(
-			tmo, LvVdoPool._enable_disable_deduplication,
-			(self.Uuid, self.lvm_id, True, dedup_options),
-			cb, cbe, False)
-		cfg.worker_q.put(r)
-
-	@dbus.service.method(
-	dbus_interface=VDO_POOL_INTERFACE,
-	in_signature='ia{sv}',
-	out_signature='o',
-	async_callbacks=('cb', 'cbe'))
-	def DisableDeduplication(self, tmo, dedup_options, cb, cbe):
-		r = RequestEntry(
-			tmo, LvVdoPool._enable_disable_deduplication,
-			(self.Uuid, self.lvm_id, False, dedup_options),
-			cb, cbe, False)
-		cfg.worker_q.put(r)
-
 
 # noinspection PyPep8Naming
 class LvThinPool(Lv):
@@ -912,8 +678,10 @@ class LvThinPool(Lv):
 	def _lv_create(lv_uuid, lv_name, name, size_bytes, create_options):
 		# Make sure we have a dbus object representing it
 		dbo = LvCommon.validate_dbus_object(lv_uuid, lv_name)
-		LvCommon.handle_execute(*cmdhandler.lv_lv_create(
-			lv_name, create_options, name, size_bytes))
+
+		rc, out, err = cmdhandler.lv_lv_create(
+			lv_name, create_options, name, size_bytes)
+		LvCommon.handle_execute(rc, out, err)
 		full_name = "%s/%s" % (dbo.vg_name_lookup(), name)
 		return cfg.om.get_object_path_by_lvm_id(full_name)
 

daemons/lvmdbusd/lvm_shell_proxy.py.in

@@ -220,10 +220,7 @@ class LVMShellProxy(object):
 
 		# Parse the report to see what happened
 		if 'log' in report_json:
-			ret_code = int(report_json['log'][-1:][0]['log_ret_code'])
-			# If we have an exported vg we get a log_ret_code == 5 when
-			# we do a 'fullreport'
-			if (ret_code == 1) or (ret_code == 5 and argv[0] == 'fullreport'):
+			if report_json['log'][-1:][0]['log_ret_code'] == '1':
 				rc = 0
 			else:
 				error_msg = self.get_error_msg()

daemons/lvmdbusd/lvmdb.py.in

@@ -20,7 +20,7 @@ from lvmdbusd.utils import log_debug, log_error
 
 
 class DataStore(object):
-	def __init__(self, usejson=True, vdo_support=False):
+	def __init__(self, usejson=True):
 		self.pvs = {}
 		self.vgs = {}
 		self.lvs = {}
@@ -43,8 +43,6 @@ class DataStore(object):
 		else:
 			self.json = usejson
 
-		self.vdo_support = vdo_support
-
 	@staticmethod
 	def _insert_record(table, key, record, allowed_multiple):
 		if key in table:
@@ -143,22 +141,13 @@ class DataStore(object):
 
 	@staticmethod
 	def _parse_vgs(_vgs):
-		vgs = sorted(_vgs, key=lambda vk: vk['vg_uuid'])
+		vgs = sorted(_vgs, key=lambda vk: vk['vg_name'])
 
 		c_vgs = OrderedDict()
 		c_lookup = {}
 
 		for i in vgs:
-			vg_name = i['vg_name']
-
-			# Lvm allows duplicate vg names.  When this occurs, each subsequent
-			# matching VG name will be called vg_name:vg_uuid.  Note: ':' is an
-			# invalid character for lvm VG names
-			if vg_name in c_lookup:
-				vg_name = "%s:%s" % (vg_name, i['vg_uuid'])
-				i['vg_name'] = vg_name
-
-			c_lookup[vg_name] = i['vg_uuid']
+			c_lookup[i['vg_name']] = i['vg_uuid']
 			DataStore._insert_record(c_vgs, i['vg_uuid'], i, [])
 
 		return c_vgs, c_lookup
@@ -173,22 +162,13 @@ class DataStore(object):
 				tmp_vg.extend(r['vg'])
 
 		# Sort for consistent output, however this is optional
-		vgs = sorted(tmp_vg, key=lambda vk: vk['vg_uuid'])
+		vgs = sorted(tmp_vg, key=lambda vk: vk['vg_name'])
 
 		c_vgs = OrderedDict()
 		c_lookup = {}
 
 		for i in vgs:
-			vg_name = i['vg_name']
-
-			# Lvm allows duplicate vg names.  When this occurs, each subsequent
-			# matching VG name will be called vg_name:vg_uuid.  Note: ':' is an
-			# invalid character for lvm VG names
-			if vg_name in c_lookup:
-				vg_name = "%s:%s" % (vg_name, i['vg_uuid'])
-				i['vg_name'] = vg_name
-
-			c_lookup[vg_name] = i['vg_uuid']
+			c_lookup[i['vg_name']] = i['vg_uuid']
 			c_vgs[i['vg_uuid']] = i
 
 		return c_vgs, c_lookup
@@ -243,7 +223,8 @@ class DataStore(object):
 
 		return DataStore._parse_lvs_common(c_lvs, c_lv_full_lookup)
 
-	def _parse_lvs_json(self, _all):
+	@staticmethod
+	def _parse_lvs_json(_all):
 
 		c_lvs = OrderedDict()
 		c_lv_full_lookup = {}
@@ -263,13 +244,8 @@ class DataStore(object):
 				if 'seg' in r:
 					for s in r['seg']:
 						r = c_lvs[s['lv_uuid']]
-						r.setdefault('seg_pe_ranges', []).\
-							append(s['seg_pe_ranges'])
+						r.setdefault('seg_pe_ranges', []).append(s['seg_pe_ranges'])
 						r.setdefault('segtype', []).append(s['segtype'])
-						if self.vdo_support:
-							for seg_key, seg_val in s.items():
-								if seg_key.startswith("vdo_"):
-									r[seg_key] = seg_val
 
 		return DataStore._parse_lvs_common(c_lvs, c_lv_full_lookup)
 
@@ -545,10 +521,6 @@ if __name__ == "__main__":
 	for v in ds.vgs.values():
 		pp.pprint(v)
 
-	print("VG name to UUID")
-	for k, v in ds.vg_name_to_uuid.items():
-		print("%s: %s" % (k, v))
-
 	print("LVS")
 	for v in ds.lvs.values():
 		pp.pprint(v)

daemons/lvmdbusd/main.py

@@ -29,7 +29,7 @@ from .utils import log_debug, log_error
 import argparse
 import os
 import sys
-from .cmdhandler import LvmFlightRecorder, supports_vdo
+from .cmdhandler import LvmFlightRecorder
 from .request import RequestEntry
 
 
@@ -44,10 +44,10 @@ def process_request():
 		try:
 			req = cfg.worker_q.get(True, 5)
 			log_debug(
-				"Method start: %s with args %s (callback = %s)" %
-				(str(req.method), str(req.arguments), str(req.cb)))
+				"Running method: %s with args %s" %
+				(str(req.method), str(req.arguments)))
 			req.run_cmd()
-			log_debug("Method complete: %s" % str(req.method))
+			log_debug("Method complete ")
 		except queue.Empty:
 			pass
 		except Exception:
@@ -127,14 +127,6 @@ def main():
 		log_error("You cannot specify --lvmshell and --nojson")
 		sys.exit(1)
 
-	# We will dynamically add interfaces which support vdo if it
-	# exists.
-	cfg.vdo_support = supports_vdo()
-
-	if cfg.vdo_support and not cfg.args.use_json:
-		log_error("You cannot specify --nojson when lvm has VDO support")
-		sys.exit(1)
-
 	# List of threads that we start up
 	thread_list = []
 
@@ -155,12 +147,12 @@ def main():
 	cfg.om = Lvm(BASE_OBJ_PATH)
 	cfg.om.register_object(Manager(MANAGER_OBJ_PATH))
 
-	cfg.db = lvmdb.DataStore(cfg.args.use_json, cfg.vdo_support)
+	cfg.db = lvmdb.DataStore(cfg.args.use_json)
 
 	# Using a thread to process requests, we cannot hang the dbus library
 	# thread that is handling the dbus interface
-	thread_list.append(
-		threading.Thread(target=process_request, name='process_request'))
+	thread_list.append(threading.Thread(target=process_request,
+										name='process_request'))
 
 	# Have a single thread handling updating lvm and the dbus model so we
 	# don't have multiple threads doing this as the same time

daemons/lvmdbusd/manager.py

@@ -27,7 +27,7 @@ class Manager(AutomatedProperties):
 
 	@property
 	def Version(self):
-		return dbus.String('1.1.0')
+		return dbus.String('1.0.0')
 
 	@staticmethod
 	def handle_execute(rc, out, err):
@@ -107,10 +107,10 @@ class Manager(AutomatedProperties):
 		rc = cfg.load(log=False)
 
 		if rc != 0:
-			utils.log_debug('Manager.Refresh - exit %d %d' % (rc, lc),
+			utils.log_debug('Manager.Refresh - exit %d' % (rc),
 							'bg_black', 'fg_light_red')
 		else:
-			utils.log_debug('Manager.Refresh - exit %d %d' % (rc, lc))
+			utils.log_debug('Manager.Refresh - exit %d' % (rc))
 		return rc + lc
 
 	@dbus.service.method(
@@ -164,8 +164,6 @@ class Manager(AutomatedProperties):
 		return the object path in O(1) time.
 
 		:param key: The lookup value
-		:param cb:	dbus python call back parameter, not client visible
-		:param cbe:	dbus python error call back parameter, not client visible
 		:return: Return the object path.  If object not found you will get '/'
 		"""
 		r = RequestEntry(-1, Manager._lookup_by_lvm_id, (key,), cb, cbe, False)

daemons/lvmdbusd/objectmanager.py

@@ -189,8 +189,8 @@ class ObjectManager(AutomatedProperties):
 			path = dbus_object.dbus_object_path()
 			interfaces = dbus_object.interface()
 
-			# print('UN-Registering object path %s for %s' %
-			#		(path, dbus_object.lvm_id))
+			# print 'UN-Registering object path %s for %s' % \
+			#      (path, dbus_object.lvm_id)
 
 			self._lookup_remove(path)
 
@@ -240,19 +240,39 @@ class ObjectManager(AutomatedProperties):
 				return lookup_rc
 			return '/'
 
-	def _id_verify(self, path, uuid, lvm_id):
+	def _uuid_verify(self, path, uuid, lvm_id):
 		"""
-		Ensure our lookups are correct
+		Ensure uuid is present for a successful lvm_id lookup
 		NOTE: Internal call, assumes under object manager lock
 		:param path: 		Path to object we looked up
-		:param uuid: 		uuid lookup
-		:param lvm_id:		lvm_id lookup
+		:param uuid: 		lvm uuid to verify
+		:param lvm_id:		lvm_id used to find object
 		:return: None
 		"""
-		# There is no durable non-changeable name in lvm
+		# This gets called when we found an object based on lvm_id, ensure
+		# uuid is correct too, as they can change. There is no durable
+		# non-changeable name in lvm
 		if lvm_id != uuid:
-			obj = self.get_object_by_path(path)
-			self._lookup_add(obj, path, lvm_id, uuid)
+			if uuid and uuid not in self._id_to_object_path:
+				obj = self.get_object_by_path(path)
+				self._lookup_add(obj, path, lvm_id, uuid)
+
+	def _lvm_id_verify(self, path, uuid, lvm_id):
+		"""
+		Ensure lvm_id is present for a successful uuid lookup
+		NOTE: Internal call, assumes under object manager lock
+		:param path: 		Path to object we looked up
+		:param uuid: 		uuid used to find object
+		:param lvm_id:		lvm_id to verify
+		:return: None
+		"""
+		# This gets called when we found an object based on uuid, ensure
+		# lvm_id is correct too, as they can change.  There is no durable
+		# non-changeable name in lvm
+		if lvm_id != uuid:
+			if lvm_id and lvm_id not in self._id_to_object_path:
+				obj = self.get_object_by_path(path)
+				self._lookup_add(obj, path, lvm_id, uuid)
 
 	def _id_lookup(self, the_id):
 		path = None
@@ -319,22 +339,22 @@ class ObjectManager(AutomatedProperties):
 				# Lets check for the uuid first
 				path = self._id_lookup(uuid)
 				if path:
-					# Ensure table lookups are correct
-					self._id_verify(path, uuid, lvm_id)
+					# Verify the lvm_id is sane
+					self._lvm_id_verify(path, uuid, lvm_id)
 				else:
 					# Unable to find by UUID, lets lookup by lvm_id
 					path = self._id_lookup(lvm_id)
 					if path:
-						# Ensure table lookups are correct
-						self._id_verify(path, uuid, lvm_id)
+						# Verify the uuid is sane
+						self._uuid_verify(path, uuid, lvm_id)
 					else:
 						# We have exhausted all lookups, let's create if we can
 						if path_create:
 							path = path_create()
 							self._lookup_add(None, path, lvm_id, uuid)
 
-			# print('get_object_path_by_lvm_id(%s, %s, %s): return %s' %
-			#	(uuid, lvm_id, str(path_create), path))
+			# print('get_object_path_by_lvm_id(%s, %s, %s, %s: return %s' %
+			# 	   (uuid, lvm_id, str(path_create), str(gen_new), path))
 
 			return path
 

daemons/lvmdbusd/pv.py

@@ -14,7 +14,7 @@ import dbus
 from .cfg import PV_INTERFACE
 from . import cmdhandler
 from .utils import vg_obj_path_generate, n, pv_obj_path_generate, \
-	lv_object_path_method, _handle_execute
+	lv_object_path_method
 from .loader import common
 from .request import RequestEntry
 from .state import State
@@ -138,12 +138,19 @@ class Pv(AutomatedProperties):
 		# Remove the PV, if successful then remove from the model
 		# Make sure we have a dbus object representing it
 		Pv.validate_dbus_object(pv_uuid, pv_name)
-		Pv.handle_execute(*cmdhandler.pv_remove(pv_name, remove_options))
+		rc, out, err = cmdhandler.pv_remove(pv_name, remove_options)
+		Pv.handle_execute(rc, out, err)
 		return '/'
 
 	@staticmethod
 	def handle_execute(rc, out, err):
-		return _handle_execute(rc, out, err, PV_INTERFACE)
+		if rc == 0:
+			cfg.load()
+		else:
+			# Need to work on error handling, need consistent
+			raise dbus.exceptions.DBusException(
+				PV_INTERFACE,
+				'Exit code %s, stderr = %s' % (str(rc), err))
 
 	@staticmethod
 	def validate_dbus_object(pv_uuid, pv_name):
@@ -171,8 +178,10 @@ class Pv(AutomatedProperties):
 	def _resize(pv_uuid, pv_name, new_size_bytes, resize_options):
 		# Make sure we have a dbus object representing it
 		Pv.validate_dbus_object(pv_uuid, pv_name)
-		Pv.handle_execute(*cmdhandler.pv_resize(pv_name, new_size_bytes,
-												resize_options))
+
+		rc, out, err = cmdhandler.pv_resize(pv_name, new_size_bytes,
+												resize_options)
+		Pv.handle_execute(rc, out, err)
 		return '/'
 
 	@dbus.service.method(
@@ -191,8 +200,9 @@ class Pv(AutomatedProperties):
 	def _allocation_enabled(pv_uuid, pv_name, yes_no, allocation_options):
 		# Make sure we have a dbus object representing it
 		Pv.validate_dbus_object(pv_uuid, pv_name)
-		Pv.handle_execute(*cmdhandler.pv_allocatable(pv_name, yes_no,
-														allocation_options))
+		rc, out, err = cmdhandler.pv_allocatable(
+			pv_name, yes_no, allocation_options)
+		Pv.handle_execute(rc, out, err)
 		return '/'
 
 	@dbus.service.method(

daemons/lvmdbusd/utils.py

@@ -26,15 +26,6 @@ import signal
 STDOUT_TTY = os.isatty(sys.stdout.fileno())
 
 
-def _handle_execute(rc, out, err, interface):
-	if rc == 0:
-		cfg.load()
-	else:
-		# Need to work on error handling, need consistent
-		raise dbus.exceptions.DBusException(
-			interface, 'Exit code %s, stderr = %s' % (str(rc), err))
-
-
 def rtype(dbus_type):
 	"""
 	Decorator making sure that the decorated function returns a value of
@@ -66,20 +57,8 @@ def n32(v):
 	return int(float(v))
 
 
-@rtype(dbus.Double)
-def d(v):
-	if not v:
-		return 0.0
-	return float(v)
-
-
-def _snake_to_pascal(s):
-	return ''.join(x.title() for x in s.split('_'))
-
-
 # noinspection PyProtectedMember
-def init_class_from_arguments(
-		obj_instance, begin_suffix=None, snake_to_pascal=False):
+def init_class_from_arguments(obj_instance):
 	for k, v in list(sys._getframe(1).f_locals.items()):
 		if k != 'self':
 			nt = k
@@ -90,17 +69,8 @@ def init_class_from_arguments(
 			cur = getattr(obj_instance, nt, v)
 
 			# print 'Init class %s = %s' % (nt, str(v))
-			if not (cur and len(str(cur)) and (v is None or len(str(v))) == 0)\
-					and (begin_suffix is None or nt.startswith(begin_suffix)):
-
-				if begin_suffix and nt.startswith(begin_suffix):
-					name = nt[len(begin_suffix):]
-					if snake_to_pascal:
-						name = _snake_to_pascal(name)
-
-					setattr(obj_instance, name, v)
-				else:
-					setattr(obj_instance, nt, v)
+			if not (cur and len(str(cur)) and (v is None or len(str(v))) == 0):
+				setattr(obj_instance, nt, v)
 
 
 def get_properties(f):
@@ -368,8 +338,6 @@ def lv_object_path_method(name, meta):
 		return _hidden_lv_obj_path_generate
 	elif meta[0][0] == 't':
 		return _thin_pool_obj_path_generate
-	elif meta[0][0] == 'd':
-		return _vdo_pool_object_path_generate
 	elif meta[0][0] == 'C' and 'pool' in meta[1]:
 		return _cache_pool_obj_path_generate
 
@@ -387,10 +355,6 @@ def _thin_pool_obj_path_generate():
 	return cfg.THIN_POOL_PATH + "/%d" % next(cfg.thin_id)
 
 
-def _vdo_pool_object_path_generate():
-	return cfg.VDO_POOL_PATH + "/%d" % next(cfg.vdo_id)
-
-
 def _cache_pool_obj_path_generate():
 	return cfg.CACHE_POOL_PATH + "/%d" % next(cfg.cache_pool_id)
 
@@ -482,7 +446,7 @@ _ALLOWABLE_CH_SET = set(_ALLOWABLE_CH)
 _ALLOWABLE_VG_LV_CH = string.ascii_letters + string.digits + '.-_+'
 _ALLOWABLE_VG_LV_CH_SET = set(_ALLOWABLE_VG_LV_CH)
 _LV_NAME_RESERVED = ("_cdata", "_cmeta", "_corig", "_mimage", "_mlog",
-	"_pmspare", "_rimage", "_rmeta", "_tdata", "_tmeta", "_vorigin", "_vdata")
+	"_pmspare", "_rimage", "_rmeta", "_tdata", "_tmeta", "_vorigin")
 
 # Tags can have the characters, based on the code
 # a-zA-Z0-9._-+/=!:&#

daemons/lvmdbusd/vg.py

@@ -10,11 +10,10 @@
 from .automatedproperties import AutomatedProperties
 
 from . import utils
-from .utils import pv_obj_path_generate, vg_obj_path_generate, n, \
-	_handle_execute
+from .utils import pv_obj_path_generate, vg_obj_path_generate, n
 import dbus
 from . import cfg
-from .cfg import VG_INTERFACE, VG_VDO_INTERFACE
+from .cfg import VG_INTERFACE
 from . import cmdhandler
 from .request import RequestEntry
 from .loader import common
@@ -47,29 +46,24 @@ def vgs_state_retrieve(selection, cache_refresh=True):
 
 def load_vgs(vg_specific=None, object_path=None, refresh=False,
 		emit_signal=False, cache_refresh=True):
-	return common(vgs_state_retrieve, (Vg, VgVdo, ), vg_specific, object_path, refresh,
+	return common(vgs_state_retrieve, (Vg,), vg_specific, object_path, refresh,
 					emit_signal, cache_refresh)
 
 
 # noinspection PyPep8Naming,PyUnresolvedReferences,PyUnusedLocal
 class VgState(State):
-
-	@property
-	def internal_name(self):
-		return self.Name
-
 	@property
 	def lvm_id(self):
-		return self.internal_name
+		return self.Name
 
 	def identifiers(self):
-		return (self.Uuid, self.internal_name)
+		return (self.Uuid, self.Name)
 
 	def _lv_paths_build(self):
 		rc = []
 		for lv in cfg.db.lvs_in_vg(self.Uuid):
 			(lv_name, meta, lv_uuid) = lv
-			full_name = "%s/%s" % (self.internal_name, lv_name)
+			full_name = "%s/%s" % (self.Name, lv_name)
 
 			gen = utils.lv_object_path_method(lv_name, meta)
 
@@ -98,12 +92,8 @@ class VgState(State):
 	def create_dbus_object(self, path):
 		if not path:
 			path = cfg.om.get_object_path_by_uuid_lvm_id(
-				self.Uuid, self.internal_name, vg_obj_path_generate)
-
-		if cfg.vdo_support:
-			return VgVdo(path, self)
-		else:
-			return Vg(path, self)
+				self.Uuid, self.Name, vg_obj_path_generate)
+		return Vg(path, self)
 
 	# noinspection PyMethodMayBeStatic
 	def creation_signature(self):
@@ -112,6 +102,7 @@ class VgState(State):
 
 # noinspection PyPep8Naming
 @utils.dbus_property(VG_INTERFACE, 'Uuid', 's')
+@utils.dbus_property(VG_INTERFACE, 'Name', 's')
 @utils.dbus_property(VG_INTERFACE, 'Fmt', 's')
 @utils.dbus_property(VG_INTERFACE, 'SizeBytes', 't', 0)
 @utils.dbus_property(VG_INTERFACE, 'FreeBytes', 't', 0)
@@ -144,7 +135,6 @@ class Vg(AutomatedProperties):
 	_AllocNormal_meta = ('b', VG_INTERFACE)
 	_AllocAnywhere_meta = ('b', VG_INTERFACE)
 	_Clustered_meta = ('b', VG_INTERFACE)
-	_Name_meta = ('s', VG_INTERFACE)
 
 	# noinspection PyUnusedLocal,PyPep8Naming
 	def __init__(self, object_path, object_state):
@@ -159,7 +149,13 @@ class Vg(AutomatedProperties):
 
 	@staticmethod
 	def handle_execute(rc, out, err):
-		return _handle_execute(rc, out, err, VG_INTERFACE)
+		if rc == 0:
+			cfg.load()
+		else:
+			# Need to work on error handling, need consistent
+			raise dbus.exceptions.DBusException(
+				VG_INTERFACE,
+				'Exit code %s, stderr = %s' % (str(rc), err))
 
 	@staticmethod
 	def validate_dbus_object(vg_uuid, vg_name):
@@ -175,8 +171,9 @@ class Vg(AutomatedProperties):
 	def _rename(uuid, vg_name, new_name, rename_options):
 		# Make sure we have a dbus object representing it
 		Vg.validate_dbus_object(uuid, vg_name)
-		Vg.handle_execute(*cmdhandler.vg_rename(
-			uuid, new_name, rename_options))
+		rc, out, err = cmdhandler.vg_rename(
+			vg_name, new_name, rename_options)
+		Vg.handle_execute(rc, out, err)
 		return '/'
 
 	@dbus.service.method(
@@ -195,7 +192,8 @@ class Vg(AutomatedProperties):
 		# Make sure we have a dbus object representing it
 		Vg.validate_dbus_object(uuid, vg_name)
 		# Remove the VG, if successful then remove from the model
-		Vg.handle_execute(*cmdhandler.vg_remove(vg_name, remove_options))
+		rc, out, err = cmdhandler.vg_remove(vg_name, remove_options)
+		Vg.handle_execute(rc, out, err)
 		return '/'
 
 	@dbus.service.method(
@@ -211,13 +209,14 @@ class Vg(AutomatedProperties):
 	@staticmethod
 	def _change(uuid, vg_name, change_options):
 		Vg.validate_dbus_object(uuid, vg_name)
-		Vg.handle_execute(*cmdhandler.vg_change(change_options, vg_name))
+		rc, out, err = cmdhandler.vg_change(change_options, vg_name)
+		Vg.handle_execute(rc, out, err)
 		return '/'
 
 	# TODO: This should be broken into a number of different methods
 	# instead of having one method that takes a hash for parameters.  Some of
 	# the changes that vgchange does works on entire system, not just a
-	# specific vg, thus that should be in the Manager interface.
+	# specfic vg, thus that should be in the Manager interface.
 	@dbus.service.method(
 		dbus_interface=VG_INTERFACE,
 		in_signature='ia{sv}',
@@ -247,8 +246,9 @@ class Vg(AutomatedProperties):
 						VG_INTERFACE,
 						'PV Object path not found = %s!' % pv_op)
 
-		Vg.handle_execute(*cmdhandler.vg_reduce(
-			vg_name, missing, pv_devices, reduce_options))
+		rc, out, err = cmdhandler.vg_reduce(vg_name, missing, pv_devices,
+											reduce_options)
+		Vg.handle_execute(rc, out, err)
 		return '/'
 
 	@dbus.service.method(
@@ -278,8 +278,9 @@ class Vg(AutomatedProperties):
 					VG_INTERFACE, 'PV Object path not found = %s!' % i)
 
 		if len(extend_devices):
-			Vg.handle_execute(*cmdhandler.vg_extend(
-				vg_name, extend_devices, extend_options))
+			rc, out, err = cmdhandler.vg_extend(vg_name, extend_devices,
+												extend_options)
+			Vg.handle_execute(rc, out, err)
 		else:
 			raise dbus.exceptions.DBusException(
 				VG_INTERFACE, 'No pv_object_paths provided!')
@@ -333,8 +334,10 @@ class Vg(AutomatedProperties):
 
 				pv_dests.append((pv_dbus_obj.lvm_id, pr[1], pr[2]))
 
-		Vg.handle_execute(*cmdhandler.vg_lv_create(
-			vg_name, create_options, name, size_bytes, pv_dests))
+		rc, out, err = cmdhandler.vg_lv_create(
+			vg_name, create_options, name, size_bytes, pv_dests)
+
+		Vg.handle_execute(rc, out, err)
 		return Vg.fetch_new_lv(vg_name, name)
 
 	@dbus.service.method(
@@ -372,8 +375,11 @@ class Vg(AutomatedProperties):
 			thin_pool, create_options):
 		# Make sure we have a dbus object representing it
 		Vg.validate_dbus_object(uuid, vg_name)
-		Vg.handle_execute(*cmdhandler.vg_lv_create_linear(
-			vg_name, create_options, name, size_bytes, thin_pool))
+
+		rc, out, err = cmdhandler.vg_lv_create_linear(
+			vg_name, create_options, name, size_bytes, thin_pool)
+
+		Vg.handle_execute(rc, out, err)
 		return Vg.fetch_new_lv(vg_name, name)
 
 	@dbus.service.method(
@@ -395,9 +401,10 @@ class Vg(AutomatedProperties):
 			stripe_size_kb, thin_pool, create_options):
 		# Make sure we have a dbus object representing it
 		Vg.validate_dbus_object(uuid, vg_name)
-		Vg.handle_execute(*cmdhandler.vg_lv_create_striped(
+		rc, out, err = cmdhandler.vg_lv_create_striped(
 			vg_name, create_options, name, size_bytes,
-			num_stripes, stripe_size_kb, thin_pool))
+			num_stripes, stripe_size_kb, thin_pool)
+		Vg.handle_execute(rc, out, err)
 		return Vg.fetch_new_lv(vg_name, name)
 
 	@dbus.service.method(
@@ -422,8 +429,9 @@ class Vg(AutomatedProperties):
 			num_copies, create_options):
 		# Make sure we have a dbus object representing it
 		Vg.validate_dbus_object(uuid, vg_name)
-		Vg.handle_execute(*cmdhandler.vg_lv_create_mirror(
-			vg_name, create_options, name, size_bytes, num_copies))
+		rc, out, err = cmdhandler.vg_lv_create_mirror(
+			vg_name, create_options, name, size_bytes, num_copies)
+		Vg.handle_execute(rc, out, err)
 		return Vg.fetch_new_lv(vg_name, name)
 
 	@dbus.service.method(
@@ -446,9 +454,10 @@ class Vg(AutomatedProperties):
 						num_stripes, stripe_size_kb, create_options):
 		# Make sure we have a dbus object representing it
 		Vg.validate_dbus_object(uuid, vg_name)
-		Vg.handle_execute(*cmdhandler.vg_lv_create_raid(
+		rc, out, err = cmdhandler.vg_lv_create_raid(
 			vg_name, create_options, name, raid_type, size_bytes,
-			num_stripes, stripe_size_kb))
+			num_stripes, stripe_size_kb)
+		Vg.handle_execute(rc, out, err)
 		return Vg.fetch_new_lv(vg_name, name)
 
 	@dbus.service.method(
@@ -546,8 +555,9 @@ class Vg(AutomatedProperties):
 				raise dbus.exceptions.DBusException(
 					VG_INTERFACE, 'PV object path = %s not found' % p)
 
-		Vg.handle_execute(*cmdhandler.pv_tag(
-			pv_devices, tags_add, tags_del, tag_options))
+		rc, out, err = cmdhandler.pv_tag(
+			pv_devices, tags_add, tags_del, tag_options)
+		Vg.handle_execute(rc, out, err)
 		return '/'
 
 	@dbus.service.method(
@@ -588,8 +598,9 @@ class Vg(AutomatedProperties):
 		# Make sure we have a dbus object representing it
 		Vg.validate_dbus_object(uuid, vg_name)
 
-		Vg.handle_execute(*cmdhandler.vg_tag(
-			vg_name, tags_add, tags_del, tag_options))
+		rc, out, err = cmdhandler.vg_tag(
+			vg_name, tags_add, tags_del, tag_options)
+		Vg.handle_execute(rc, out, err)
 		return '/'
 
 	@dbus.service.method(
@@ -628,7 +639,8 @@ class Vg(AutomatedProperties):
 	def _vg_change_set(uuid, vg_name, method, value, options):
 		# Make sure we have a dbus object representing it
 		Vg.validate_dbus_object(uuid, vg_name)
-		Vg.handle_execute(*method(vg_name, value, options))
+		rc, out, err = method(vg_name, value, options)
+		Vg.handle_execute(rc, out, err)
 		return '/'
 
 	@dbus.service.method(
@@ -688,8 +700,9 @@ class Vg(AutomatedProperties):
 								options):
 		# Make sure we have a dbus object representing it
 		Vg.validate_dbus_object(uuid, vg_name)
-		Vg.handle_execute(*cmdhandler.activate_deactivate(
-			'vgchange', vg_name, activate, control_flags, options))
+		rc, out, err = cmdhandler.activate_deactivate(
+			'vgchange', vg_name, activate, control_flags, options)
+		Vg.handle_execute(rc, out, err)
 		return '/'
 
 	@dbus.service.method(
@@ -716,12 +729,6 @@ class Vg(AutomatedProperties):
 				cb, cbe, return_tuple=False)
 		cfg.worker_q.put(r)
 
-	@property
-	def Name(self):
-		if ':' in self.state.Name:
-			return self.state.Name.split(':')[0]
-		return self.state.Name
-
 	@property
 	def Tags(self):
 		return utils.parse_tags(self.state.tags)
@@ -777,71 +784,3 @@ class Vg(AutomatedProperties):
 	@property
 	def Clustered(self):
 		return self._attribute(5, 'c')
-
-
-class VgVdo(Vg):
-
-	# noinspection PyUnusedLocal,PyPep8Naming
-	def __init__(self, object_path, object_state):
-		super(VgVdo, self).__init__(object_path, vgs_state_retrieve)
-		self.set_interface(VG_VDO_INTERFACE)
-		self._object_path = object_path
-		self.state = object_state
-
-	@staticmethod
-	def _lv_vdo_pool_create_with_lv(uuid, vg_name, pool_name, lv_name,
-									data_size, virtual_size, create_options):
-		Vg.validate_dbus_object(uuid, vg_name)
-		Vg.handle_execute(*cmdhandler.vg_create_vdo_pool_lv_and_lv(
-			vg_name, pool_name, lv_name, data_size, virtual_size,
-			create_options))
-		return Vg.fetch_new_lv(vg_name, pool_name)
-
-	@dbus.service.method(
-		dbus_interface=VG_VDO_INTERFACE,
-		in_signature='ssttia{sv}',
-		out_signature='(oo)',
-		async_callbacks=('cb', 'cbe'))
-	def CreateVdoPoolandLv(self, pool_name, lv_name, data_size, virtual_size,
-							tmo, create_options, cb, cbe):
-		utils.validate_lv_name(VG_VDO_INTERFACE, self.Name, pool_name)
-		utils.validate_lv_name(VG_VDO_INTERFACE, self.Name, lv_name)
-
-		r = RequestEntry(tmo, VgVdo._lv_vdo_pool_create_with_lv,
-							(self.state.Uuid, self.state.lvm_id,
-							pool_name, lv_name, round_size(data_size),
-							round_size(virtual_size),
-							create_options), cb, cbe)
-		cfg.worker_q.put(r)
-
-	@staticmethod
-	def _vdo_pool_create(uuid, vg_name, pool_lv, name, virtual_size, create_options):
-		Vg.validate_dbus_object(uuid, vg_name)
-
-		# Retrieve the full name of the pool lv
-		pool = cfg.om.get_object_by_path(pool_lv)
-		if not pool:
-			msg = 'LV with object path %s not present!' % \
-					(pool_lv)
-			raise dbus.exceptions.DBusException(VG_VDO_INTERFACE, msg)
-
-		Vg.handle_execute(*cmdhandler.vg_create_vdo_pool(
-			pool.lv_full_name(), name, virtual_size,
-			create_options))
-		return Vg.fetch_new_lv(vg_name, pool.Name)
-
-	@dbus.service.method(
-		dbus_interface=VG_VDO_INTERFACE,
-		in_signature='ostia{sv}',
-		out_signature='(oo)',
-		async_callbacks=('cb', 'cbe'))
-	def CreateVdoPool(self, pool_lv, name, virtual_size,
-						tmo, create_options, cb, cbe):
-		utils.validate_lv_name(VG_VDO_INTERFACE, self.Name, name)
-
-		r = RequestEntry(tmo, VgVdo._vdo_pool_create,
-							(self.state.Uuid, self.state.lvm_id,
-							pool_lv, name,
-							round_size(virtual_size),
-							create_options), cb, cbe)
-		cfg.worker_q.put(r)

daemons/lvmetad/.gitignore

@@ -0,0 +1,2 @@
+lvmetad
+lvmetactl

daemons/lvmetad/Makefile.in

@@ -0,0 +1,62 @@
+#
+# Copyright (C) 2011-2012 Red Hat, Inc.
+#
+# 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
+
+srcdir = @srcdir@
+top_srcdir = @top_srcdir@
+top_builddir = @top_builddir@
+
+SOURCES = lvmetad-core.c
+SOURCES2 = lvmetactl.c
+
+TARGETS = lvmetad lvmetactl
+
+.PHONY: install_lvmetad
+
+CFLOW_LIST = $(SOURCES)
+CFLOW_LIST_TARGET = $(LIB_NAME).cflow
+CFLOW_TARGET = lvmetad
+
+include $(top_builddir)/make.tmpl
+
+CFLAGS_lvmetactl.o += $(EXTRA_EXEC_CFLAGS)
+CFLAGS_lvmetad-core.o += $(EXTRA_EXEC_CFLAGS)
+INCLUDES += -I$(top_srcdir)/libdaemon/server
+LDFLAGS += -L$(top_builddir)/libdaemon/server $(EXTRA_EXEC_LDFLAGS) $(ELDFLAGS)
+LIBS += $(RT_LIBS) $(DAEMON_LIBS) -ldevmapper $(PTHREAD_LIBS)
+
+lvmetad: $(OBJECTS) $(top_builddir)/libdaemon/client/libdaemonclient.a \
+		    $(top_builddir)/libdaemon/server/libdaemonserver.a
+	$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJECTS) -ldaemonserver $(LIBS)
+
+lvmetactl: lvmetactl.o $(top_builddir)/libdaemon/client/libdaemonclient.a \
+	$(top_builddir)/libdaemon/server/libdaemonserver.a
+	$(CC) $(CFLAGS) $(LDFLAGS) -o $@ lvmetactl.o $(LIBS)
+
+CLEAN_TARGETS += lvmetactl.o
+
+# TODO: No idea. No idea how to test either.
+#ifneq ("$(CFLOW_CMD)", "")
+#CFLOW_SOURCES = $(addprefix $(srcdir)/, $(SOURCES))
+#-include $(top_builddir)/libdm/libdevmapper.cflow
+#-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_lvmetad: lvmetad
+	$(INSTALL_PROGRAM) -D $< $(sbindir)/$(<F)
+
+install_lvm2: install_lvmetad
+
+install: install_lvm2

daemons/lvmetad/lvmetactl.c

@@ -0,0 +1,249 @@
+/*
+ * Copyright (C) 2014 Red Hat, Inc.
+ *
+ * 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.
+ */
+
+#include "tool.h"
+
+#include "lvmetad-client.h"
+
+daemon_handle h;
+
+static void print_reply(daemon_reply reply)
+{
+	const char *a = daemon_reply_str(reply, "response", NULL);
+	const char *b = daemon_reply_str(reply, "status", NULL);
+	const char *c = daemon_reply_str(reply, "reason", NULL);
+
+	printf("response \"%s\" status \"%s\" reason \"%s\"\n",
+	       a ? a : "", b ? b : "", c ? c : "");
+}
+
+int main(int argc, char **argv)
+{
+	daemon_reply reply;
+	char *cmd;
+	char *uuid;
+	char *name;
+	int val;
+	int ver;
+
+	if (argc < 2) {
+		printf("lvmetactl dump\n");
+		printf("lvmetactl pv_list\n");
+		printf("lvmetactl vg_list\n");
+		printf("lvmetactl get_global_info\n");
+		printf("lvmetactl vg_lookup_name <name>\n");
+		printf("lvmetactl vg_lookup_uuid <uuid>\n");
+		printf("lvmetactl pv_lookup_uuid <uuid>\n");
+		printf("lvmetactl set_global_invalid 0|1\n");
+		printf("lvmetactl set_global_disable 0|1\n");
+		printf("lvmetactl set_vg_version <uuid> <name> <version>\n");
+		printf("lvmetactl vg_lock_type <uuid>\n");
+		return -1;
+	}
+
+	cmd = argv[1];
+
+	h = lvmetad_open(NULL);
+
+	if (!strcmp(cmd, "dump")) {
+		reply = daemon_send_simple(h, "dump",
+					   "token = %s", "skip",
+					   "pid = " FMTd64, (int64_t)getpid(),
+					   "cmd = %s", "lvmetactl",
+					   NULL);
+		printf("%s\n", reply.buffer.mem);
+
+	} else if (!strcmp(cmd, "pv_list")) {
+		reply = daemon_send_simple(h, "pv_list",
+					   "token = %s", "skip",
+					   "pid = " FMTd64, (int64_t)getpid(),
+					   "cmd = %s", "lvmetactl",
+					   NULL);
+		printf("%s\n", reply.buffer.mem);
+
+	} else if (!strcmp(cmd, "vg_list")) {
+		reply = daemon_send_simple(h, "vg_list",
+					   "token = %s", "skip",
+					   "pid = " FMTd64, (int64_t)getpid(),
+					   "cmd = %s", "lvmetactl",
+					   NULL);
+		printf("%s\n", reply.buffer.mem);
+
+	} else if (!strcmp(cmd, "get_global_info")) {
+		reply = daemon_send_simple(h, "get_global_info",
+					   "token = %s", "skip",
+					   "pid = " FMTd64, (int64_t)getpid(),
+					   "cmd = %s", "lvmetactl",
+					   NULL);
+		printf("%s\n", reply.buffer.mem);
+
+	} else if (!strcmp(cmd, "set_global_invalid")) {
+		if (argc < 3) {
+			printf("set_global_invalid 0|1\n");
+			return -1;
+		}
+		val = atoi(argv[2]);
+
+		reply = daemon_send_simple(h, "set_global_info",
+					   "global_invalid = " FMTd64, (int64_t) val,
+					   "token = %s", "skip",
+					   "pid = " FMTd64, (int64_t)getpid(),
+					   "cmd = %s", "lvmetactl",
+					   NULL);
+		print_reply(reply);
+
+	} else if (!strcmp(cmd, "set_global_disable")) {
+		if (argc < 3) {
+			printf("set_global_disable 0|1\n");
+			return -1;
+		}
+		val = atoi(argv[2]);
+
+		reply = daemon_send_simple(h, "set_global_info",
+					   "global_disable = " FMTd64, (int64_t) val,
+					   "disable_reason = %s", LVMETAD_DISABLE_REASON_DIRECT,
+					   "token = %s", "skip",
+					   "pid = " FMTd64, (int64_t)getpid(),
+					   "cmd = %s", "lvmetactl",
+					   NULL);
+		print_reply(reply);
+
+	} else if (!strcmp(cmd, "set_vg_version")) {
+		if (argc < 5) {
+			printf("set_vg_version <uuid> <name> <ver>\n");
+			return -1;
+		}
+		uuid = argv[2];
+		name = argv[3];
+		ver = atoi(argv[4]);
+
+		if ((strlen(uuid) == 1) && (uuid[0] == '-'))
+			uuid = NULL;
+		if ((strlen(name) == 1) && (name[0] == '-'))
+			name = NULL;
+
+		if (uuid && name) {
+			reply = daemon_send_simple(h, "set_vg_info",
+						   "uuid = %s", uuid,
+						   "name = %s", name,
+						   "version = " FMTd64, (int64_t) ver,
+						   "token = %s", "skip",
+						   "pid = " FMTd64, (int64_t)getpid(),
+						   "cmd = %s", "lvmetactl",
+						   NULL);
+		} else if (uuid) {
+			reply = daemon_send_simple(h, "set_vg_info",
+						   "uuid = %s", uuid,
+						   "version = " FMTd64, (int64_t) ver,
+						   "token = %s", "skip",
+						   "pid = " FMTd64, (int64_t)getpid(),
+						   "cmd = %s", "lvmetactl",
+						   NULL);
+		} else if (name) {
+			reply = daemon_send_simple(h, "set_vg_info",
+						   "name = %s", name,
+						   "version = " FMTd64, (int64_t) ver,
+						   "token = %s", "skip",
+						   "pid = " FMTd64, (int64_t)getpid(),
+						   "cmd = %s", "lvmetactl",
+						   NULL);
+		} else {
+			printf("name or uuid required\n");
+			return -1;
+		}
+
+		print_reply(reply);
+
+	} else if (!strcmp(cmd, "vg_lookup_name")) {
+		if (argc < 3) {
+			printf("vg_lookup_name <name>\n");
+			return -1;
+		}
+		name = argv[2];
+
+		reply = daemon_send_simple(h, "vg_lookup",
+					   "name = %s", name,
+					   "token = %s", "skip",
+					   "pid = " FMTd64, (int64_t)getpid(),
+					   "cmd = %s", "lvmetactl",
+					   NULL);
+		printf("%s\n", reply.buffer.mem);
+
+	} else if (!strcmp(cmd, "vg_lookup_uuid")) {
+		if (argc < 3) {
+			printf("vg_lookup_uuid <uuid>\n");
+			return -1;
+		}
+		uuid = argv[2];
+
+		reply = daemon_send_simple(h, "vg_lookup",
+					   "uuid = %s", uuid,
+					   "token = %s", "skip",
+					   "pid = " FMTd64, (int64_t)getpid(),
+					   "cmd = %s", "lvmetactl",
+					   NULL);
+		printf("%s\n", reply.buffer.mem);
+
+	} else if (!strcmp(cmd, "vg_lock_type")) {
+		struct dm_config_node *metadata;
+		const char *lock_type;
+
+		if (argc < 3) {
+			printf("vg_lock_type <uuid>\n");
+			return -1;
+		}
+		uuid = argv[2];
+
+		reply = daemon_send_simple(h, "vg_lookup",
+					   "uuid = %s", uuid,
+					   "token = %s", "skip",
+					   "pid = " FMTd64, (int64_t)getpid(),
+					   "cmd = %s", "lvmetactl",
+					   NULL);
+		/* printf("%s\n", reply.buffer.mem); */
+
+		metadata = dm_config_find_node(reply.cft->root, "metadata");
+		if (!metadata) {
+			printf("no metadata\n");
+			goto out;
+		}
+
+		lock_type = dm_config_find_str(metadata, "metadata/lock_type", NULL);
+		if (!lock_type) {
+			printf("no lock_type\n");
+			goto out;
+		}
+		printf("lock_type %s\n", lock_type);
+
+	} else if (!strcmp(cmd, "pv_lookup_uuid")) {
+		if (argc < 3) {
+			printf("pv_lookup_uuid <uuid>\n");
+			return -1;
+		}
+		uuid = argv[2];
+
+		reply = daemon_send_simple(h, "pv_lookup",
+					   "uuid = %s", uuid,
+					   "token = %s", "skip",
+					   "pid = " FMTd64, (int64_t)getpid(),
+					   "cmd = %s", "lvmetactl",
+					   NULL);
+		printf("%s\n", reply.buffer.mem);
+
+	} else {
+		printf("unknown command\n");
+		goto out_close;
+	}
+out:
+	daemon_reply_destroy(reply);
+out_close:
+	daemon_close(h);
+	return 0;
+}

daemons/lvmetad/lvmetad-client.h

@@ -0,0 +1,90 @@
+/*
+ * Copyright (C) 2011-2012 Red Hat, Inc.
+ *
+ * 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_LVMETAD_CLIENT_H
+#define _LVM_LVMETAD_CLIENT_H
+
+#include "daemon-client.h"
+
+#define LVMETAD_SOCKET DEFAULT_RUN_DIR "/lvmetad.socket"
+
+#define LVMETAD_TOKEN_UPDATE_IN_PROGRESS "update in progress"
+
+#define LVMETAD_DISABLE_REASON_DIRECT		"DIRECT"
+#define LVMETAD_DISABLE_REASON_DUPLICATES	"DUPLICATES"
+#define LVMETAD_DISABLE_REASON_VGRESTORE	"VGRESTORE"
+#define LVMETAD_DISABLE_REASON_REPAIR		"REPAIR"
+
+struct volume_group;
+
+/* Different types of replies we may get from lvmetad. */
+
+typedef struct {
+	daemon_reply r;
+	const char **uuids; /* NULL terminated array */
+} lvmetad_uuidlist;
+
+typedef struct {
+	daemon_reply r;
+	struct dm_config_tree *cft;
+} lvmetad_vg;
+
+/* Get a list of VG UUIDs that match a given VG name. */
+lvmetad_uuidlist lvmetad_lookup_vgname(daemon_handle h, const char *name);
+
+/* Get the metadata of a single VG, identified by UUID. */
+lvmetad_vg lvmetad_get_vg(daemon_handle h, const char *uuid);
+
+/*
+ * Add and remove PVs on demand. Udev-driven systems will use this interface
+ * instead of scanning.
+ */
+daemon_reply lvmetad_add_pv(daemon_handle h, const char *pv_uuid, const char *mda_content);
+daemon_reply lvmetad_remove_pv(daemon_handle h, const char *pv_uuid);
+
+/* Trigger a full disk scan, throwing away all caches. XXX do we eventually want
+ * this? Probably not yet, anyway.
+ *     daemon_reply lvmetad_rescan(daemon_handle h);
+ */
+
+/*
+ * Update the version of metadata of a volume group. The VG has to be locked for
+ * writing for this, and the VG metadata here has to match whatever has been
+ * written to the disk (under this lock). This initially avoids the requirement
+ * for lvmetad to write to disk (in later revisions, lvmetad_supersede_vg may
+ * also do the writing, or we probably add another function to do that).
+ */
+daemon_reply lvmetad_supersede_vg(daemon_handle h, struct volume_group *vg);
+
+/* Wrappers to open/close connection */
+
+static inline daemon_handle lvmetad_open(const char *socket)
+{
+	daemon_info lvmetad_info = {
+		.path = "lvmetad",
+		.socket = socket ?: LVMETAD_SOCKET,
+		.protocol = "lvmetad",
+		.protocol_version = 1,
+		.autostart = 0
+	};
+
+	return daemon_open(lvmetad_info);
+}
+
+static inline void lvmetad_close(daemon_handle h)
+{
+	return daemon_close(h);
+}
+
+#endif

daemons/lvmetad/test.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+export LD_LIBRARY_PATH="$1"
+
+test -n "$2" && {
+    rm -f /var/run/lvmetad.{socket,pid}
+    chmod +rx lvmetad
+    valgrind ./lvmetad -f &
+    PID=$!
+    sleep 1
+    ./testclient
+    kill $PID
+    exit 0
+}
+
+sudo ./test.sh "$1" .

daemons/lvmetad/testclient.c

@@ -0,0 +1,147 @@
+/*
+ * Copyright (C) 2011-2014 Red Hat, Inc.
+ *
+ * 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 General Public License v.2.
+ *
+ * You should have received a copy of the GNU 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 "tool.h"
+
+#include "lvmetad-client.h"
+#include "label.h"
+#include "lvmcache.h"
+#include "metadata.h"
+
+const char *uuid1 = "abcd-efgh";
+const char *uuid2 = "bbcd-efgh";
+const char *vgid = "yada-yada";
+const char *uuid3 = "cbcd-efgh";
+
+const char *metadata2 = "{\n"
+	"id = \"yada-yada\"\n"
+	"seqno = 15\n"
+	"status = [\"READ\", \"WRITE\"]\n"
+	"flags = []\n"
+	"extent_size = 8192\n"
+	"physical_volumes {\n"
+	"    pv0 {\n"
+	"        id = \"abcd-efgh\"\n"
+	"    }\n"
+	"    pv1 {\n"
+	"        id = \"bbcd-efgh\"\n"
+	"    }\n"
+	"    pv2 {\n"
+	"        id = \"cbcd-efgh\"\n"
+	"    }\n"
+	"}\n"
+	"}\n";
+
+void _handle_reply(daemon_reply reply) {
+	const char *repl = daemon_reply_str(reply, "response", NULL);
+	const char *status = daemon_reply_str(reply, "status", NULL);
+	const char *vgid = daemon_reply_str(reply, "vgid", NULL);
+
+	fprintf(stderr, "[C] REPLY: %s\n", repl);
+	if (!strcmp(repl, "failed"))
+		fprintf(stderr, "[C] REASON: %s\n", daemon_reply_str(reply, "reason", "unknown"));
+	if (vgid)
+		fprintf(stderr, "[C] VGID: %s\n", vgid);
+	if (status)
+		fprintf(stderr, "[C] STATUS: %s\n", status);
+	daemon_reply_destroy(reply);
+}
+
+void _pv_add(daemon_handle h, const char *uuid, const char *metadata)
+{
+	daemon_reply reply = daemon_send_simple(h, "pv_add", "uuid = %s", uuid,
+						             "metadata = %b", metadata,
+						             NULL);
+	_handle_reply(reply);
+}
+
+int scan(daemon_handle h, char *fn) {
+	struct device *dev = dev_cache_get(fn, NULL);
+
+	struct label *label;
+	if (!label_read(dev, &label, 0)) {
+		fprintf(stderr, "[C] no label found on %s\n", fn);
+		return;
+	}
+
+	char uuid[64];
+	if (!id_write_format(dev->pvid, uuid, 64)) {
+		fprintf(stderr, "[C] Failed to format PV UUID for %s", dev_name(dev));
+		return;
+	}
+	fprintf(stderr, "[C] found PV: %s\n", uuid);
+	struct lvmcache_info *info = (struct lvmcache_info *) label->info;
+	struct physical_volume pv = { 0, };
+
+	if (!(info->fmt->ops->pv_read(info->fmt, dev_name(dev), &pv, 0))) {
+		fprintf(stderr, "[C] Failed to read PV %s", dev_name(dev));
+		return;
+	}
+
+	struct format_instance_ctx fic;
+	struct format_instance *fid = info->fmt->ops->create_instance(info->fmt, &fic);
+	struct metadata_area *mda;
+	struct volume_group *vg = NULL;
+	dm_list_iterate_items(mda, &info->mdas) {
+		struct volume_group *this = mda->ops->vg_read(fid, "", mda);
+		if (this && !vg || this->seqno > vg->seqno)
+			vg = this;
+	}
+	if (vg) {
+		char *buf = NULL;
+		/* TODO. This is not entirely correct, since export_vg_to_buffer
+		 * adds trailing garbage to the buffer. We may need to use
+		 * export_vg_to_config_tree and format the buffer ourselves. It
+		 * does, however, work for now, since the garbage is well
+		 * formatted and has no conflicting keys with the rest of the
+		 * request.  */
+		export_vg_to_buffer(vg, &buf);
+		daemon_reply reply =
+			daemon_send_simple(h, "pv_add", "uuid = %s", uuid,
+					      "metadata = %b", strchr(buf, '{'),
+					      NULL);
+		_handle_reply(reply);
+	}
+}
+
+void _dump_vg(daemon_handle h, const char *uuid)
+{
+	daemon_reply reply = daemon_send_simple(h, "vg_by_uuid", "uuid = %s", uuid, NULL);
+	fprintf(stderr, "[C] reply buffer: %s\n", reply.buffer);
+	daemon_reply_destroy(reply);
+}
+
+int main(int argc, char **argv) {
+	daemon_handle h = lvmetad_open();
+	/* FIXME Missing error path */
+
+	if (argc > 1) {
+		int i;
+		struct cmd_context *cmd = create_toolcontext(0, NULL, 0, 0, 1, 1);
+		for (i = 1; i < argc; ++i) {
+			const char *uuid = NULL;
+			scan(h, argv[i]);
+		}
+		destroy_toolcontext(cmd);
+		/* FIXME Missing lvmetad_close() */
+		return 0;
+	}
+
+	_pv_add(h, uuid1, NULL);
+	_pv_add(h, uuid2, metadata2);
+	_dump_vg(h, vgid);
+	_pv_add(h, uuid3, NULL);
+
+	daemon_close(h);	/* FIXME lvmetad_close? */
+	return 0;
+}

daemons/lvmlockd/Makefile.in

@@ -15,8 +15,6 @@ srcdir = @srcdir@
 top_srcdir = @top_srcdir@
 top_builddir = @top_builddir@
 
-USE_SD_NOTIFY=yes
-
 SOURCES = lvmlockd-core.c
 
 ifeq ("@BUILD_LOCKDSANLOCK@", "yes")
@@ -27,7 +25,6 @@ endif
 ifeq ("@BUILD_LOCKDDLM@", "yes")
   SOURCES += lvmlockd-dlm.c
   LOCK_LIBS += -ldlm_lt
-  LOCK_LIBS += -ldlmcontrol
 endif
 
 SOURCES2 = lvmlockctl.c
@@ -41,30 +38,20 @@ 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) $(PTHREAD_LIBS)
-
-
-ifeq ($(USE_SD_NOTIFY),yes)
-	CFLAGS += $(shell pkg-config --cflags libsystemd) -DUSE_SD_NOTIFY
-	LIBS += $(shell pkg-config --libs libsystemd)
-endif
+LIBS += $(RT_LIBS) $(DAEMON_LIBS) -ldevmapper $(PTHREAD_LIBS)
 
 lvmlockd: $(OBJECTS) $(top_builddir)/libdaemon/client/libdaemonclient.a \
 		    $(top_builddir)/libdaemon/server/libdaemonserver.a
-	@echo "    [CC] $@"
-	$(Q) $(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJECTS) $(LOCK_LIBS) -ldaemonserver $(INTERNAL_LIBS) $(LIBS)
+	$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJECTS) $(LOCK_LIBS) -ldaemonserver $(LIBS)
 
 lvmlockctl: lvmlockctl.o $(top_builddir)/libdaemon/client/libdaemonclient.a
-	@echo "    [CC] $@"
-	$(Q) $(CC) $(CFLAGS) $(LDFLAGS) -o $@ lvmlockctl.o $(INTERNAL_LIBS) $(LIBS)
+	$(CC) $(CFLAGS) $(LDFLAGS) -o $@ lvmlockctl.o $(LIBS)
 
 install_lvmlockd: lvmlockd
-	@echo "    [INSTALL] $<"
-	$(Q) $(INSTALL_PROGRAM) -D $< $(sbindir)/$(<F)
+	$(INSTALL_PROGRAM) -D $< $(sbindir)/$(<F)
 
 install_lvmlockctl: lvmlockctl
-	@echo "    [INSTALL] $<"
-	$(Q) $(INSTALL_PROGRAM) -D $< $(sbindir)/$(<F)
+	$(INSTALL_PROGRAM) -D $< $(sbindir)/$(<F)
 
 install_lvm2: install_lvmlockd install_lvmlockctl
 

daemons/lvmlockd/lvmlockctl.c

@@ -8,9 +8,9 @@
  * of the GNU Lesser General Public License v.2.1.
  */
 
-#include "tools/tool.h"
+#include "tool.h"
 
-#include "daemons/lvmlockd/lvmlockd-client.h"
+#include "lvmlockd-client.h"
 
 #include <stddef.h>
 #include <getopt.h>
@@ -24,7 +24,7 @@
 static int quit = 0;
 static int info = 0;
 static int dump = 0;
-static int wait_opt = 1;
+static int wait_opt = 0;
 static int force_opt = 0;
 static int kill_vg = 0;
 static int drop_vg = 0;
@@ -280,12 +280,13 @@ static void format_info_line(char *line, char *r_name, char *r_type)
 
 static void format_info(void)
 {
-	char line[MAX_LINE] = { 0 };
-	char r_name[MAX_NAME+1] = { 0 };
-	char r_type[MAX_NAME+1] = { 0 };
+	char line[MAX_LINE];
+	char r_name[MAX_NAME+1];
+	char r_type[MAX_NAME+1];
 	int i, j;
 
 	j = 0;
+	memset(line, 0, sizeof(line));
 
 	for (i = 0; i < dump_len; i++) {
 		line[j++] = dump_buf[i];
@@ -325,8 +326,6 @@ static int _lvmlockd_result(daemon_reply reply, int *result)
 {
 	int reply_result;
 
-	*result = NO_LOCKD_RESULT;
-
 	if (reply.error) {
 		log_error("lvmlockd_result reply error %d", reply.error);
 		return 0;
@@ -338,7 +337,7 @@ static int _lvmlockd_result(daemon_reply reply, int *result)
 	}
 
 	reply_result = daemon_reply_int(reply, "op_result", NO_LOCKD_RESULT);
-	if (reply_result == NO_LOCKD_RESULT) {
+	if (reply_result == -1000) {
 		log_error("lvmlockd_result no op_result");
 		return 0;
 	}

daemons/lvmlockd/lvmlockd-client.h

@@ -11,10 +11,9 @@
 #ifndef _LVM_LVMLOCKD_CLIENT_H
 #define _LVM_LVMLOCKD_CLIENT_H
 
-#include "libdaemon/client/daemon-client.h"
+#include "daemon-client.h"
 
 #define LVMLOCKD_SOCKET DEFAULT_RUN_DIR "/lvmlockd.socket"
-#define LVMLOCKD_ADOPT_FILE DEFAULT_RUN_DIR "/lvmlockd.adopt"
 
 /* Wrappers to open/close connection */
 
@@ -23,9 +22,9 @@ 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 +32,7 @@ static inline daemon_handle lvmlockd_open(const char *sock)
 
 static inline void lvmlockd_close(daemon_handle h)
 {
-	daemon_close(h);
+	return daemon_close(h);
 }
 
 /*

daemons/lvmlockd/lvmlockd-core.c

@@ -8,13 +8,18 @@
  * of the GNU Lesser General Public License v.2.1.
  */
 
-#include "tools/tool.h"
+#define _XOPEN_SOURCE 500  /* pthread */
+#define _ISOC99_SOURCE
+#define _REENTRANT
 
-#include "libdaemon/client/daemon-io.h"
+#include "tool.h"
+
+#include "daemon-io.h"
 #include "daemon-server.h"
 #include "lvm-version.h"
-#include "daemons/lvmlockd/lvmlockd-client.h"
-#include "device_mapper/misc/dm-ioctl.h"
+#include "lvmetad-client.h"
+#include "lvmlockd-client.h"
+#include "dm-ioctl.h" /* for DM_UUID_LEN */
 
 /* #include <assert.h> */
 #include <errno.h>
@@ -31,15 +36,9 @@
 #include <sys/utsname.h>
 #include <sys/un.h>
 
-#ifdef USE_SD_NOTIFY
-#include <systemd/sd-daemon.h>
-#endif
-
 #define EXTERN
 #include "lvmlockd-internal.h"
 
-static int str_to_mode(const char *str);
-
 /*
  * Basic operation of lvmlockd
  *
@@ -144,8 +143,10 @@ static const char *lvmlockd_protocol = "lvmlockd";
 static const int lvmlockd_protocol_version = 1;
 static int daemon_quit;
 static int adopt_opt;
-static uint32_t adopt_update_count;
-static const char *adopt_file;
+
+static daemon_handle lvmetad_handle;
+static pthread_mutex_t lvmetad_mutex;
+static int lvmetad_connected;
 
 /*
  * We use a separate socket for dumping daemon info.
@@ -409,11 +410,12 @@ struct lockspace *alloc_lockspace(void)
 {
 	struct lockspace *ls;
 
-	if (!(ls = zalloc(sizeof(struct lockspace)))) {
+	if (!(ls = malloc(sizeof(struct lockspace)))) {
 		log_error("out of memory for lockspace");
 		return NULL;
 	}
 
+	memset(ls, 0, sizeof(struct lockspace));
 	INIT_LIST_HEAD(&ls->actions);
 	INIT_LIST_HEAD(&ls->resources);
 	pthread_mutex_init(&ls->mutex, NULL);
@@ -506,10 +508,6 @@ static struct lock *alloc_lock(void)
 
 static void free_action(struct action *act)
 {
-	if (act->path) {
-		free(act->path);
-		act->path = NULL;
-	}
 	pthread_mutex_lock(&unused_struct_mutex);
 	if (unused_action_count >= MAX_UNUSED_ACTION) {
 		free(act);
@@ -733,8 +731,6 @@ static const char *op_str(int x)
 		return "rename_final";
 	case LD_OP_RUNNING_LM:
 		return "running_lm";
-	case LD_OP_QUERY_LOCK:
-		return "query_lock";
 	case LD_OP_FIND_FREE_LOCK:
 		return "find_free_lock";
 	case LD_OP_KILL_VG:
@@ -747,8 +743,6 @@ static const char *op_str(int x)
 		return "dump_info";
 	case LD_OP_BUSY:
 		return "busy";
-	case LD_OP_REFRESH_LV:
-		return "refresh_lv";
 	default:
 		return "op_unknown";
 	};
@@ -815,144 +809,6 @@ int version_from_args(char *args, unsigned int *major, unsigned int *minor, unsi
 	return 0;
 }
 
-/*
- * Write new info when a command exits if that command has acquired a new LV
- * lock.  If the command has released an LV lock we don't bother updating the
- * info.  When adopting, we eliminate any LV lock adoptions if there is no dm
- * device for that LV.  If lvmlockd is terminated after acquiring but before
- * writing this file, those LV locks would not be adopted on restart.
- */
-
-#define ADOPT_VERSION_MAJOR 1
-#define ADOPT_VERSION_MINOR 0
-
-static void write_adopt_file(void)
-{
-	struct lockspace *ls;
-	struct resource *r;
-	struct lock *lk;
-	time_t t;
-	FILE *fp;
-
-	if (!(fp = fopen(adopt_file, "w")))
-		return;
-
-	adopt_update_count++;
-
-	t = time(NULL);
-	fprintf(fp, "lvmlockd adopt_version %u.%u pid %d updates %u %s",
-		ADOPT_VERSION_MAJOR, ADOPT_VERSION_MINOR, getpid(), adopt_update_count, ctime(&t));
-
-	pthread_mutex_lock(&lockspaces_mutex);
-	list_for_each_entry(ls, &lockspaces, list) {
-		if (ls->lm_type == LD_LM_DLM && !strcmp(ls->name, gl_lsname_dlm))
-			continue;
-		fprintf(fp, "VG: %38s %s %s %s\n",
-			ls->vg_uuid, ls->vg_name, lm_str(ls->lm_type), ls->vg_args);
-		list_for_each_entry(r, &ls->resources, list) {
-			if (r->type != LD_RT_LV)
-				continue;
-			if ((r->mode != LD_LK_EX) && (r->mode != LD_LK_SH))
-				continue;
-			list_for_each_entry(lk, &r->locks, list) {
-				fprintf(fp, "LV: %38s %s %s %s %u\n",
-					ls->vg_uuid, r->name, r->lv_args, mode_str(r->mode), r->version);
-			}
-		}
-	}
-	pthread_mutex_unlock(&lockspaces_mutex);
-
-	fflush(fp);
-	fclose(fp);
-}
-
-static int read_adopt_file(struct list_head *vg_lockd)
-{
-	char adopt_line[512];
-	char vg_uuid[72];
-	char lm_type_str[16];
-	char mode[8];
-	struct lockspace *ls, *ls2;
-	struct resource *r;
-	FILE *fp;
-
-	if (MAX_ARGS != 64 || MAX_NAME != 64)
-		return -1;
-
-	if (!(fp = fopen(adopt_file, "r")))
-		return 0;
-
-	while (fgets(adopt_line, sizeof(adopt_line), fp)) {
-		if (adopt_line[0] == '#')
-			continue;
-		else if (!strncmp(adopt_line, "lvmlockd", 8)) {
-			unsigned int v_major = 0, v_minor = 0;
-			if ((sscanf(adopt_line, "lvmlockd adopt_version %u.%u", &v_major, &v_minor) != 2) ||
-			    (v_major != ADOPT_VERSION_MAJOR))
-				goto fail;
-
-		} else if (!strncmp(adopt_line, "VG:", 3)) {
-			if (!(ls = alloc_lockspace()))
-				goto fail;
-
-			memset(vg_uuid, 0, sizeof(vg_uuid));
-
-			if (sscanf(adopt_line, "VG: %63s %64s %16s %64s",
-				   vg_uuid, ls->vg_name, lm_type_str, ls->vg_args) != 4) {
-				goto fail;
-			}
-
-			memcpy(ls->vg_uuid, vg_uuid, 64);
-
-			if ((ls->lm_type = str_to_lm(lm_type_str)) < 0)
-				goto fail;
-
-			list_add(&ls->list, vg_lockd);
-
-		} else if (!strncmp(adopt_line, "LV:", 3)) {
-			if (!(r = alloc_resource()))
-				goto fail;
-
-			r->type = LD_RT_LV;
-
-			memset(vg_uuid, 0, sizeof(vg_uuid));
-
-			if (sscanf(adopt_line, "LV: %64s %64s %s %8s %u",
-				   vg_uuid, r->name, r->lv_args, mode, &r->version) != 5) {
-				goto fail;
-			}
-
-			if ((r->adopt_mode = str_to_mode(mode)) == LD_LK_IV)
-				goto fail;
-
-			if (ls && !memcmp(ls->vg_uuid, vg_uuid, 64)) {
-				list_add(&r->list, &ls->resources);
-				r = NULL;
-			} else {
-				list_for_each_entry(ls2, vg_lockd, list) {
-					if (memcmp(ls2->vg_uuid, vg_uuid, 64))
-						continue;
-					list_add(&r->list, &ls2->resources);
-					r = NULL;
-					break;
-				}
-			}
-
-			if (r) {
-				log_error("No lockspace found for resource %s vg_uuid %s", r->name, vg_uuid);
-				goto fail;
-			}
-		}
-	}
-
-	fclose(fp);
-	return 0;
-
-fail:
-	fclose(fp);
-	return -1;
-}
-
 /*
  * These are few enough that arrays of function pointers can
  * be avoided.
@@ -1074,12 +930,12 @@ static void lm_rem_resource(struct lockspace *ls, struct resource *r)
 		lm_rem_resource_sanlock(ls, r);
 }
 
-static int lm_find_free_lock(struct lockspace *ls, uint64_t *free_offset, int *sector_size, int *align_size)
+static int lm_find_free_lock(struct lockspace *ls, uint64_t *free_offset)
 {
 	if (ls->lm_type == LD_LM_DLM)
 		return 0;
 	else if (ls->lm_type == LD_LM_SANLOCK)
-		return lm_find_free_lock_sanlock(ls, free_offset, sector_size, align_size);
+		return lm_find_free_lock_sanlock(ls, free_offset);
 	return -1;
 }
 
@@ -1153,6 +1009,54 @@ static void add_work_action(struct action *act)
 	pthread_mutex_unlock(&worker_mutex);
 }
 
+#define ERR_LVMETAD_NOT_RUNNING -200
+
+static daemon_reply send_lvmetad(const char *id, ...)
+{
+	daemon_reply reply;
+	va_list ap;
+	int retries = 0;
+	int err;
+
+	va_start(ap, id);
+
+	/*
+	 * mutex is used because all threads share a single
+	 * lvmetad connection/handle.
+	 */
+	pthread_mutex_lock(&lvmetad_mutex);
+retry:
+	if (!lvmetad_connected) {
+		lvmetad_handle = lvmetad_open(NULL);
+		if (lvmetad_handle.error || lvmetad_handle.socket_fd < 0) {
+			err = lvmetad_handle.error ?: lvmetad_handle.socket_fd;
+			pthread_mutex_unlock(&lvmetad_mutex);
+			log_debug("lvmetad_open reconnect error %d", err);
+			memset(&reply, 0, sizeof(reply));
+			reply.error = ERR_LVMETAD_NOT_RUNNING;
+			va_end(ap);
+			return reply;
+		} else {
+			log_debug("lvmetad reconnected");
+			lvmetad_connected = 1;
+		}
+	}
+
+	reply = daemon_send_simple_v(lvmetad_handle, id, ap);
+
+	/* lvmetad may have been restarted */
+	if ((reply.error == ECONNRESET) && (retries < 2)) {
+		daemon_close(lvmetad_handle);
+		lvmetad_connected = 0;
+		retries++;
+		goto retry;
+	}
+	pthread_mutex_unlock(&lvmetad_mutex);
+
+	va_end(ap);
+	return reply;
+}
+
 static int res_lock(struct lockspace *ls, struct resource *r, struct action *act, int *retry)
 {
 	struct lock *lk;
@@ -1348,18 +1252,6 @@ static int res_lock(struct lockspace *ls, struct resource *r, struct action *act
 		rv = -EREMOVED;
 	}
 
-	/*
-	 * lvmetad is no longer used, but the infrastructure for
-	 * distributed cache validation remains.  The points
-	 * where vg or global cache state would be invalidated
-	 * remain below and log_debug messages point out where
-	 * they would occur.
-	 *
-	 * The comments related to "lvmetad" remain because they
-	 * describe how some other local cache like lvmetad would
-	 * be invalidated here.
-	 */
-
 	/*
 	 * r is vglk: tell lvmetad to set the vg invalid
 	 * flag, and provide the new r_version.  If lvmetad finds
@@ -1385,12 +1277,47 @@ static int res_lock(struct lockspace *ls, struct resource *r, struct action *act
 	 */
 
 	if (inval_meta && (r->type == LD_RT_VG)) {
-		log_debug("S %s R %s res_lock invalidate vg state version %u",
+		daemon_reply reply;
+		char *uuid;
+
+		log_debug("S %s R %s res_lock set lvmetad vg version %u",
 			  ls->name, r->name, new_version);
+	
+		if (!ls->vg_uuid[0] || !strcmp(ls->vg_uuid, "none"))
+			uuid = (char *)"none";
+		else
+			uuid = ls->vg_uuid;
+
+		reply = send_lvmetad("set_vg_info",
+				     "token = %s", "skip",
+				     "uuid = %s", uuid,
+				     "name = %s", ls->vg_name,
+				     "version = " FMTd64, (int64_t)new_version,
+				     NULL);
+
+		if (reply.error || strcmp(daemon_reply_str(reply, "response", ""), "OK")) {
+			if (reply.error != ERR_LVMETAD_NOT_RUNNING)
+				log_error("set_vg_info in lvmetad failed %d", reply.error);
+		}
+		daemon_reply_destroy(reply);
 	}
 
 	if (inval_meta && (r->type == LD_RT_GL)) {
-		log_debug("S %s R %s res_lock invalidate global state", ls->name, r->name);
+		daemon_reply reply;
+
+		log_debug("S %s R %s res_lock set lvmetad global invalid",
+			  ls->name, r->name);
+
+		reply = send_lvmetad("set_global_info",
+				     "token = %s", "skip",
+				     "global_invalid = " FMTd64, INT64_C(1),
+				     NULL);
+
+		if (reply.error || strcmp(daemon_reply_str(reply, "response", ""), "OK")) {
+			if (reply.error != ERR_LVMETAD_NOT_RUNNING)
+				log_error("set_global_info in lvmetad failed %d", reply.error);
+		}
+		daemon_reply_destroy(reply);
 	}
 
 	/*
@@ -1964,9 +1891,9 @@ static void res_process(struct lockspace *ls, struct resource *r,
 			add_client_result(act);
 		} else {
 			/* persistent lock is sh, transient request is ex */
+			/* FIXME: can we remove this case? do a convert here? */
 			log_debug("res_process %s existing persistent lock new transient", r->name);
 			r->last_client_id = act->client_id;
-			act->flags |= LD_AF_SH_EXISTS;
 			act->result = -EEXIST;
 			list_del(&act->list);
 			add_client_result(act);
@@ -2346,7 +2273,6 @@ static int process_op_during_kill(struct action *act)
 	case LD_OP_UPDATE:
 	case LD_OP_RENAME_BEFORE:
 	case LD_OP_RENAME_FINAL:
-	case LD_OP_QUERY_LOCK:
 	case LD_OP_FIND_FREE_LOCK:
 		return 0;
 	};
@@ -2372,7 +2298,7 @@ static void *lockspace_thread_main(void *arg_in)
 	struct action *act_op_free = NULL;
 	struct list_head tmp_act;
 	struct list_head act_close;
-	char tmp_name[MAX_NAME+5];
+	char tmp_name[MAX_NAME+1];
 	int free_vg = 0;
 	int drop_vg = 0;
 	int error = 0;
@@ -2571,31 +2497,13 @@ static void *lockspace_thread_main(void *arg_in)
 				break;
 			}
 
-			if (act->op == LD_OP_QUERY_LOCK) {
-				r = find_resource_act(ls, act, 0);
-				if (!r)
-					act->result = -ENOENT;
-				else {
-					act->result = 0;
-					act->mode = r->mode;
-				}
-				list_del(&act->list);
-				add_client_result(act);
-				continue;
-			}
-
 			if (act->op == LD_OP_FIND_FREE_LOCK && act->rt == LD_RT_VG) {
 				uint64_t free_offset = 0;
-				int sector_size = 0;
-				int align_size = 0;
-
 				log_debug("S %s find free lock", ls->name);
-				rv = lm_find_free_lock(ls, &free_offset, &sector_size, &align_size);
-				log_debug("S %s find free lock %d offset %llu sector_size %d align_size %d",
-					  ls->name, rv, (unsigned long long)free_offset, sector_size, align_size);
+				rv = lm_find_free_lock(ls, &free_offset);
+				log_debug("S %s find free lock %d offset %llu",
+					  ls->name, rv, (unsigned long long)free_offset);
 				ls->free_lock_offset = free_offset;
-				ls->free_lock_sector_size = sector_size;
-				ls->free_lock_align_size = align_size;
 				list_del(&act->list);
 				act->result = rv;
 				add_client_result(act);
@@ -2766,10 +2674,8 @@ out_act:
 	 * blank or fill it with garbage, but instead set it to REM:<name>
 	 * to make it easier to follow progress of freeing is via log_debug.
 	 */
-	memset(tmp_name, 0, sizeof(tmp_name));
-	memcpy(tmp_name, "REM:", 4);
-	strncpy(tmp_name+4, ls->name, sizeof(tmp_name)-4);
-	memcpy(ls->name, tmp_name, sizeof(ls->name));
+	dm_strncpy(tmp_name, ls->name, sizeof(tmp_name));
+	snprintf(ls->name, sizeof(ls->name), "REM:%s", tmp_name);
 	pthread_mutex_unlock(&lockspaces_mutex);
 
 	/* worker_thread will join this thread, and free the ls */
@@ -3406,8 +3312,6 @@ static int work_init_lv(struct action *act)
 	char vg_args[MAX_ARGS+1];
 	char lv_args[MAX_ARGS+1];
 	uint64_t free_offset = 0;
-	int sector_size = 0;
-	int align_size = 0;
 	int lm_type = 0;
 	int rv = 0;
 
@@ -3423,8 +3327,6 @@ static int work_init_lv(struct action *act)
 		lm_type = ls->lm_type;
 		memcpy(vg_args, ls->vg_args, MAX_ARGS);
 		free_offset = ls->free_lock_offset;
-		sector_size = ls->free_lock_sector_size;
-		align_size = ls->free_lock_align_size;
 	}
 	pthread_mutex_unlock(&lockspaces_mutex);
 
@@ -3441,7 +3343,7 @@ static int work_init_lv(struct action *act)
 
 	if (lm_type == LD_LM_SANLOCK) {
 		rv = lm_init_lv_sanlock(ls_name, act->vg_name, act->lv_uuid,
-					vg_args, lv_args, sector_size, align_size, free_offset);
+					vg_args, lv_args, free_offset);
 
 		memcpy(act->lv_args, lv_args, MAX_ARGS);
 		return rv;
@@ -3571,15 +3473,6 @@ static void *worker_thread_main(void *arg_in)
 			else
 				list_add(&act->list, &delayed_list);
 
-		} else if (act->op == LD_OP_REFRESH_LV) {
-			log_debug("work refresh_lv %s %s", act->lv_uuid, act->path);
-			rv = lm_refresh_lv_start_dlm(act);
-			if (rv < 0) {
-				act->result = rv;
-				add_client_result(act);
-			} else
-				list_add(&act->list, &delayed_list);
-
 		} else {
 			log_error("work unknown op %d", act->op);
 			act->result = -EINVAL;
@@ -3615,19 +3508,6 @@ static void *worker_thread_main(void *arg_in)
 					act->result = 0;
 					add_client_result(act);
 				}
-
-			} else if (act->op == LD_OP_REFRESH_LV) {
-				log_debug("work delayed refresh_lv");
-				rv = lm_refresh_lv_check_dlm(act);
-				if (!rv) {
-					list_del(&act->list);
-					act->result = 0;
-					add_client_result(act);
-				} else if ((rv < 0) && (rv != -EAGAIN)) {
-					list_del(&act->list);
-					act->result = rv;
-					add_client_result(act);
-				}
 			}
 		}
 
@@ -3833,9 +3713,6 @@ static int client_send_result(struct client *cl, struct action *act)
 	if ((act->flags & LD_AF_WARN_GL_REMOVED) || gl_vg_removed)
 		strcat(result_flags, "WARN_GL_REMOVED,");
 	
-	if (act->flags & LD_AF_SH_EXISTS)
-		strcat(result_flags, "SH_EXISTS,");
-
 	if (act->op == LD_OP_INIT) {
 		/*
 		 * init is a special case where lock args need
@@ -3864,20 +3741,6 @@ static int client_send_result(struct client *cl, struct action *act)
 					  "result_flags = %s", result_flags[0] ? result_flags : "none",
 					  NULL);
 
-	} else if (act->op == LD_OP_QUERY_LOCK) {
-
-		log_debug("send %s[%d] cl %u %s %s rv %d mode %d",
-			  cl->name[0] ? cl->name : "client", cl->pid, cl->id,
-			  op_str(act->op), rt_str(act->rt),
-			  act->result, act->mode);
-
-		res = daemon_reply_simple("OK",
-					  "op = " FMTd64, (int64_t)act->op,
-					  "op_result = " FMTd64, (int64_t) act->result,
-					  "lock_type = %s", lm_str(act->lm_type),
-					  "mode = %s", mode_str(act->mode),
-					  NULL);
-
 	} else if (act->op == LD_OP_DUMP_LOG || act->op == LD_OP_DUMP_INFO) {
 		/*
 		 * lvmlockctl creates the unix socket then asks us to write to it.
@@ -4208,16 +4071,6 @@ static int str_to_op_rt(const char *req_name, int *op, int *rt)
 		*rt = 0;
 		return 0;
 	}
-	if (!strcmp(req_name, "query_lock_vg")) {
-		*op = LD_OP_QUERY_LOCK;
-		*rt = LD_RT_VG;
-		return 0;
-	}
-	if (!strcmp(req_name, "query_lock_lv")) {
-		*op = LD_OP_QUERY_LOCK;
-		*rt = LD_RT_LV;
-		return 0;
-	}
 	if (!strcmp(req_name, "find_free_lock")) {
 		*op = LD_OP_FIND_FREE_LOCK;
 		*rt = LD_RT_VG;
@@ -4233,11 +4086,6 @@ static int str_to_op_rt(const char *req_name, int *op, int *rt)
 		*rt = LD_RT_VG;
 		return 0;
 	}
-	if (!strcmp(req_name, "refresh_lv")) {
-		*op = LD_OP_REFRESH_LV;
-		*rt = 0;
-		return 0;
-	}
 out:
 	return -1;
 }
@@ -4599,7 +4447,6 @@ static void client_recv_action(struct client *cl)
 	const char *vg_name;
 	const char *vg_uuid;
 	const char *vg_sysid;
-	const char *path;
 	const char *str;
 	int64_t val;
 	uint32_t opts = 0;
@@ -4686,7 +4533,6 @@ static void client_recv_action(struct client *cl)
 	opts = str_to_opts(str);
 	str = daemon_request_str(req, "vg_lock_type", NULL);
 	lm = str_to_lm(str);
-	path = daemon_request_str(req, "path", NULL);
 
 	if (cl_pid && cl_pid != cl->pid)
 		log_error("client recv bad message pid %d client %d", cl_pid, cl->pid);
@@ -4719,9 +4565,6 @@ static void client_recv_action(struct client *cl)
 	act->flags = opts;
 	act->lm_type = lm;
 
-	if (path)
-		act->path = strdup(path);
-
 	if (vg_name && strcmp(vg_name, "none"))
 		strncpy(act->vg_name, vg_name, MAX_NAME);
 
@@ -4798,7 +4641,6 @@ static void client_recv_action(struct client *cl)
 	case LD_OP_STOP_ALL:
 	case LD_OP_RENAME_FINAL:
 	case LD_OP_RUNNING_LM:
-	case LD_OP_REFRESH_LV:
 		add_work_action(act);
 		rv = 0;
 		break;
@@ -4808,7 +4650,6 @@ static void client_recv_action(struct client *cl)
 	case LD_OP_DISABLE:
 	case LD_OP_FREE:
 	case LD_OP_RENAME_BEFORE:
-	case LD_OP_QUERY_LOCK:
 	case LD_OP_FIND_FREE_LOCK:
 	case LD_OP_KILL_VG:
 	case LD_OP_DROP_VG:
@@ -4831,7 +4672,6 @@ static void *client_thread_main(void *arg_in)
 	struct client *cl;
 	struct action *act;
 	struct action *act_un;
-	uint32_t lock_acquire_count = 0, lock_acquire_written = 0;
 	int rv;
 
 	while (1) {
@@ -4863,9 +4703,6 @@ static void *client_thread_main(void *arg_in)
 				rv = -1;
 			}
 
-			if (act->flags & LD_AF_LV_LOCK)
-				lock_acquire_count++;
-
 			/*
 			 * The client failed after we acquired an LV lock for
 			 * it, but before getting this reply saying it's done.
@@ -4887,11 +4724,6 @@ static void *client_thread_main(void *arg_in)
 			continue;
 		}
 
-		if (adopt_opt && (lock_acquire_count > lock_acquire_written)) {
-			lock_acquire_written = lock_acquire_count;
-			write_adopt_file();
-		}
-
 		/*
 		 * Queue incoming actions for lockspace threads
 		 */
@@ -4965,8 +4797,6 @@ static void *client_thread_main(void *arg_in)
 			pthread_mutex_unlock(&client_mutex);
 	}
 out:
-	if (adopt_opt && lock_acquire_written)
-		unlink(adopt_file);
 	return NULL;
 }
 
@@ -4999,6 +4829,176 @@ static void close_client_thread(void)
 		log_error("pthread_join client_thread error %d", perrno);
 }
 
+/*
+ * Get a list of all VGs with a lockd type (sanlock|dlm) from lvmetad.
+ * We'll match this list against a list of existing lockspaces that are
+ * found in the lock manager.
+ *
+ * For each of these VGs, also create a struct resource on ls->resources to
+ * represent each LV in the VG that uses a lock.  For each of these LVs
+ * that are active, we'll attempt to adopt a lock.
+ */
+
+static int get_lockd_vgs(struct list_head *vg_lockd)
+{
+	struct list_head update_vgs;
+	daemon_reply reply;
+	struct dm_config_node *cn;
+	struct dm_config_node *metadata;
+	struct dm_config_node *md_cn;
+	struct dm_config_node *lv_cn;
+	struct lockspace *ls, *safe;
+	struct resource *r;
+	const char *vg_name;
+	const char *vg_uuid;
+	const char *lv_uuid;
+	const char *lock_type;
+	const char *lock_args;
+	char find_str_path[PATH_MAX];
+	int rv = 0;
+
+	INIT_LIST_HEAD(&update_vgs);
+
+	reply = send_lvmetad("vg_list", "token = %s", "skip", NULL);
+
+	if (reply.error || strcmp(daemon_reply_str(reply, "response", ""), "OK")) {
+		log_error("vg_list from lvmetad failed %d", reply.error);
+		rv = -EINVAL;
+		goto destroy;
+	}
+
+	if (!(cn = dm_config_find_node(reply.cft->root, "volume_groups"))) {
+		log_error("get_lockd_vgs no vgs");
+		rv = -EINVAL;
+		goto destroy;
+	}
+
+	/* create an update_vgs list of all vg uuids */
+
+	for (cn = cn->child; cn; cn = cn->sib) {
+		vg_uuid = cn->key;
+
+		if (!(ls = alloc_lockspace())) {
+			rv = -ENOMEM;
+			break;
+		}
+
+		strncpy(ls->vg_uuid, vg_uuid, 64);
+		list_add_tail(&ls->list, &update_vgs);
+		log_debug("get_lockd_vgs %s", vg_uuid);
+	}
+ destroy:
+	daemon_reply_destroy(reply);
+
+	if (rv < 0)
+		goto out;
+
+	/* get vg_name and lock_type for each vg uuid entry in update_vgs */
+
+	list_for_each_entry(ls, &update_vgs, list) {
+		reply = send_lvmetad("vg_lookup",
+				     "token = %s", "skip",
+				     "uuid = %s", ls->vg_uuid,
+				     NULL);
+
+		if (reply.error || strcmp(daemon_reply_str(reply, "response", ""), "OK")) {
+			log_error("vg_lookup from lvmetad failed %d", reply.error);
+			rv = -EINVAL;
+			goto next;
+		}
+
+		vg_name = daemon_reply_str(reply, "name", NULL);
+		if (!vg_name) {
+			log_error("get_lockd_vgs %s no name", ls->vg_uuid);
+			rv = -EINVAL;
+			goto next;
+		}
+
+		strncpy(ls->vg_name, vg_name, MAX_NAME);
+
+		metadata = dm_config_find_node(reply.cft->root, "metadata");
+		if (!metadata) {
+			log_error("get_lockd_vgs %s name %s no metadata",
+				  ls->vg_uuid, ls->vg_name);
+			rv = -EINVAL;
+			goto next;
+		}
+
+		lock_type = dm_config_find_str(metadata, "metadata/lock_type", NULL);
+		ls->lm_type = str_to_lm(lock_type);
+
+		if ((ls->lm_type != LD_LM_SANLOCK) && (ls->lm_type != LD_LM_DLM)) {
+			log_debug("get_lockd_vgs %s not lockd type", ls->vg_name);
+			continue;
+		}
+
+		lock_args = dm_config_find_str(metadata, "metadata/lock_args", NULL);
+		if (lock_args)
+			strncpy(ls->vg_args, lock_args, MAX_ARGS);
+
+		log_debug("get_lockd_vgs %s lock_type %s lock_args %s",
+			  ls->vg_name, lock_type, lock_args ?: "none");
+
+		/*
+		 * Make a record (struct resource) of each lv that uses a lock.
+		 * For any lv that uses a lock, we'll check if the lv is active
+		 * and if so try to adopt a lock for it.
+		 */
+
+		for (md_cn = metadata->child; md_cn; md_cn = md_cn->sib) {
+			if (strcmp(md_cn->key, "logical_volumes"))
+				continue;
+
+			for (lv_cn = md_cn->child; lv_cn; lv_cn = lv_cn->sib) {
+				snprintf(find_str_path, PATH_MAX, "%s/lock_args", lv_cn->key);
+				lock_args = dm_config_find_str(lv_cn, find_str_path, NULL);
+				if (!lock_args)
+					continue;
+
+				snprintf(find_str_path, PATH_MAX, "%s/id", lv_cn->key);
+				lv_uuid = dm_config_find_str(lv_cn, find_str_path, NULL);
+
+				if (!lv_uuid) {
+					log_error("get_lock_vgs no lv id for name %s", lv_cn->key);
+					continue;
+				}
+
+				if (!(r = alloc_resource())) {
+					rv = -ENOMEM;
+					goto next;
+				}
+
+				r->use_vb = 0;
+				r->type = LD_RT_LV;
+				strncpy(r->name, lv_uuid, MAX_NAME);
+				if (lock_args)
+					strncpy(r->lv_args, lock_args, MAX_ARGS);
+				list_add_tail(&r->list, &ls->resources);
+				log_debug("get_lockd_vgs %s lv %s %s (name %s)",
+					  ls->vg_name, r->name, lock_args ? lock_args : "", lv_cn->key);
+			}
+		}
+ next:
+		daemon_reply_destroy(reply);
+
+		if (rv < 0)
+			break;
+	}
+out:
+	/* Return lockd VG's on the vg_lockd list. */
+
+	list_for_each_entry_safe(ls, safe, &update_vgs, list) {
+		list_del(&ls->list);
+
+		if ((ls->lm_type == LD_LM_SANLOCK) || (ls->lm_type == LD_LM_DLM))
+			list_add_tail(&ls->list, vg_lockd);
+		else
+			free(ls);
+	}
+
+	return rv;
+}
+
 static char _dm_uuid[DM_UUID_LEN];
 
 static char *get_dm_uuid(char *dm_name)
@@ -5215,9 +5215,9 @@ static void adopt_locks(void)
 	INIT_LIST_HEAD(&to_unlock);
 
 	/*
-	 * Get list of lockspaces from currently running lock managers.
-	 * Get list of shared VGs from file written by prior lvmlockd.
-	 * Get list of active LVs (in the shared VGs) from the file.
+	 * Get list of lockspaces from lock managers.
+	 * Get list of VGs from lvmetad with a lockd type.
+	 * Get list of active lockd type LVs from /dev.
 	 */
 
 	if (lm_support_dlm() && lm_is_running_dlm()) {
@@ -5241,17 +5241,12 @@ static void adopt_locks(void)
 	 * Adds a struct lockspace to vg_lockd for each lockd VG.
 	 * Adds a struct resource to ls->resources for each LV.
 	 */
-	rv = read_adopt_file(&vg_lockd);
+	rv = get_lockd_vgs(&vg_lockd);
 	if (rv < 0) {
-		log_error("adopt_locks read_adopt_file failed");
+		log_error("adopt_locks get_lockd_vgs failed");
 		goto fail;
 	}
 
-	if (list_empty(&vg_lockd)) {
-		log_debug("No lockspaces in adopt file");
-		return;
-	}
-
 	/*
 	 * For each resource on each lockspace, check if the
 	 * corresponding LV is active.  If so, leave the
@@ -5276,7 +5271,7 @@ static void adopt_locks(void)
 		gl_use_sanlock = 1;
 
 	list_for_each_entry(ls, &vg_lockd, list) {
-		log_debug("adopt vg %s lock_type %s lock_args %s",
+		log_debug("adopt lvmetad vg %s lock_type %s lock_args %s",
 			  ls->vg_name, lm_str(ls->lm_type), ls->vg_args);
 
 		list_for_each_entry(r, &ls->resources, list)
@@ -5341,7 +5336,7 @@ static void adopt_locks(void)
 		/*
 		 * LS in ls_found, not in vg_lockd.
 		 * An lvm lockspace found in the lock manager has no
-		 * corresponding VG.  This shouldn't usually
+		 * corresponding VG in lvmetad.  This shouldn't usually
 		 * happen, but it's possible the VG could have been removed
 		 * while the orphaned lockspace from it was still around.
 		 * Report an error and leave the ls in the lm alone.
@@ -5356,7 +5351,7 @@ static void adopt_locks(void)
 
 	/*
 	 * LS in vg_lockd, not in ls_found.
-	 * lockd vgs that do not have an existing lockspace.
+	 * lockd vgs from lvmetad that do not have an existing lockspace.
 	 * This wouldn't be unusual; we just skip the vg.
 	 * But, if the vg has active lvs, then it should have had locks
 	 * and a lockspace.  Should we attempt to join the lockspace and
@@ -5408,6 +5403,8 @@ static void adopt_locks(void)
 		memcpy(act->vg_args, ls->vg_args, MAX_ARGS);
 		act->host_id = ls->host_id;
 
+		/* set act->version from lvmetad data? */
+
 		log_debug("adopt add %s vg lockspace %s", lm_str(act->lm_type), act->vg_name);
 
 		rv = add_lockspace_thread(ls->name, act->vg_name, act->vg_uuid,
@@ -5490,7 +5487,7 @@ static void adopt_locks(void)
 				goto fail;
 			act->op = LD_OP_LOCK;
 			act->rt = LD_RT_LV;
-			act->mode = r->adopt_mode;
+			act->mode = LD_LK_EX;
 			act->flags = (LD_AF_ADOPT | LD_AF_PERSISTENT);
 			act->client_id = INTERNAL_CLIENT_ID;
 			act->lm_type = ls->lm_type;
@@ -5588,9 +5585,8 @@ static void adopt_locks(void)
 			 * Adopt failed because the orphan has a different mode
 			 * than initially requested.  Repeat the lock-adopt operation
 			 * with the other mode.  N.B. this logic depends on first
-			 * trying sh then ex for GL/VG locks; for LV locks the mode
-			 * from the adopt file is tried first, the alternate
-			 * (if the mode in adopt file was wrong somehow.)
+			 * trying sh then ex for GL/VG locks, and ex then sh for
+			 * LV locks.
 			 */
 
 			if ((act->rt != LD_RT_LV) && (act->mode == LD_LK_SH)) {
@@ -5598,12 +5594,9 @@ static void adopt_locks(void)
 				act->mode = LD_LK_EX;
 				rv = add_lock_action(act);
 
-			} else if (act->rt == LD_RT_LV) {
-				/* LV locks: attempt to adopt the other mode. */
-				if (act->mode == LD_LK_EX)
-					act->mode = LD_LK_SH;
-				else if (act->mode == LD_LK_SH)
-					act->mode = LD_LK_EX;
+			} else if ((act->rt == LD_RT_LV) && (act->mode == LD_LK_EX)) {
+				/* LV locks: attempt to adopt sh after ex failed. */
+				act->mode = LD_LK_SH;
 				rv = add_lock_action(act);
 
 			} else {
@@ -5738,13 +5731,10 @@ static void adopt_locks(void)
 	if (count_start_fail || count_adopt_fail)
 		goto fail;
 
-	unlink(adopt_file);
-	write_adopt_file();
 	log_debug("adopt_locks done");
 	return;
 
 fail:
-	unlink(adopt_file);
 	log_error("adopt_locks failed, reset host");
 }
 
@@ -5873,16 +5863,24 @@ static int main_loop(daemon_state *ds_arg)
 	setup_worker_thread();
 	setup_restart();
 
-#ifdef USE_SD_NOTIFY
-	sd_notify(0, "READY=1");
-#endif
+	pthread_mutex_init(&lvmetad_mutex, NULL);
+	lvmetad_handle = lvmetad_open(NULL);
+	if (lvmetad_handle.error || lvmetad_handle.socket_fd < 0)
+		log_debug("lvmetad_open error %d", lvmetad_handle.error);
+	else
+		lvmetad_connected = 1;
 
 	/*
 	 * Attempt to rejoin lockspaces and adopt locks from a previous
 	 * instance of lvmlockd that left behind lockspaces/locks.
 	 */
-	if (adopt_opt)
-		adopt_locks();
+	if (adopt_opt) {
+		/* FIXME: implement this without lvmetad */
+		if (!lvmetad_connected)
+			log_error("Cannot adopt locks without lvmetad running.");
+		else
+			adopt_locks();
+	}
 
 	while (1) {
 		rv = poll(pollfd, pollfd_maxi + 1, -1);
@@ -5998,6 +5996,7 @@ static int main_loop(daemon_state *ds_arg)
 	close_worker_thread();
 	close_client_thread();
 	closelog();
+	daemon_close(lvmetad_handle);
 	return 1; /* libdaemon uses 1 for success */
 }
 
@@ -6019,8 +6018,6 @@ static void usage(char *prog, FILE *file)
 	fprintf(file, "        Set path to the pid file. [%s]\n", LVMLOCKD_PIDFILE);
 	fprintf(file, "  --socket-path | -s <path>\n");
 	fprintf(file, "        Set path to the socket to listen on. [%s]\n", LVMLOCKD_SOCKET);
-	fprintf(file, "  --adopt-file <path>\n");
-	fprintf(file, "        Set path to the adopt file. [%s]\n", LVMLOCKD_ADOPT_FILE);
 	fprintf(file, "  --syslog-priority | -S err|warning|debug\n");
 	fprintf(file, "        Write log messages from this level up to syslog. [%s]\n", _syslog_num_to_name(LOG_SYSLOG_PRIO));
 	fprintf(file, "  --gl-type | -g <str>\n");
@@ -6038,14 +6035,14 @@ static void usage(char *prog, FILE *file)
 int main(int argc, char *argv[])
 {
 	daemon_state ds = {
-		.name = "lvmlockd",
+		.daemon_main = main_loop,
+		.daemon_init = NULL,
+		.daemon_fini = NULL,
 		.pidfile = getenv("LVM_LVMLOCKD_PIDFILE"),
 		.socket_path = getenv("LVM_LVMLOCKD_SOCKET"),
 		.protocol = lvmlockd_protocol,
 		.protocol_version = lvmlockd_protocol_version,
-		.daemon_init = NULL,
-		.daemon_fini = NULL,
-		.daemon_main = main_loop,
+		.name = "lvmlockd",
 	};
 
 	static struct option long_options[] = {
@@ -6056,7 +6053,6 @@ int main(int argc, char *argv[])
 		{"daemon-debug",    no_argument,       0, 'D' },
 		{"pid-file",        required_argument, 0, 'p' },
 		{"socket-path",     required_argument, 0, 's' },
-		{"adopt-file",      required_argument, 0, 128 },
 		{"gl-type",         required_argument, 0, 'g' },
 		{"host-id",         required_argument, 0, 'i' },
 		{"host-id-file",    required_argument, 0, 'F' },
@@ -6079,9 +6075,6 @@ int main(int argc, char *argv[])
 		switch (c) {
 		case '0':
 			break;
-		case 128:
-			adopt_file = strdup(optarg);
-			break;
 		case 'h':
 			usage(argv[0], stdout);
 			exit(EXIT_SUCCESS);
@@ -6143,9 +6136,6 @@ int main(int argc, char *argv[])
 	if (!ds.socket_path)
 		ds.socket_path = LVMLOCKD_SOCKET;
 
-	if (!adopt_file)
-		adopt_file = LVMLOCKD_ADOPT_FILE;
-
 	/* runs daemon_main/main_loop */
 	daemon_start(ds);
 

daemons/lvmlockd/lvmlockd-dlm.c

@@ -11,20 +11,19 @@
 #define _XOPEN_SOURCE 500  /* pthread */
 #define _ISOC99_SOURCE
 
-#include "tools/tool.h"
+#include "tool.h"
 
 #include "daemon-server.h"
-#include "lib/mm/xlate.h"
+#include "xlate.h"
 
 #include "lvmlockd-internal.h"
-#include "daemons/lvmlockd/lvmlockd-client.h"
+#include "lvmlockd-client.h"
 
 /*
  * Using synchronous _wait dlm apis so do not define _REENTRANT and
  * link with non-threaded version of library, libdlm_lt.
  */
 #include "libdlm.h"
-#include "libdlmcontrol.h"
 
 #include <stddef.h>
 #include <poll.h>
@@ -128,18 +127,16 @@ static int read_cluster_name(char *clustername)
 	return 0;
 }
 
-#define MAX_VERSION 16
-
 int lm_init_vg_dlm(char *ls_name, char *vg_name, uint32_t flags, char *vg_args)
 {
 	char clustername[MAX_ARGS+1];
-	char lock_args_version[MAX_VERSION+1];
+	char lock_args_version[MAX_ARGS+1];
 	int rv;
 
 	memset(clustername, 0, sizeof(clustername));
 	memset(lock_args_version, 0, sizeof(lock_args_version));
 
-	snprintf(lock_args_version, MAX_VERSION, "%u.%u.%u",
+	snprintf(lock_args_version, MAX_ARGS, "%u.%u.%u",
 		 VG_LOCK_ARGS_MAJOR, VG_LOCK_ARGS_MINOR, VG_LOCK_ARGS_PATCH);
 
 	rv = read_cluster_name(clustername);
@@ -151,9 +148,7 @@ int lm_init_vg_dlm(char *ls_name, char *vg_name, uint32_t flags, char *vg_args)
 		return -EARGS;
 	}
 
-	rv = snprintf(vg_args, MAX_ARGS, "%s:%s", lock_args_version, clustername);
-	if (rv >= MAX_ARGS)
-		log_debug("init_vg_dlm vg_args may be too long %d %s", rv, vg_args);
+	snprintf(vg_args, MAX_ARGS, "%s:%s", lock_args_version, clustername);
 	rv = 0;
 
 	log_debug("init_vg_dlm done %s vg_args %s", ls_name, vg_args);
@@ -277,9 +272,10 @@ static int lm_add_resource_dlm(struct lockspace *ls, struct resource *r, int wit
 	int rv;
 
 	if (r->type == LD_RT_GL || r->type == LD_RT_VG) {
-		buf = zalloc(sizeof(struct val_blk) + DLM_LVB_LEN);
+		buf = malloc(sizeof(struct val_blk) + DLM_LVB_LEN);
 		if (!buf)
 			return -ENOMEM;
+		memset(buf, 0, sizeof(struct val_blk) + DLM_LVB_LEN);
 
 		rdd->vb = (struct val_blk *)buf;
 		rdd->lksb.sb_lvbptr = buf + sizeof(struct val_blk);
@@ -398,18 +394,12 @@ static int lm_adopt_dlm(struct lockspace *ls, struct resource *r, int ld_mode,
 			  (void *)1, (void *)1, (void *)1,
 			  NULL, NULL);
 
-	if (rv == -1 && (errno == EAGAIN)) {
+	if (rv == -1 && errno == -EAGAIN) {
 		log_debug("S %s R %s adopt_dlm adopt mode %d try other mode",
 			  ls->name, r->name, ld_mode);
 		rv = -EUCLEAN;
 		goto fail;
 	}
-	if (rv == -1 && (errno == ENOENT)) {
-		log_debug("S %s R %s adopt_dlm adopt mode %d no lock",
-			  ls->name, r->name, ld_mode);
-		rv = -ENOENT;
-		goto fail;
-	}
 	if (rv < 0) {
 		log_debug("S %s R %s adopt_dlm mode %d flags %x error %d errno %d",
 			  ls->name, r->name, mode, flags, rv, errno);
@@ -787,107 +777,3 @@ int lm_is_running_dlm(void)
 	return 1;
 }
 
-#ifdef LOCKDDLM_CONTROL_SUPPORT
-
-int lm_refresh_lv_start_dlm(struct action *act)
-{
-	char path[PATH_MAX];
-	char command[DLMC_RUN_COMMAND_LEN];
-	char run_uuid[DLMC_RUN_UUID_LEN];
-	char *p, *vgname, *lvname;
-	int rv;
-
-	/* split /dev/vgname/lvname into vgname and lvname strings */
-	strncpy(path, act->path, strlen(act->path));
-
-	/* skip past dev */
-	p = strchr(path + 1, '/');
-
-	/* skip past slashes */
-	while (*p == '/')
-		p++;
-
-	/* start of vgname */
-	vgname = p;
-
-	/* skip past vgname */
-	while (*p != '/')
-		p++;
-
-	/* terminate vgname */
-	*p = '\0';
-	p++;
-
-	/* skip past slashes */
-	while (*p == '/')
-		p++;
-
-	lvname = p;
-
-	memset(command, 0, sizeof(command));
-	memset(run_uuid, 0, sizeof(run_uuid));
-
-	/* todo: add --readonly */
-
-	snprintf(command, DLMC_RUN_COMMAND_LEN,
-		 "lvm lvchange --refresh --partial --nolocking %s/%s",
-		 vgname, lvname);
-
-	rv = dlmc_run_start(command, strlen(command), 0,
-			    DLMC_FLAG_RUN_START_NODE_NONE,
-			    run_uuid);
-	if (rv < 0) {
-		log_debug("refresh_lv run_start error %d", rv);
-		return rv;
-	}
-
-	log_debug("refresh_lv run_start %s", run_uuid);
-
-	/* Bit of a hack here, we don't need path once started,
-	   but we do need to save the run_uuid somewhere, so just
-	   replace the path with the uuid. */
-
-	free(act->path);
-	act->path = strdup(run_uuid);
-	return 0;
-}
-
-int lm_refresh_lv_check_dlm(struct action *act)
-{
-	uint32_t check_status = 0;
-	int rv;
-
-	/* NB act->path was replaced with run_uuid */
-
-	rv = dlmc_run_check(act->path, strlen(act->path), 0,
-			    DLMC_FLAG_RUN_CHECK_CLEAR,
-			    &check_status);
-	if (rv < 0) {
-		log_debug("refresh_lv check error %d", rv);
-		return rv;
-	}
-
-	log_debug("refresh_lv check %s status %x", act->path, check_status);
-
-	if (!(check_status & DLMC_RUN_STATUS_DONE))
-		return -EAGAIN;
-
-	if (check_status & DLMC_RUN_STATUS_FAILED)
-		return -1;
-
-	return 0;
-}
-
-#else /* LOCKDDLM_CONTROL_SUPPORT */
-
-int lm_refresh_lv_start_dlm(struct action *act)
-{
-	return 0;
-}
-
-int lm_refresh_lv_check_dlm(struct action *act)
-{
-	return 0;
-}
-
-#endif /* LOCKDDLM_CONTROL_SUPPORT */

daemons/lvmlockd/lvmlockd-internal.h

@@ -11,8 +11,6 @@
 #ifndef _LVM_LVMLOCKD_INTERNAL_H
 #define _LVM_LVMLOCKD_INTERNAL_H
 
-#include "base/memory/container_of.h"
-
 #define MAX_NAME 64
 #define MAX_ARGS 64
 
@@ -55,8 +53,6 @@ enum {
 	LD_OP_KILL_VG,
 	LD_OP_DROP_VG,
 	LD_OP_BUSY,
-	LD_OP_QUERY_LOCK,
-	LD_OP_REFRESH_LV,
 };
 
 /* resource types */
@@ -109,7 +105,6 @@ struct client {
 #define LD_AF_WARN_GL_REMOVED	   0x00020000
 #define LD_AF_LV_LOCK              0x00040000
 #define LD_AF_LV_UNLOCK            0x00080000
-#define LD_AF_SH_EXISTS            0x00100000
 
 /*
  * Number of times to repeat a lock request after
@@ -132,7 +127,6 @@ struct action {
 	int max_retries;
 	int result;
 	int lm_rv;			/* return value from lm_ function */
-	char *path;
 	char vg_uuid[64];
 	char vg_name[MAX_NAME+1];
 	char lv_name[MAX_NAME+1];
@@ -147,7 +141,6 @@ struct resource {
 	char name[MAX_NAME+1];		/* vg name or lv name */
 	int8_t type;			/* resource type LD_RT_ */
 	int8_t mode;
-	int8_t adopt_mode;
 	unsigned int sh_count;		/* number of sh locks on locks list */
 	uint32_t version;
 	uint32_t last_client_id;	/* last client_id to lock or unlock resource */
@@ -158,7 +151,7 @@ struct resource {
 	struct list_head locks;
 	struct list_head actions;
 	char lv_args[MAX_ARGS+1];
-	char lm_data[];			/* lock manager specific data */
+	char lm_data[0];		/* lock manager specific data */
 };
 
 #define LD_LF_PERSISTENT 0x00000001
@@ -181,9 +174,7 @@ struct lockspace {
 	int8_t lm_type;			/* lock manager: LM_DLM, LM_SANLOCK */
 	void *lm_data;
 	uint64_t host_id;
-	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 */
+	uint64_t free_lock_offset;	/* start search for free lock here */
 
 	uint32_t start_client_id;	/* client_id that started the lockspace */
 	pthread_t thread;		/* makes synchronous lock requests */
@@ -219,6 +210,10 @@ 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;
@@ -392,8 +387,6 @@ int lm_get_lockspaces_dlm(struct list_head *ls_rejoin);
 int lm_data_size_dlm(void);
 int lm_is_running_dlm(void);
 int lm_hosts_dlm(struct lockspace *ls, int notify);
-int lm_refresh_lv_start_dlm(struct action *act);
-int lm_refresh_lv_check_dlm(struct action *act);
 
 static inline int lm_support_dlm(void)
 {
@@ -470,22 +463,12 @@ static inline int lm_hosts_dlm(struct lockspace *ls, int notify)
 	return 0;
 }
 
-static inline int lm_refresh_lv_start_dlm(struct action *act)
-{
-	return 0;
-}
-
-static inline int lm_refresh_lv_check_dlm(struct action *act)
-{
-	return 0;
-}
-
 #endif /* dlm support */
 
 #ifdef LOCKDSANLOCK_SUPPORT
 
 int lm_init_vg_sanlock(char *ls_name, char *vg_name, uint32_t flags, char *vg_args);
-int lm_init_lv_sanlock(char *ls_name, char *vg_name, char *lv_name, char *vg_args, char *lv_args, int sector_size, int align_size, uint64_t free_offset);
+int lm_init_lv_sanlock(char *ls_name, char *vg_name, char *lv_name, char *vg_args, char *lv_args, uint64_t free_offset);
 int lm_free_lv_sanlock(struct lockspace *ls, struct resource *r);
 int lm_rename_vg_sanlock(char *ls_name, char *vg_name, uint32_t flags, char *vg_args);
 int lm_prepare_lockspace_sanlock(struct lockspace *ls);
@@ -505,7 +488,7 @@ int lm_gl_is_enabled(struct lockspace *ls);
 int lm_get_lockspaces_sanlock(struct list_head *ls_rejoin);
 int lm_data_size_sanlock(void);
 int lm_is_running_sanlock(void);
-int lm_find_free_lock_sanlock(struct lockspace *ls, uint64_t *free_offset, int *sector_size, int *align_size);
+int lm_find_free_lock_sanlock(struct lockspace *ls, uint64_t *free_offset);
 
 static inline int lm_support_sanlock(void)
 {
@@ -519,7 +502,7 @@ static inline int lm_init_vg_sanlock(char *ls_name, char *vg_name, uint32_t flag
 	return -1;
 }
 
-static inline int lm_init_lv_sanlock(char *ls_name, char *vg_name, char *lv_name, char *vg_args, char *lv_args, int sector_size, int align_size, uint64_t free_offset)
+static inline int lm_init_lv_sanlock(char *ls_name, char *vg_name, char *lv_name, char *vg_args, char *lv_args, uint64_t free_offset)
 {
 	return -1;
 }
@@ -607,7 +590,7 @@ static inline int lm_is_running_sanlock(void)
 	return 0;
 }
 
-static inline int lm_find_free_lock_sanlock(struct lockspace *ls, uint64_t *free_offset, int *sector_size, int *align_size)
+static inline int lm_find_free_lock_sanlock(struct lockspace *ls, uint64_t *free_offset)
 {
 	return -1;
 }

daemons/lvmlockd/lvmlockd-sanlock.c

@@ -11,42 +11,23 @@
 #define _XOPEN_SOURCE 500  /* pthread */
 #define _ISOC99_SOURCE
 
-#include "tools/tool.h"
+#include "tool.h"
 
 #include "daemon-server.h"
-#include "lib/mm/xlate.h"
+#include "xlate.h"
 
 #include "lvmlockd-internal.h"
-#include "daemons/lvmlockd/lvmlockd-client.h"
+#include "lvmlockd-client.h"
 
 #include "sanlock.h"
 #include "sanlock_rv.h"
 #include "sanlock_admin.h"
 #include "sanlock_resource.h"
 
-/* FIXME: these are copied from sanlock.h only until
-   an updated version of sanlock is available with them. */
-#define SANLK_RES_ALIGN1M       0x00000010
-#define SANLK_RES_ALIGN2M       0x00000020
-#define SANLK_RES_ALIGN4M       0x00000040
-#define SANLK_RES_ALIGN8M       0x00000080
-#define SANLK_RES_SECTOR512     0x00000100
-#define SANLK_RES_SECTOR4K      0x00000200
-#define SANLK_LSF_ALIGN1M       0x00000010
-#define SANLK_LSF_ALIGN2M       0x00000020
-#define SANLK_LSF_ALIGN4M       0x00000040
-#define SANLK_LSF_ALIGN8M       0x00000080
-#define SANLK_LSF_SECTOR512     0x00000100
-#define SANLK_LSF_SECTOR4K      0x00000200
-
 #include <stddef.h>
 #include <poll.h>
 #include <errno.h>
 #include <syslog.h>
-#include <blkid/blkid.h>
-#include <sys/sysmacros.h>
-
-#define ONE_MB 1048576
 
 /*
 -------------------------------------------------------------------------------
@@ -158,7 +139,6 @@ release all the leases for the VG.
 
 struct lm_sanlock {
 	struct sanlk_lockspace ss;
-	int sector_size;
 	int align_size;
 	int sock; /* sanlock daemon connection */
 };
@@ -221,6 +201,7 @@ int lm_data_size_sanlock(void)
  * ...
  */
 
+#define LS_BEGIN 0
 #define GL_LOCK_BEGIN UINT64_C(65)
 #define VG_LOCK_BEGIN UINT64_C(66)
 #define LV_LOCK_BEGIN UINT64_C(67)
@@ -307,8 +288,7 @@ static int read_host_id_file(void)
 		}
 	}
 	if (fclose(file))
-		log_debug("Failed to fclose host id file %s (%s).",
-			  daemon_host_id_file, strerror(errno));
+		log_error("failed to close host id file %s", daemon_host_id_file);
 out:
 	log_debug("host_id %d from %s", host_id, daemon_host_id_file);
 	return host_id;
@@ -344,154 +324,6 @@ fail:
 	return rv;
 }
 
-static void _read_sysfs_size(dev_t devno, const char *name, unsigned int *val)
-{
-	char path[PATH_MAX];
-	char buf[32];
-	FILE *fp;
-	size_t len;
-
-	snprintf(path, sizeof(path), "/sys/dev/block/%d:%d/queue/%s",
-		 (int)major(devno), (int)minor(devno), name);
-
-	if (!(fp = fopen(path, "r")))
-		return;
-
-	if (!fgets(buf, sizeof(buf), fp))
-		goto out;
-
-	if ((len = strlen(buf)) && buf[len - 1] == '\n')
-		buf[--len] = '\0';
-
-	if (strlen(buf))
-		*val = atoi(buf);
-out:
-	if (fclose(fp))
-		log_debug("Failed to fclose host id file %s (%s).", path, strerror(errno));
-
-}
-
-/* Select sector/align size for a new VG based on what the device reports for
-   sector size of the lvmlock LV. */
-
-static int get_sizes_device(char *path, int *sector_size, int *align_size)
-{
-	unsigned int physical_block_size = 0;
-	unsigned int logical_block_size = 0;
-	struct stat st;
-	int rv;
-
-	rv = stat(path, &st);
-	if (rv < 0) {
-		log_error("Failed to stat device to get block size %s %d", path, errno);
-		return -1;
-	}
-
-	_read_sysfs_size(st.st_rdev, "physical_block_size", &physical_block_size);
-	_read_sysfs_size(st.st_rdev, "logical_block_size", &logical_block_size);
-
-	if ((physical_block_size == 512) && (logical_block_size == 512)) {
-		*sector_size = 512;
-		*align_size = ONE_MB;
-		return 0;
-	}
-
-	if ((physical_block_size == 4096) && (logical_block_size == 4096)) {
-		*sector_size = 4096;
-		*align_size = 8 * ONE_MB;
-		return 0;
-	}
-
-	if (physical_block_size && (physical_block_size != 512) && (physical_block_size != 4096)) {
-		log_warn("WARNING: invalid block sizes physical %u logical %u for %s",
-			 physical_block_size, logical_block_size, path);
-		physical_block_size = 0;
-	}
-
-	if (logical_block_size && (logical_block_size != 512) && (logical_block_size != 4096)) {
-		log_warn("WARNING: invalid block sizes physical %u logical %u for %s",
-			 physical_block_size, logical_block_size, path);
-		logical_block_size = 0;
-	}
-
-	if (!physical_block_size && !logical_block_size) {
-		log_error("Failed to get a block size for %s", path);
-		return -1;
-	}
-
-	if (!physical_block_size || !logical_block_size) {
-		log_warn("WARNING: incomplete block size information physical %u logical %u for %s",
-			 physical_block_size, logical_block_size, path);
-		if (!physical_block_size)
-			physical_block_size = logical_block_size;
-		if (!logical_block_size)
-			logical_block_size = physical_block_size;
-	}
-
-	if ((logical_block_size == 4096) && (physical_block_size == 512)) {
-		log_warn("WARNING: mixed block sizes physical %u logical %u (using 4096) for %s",
-			 physical_block_size, logical_block_size, path);
-		*sector_size = 4096;
-		*align_size = 8 * ONE_MB;
-		return 0;
-	}
-
-	if ((physical_block_size == 4096) && (logical_block_size == 512)) {
-		log_warn("WARNING: mixed block sizes physical %u logical %u (using 4096) for %s",
-			 physical_block_size, logical_block_size, path);
-		*sector_size = 4096;
-		*align_size = 8 * ONE_MB;
-		return 0;
-	}
-
-	if (physical_block_size == 512) {
-		*sector_size = 512;
-		*align_size = ONE_MB;
-		return 0;
-	}
-
-	if (physical_block_size == 4096) {
-		*sector_size = 4096;
-		*align_size = 8 * ONE_MB;
-		return 0;
-	}
-
-	log_error("Failed to get a block size for %s", path);
-	return -1;
-}
-
-
-/* Get the sector/align sizes that were used to create an existing VG.
-   sanlock encoded this in the lockspace/resource structs on disk. */
-
-static int get_sizes_lockspace(char *path, int *sector_size, int *align_size)
-{
-	struct sanlk_lockspace ss;
-	uint32_t io_timeout = 0;
-	int rv;
-
-	memset(&ss, 0, sizeof(ss));
-	memcpy(ss.host_id_disk.path, path, SANLK_PATH_LEN);
-	ss.host_id_disk.offset = 0;
-
-	rv = sanlock_read_lockspace(&ss, 0, &io_timeout);
-	if (rv < 0) {
-		log_error("get_sizes_lockspace %s error %d", path, rv);
-		return rv;
-	}
-
-	if ((ss.flags & SANLK_LSF_SECTOR4K) && (ss.flags & SANLK_LSF_ALIGN8M)) {
-		*sector_size = 4096;
-		*align_size = 8 * ONE_MB;
-	} else if ((ss.flags & SANLK_LSF_SECTOR512) && (ss.flags & SANLK_LSF_ALIGN1M)) {
-		*sector_size = 512;
-		*align_size = ONE_MB;
-	}
-
-	log_debug("get_sizes_lockspace found %d %d", *sector_size, *align_size);
-	return 0;
-}
-
 /*
  * vgcreate
  *
@@ -500,21 +332,18 @@ static int get_sizes_lockspace(char *path, int *sector_size, int *align_size)
  * version and lv name, and returns the real lock_args in vg_args.
  */
 
-#define MAX_VERSION 16
-
 int lm_init_vg_sanlock(char *ls_name, char *vg_name, uint32_t flags, char *vg_args)
 {
 	struct sanlk_lockspace ss;
 	struct sanlk_resourced rd;
 	struct sanlk_disk disk;
 	char lock_lv_name[MAX_ARGS+1];
-	char lock_args_version[MAX_VERSION+1];
+	char lock_args_version[MAX_ARGS+1];
 	const char *gl_name = NULL;
 	uint32_t daemon_version;
 	uint32_t daemon_proto;
 	uint64_t offset;
-	int sector_size = 0;
-	int align_size = 0;
+	int align_size;
 	int i, rv;
 
 	memset(&ss, 0, sizeof(ss));
@@ -528,7 +357,7 @@ int lm_init_vg_sanlock(char *ls_name, char *vg_name, uint32_t flags, char *vg_ar
 		return -EARGS;
 	}
 
-	snprintf(lock_args_version, MAX_VERSION, "%u.%u.%u",
+	snprintf(lock_args_version, MAX_ARGS, "%u.%u.%u",
 		 VG_LOCK_ARGS_MAJOR, VG_LOCK_ARGS_MINOR, VG_LOCK_ARGS_PATCH);
 
 	/* see comment above about input vg_args being only lock_lv_name */
@@ -545,9 +374,7 @@ int lm_init_vg_sanlock(char *ls_name, char *vg_name, uint32_t flags, char *vg_ar
 	if (daemon_test) {
 		if (!gl_lsname_sanlock[0])
 			strncpy(gl_lsname_sanlock, ls_name, MAX_NAME);
-		rv = snprintf(vg_args, MAX_ARGS, "%s:%s", lock_args_version, lock_lv_name);
-		if (rv >= MAX_ARGS)
-			log_debug("init_vg_san vg_args may be too long %d %s", rv, vg_args);
+		snprintf(vg_args, MAX_ARGS, "%s:%s", lock_args_version, lock_lv_name);
 		return 0;
 	}
 
@@ -560,25 +387,23 @@ int lm_init_vg_sanlock(char *ls_name, char *vg_name, uint32_t flags, char *vg_ar
 	log_debug("sanlock daemon version %08x proto %08x",
 		  daemon_version, daemon_proto);
 
-	/* Nothing formatted on disk yet, use what the device reports. */
-	rv = get_sizes_device(disk.path, &sector_size, &align_size);
-	if (rv < 0) {
+	rv = sanlock_align(&disk);
+	if (rv <= 0) {
 		if (rv == -EACCES) {
 			log_error("S %s init_vg_san sanlock error -EACCES: no permission to access %s",
 				  ls_name, disk.path);
 			return -EDEVOPEN;
 		} else {
-			log_error("S %s init_vg_san sanlock error %d trying to get sector/align size of %s",
+			log_error("S %s init_vg_san sanlock error %d trying to get align size of %s",
 				  ls_name, rv, disk.path);
 			return -EARGS;
 		}
-	}
+	} else
+		align_size = rv;
 
 	strncpy(ss.name, ls_name, SANLK_NAME_LEN);
 	memcpy(ss.host_id_disk.path, disk.path, SANLK_PATH_LEN);
-	ss.host_id_disk.offset = 0;
-	ss.flags = (sector_size == 4096) ? (SANLK_LSF_SECTOR4K | SANLK_LSF_ALIGN8M) :
-					   (SANLK_LSF_SECTOR512 | SANLK_LSF_ALIGN1M);
+	ss.host_id_disk.offset = LS_BEGIN * align_size;
 
 	rv = sanlock_write_lockspace(&ss, 0, 0, sanlock_io_timeout);
 	if (rv < 0) {
@@ -611,8 +436,6 @@ int lm_init_vg_sanlock(char *ls_name, char *vg_name, uint32_t flags, char *vg_ar
 	memcpy(rd.rs.disks[0].path, disk.path, SANLK_PATH_LEN);
 	rd.rs.disks[0].offset = align_size * GL_LOCK_BEGIN;
 	rd.rs.num_disks = 1;
-	rd.rs.flags = (sector_size == 4096) ? (SANLK_RES_SECTOR4K | SANLK_RES_ALIGN8M) :
-					      (SANLK_RES_SECTOR512 | SANLK_RES_ALIGN1M);
 
 	rv = sanlock_write_resource(&rd.rs, 0, 0, 0);
 	if (rv < 0) {
@@ -626,8 +449,6 @@ int lm_init_vg_sanlock(char *ls_name, char *vg_name, uint32_t flags, char *vg_ar
 	memcpy(rd.rs.disks[0].path, disk.path, SANLK_PATH_LEN);
 	rd.rs.disks[0].offset = align_size * VG_LOCK_BEGIN;
 	rd.rs.num_disks = 1;
-	rd.rs.flags = (sector_size == 4096) ? (SANLK_RES_SECTOR4K | SANLK_RES_ALIGN8M) :
-					      (SANLK_RES_SECTOR512 | SANLK_RES_ALIGN1M);
 
 	rv = sanlock_write_resource(&rd.rs, 0, 0, 0);
 	if (rv < 0) {
@@ -639,9 +460,7 @@ int lm_init_vg_sanlock(char *ls_name, char *vg_name, uint32_t flags, char *vg_ar
 	if (!strcmp(gl_name, R_NAME_GL))
 		strncpy(gl_lsname_sanlock, ls_name, MAX_NAME);
  
-	rv = snprintf(vg_args, MAX_ARGS, "%s:%s", lock_args_version, lock_lv_name);
-	if (rv >= MAX_ARGS)
-		log_debug("init_vg_san vg_args may be too long %d %s", rv, vg_args);
+	snprintf(vg_args, MAX_ARGS, "%s:%s", lock_args_version, lock_lv_name);
 
 	log_debug("S %s init_vg_san done vg_args %s", ls_name, vg_args);
 
@@ -653,8 +472,6 @@ int lm_init_vg_sanlock(char *ls_name, char *vg_name, uint32_t flags, char *vg_ar
 
 	memset(&rd, 0, sizeof(rd));
 	rd.rs.num_disks = 1;
-	rd.rs.flags = (sector_size == 4096) ? (SANLK_RES_SECTOR4K | SANLK_RES_ALIGN8M) :
-					      (SANLK_RES_SECTOR512 | SANLK_RES_ALIGN1M);
 	memcpy(rd.rs.disks[0].path, disk.path, SANLK_PATH_LEN);
 	strncpy(rd.rs.lockspace_name, ls_name, SANLK_NAME_LEN);
 	strcpy(rd.rs.name, "#unused");
@@ -693,13 +510,13 @@ int lm_init_vg_sanlock(char *ls_name, char *vg_name, uint32_t flags, char *vg_ar
  */
 
 int lm_init_lv_sanlock(char *ls_name, char *vg_name, char *lv_name,
-		       char *vg_args, char *lv_args,
-		       int sector_size, int align_size, uint64_t free_offset)
+		       char *vg_args, char *lv_args, uint64_t free_offset)
 {
 	struct sanlk_resourced rd;
 	char lock_lv_name[MAX_ARGS+1];
-	char lock_args_version[MAX_VERSION+1];
+	char lock_args_version[MAX_ARGS+1];
 	uint64_t offset;
+	int align_size;
 	int rv;
 
 	memset(&rd, 0, sizeof(rd));
@@ -713,11 +530,11 @@ int lm_init_lv_sanlock(char *ls_name, char *vg_name, char *lv_name,
 		return rv;
 	}
 
-	snprintf(lock_args_version, MAX_VERSION, "%u.%u.%u",
+	snprintf(lock_args_version, MAX_ARGS, "%u.%u.%u",
 		 LV_LOCK_ARGS_MAJOR, LV_LOCK_ARGS_MINOR, LV_LOCK_ARGS_PATCH);
 
 	if (daemon_test) {
-		align_size = ONE_MB;
+		align_size = 1048576;
 		snprintf(lv_args, MAX_ARGS, "%s:%llu",
 			 lock_args_version,
 			 (unsigned long long)((align_size * LV_LOCK_BEGIN) + (align_size * daemon_test_lv_count)));
@@ -730,35 +547,12 @@ int lm_init_lv_sanlock(char *ls_name, char *vg_name, char *lv_name,
 	if ((rv = build_dm_path(rd.rs.disks[0].path, SANLK_PATH_LEN, vg_name, lock_lv_name)))
 		return rv;
 
-	/*
-	 * These should not usually be zero, maybe only the first time this function is called?
-	 * We need to use the same sector/align sizes that are already being used.
-	 */
-	if (!sector_size || !align_size) {
-		rv = get_sizes_lockspace(rd.rs.disks[0].path, &sector_size, &align_size);
-		if (rv < 0) {
-			log_error("S %s init_lv_san read_lockspace error %d %s",
-				  ls_name, rv, rd.rs.disks[0].path);
-			return rv;
-		}
-
-		if (sector_size)
-			log_debug("S %s init_lv_san found ls sector_size %d align_size %d", ls_name, sector_size, align_size);
-		else {
-			/* use the old method */
-			align_size = sanlock_align(&rd.rs.disks[0]);
-			if (align_size <= 0) {
-				log_error("S %s init_lv_san align error %d", ls_name, align_size);
-				return -EINVAL;
-			}
-			sector_size = (align_size == ONE_MB) ? 512 : 4096;
-			log_debug("S %s init_lv_san found old sector_size %d align_size %d", ls_name, sector_size, align_size);
-		}
+	align_size = sanlock_align(&rd.rs.disks[0]);
+	if (align_size <= 0) {
+		log_error("S %s init_lv_san align error %d", ls_name, align_size);
+		return -EINVAL;
 	}
 
-	rd.rs.flags = (sector_size == 4096) ? (SANLK_RES_SECTOR4K | SANLK_RES_ALIGN8M) :
-					      (SANLK_RES_SECTOR512 | SANLK_RES_ALIGN1M);
-
 	if (free_offset)
 		offset = free_offset;
 	else
@@ -801,8 +595,6 @@ int lm_init_lv_sanlock(char *ls_name, char *vg_name, char *lv_name,
 				  ls_name, lv_name, (unsigned long long)offset);
 
 			strncpy(rd.rs.name, lv_name, SANLK_NAME_LEN);
-			rd.rs.flags = (sector_size == 4096) ? (SANLK_RES_SECTOR4K | SANLK_RES_ALIGN8M) :
-							      (SANLK_RES_SECTOR512 | SANLK_RES_ALIGN1M);
 
 			rv = sanlock_write_resource(&rd.rs, 0, 0, 0);
 			if (!rv) {
@@ -834,8 +626,7 @@ int lm_rename_vg_sanlock(char *ls_name, char *vg_name, uint32_t flags, char *vg_
 	char lock_lv_name[MAX_ARGS+1];
 	uint64_t offset;
 	uint32_t io_timeout;
-	int sector_size = 0;
-	int align_size = 0;
+	int align_size;
 	int i, rv;
 
 	memset(&disk, 0, sizeof(disk));
@@ -864,13 +655,20 @@ int lm_rename_vg_sanlock(char *ls_name, char *vg_name, uint32_t flags, char *vg_
 	/* FIXME: device is not always ready for us here */
 	sleep(1);
 
+	align_size = sanlock_align(&disk);
+	if (align_size <= 0) {
+		log_error("S %s rename_vg_san bad align size %d %s",
+			  ls_name, align_size, disk.path);
+		return -EINVAL;
+	}
+
 	/*
 	 * Lockspace
 	 */
 
 	memset(&ss, 0, sizeof(ss));
 	memcpy(ss.host_id_disk.path, disk.path, SANLK_PATH_LEN);
-	ss.host_id_disk.offset = 0;
+	ss.host_id_disk.offset = LS_BEGIN * align_size;
 
 	rv = sanlock_read_lockspace(&ss, 0, &io_timeout);
 	if (rv < 0) {
@@ -879,26 +677,6 @@ int lm_rename_vg_sanlock(char *ls_name, char *vg_name, uint32_t flags, char *vg_
 		return rv;
 	}
 
-	if ((ss.flags & SANLK_LSF_SECTOR4K) && (ss.flags & SANLK_LSF_ALIGN8M)) {
-		sector_size = 4096;
-		align_size = 8 * ONE_MB;
-	} else if ((ss.flags & SANLK_LSF_SECTOR512) && (ss.flags & SANLK_LSF_ALIGN1M)) {
-		sector_size = 512;
-		align_size = ONE_MB;
-	} else {
-		/* use the old method */
-		align_size = sanlock_align(&ss.host_id_disk);
-		if (align_size <= 0) {
-			log_error("S %s rename_vg_san unknown sector/align size for %s",
-				 ls_name, ss.host_id_disk.path);
-			return -1;
-		}
-		sector_size = (align_size == ONE_MB) ? 512 : 4096;
-	}
-
-	if (!sector_size || !align_size)
-		return -1;
-
 	strncpy(ss.name, ls_name, SANLK_NAME_LEN);
 
 	rv = sanlock_write_lockspace(&ss, 0, 0, sanlock_io_timeout);
@@ -1052,11 +830,6 @@ int lm_ex_disable_gl_sanlock(struct lockspace *ls)
 	rd1.rs.num_disks = 1;
 	strncpy(rd1.rs.disks[0].path, lms->ss.host_id_disk.path, SANLK_PATH_LEN-1);
 	rd1.rs.disks[0].offset = lms->align_size * GL_LOCK_BEGIN;
-	
-	rd1.rs.flags = (lms->sector_size == 4096) ? (SANLK_RES_SECTOR4K | SANLK_RES_ALIGN8M) :
-						    (SANLK_RES_SECTOR512 | SANLK_RES_ALIGN1M);
-	rd2.rs.flags = (lms->sector_size == 4096) ? (SANLK_RES_SECTOR4K | SANLK_RES_ALIGN8M) :
-						    (SANLK_RES_SECTOR512 | SANLK_RES_ALIGN1M);
 
 	rv = sanlock_acquire(lms->sock, -1, 0, 1, &rs1, NULL);
 	if (rv < 0) {
@@ -1118,8 +891,6 @@ int lm_able_gl_sanlock(struct lockspace *ls, int enable)
 	rd.rs.num_disks = 1;
 	strncpy(rd.rs.disks[0].path, lms->ss.host_id_disk.path, SANLK_PATH_LEN-1);
 	rd.rs.disks[0].offset = lms->align_size * GL_LOCK_BEGIN;
-	rd.rs.flags = (lms->sector_size == 4096) ? (SANLK_RES_SECTOR4K | SANLK_RES_ALIGN8M) :
-						   (SANLK_RES_SECTOR512 | SANLK_RES_ALIGN1M);
 
 	rv = sanlock_write_resource(&rd.rs, 0, 0, 0);
 	if (rv < 0) {
@@ -1165,8 +936,7 @@ static int gl_is_enabled(struct lockspace *ls, struct lm_sanlock *lms)
 
 	rv = sanlock_read_resource(&rd.rs, 0);
 	if (rv < 0) {
-		log_error("gl_is_enabled read_resource align_size %d offset %llu error %d",
-			  lms->align_size, (unsigned long long)offset, rv);
+		log_error("gl_is_enabled read_resource error %d", rv);
 		return rv;
 	}
 
@@ -1203,7 +973,7 @@ int lm_gl_is_enabled(struct lockspace *ls)
  * been disabled.)
  */
 
-int lm_find_free_lock_sanlock(struct lockspace *ls, uint64_t *free_offset, int *sector_size, int *align_size)
+int lm_find_free_lock_sanlock(struct lockspace *ls, uint64_t *free_offset)
 {
 	struct lm_sanlock *lms = (struct lm_sanlock *)ls->lm_data;
 	struct sanlk_resourced rd;
@@ -1213,22 +983,15 @@ int lm_find_free_lock_sanlock(struct lockspace *ls, uint64_t *free_offset, int *
 	int round = 0;
 
 	if (daemon_test) {
-		*free_offset = (ONE_MB * LV_LOCK_BEGIN) + (ONE_MB * (daemon_test_lv_count + 1));
-		*sector_size = 512;
-		*align_size = ONE_MB;
+		*free_offset = (1048576 * LV_LOCK_BEGIN) + (1048576 * (daemon_test_lv_count + 1));
 		return 0;
 	}
 
-	*sector_size = lms->sector_size;
-	*align_size = lms->align_size;
-
 	memset(&rd, 0, sizeof(rd));
 
 	strncpy(rd.rs.lockspace_name, ls->name, SANLK_NAME_LEN);
 	rd.rs.num_disks = 1;
 	strncpy(rd.rs.disks[0].path, lms->ss.host_id_disk.path, SANLK_PATH_LEN-1);
-	rd.rs.flags = (lms->sector_size == 4096) ? (SANLK_RES_SECTOR4K | SANLK_RES_ALIGN8M) :
-						   (SANLK_RES_SECTOR512 | SANLK_RES_ALIGN1M);
 
 	if (ls->free_lock_offset)
 		offset = ls->free_lock_offset;
@@ -1328,8 +1091,6 @@ int lm_prepare_lockspace_sanlock(struct lockspace *ls)
 	char disk_path[SANLK_PATH_LEN];
 	char killpath[SANLK_PATH_LEN];
 	char killargs[SANLK_PATH_LEN];
-	int sector_size = 0;
-	int align_size = 0;
 	int gl_found;
 	int ret, rv;
 
@@ -1399,7 +1160,7 @@ int lm_prepare_lockspace_sanlock(struct lockspace *ls)
 		goto fail;
 	}
 
-	lms = zalloc(sizeof(struct lm_sanlock));
+	lms = malloc(sizeof(struct lm_sanlock));
 	if (!lms) {
 		ret = -ENOMEM;
 		goto fail;
@@ -1408,6 +1169,7 @@ int lm_prepare_lockspace_sanlock(struct lockspace *ls)
 	memset(lsname, 0, sizeof(lsname));
 	strncpy(lsname, ls->name, SANLK_NAME_LEN);
 
+	memset(lms, 0, sizeof(struct lm_sanlock));
 	memcpy(lms->ss.name, lsname, SANLK_NAME_LEN);
 	lms->ss.host_id_disk.offset = 0;
 	lms->ss.host_id = ls->host_id;
@@ -1445,34 +1207,13 @@ int lm_prepare_lockspace_sanlock(struct lockspace *ls)
 		goto fail;
 	}
 
-	rv = get_sizes_lockspace(disk_path, &sector_size, &align_size);
-	if (rv < 0) {
-		log_error("S %s prepare_lockspace_san cannot get sector/align sizes %d", lsname, rv);
+	lms->align_size = sanlock_align(&lms->ss.host_id_disk);
+	if (lms->align_size <= 0) {
+		log_error("S %s prepare_lockspace_san align error %d", lsname, lms->align_size);
 		ret = -EMANAGER;
 		goto fail;
 	}
 
-	if (!sector_size) {
-		log_debug("S %s prepare_lockspace_san using old size method", lsname);
-		/* use the old method */
-		align_size = sanlock_align(&lms->ss.host_id_disk);
-		if (align_size <= 0) {
-			log_error("S %s prepare_lockspace_san align error %d", lsname, align_size);
-			ret = -EINVAL;
-			goto fail;
-		}
-		sector_size = (align_size == ONE_MB) ? 512 : 4096;
-		log_debug("S %s prepare_lockspace_san found old sector_size %d align_size %d", lsname, sector_size, align_size);
-	}
-
-	log_debug("S %s prepare_lockspace_san sizes %d %d", lsname, sector_size, align_size);
-
-	lms->align_size = align_size;
-	lms->sector_size = sector_size;
-
-	lms->ss.flags = (sector_size == 4096) ? (SANLK_LSF_SECTOR4K | SANLK_LSF_ALIGN8M) :
-						(SANLK_LSF_SECTOR512 | SANLK_LSF_ALIGN1M);
-
 	gl_found = gl_is_enabled(ls, lms);
 	if (gl_found < 0) {
 		log_error("S %s prepare_lockspace_san gl_enabled error %d", lsname, gl_found);
@@ -1610,7 +1351,6 @@ static int lm_add_resource_sanlock(struct lockspace *ls, struct resource *r)
 	strncpy(rds->rs.name, r->name, SANLK_NAME_LEN);
 	rds->rs.num_disks = 1;
 	memcpy(rds->rs.disks[0].path, lms->ss.host_id_disk.path, SANLK_PATH_LEN);
-	rds->rs.flags = (lms->sector_size == 4096) ? (SANLK_RES_SECTOR4K | SANLK_RES_ALIGN8M) : (SANLK_RES_SECTOR512 | SANLK_RES_ALIGN1M);
 
 	if (r->type == LD_RT_GL)
 		rds->rs.disks[0].offset = GL_LOCK_BEGIN * lms->align_size;
@@ -1620,9 +1360,10 @@ static int lm_add_resource_sanlock(struct lockspace *ls, struct resource *r)
 	/* LD_RT_LV offset is set in each lm_lock call from lv_args. */
 
 	if (r->type == LD_RT_GL || r->type == LD_RT_VG) {
-		rds->vb = zalloc(sizeof(struct val_blk));
+		rds->vb = malloc(sizeof(struct val_blk));
 		if (!rds->vb)
 			return -ENOMEM;
+		memset(rds->vb, 0, sizeof(struct val_blk));
 	}
 
 	return 0;
@@ -2119,20 +1860,12 @@ int lm_unlock_sanlock(struct lockspace *ls, struct resource *r,
 	if (rv < 0)
 		log_error("S %s R %s unlock_san release error %d", ls->name, r->name, rv);
 
-	/*
-	 * sanlock may return an error here if it fails to release the lease on
-	 * disk because of an io timeout.  But, sanlock will continue trying to
-	 * release the lease after this call returns.  We shouldn't return an
-	 * error here which would result in lvmlockd-core keeping the lock
-	 * around.  By releasing the lock in lvmlockd-core at this point,
-	 * lvmlockd may send another acquire request to lvmlockd.  If sanlock
-	 * has not been able to release the previous instance of the lock yet,
-	 * then it will return an error for the new request.  But, acquiring a
-	 * new lock is able o fail gracefully, until sanlock is finally able to
-	 * release the old lock.
-	 */
+	if (rv == -EIO)
+		rv = -ELOCKIO;
+	else if (rv < 0)
+		rv = -ELMERR;
 
-	return 0;
+	return rv;
 }
 
 int lm_hosts_sanlock(struct lockspace *ls, int notify)

daemons/lvmpolld/Makefile.in

@@ -29,16 +29,15 @@ include $(top_builddir)/make.tmpl
 
 CFLAGS += $(EXTRA_EXEC_CFLAGS)
 INCLUDES += -I$(top_srcdir)/libdaemon/server
-LDFLAGS += $(EXTRA_EXEC_LDFLAGS) $(ELDFLAGS)
-LIBS += $(DAEMON_LIBS) $(PTHREAD_LIBS)
+LDFLAGS += -L$(top_builddir)/libdaemon/server $(EXTRA_EXEC_LDFLAGS) $(ELDFLAGS)
+LIBS += $(DAEMON_LIBS) -ldaemonserver -ldevmapper $(PTHREAD_LIBS)
 
-lvmpolld: $(OBJECTS) $(top_builddir)/libdaemon/server/libdaemonserver.a $(INTERNAL_LIBS)
-	@echo "    [CC] $@"
-	$(Q) $(CC) $(CFLAGS) $(LDFLAGS) -o $@ $+ $(LIBS)
+lvmpolld: $(OBJECTS) $(top_builddir)/libdaemon/client/libdaemonclient.a \
+		    $(top_builddir)/libdaemon/server/libdaemonserver.a
+	$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJECTS) $(LIBS)
 
 install_lvmpolld: lvmpolld
-	@echo "    [INSTALL] $<"
-	$(Q) $(INSTALL_PROGRAM) -D $< $(sbindir)/$(<F)
+	$(INSTALL_PROGRAM) -D $< $(sbindir)/$(<F)
 
 install_lvm2: install_lvmpolld
 

daemons/lvmpolld/lvmpolld-cmd-utils.c

@@ -36,7 +36,7 @@ static int add_to_cmd_arr(const char ***cmdargv, const char *str, unsigned *ind)
 	const char **newargv;
 
 	if (*ind && !(*ind % MIN_ARGV_SIZE)) {
-		newargv = realloc(*cmdargv, (*ind / MIN_ARGV_SIZE + 1) * MIN_ARGV_SIZE * sizeof(char *));
+		newargv = dm_realloc(*cmdargv, (*ind / MIN_ARGV_SIZE + 1) * MIN_ARGV_SIZE * sizeof(char *));
 		if (!newargv)
 			return 0;
 		*cmdargv = newargv;
@@ -50,7 +50,7 @@ static int add_to_cmd_arr(const char ***cmdargv, const char *str, unsigned *ind)
 const char **cmdargv_ctr(const struct lvmpolld_lv *pdlv, const char *lvm_binary, unsigned abort_polling, unsigned handle_missing_pvs)
 {
 	unsigned i = 0;
-	const char **cmd_argv = malloc(MIN_ARGV_SIZE * sizeof(char *));
+	const char **cmd_argv = dm_malloc(MIN_ARGV_SIZE * sizeof(char *));
 
 	if (!cmd_argv)
 		return NULL;
@@ -98,7 +98,7 @@ const char **cmdargv_ctr(const struct lvmpolld_lv *pdlv, const char *lvm_binary,
 
 	return cmd_argv;
 err:
-	free(cmd_argv);
+	dm_free(cmd_argv);
 	return NULL;
 }
 
@@ -122,7 +122,7 @@ static int copy_env(const char ***cmd_envp, unsigned *i, const char *exclude)
 const char **cmdenvp_ctr(const struct lvmpolld_lv *pdlv)
 {
 	unsigned i = 0;
-	const char **cmd_envp = malloc(MIN_ARGV_SIZE * sizeof(char *));
+	const char **cmd_envp = dm_malloc(MIN_ARGV_SIZE * sizeof(char *));
 
 	if (!cmd_envp)
 		return NULL;
@@ -141,6 +141,6 @@ const char **cmdenvp_ctr(const struct lvmpolld_lv *pdlv)
 
 	return cmd_envp;
 err:
-	free(cmd_envp);
+	dm_free(cmd_envp);
 	return NULL;
 }

daemons/lvmpolld/lvmpolld-common.h

@@ -18,10 +18,12 @@
 #ifndef _LVM_LVMPOLLD_COMMON_H
 #define _LVM_LVMPOLLD_COMMON_H
 
-#include "tools/tool.h"
+#define _REENTRANT
+
+#include "tool.h"
 
 #include "lvmpolld-cmd-utils.h"
-#include "daemons/lvmpolld/lvmpolld-protocol.h"
+#include "lvmpolld-protocol.h"
 
 #include <assert.h>
 #include <errno.h>