Fix bug where IMSM arrays stay inactive in case of reboot during reshape

Signed-off-by: Jes Sorensen <Jes.Sorensen@redhat.com>

mdadm-3.2.3-FIX-Array-is-not-run-when-expansion-disks-are-added.patch

@@ -0,0 +1,30 @@
+From 111e9fdaa8a5084bd329819a0906a685b2271c0d Mon Sep 17 00:00:00 2001
+From: Adam Kwolek <adam.kwolek@intel.com>
+Date: Tue, 7 Feb 2012 15:03:19 +0100
+Subject: [PATCH 03/12] FIX: Array is not run when expansion disks are added
+
+When added disk is disk added by expansion and this is last disk added
+to array, assemble_container_content() will not even try to run such array.
+
+Signed-off-by: Adam Kwolek <adam.kwolek@intel.com>
+Signed-off-by: NeilBrown <neilb@suse.de>
+---
+ Assemble.c |    2 +-
+ 1 files changed, 1 insertions(+), 1 deletions(-)
+
+diff --git a/Assemble.c b/Assemble.c
+index ad4eb9c..13adfc3 100644
+--- a/Assemble.c
++++ b/Assemble.c
+@@ -1557,7 +1557,7 @@ int assemble_container_content(struct supertype *st, int mdfd,
+ 				working++;
+ 		} else if (errno == EEXIST)
+ 			preexist++;
+-	if (working == 0)
++	if (working + expansion == 0)
+ 		return 1;/* Nothing new, don't try to start */
+ 
+ 	map_update(&map, fd2devnum(mdfd),
+-- 
+1.7.4.4
+

mdadm-3.2.3-FIX-Changes-in-0-case-for-reshape-position-verificat.patch

@@ -0,0 +1,63 @@
+From d7592845d4a9b885af7121f8ff6ba4f77610cd32 Mon Sep 17 00:00:00 2001
+From: Adam Kwolek <adam.kwolek@intel.com>
+Date: Thu, 16 Feb 2012 14:16:04 +0100
+Subject: [PATCH 15/15] FIX: Changes in '0' case for reshape position
+ verification
+
+Reading sysfs entry that is '0' long should cause an error.
+Reshape position cannot be empty.
+
+Absence of reshape position should be ignored. It is possible
+that we are about raid0 reshape continuation and it is before takeover.
+This means that according metadata (changed by mdmon) it should be reshaped
+but md knows nothing about it at this moment. Reshape continuation
+in reshape_array() will change it to raid4 and reshape position appears
+in sysfs.
+
+Signed-off-by: Adam Kwolek <adam.kwolek@intel.com>
+---
+ Grow.c |   12 ++++++++++--
+ 1 files changed, 10 insertions(+), 2 deletions(-)
+
+diff --git a/Grow.c b/Grow.c
+index 53a7cad..239b50d 100644
+--- a/Grow.c
++++ b/Grow.c
+@@ -1876,9 +1876,12 @@ static int verify_reshape_position(struct mdinfo *info, int level)
+ {
+ 	int ret_val = 0;
+ 	char buf[40];
++	int rv;
+ 
+ 	/* read sync_max, failure can mean raid0 array */
+-	if (sysfs_get_str(info, NULL, "sync_max", buf, 40) > 0) {
++	rv = sysfs_get_str(info, NULL, "sync_max", buf, 40);
++
++	if (rv > 0) {
+ 		char *ep;
+ 		unsigned long long position = strtoull(buf, &ep, 0);
+ 
+@@ -1906,6 +1909,11 @@ static int verify_reshape_position(struct mdinfo *info, int level)
+ 				ret_val = 1;
+ 			}
+ 		}
++	} else if (rv == 0) {
++		/* for valid sysfs entry, 0-length content
++		 * should be indicated as error
++		 */
++		ret_val = -1;
+ 	}
+ 
+ 	return ret_val;
+@@ -3975,7 +3983,7 @@ int Grow_continue_command(char *devname, int fd,
+ 	 * correct position
+ 	 */
+ 	if (verify_reshape_position(content,
+-				    map_name(pers, mdstat->level)) <= 0) {
++				    map_name(pers, mdstat->level)) < 0) {
+ 		ret_val = 1;
+ 		goto Grow_continue_command_exit;
+ 	}
+-- 
+1.7.4.4
+

mdadm-3.2.3-FIX-Do-not-try-to-continue-reshape-using-inactive-ar.patch

@@ -0,0 +1,50 @@
+From 1ca90aa6484a6f5d4fdd6122ad1d2015209bd8e0 Mon Sep 17 00:00:00 2001
+From: Adam Kwolek <adam.kwolek@intel.com>
+Date: Thu, 9 Feb 2012 12:38:15 +1100
+Subject: [PATCH 12/12] FIX: Do not try to (continue) reshape using inactive
+ array
+
+When one of arrays is inactive, do not try to continue reshape
+on this array. Just skip it.
+
+Signed-off-by: Adam Kwolek <adam.kwolek@intel.com>
+Signed-off-by: NeilBrown <neilb@suse.de>
+---
+ Grow.c |   14 ++++++++++++++
+ 1 files changed, 14 insertions(+), 0 deletions(-)
+
+diff --git a/Grow.c b/Grow.c
+index 61adefa..53a7cad 100644
+--- a/Grow.c
++++ b/Grow.c
+@@ -2626,6 +2626,13 @@ int reshape_container(char *container, char *devname,
+ 						  devname2devnum(container));
+ 			if (!mdstat)
+ 				continue;
++			if (mdstat->active == 0) {
++				fprintf(stderr, Name ": Skipping inactive "
++					"array md%i.\n", mdstat->devnum);
++				free_mdstat(mdstat);
++				mdstat = NULL;
++				continue;
++			}
+ 			break;
+ 		}
+ 		if (!content)
+@@ -3922,6 +3929,13 @@ int Grow_continue_command(char *devname, int fd,
+ 			mdstat = mdstat_by_subdev(array, container_dev);
+ 			if (!mdstat)
+ 				continue;
++			if (mdstat->active == 0) {
++				fprintf(stderr, Name ": Skipping inactive "
++					"array md%i.\n", mdstat->devnum);
++				free_mdstat(mdstat);
++				mdstat = NULL;
++				continue;
++			}
+ 			break;
+ 		}
+ 		if (!content) {
+-- 
+1.7.4.4
+

mdadm-3.2.3-FIX-External-metadata-sometimes-is-not-updated.patch

@@ -0,0 +1,35 @@
+From 5d1c7cdaca575d8a32a7a82517d88e2099f6a213 Mon Sep 17 00:00:00 2001
+From: Adam Kwolek <adam.kwolek@intel.com>
+Date: Thu, 12 Jan 2012 08:12:39 +0100
+Subject: [PATCH] FIX: External metadata sometimes is not updated
+
+External metadata sometimes is not updated.
+It can be observed during 2 raid0 arrays Capacity Expansion.
+New array size is not set, because metadata is not updated and on the reshape
+end mdadm doesn't read new array size from metadata.
+This happens when mdmon finishes his work (due to takeover to raid0),
+before all metadata updates are processed.
+
+Make sure that all updates are flushed to disk before executing takeover.
+
+Signed-off-by: Adam Kwolek <adam.kwolek@intel.com>
+Signed-off-by: NeilBrown <neilb@suse.de>
+---
+ Grow.c |    1 +
+ 1 files changed, 1 insertions(+), 0 deletions(-)
+
+diff --git a/Grow.c b/Grow.c
+index b2c1360..89f563c 100644
+--- a/Grow.c
++++ b/Grow.c
+@@ -2396,6 +2396,7 @@ started:
+ 		/* Re-load the metadata as much could have changed */
+ 		int cfd = open_dev(st->container_dev);
+ 		if (cfd >= 0) {
++			ping_manager(container);
+ 			ping_monitor(container);
+ 			st->ss->free_super(st);
+ 			st->ss->load_container(st, cfd, container);
+-- 
+1.7.4.4
+

mdadm-3.2.3-FIX-NULL-pointer-to-strdup-can-be-passed.patch

@@ -0,0 +1,38 @@
+From 92d49ecfaabcd015cf9957a0863996eaa5755747 Mon Sep 17 00:00:00 2001
+From: Adam Kwolek <adam.kwolek@intel.com>
+Date: Tue, 7 Feb 2012 15:03:03 +0100
+Subject: [PATCH 01/12] FIX: NULL pointer to strdup() can be passed
+
+When result from strchr() is NULL and it is assigned to subarray,
+NULL pointer can be passed to strdup() function and coredump file
+is generated.
+
+Subarray is checked for NULL pointer, so it is assumed that it can
+be NULL at this moment.
+
+Signed-off-by: Adam Kwolek <adam.kwolek@intel.com>
+Signed-off-by: NeilBrown <neilb@suse.de>
+---
+ util.c |    5 +++--
+ 1 files changed, 3 insertions(+), 2 deletions(-)
+
+diff --git a/util.c b/util.c
+index e5f7a20..7abbff7 100644
+--- a/util.c
++++ b/util.c
+@@ -966,9 +966,10 @@ struct supertype *super_by_fd(int fd, char **subarrayp)
+ 		char *dev = verstr+1;
+ 
+ 		subarray = strchr(dev, '/');
+-		if (subarray)
++		if (subarray) {
+ 			*subarray++ = '\0';
+-		subarray = strdup(subarray);
++			subarray = strdup(subarray);
++		}
+ 		container = devname2devnum(dev);
+ 		if (sra)
+ 			sysfs_free(sra);
+-- 
+1.7.4.4
+

mdadm-3.2.3-FIX-mdmon-check-in-reshape_container-can-cause-a-pro.patch

@@ -0,0 +1,39 @@
+From 3c20f9899bc95b35f5b9544c6741b4fccd616326 Mon Sep 17 00:00:00 2001
+From: Adam Kwolek <adam.kwolek@intel.com>
+Date: Thu, 12 Jan 2012 08:12:47 +0100
+Subject: [PATCH] FIX: mdmon check in reshape_container() can cause a problem
+
+When raid0 reshape is executed mdmon can dissappear due to raid level
+takeover operation. If this happen before mdmon check, mdadm would treat
+it as error condition. It is not true for this case.
+
+Remove mdmon check from reshape_container() function.
+Error condition check will remain using reshape_array() reentry test
+for the same array (line 2577).
+
+Signed-off-by: Adam Kwolek <adam.kwolek@intel.com>
+Signed-off-by: NeilBrown <neilb@suse.de>
+---
+ Grow.c |    6 ------
+ 1 files changed, 0 insertions(+), 6 deletions(-)
+
+diff --git a/Grow.c b/Grow.c
+index 89f563c..c1bc1ca 100644
+--- a/Grow.c
++++ b/Grow.c
+@@ -2608,12 +2608,6 @@ int reshape_container(char *container, char *devname,
+ 		restart = 0;
+ 		if (rv)
+ 			break;
+-		rv = !mdmon_running(devname2devnum(container));
+-		if (rv) {
+-			printf(Name ": Mdmon is not found. "
+-			       "Cannot continue container reshape.\n");
+-			break;
+-		}
+ 	}
+ 	if (!rv)
+ 		unfreeze(st);
+-- 
+1.7.4.4
+

mdadm-3.2.3-FIX-restart-reshape-when-reshape-process-is-stopped-.patch

@@ -0,0 +1,45 @@
+From e1dd332a09c66ef0df68229cc633b8f2521e5db4 Mon Sep 17 00:00:00 2001
+From: Adam Kwolek <adam.kwolek@intel.com>
+Date: Thu, 9 Feb 2012 12:37:40 +1100
+Subject: [PATCH 11/12] FIX: restart reshape when reshape process is stopped
+ just between 2 reshapes
+
+When reshape is restarted from '0', very begin of array
+it is possible that for external metadata reshape and array
+configuration doesn't happen.
+Check if md has the same opinion, and reshape is restarted
+from 0. If so, this is regular reshape start after reshape
+switch in metadata to next array only.
+
+Signed-off-by: Adam Kwolek <adam.kwolek@intel.com>
+Signed-off-by: NeilBrown <neilb@suse.de>
+---
+ Grow.c |   12 ++++++++++++
+ 1 files changed, 12 insertions(+), 0 deletions(-)
+
+diff --git a/Grow.c b/Grow.c
+index 6b1380a..61adefa 100644
+--- a/Grow.c
++++ b/Grow.c
+@@ -1980,6 +1980,18 @@ static int reshape_array(char *container, int fd, char *devname,
+ 		goto release;
+ 	}
+ 
++	if (st->ss->external && restart && (info->reshape_progress == 0)) {
++		/* When reshape is restarted from '0', very begin of array
++		 * it is possible that for external metadata reshape and array
++		 * configuration doesn't happen.
++		 * Check if md has the same opinion, and reshape is restarted
++		 * from 0. If so, this is regular reshape start after reshape
++		 * switch in metadata to next array only.
++		 */
++		if ((verify_reshape_position(info, reshape.level) >= 0) &&
++		    (info->reshape_progress == 0))
++			restart = 0;
++	}
+ 	if (restart) {
+ 		/* reshape already started. just skip to monitoring the reshape */
+ 		if (reshape.backup_blocks == 0)
+-- 
+1.7.4.4
+

mdadm-3.2.3-FIX-use-md-position-to-reshape-restart.patch

@@ -0,0 +1,139 @@
+From f93346ef078fde20e46849901efa16dd1b05ec33 Mon Sep 17 00:00:00 2001
+From: Adam Kwolek <adam.kwolek@intel.com>
+Date: Thu, 9 Feb 2012 12:36:41 +1100
+Subject: [PATCH 08/12] FIX: use md position to reshape restart
+
+When reshape is broken, it can occur that metadata is not saved properly.
+This can cause that reshape process is farther in md than metadata states.
+
+On reshape restart use md position as start position, if it is farther than
+position specified in metadata. Opposite situation treat as error.
+
+Signed-off-by: Adam Kwolek <adam.kwolek@intel.com>
+Signed-off-by: NeilBrown <neilb@suse.de>
+---
+ Grow.c |   86 ++++++++++++++++++++++++++++++++++++++++++++-------------------
+ 1 files changed, 60 insertions(+), 26 deletions(-)
+
+diff --git a/Grow.c b/Grow.c
+index 70bdee1..6b1380a 100644
+--- a/Grow.c
++++ b/Grow.c
+@@ -1862,6 +1862,55 @@ release:
+ 	return rv;
+ }
+ 
++/* verify_reshape_position()
++ *	Function checks if reshape position in metadata is not farther
++ *	than position in md.
++ * Return value:
++ *	 0 : not valid sysfs entry
++ *		it can be caused by not started reshape, it should be started
++ *		by reshape array or raid0 array is before takeover
++ *	-1 :	error, reshape position is obviously wrong
++ *	 1 :	success, reshape progress correct or updated
++*/
++static int verify_reshape_position(struct mdinfo *info, int level)
++{
++	int ret_val = 0;
++	char buf[40];
++
++	/* read sync_max, failure can mean raid0 array */
++	if (sysfs_get_str(info, NULL, "sync_max", buf, 40) > 0) {
++		char *ep;
++		unsigned long long position = strtoull(buf, &ep, 0);
++
++		dprintf(Name": Read sync_max sysfs entry is: %s\n", buf);
++		if (!(ep == buf || (*ep != 0 && *ep != '\n' && *ep != ' '))) {
++			position *= get_data_disks(level,
++						   info->new_layout,
++						   info->array.raid_disks);
++			if (info->reshape_progress < position) {
++				dprintf("Corrected reshape progress (%llu) to "
++					"md position (%llu)\n",
++					info->reshape_progress, position);
++				info->reshape_progress = position;
++				ret_val = 1;
++			} else if (info->reshape_progress > position) {
++				fprintf(stderr, Name ": Fatal error: array "
++					"reshape was not properly frozen "
++					"(expected reshape position is %llu, "
++					"but reshape progress is %llu.\n",
++					position, info->reshape_progress);
++				ret_val = -1;
++			} else {
++				dprintf("Reshape position in md and metadata "
++					"are the same;");
++				ret_val = 1;
++			}
++		}
++	}
++
++	return ret_val;
++}
++
+ static int reshape_array(char *container, int fd, char *devname,
+ 			 struct supertype *st, struct mdinfo *info,
+ 			 int force, struct mddev_dev *devlist,
+@@ -2251,9 +2300,16 @@ started:
+ 
+ 	sra->new_chunk = info->new_chunk;
+ 
+-	if (restart)
++	if (restart) {
++		/* for external metadata checkpoint saved by mdmon can be lost
++		 * or missed /due to e.g. crash/. Check if md is not during
++		 * restart farther than metadata points to.
++		 * If so, this means metadata information is obsolete.
++		 */
++		if (st->ss->external)
++			verify_reshape_position(info, reshape.level);
+ 		sra->reshape_progress = info->reshape_progress;
+-	else {
++	} else {
+ 		sra->reshape_progress = 0;
+ 		if (reshape.after.data_disks < reshape.before.data_disks)
+ 			/* start from the end of the new array */
+@@ -3765,8 +3821,6 @@ int Grow_continue_command(char *devname, int fd,
+ 	char buf[40];
+ 	int cfd = -1;
+ 	int fd2 = -1;
+-	char *ep;
+-	unsigned long long position;
+ 
+ 	dprintf("Grow continue from command line called for %s\n",
+ 		devname);
+@@ -3894,28 +3948,8 @@ int Grow_continue_command(char *devname, int fd,
+ 	/* verify that array under reshape is started from
+ 	 * correct position
+ 	 */
+-	ret_val = sysfs_get_str(content, NULL, "sync_max", buf, 40);
+-	if (ret_val <= 0) {
+-		fprintf(stderr, Name
+-			": cannot open verify reshape progress for %s (%i)\n",
+-			content->sys_name, ret_val);
+-		ret_val = 1;
+-		goto Grow_continue_command_exit;
+-	}
+-	dprintf(Name ": Read sync_max sysfs entry is: %s\n", buf);
+-	position = strtoull(buf, &ep, 0);
+-	if (ep == buf || (*ep != 0 && *ep != '\n' && *ep != ' ')) {
+-		fprintf(stderr, Name ": Fatal error: array reshape was"
+-			" not properly frozen\n");
+-		ret_val = 1;
+-		goto Grow_continue_command_exit;
+-	}
+-	position *= get_data_disks(map_name(pers, mdstat->level),
+-				   content->new_layout,
+-				   content->array.raid_disks);
+-	if (position != content->reshape_progress) {
+-		fprintf(stderr, Name ": Fatal error: array reshape was"
+-			" not properly frozen.\n");
++	if (verify_reshape_position(content,
++				    map_name(pers, mdstat->level)) <= 0) {
+ 		ret_val = 1;
+ 		goto Grow_continue_command_exit;
+ 	}
+-- 
+1.7.4.4
+

mdadm-3.2.3-Fix-Sometimes-mdmon-throws-core-dump-during-reshape.patch

@@ -0,0 +1,46 @@
+From 50927b1323a4cfcbf3729ff552c496695d6199eb Mon Sep 17 00:00:00 2001
+From: Adam Kwolek <adam.kwolek@intel.com>
+Date: Tue, 7 Feb 2012 15:03:35 +0100
+Subject: [PATCH 05/12] Fix: Sometimes mdmon throws core dump during reshape
+
+Problem was found during reshaping 2 volumes /raid0 and raid5/ in container.
+Sometimes mdmon throws core dump due to NULL pointer exception.
+
+Problem occurs in scenario:
+- managemon: is about spare activation (degraded raid4 volume == raid0 under takeover)
+- managemon: detect level change and signals monitor (manage_member() calls replace_array())
+- monitor: detects transition raid4/5->raid0 and sets a->container to NULL
+           to indicate array deactivation
+- managemon : continues his work and tries to activate spare (a->check_degraded is set).
+              NULL pointer is passed to metadata handler activate_spare()
+              Core dump is generated.
+
+To resolve this situation managemon (after monitor kick) checks again
+a->container pointer to learn if current array is not to be deactivated.
+
+Signed-off-by: Adam Kwolek <adam.kwolek@intel.com>
+Signed-off-by: NeilBrown <neilb@suse.de>
+---
+ managemon.c |    6 ++++++
+ 1 files changed, 6 insertions(+), 0 deletions(-)
+
+diff --git a/managemon.c b/managemon.c
+index cde0d8b..6c21ecb 100644
+--- a/managemon.c
++++ b/managemon.c
+@@ -486,6 +486,12 @@ static void manage_member(struct mdstat_ent *mdstat,
+ 		}
+ 	}
+ 
++	/* we are after monitor kick,
++	 * so container field can be cleared - check it again
++	 */
++	if (a->container == NULL)
++		return;
++
+ 	/* We don't check the array while any update is pending, as it
+ 	 * might container a change (such as a spare assignment) which
+ 	 * could affect our decisions.
+-- 
+1.7.4.4
+

mdadm-3.2.3-Flush-mdmon-before-next-reshape-step-during-containe.patch

@@ -0,0 +1,96 @@
+From 78340e26a54db960de238b511f5cdc74aebe4453 Mon Sep 17 00:00:00 2001
+From: Adam Kwolek <adam.kwolek@intel.com>
+Date: Tue, 7 Feb 2012 15:03:43 +0100
+Subject: [PATCH 06/12] Flush mdmon before next reshape step during container
+ operation
+
+Using takeover operation for grow purposes, mdadm has to be sure
+that mdmon processes all updates, and if necessary it will be closed
+at takeover to raid0 operation. If mdmon is late, next array in container
+is processed and due to race condition mdmon closes itself instead to monitor
+next reshape operation.
+
+Signed-off-by: Adam Kwolek <adam.kwolek@intel.com>
+Signed-off-by: NeilBrown <neilb@suse.de>
+---
+ Grow.c |   12 ++++++++++--
+ msg.c  |   10 ++++++++++
+ msg.h  |    1 +
+ 3 files changed, 21 insertions(+), 2 deletions(-)
+
+diff --git a/Grow.c b/Grow.c
+index 36a1de7..70bdee1 100644
+--- a/Grow.c
++++ b/Grow.c
+@@ -2003,6 +2003,9 @@ static int reshape_array(char *container, int fd, char *devname,
+ 
+ 		if (reshape.level > 0 && st->ss->external) {
+ 			/* make sure mdmon is aware of the new level */
++			if (mdmon_running(st->container_dev))
++				flush_mdmon(container);
++
+ 			if (!mdmon_running(st->container_dev))
+ 				start_mdmon(st->container_dev);
+ 			ping_monitor(container);
+@@ -2396,8 +2399,7 @@ started:
+ 		/* Re-load the metadata as much could have changed */
+ 		int cfd = open_dev(st->container_dev);
+ 		if (cfd >= 0) {
+-			ping_manager(container);
+-			ping_monitor(container);
++			flush_mdmon(container);
+ 			st->ss->free_super(st);
+ 			st->ss->load_container(st, cfd, container);
+ 			close(cfd);
+@@ -2594,6 +2596,9 @@ int reshape_container(char *container, char *devname,
+ 
+ 		sysfs_init(content, fd, mdstat->devnum);
+ 
++		if (mdmon_running(devname2devnum(container)))
++			flush_mdmon(container);
++
+ 		rv = reshape_array(container, fd, adev, st,
+ 				   content, force, NULL,
+ 				   backup_file, quiet, 1, restart,
+@@ -2608,6 +2613,9 @@ int reshape_container(char *container, char *devname,
+ 		restart = 0;
+ 		if (rv)
+ 			break;
++
++		if (mdmon_running(devname2devnum(container)))
++			flush_mdmon(container);
+ 	}
+ 	if (!rv)
+ 		unfreeze(st);
+diff --git a/msg.c b/msg.c
+index dc780b3..44aad1f 100644
+--- a/msg.c
++++ b/msg.c
+@@ -487,3 +487,13 @@ int ping_manager(char *devname)
+ 	close(sfd);
+ 	return err;
+ }
++
++/* using takeover operation for grow purposes, mdadm has to be sure
++ * that mdmon processes all updates, and if necessary it will be closed
++ * at takeover to raid0 operation
++  */
++void flush_mdmon(char *container)
++{
++	ping_manager(container);
++	ping_monitor(container);
++}
+diff --git a/msg.h b/msg.h
+index c6d037d..eefa649 100644
+--- a/msg.h
++++ b/msg.h
+@@ -34,5 +34,6 @@ extern int block_monitor(char *container, const int freeze);
+ extern void unblock_monitor(char *container, const int unfreeze);
+ extern int fping_monitor(int sock);
+ extern int ping_manager(char *devname);
++extern void flush_mdmon(char *container);
+ 
+ #define MSG_MAX_LEN (4*1024*1024)
+-- 
+1.7.4.4
+

mdadm-3.2.3-imsm-FIX-Chunk-size-migration-problem.patch

@@ -0,0 +1,32 @@
+From e1742195ff3dba97929f81af6b7633481a23397a Mon Sep 17 00:00:00 2001
+From: Adam Kwolek <adam.kwolek@intel.com>
+Date: Tue, 7 Feb 2012 15:03:51 +0100
+Subject: [PATCH 07/12] imsm: FIX: Chunk size migration problem
+
+When chunk size migration occurs (e.g. 128k->4k) first checkpoint cannot
+be set in md due to too small step. Correct migration record initialization
+to allow whole copy area usage and increase migration checkpoint step.
+
+Signed-off-by: Adam Kwolek <adam.kwolek@intel.com>
+Signed-off-by: NeilBrown <neilb@suse.de>
+---
+ super-intel.c |    3 ++-
+ 1 files changed, 2 insertions(+), 1 deletions(-)
+
+diff --git a/super-intel.c b/super-intel.c
+index 19a2c84..f5762d8 100644
+--- a/super-intel.c
++++ b/super-intel.c
+@@ -8913,7 +8913,8 @@ void init_migr_record_imsm(struct supertype *st, struct imsm_dev *dev,
+ 
+ 	migr_rec->dest_depth_per_unit = GEN_MIGR_AREA_SIZE /
+ 		max(map_dest->blocks_per_strip, map_src->blocks_per_strip);
+-	migr_rec->dest_depth_per_unit *= map_dest->blocks_per_strip;
++	migr_rec->dest_depth_per_unit *=
++		max(map_dest->blocks_per_strip, map_src->blocks_per_strip);
+ 	new_data_disks = imsm_num_data_members(dev, MAP_0);
+ 	migr_rec->blocks_per_unit =
+ 		__cpu_to_le32(migr_rec->dest_depth_per_unit * new_data_disks);
+-- 
+1.7.4.4
+

mdadm-3.2.3-imsm-FIX-Clear-migration-record-when-migration-switc.patch

@@ -0,0 +1,88 @@
+From 51d83f5d119f9b727cc715b22b1625332bd0130b Mon Sep 17 00:00:00 2001
+From: Adam Kwolek <adam.kwolek@intel.com>
+Date: Thu, 9 Feb 2012 12:37:04 +1100
+Subject: [PATCH 10/12] imsm: FIX: Clear migration record when migration
+ switches to next volume.
+
+When OLCE is in progress, checkpoint steps are getting bigger due to added space during process.
+When mdadm fails after saving "max" to sync_max, mdmon will monitor process
+and switch reshape to next array. At this moment we have got information
+inconsistency between metadata and migration record.
+To avoid this, clear migration record by mdmon /exception from the rule
+that migration record is maintained by mdadm/ when reshape switches
+to next array.
+
+Signed-off-by: Adam Kwolek <adam.kwolek@intel.com>
+Signed-off-by: NeilBrown <neilb@suse.de>
+---
+ super-intel.c |   19 ++++++++++++++++---
+ 1 files changed, 16 insertions(+), 3 deletions(-)
+
+diff --git a/super-intel.c b/super-intel.c
+index 5f451f3..958edb5 100644
+--- a/super-intel.c
++++ b/super-intel.c
+@@ -353,6 +353,9 @@ struct intel_super {
+ 		void *migr_rec_buf; /* buffer for I/O operations */
+ 		struct migr_record *migr_rec; /* migration record */
+ 	};
++	int clean_migration_record_by_mdmon; /* when reshape is switched to next
++		array, it indicates that mdmon is allowed to clean migration
++		record */
+ 	size_t len; /* size of the 'buf' allocation */
+ 	void *next_buf; /* for realloc'ing buf from the manager */
+ 	size_t next_len;
+@@ -3465,6 +3468,7 @@ static int load_imsm_mpb(int fd, struct intel_super *super, char *devname)
+ 		free(super->buf);
+ 		return 2;
+ 	}
++	super->clean_migration_record_by_mdmon = 0;
+ 
+ 	if (!sectors) {
+ 		check_sum = __gen_imsm_checksum(super->anchor);
+@@ -5029,6 +5033,10 @@ static int write_super_imsm(struct supertype *st, int doclose)
+ 	sum = __gen_imsm_checksum(mpb);
+ 	mpb->check_sum = __cpu_to_le32(sum);
+ 
++	if (super->clean_migration_record_by_mdmon) {
++		clear_migration_record = 1;
++		super->clean_migration_record_by_mdmon = 0;
++	}
+ 	if (clear_migration_record)
+ 		memset(super->migr_rec_buf, 0, MIGR_REC_BUF_SIZE);
+ 
+@@ -5036,9 +5044,6 @@ static int write_super_imsm(struct supertype *st, int doclose)
+ 	for (d = super->disks; d ; d = d->next) {
+ 		if (d->index < 0 || is_failed(&d->disk))
+ 			continue;
+-		if (store_imsm_mpb(d->fd, mpb))
+-			fprintf(stderr, "%s: failed for device %d:%d (fd: %d)%s\n",
+-				__func__, d->major, d->minor, d->fd, strerror(errno));
+ 
+ 		if (clear_migration_record) {
+ 			unsigned long long dsize;
+@@ -5050,6 +5055,13 @@ static int write_super_imsm(struct supertype *st, int doclose)
+ 					perror("Write migr_rec failed");
+ 			}
+ 		}
++
++		if (store_imsm_mpb(d->fd, mpb))
++			fprintf(stderr,
++				"%s: failed for device %d:%d (fd: %d)%s\n",
++				__func__, d->major, d->minor,
++				d->fd, strerror(errno));
++
+ 		if (doclose) {
+ 			close(d->fd);
+ 			d->fd = -1;
+@@ -6928,6 +6940,7 @@ static void imsm_progress_container_reshape(struct intel_super *super)
+ 		map2->num_members = prev_num_members;
+ 
+ 		imsm_set_array_size(dev);
++		super->clean_migration_record_by_mdmon = 1;
+ 		super->updates_pending++;
+ 	}
+ }
+-- 
+1.7.4.4
+

mdadm-3.2.3-imsm-FIX-No-new-missing-disks-are-allowed-during-gen.patch

@@ -0,0 +1,44 @@
+From d2bde6d3aa9468ddf0965f09907a666b92186e42 Mon Sep 17 00:00:00 2001
+From: Adam Kwolek <adam.kwolek@intel.com>
+Date: Tue, 7 Feb 2012 15:03:11 +0100
+Subject: [PATCH 02/12] imsm: FIX: No new missing disks are allowed during
+ general migration
+
+When during incremental assembly general migration is in progress,
+starting degraded array causes that no more disks (even present)
+can be added later as array is already started.
+
+Request all previously present disks during general migration for assembly.
+
+Signed-off-by: Adam Kwolek <adam.kwolek@intel.com>
+Signed-off-by: NeilBrown <neilb@suse.de>
+---
+ super-intel.c |   12 +++++++++++-
+ 1 files changed, 11 insertions(+), 1 deletions(-)
+
+diff --git a/super-intel.c b/super-intel.c
+index eba11d6..17034bb 100644
+--- a/super-intel.c
++++ b/super-intel.c
+@@ -2683,7 +2683,17 @@ static void getinfo_super_imsm(struct supertype *st, struct mdinfo *info, char *
+ 			enough = 0;
+ 		else /* we're normal, or already degraded */
+ 			enough = 1;
+-
++		if (is_gen_migration(dev) && missing) {
++			/* during general migration we need all disks
++			 * that process is running on.
++			 * No new missing disk is allowed.
++			 */
++			max_enough = -1;
++			enough = -1;
++			/* no more checks necessary
++			 */
++			break;
++		}
+ 		/* in the missing/failed disk case check to see
+ 		 * if at least one array is runnable
+ 		 */
+-- 
+1.7.4.4
+

mdadm-3.2.3-imsm-FIX-imsm_get_allowed_degradation-doesn-t-count-.patch

@@ -0,0 +1,29 @@
+From bf5cf7c705f292a070746c83f9dd00d7662f458d Mon Sep 17 00:00:00 2001
+From: Adam Kwolek <adam.kwolek@intel.com>
+Date: Tue, 7 Feb 2012 15:03:27 +0100
+Subject: [PATCH 04/12] imsm: FIX: imsm_get_allowed_degradation() doesn't
+ count degradation for raid1
+
+Missing case raid1 added to function.
+
+Signed-off-by: Adam Kwolek <adam.kwolek@intel.com>
+Signed-off-by: NeilBrown <neilb@suse.de>
+---
+ super-intel.c |    1 +
+ 1 files changed, 1 insertions(+), 0 deletions(-)
+
+diff --git a/super-intel.c b/super-intel.c
+index 17034bb..19a2c84 100644
+--- a/super-intel.c
++++ b/super-intel.c
+@@ -8771,6 +8771,7 @@ static int imsm_get_allowed_degradation(int level, int raid_disks,
+ 					struct imsm_dev *dev)
+ {
+ 	switch (level) {
++	case 1:
+ 	case 10:{
+ 		int ret_val = 0;
+ 		struct imsm_map *map;
+-- 
+1.7.4.4
+

mdadm-3.2.3-imsm-FIX-use-md-position-to-reshape-restart.patch

@@ -0,0 +1,43 @@
+From 6a75c8ca79b4cf89a5d1ac24b484b75e8a7e9fb4 Mon Sep 17 00:00:00 2001
+From: Adam Kwolek <adam.kwolek@intel.com>
+Date: Thu, 9 Feb 2012 12:36:42 +1100
+Subject: [PATCH 09/12] imsm: FIX: use md position to reshape restart
+
+When reshape is broken it can occur that metadata is not saved properly.
+This can cause that reshape process is farther in md than metadata states.
+
+On restart save checkpoint to store current position /probably farther/
+that can be read from md.
+
+Signed-off-by: Adam Kwolek <adam.kwolek@intel.com>
+Signed-off-by: NeilBrown <neilb@suse.de>
+---
+ super-intel.c |   12 ++++++++++++
+ 1 files changed, 12 insertions(+), 0 deletions(-)
+
+diff --git a/super-intel.c b/super-intel.c
+index f5762d8..5f451f3 100644
+--- a/super-intel.c
++++ b/super-intel.c
+@@ -10067,6 +10067,18 @@ static int imsm_manage_reshape(
+ 				"are present in copy area.\n");
+ 			goto abort;
+ 		}
++		/* Save checkpoint to update migration record for current
++		 * reshape position (in md). It can be farther than current
++		 * reshape position in metadata.
++		 */
++		if (save_checkpoint_imsm(st, sra, UNIT_SRC_NORMAL) == 1) {
++			/* ignore error == 2, this can mean end of reshape here
++			 */
++			dprintf("imsm: Cannot write checkpoint to "
++				"migration record (UNIT_SRC_NORMAL, "
++				"initial save)\n");
++			goto abort;
++		}
+ 	}
+ 
+ 	/* size for data */
+-- 
+1.7.4.4
+

mdadm-3.2.3-imsm-display-fd-in-error-trace-when-when-store_imsm_.patch

@@ -0,0 +1,31 @@
+From 30602f533f151c24fe1345f495f02c30f98895f1 Mon Sep 17 00:00:00 2001
+From: Labun, Marcin <Marcin.Labun@intel.com>
+Date: Mon, 30 Jan 2012 12:00:43 +1100
+Subject: [PATCH] imsm: display fd in error trace when when store_imsm_mpb
+ failes
+
+Signed-off-by: Marcin Labun <marcin.labun@intel.com>
+Signed-off-by: NeilBrown <neilb@suse.de>
+---
+ super-intel.c |    5 +++--
+ 1 files changed, 3 insertions(+), 2 deletions(-)
+
+diff --git a/super-intel.c b/super-intel.c
+index 7db5177..8d67a14 100644
+--- a/super-intel.c
++++ b/super-intel.c
+@@ -5027,8 +5027,9 @@ static int write_super_imsm(struct supertype *st, int doclose)
+ 		if (d->index < 0 || is_failed(&d->disk))
+ 			continue;
+ 		if (store_imsm_mpb(d->fd, mpb))
+-			fprintf(stderr, "%s: failed for device %d:%d %s\n",
+-				__func__, d->major, d->minor, strerror(errno));
++			fprintf(stderr, "%s: failed for device %d:%d (fd: %d)%s\n",
++				__func__, d->major, d->minor, d->fd, strerror(errno));
++
+ 		if (clear_migration_record) {
+ 			unsigned long long dsize;
+ 
+-- 
+1.7.4.4
+

mdadm.spec

@@ -1,7 +1,7 @@
 Summary:     The mdadm program controls Linux md devices (software RAID arrays)
 Name:        mdadm
 Version:     3.2.3
-Release:     7%{?dist}
+Release:     8%{?dist}
 Source:      http://www.kernel.org/pub/linux/utils/raid/mdadm/mdadm-%{version}.tar.bz2
 Source1:     mdmonitor.init
 Source2:     raid-check
@@ -22,8 +22,24 @@ Patch8:	     mdadm-3.2.3-super1-make-aread-awrite-always-use-an-aligned-buffe.pa
 Patch9:	     mdadm-3.2.3-avoid-double-free-upon-old-buggy-kernel-sysfs_read-f.patch
 Patch10:     mdadm-3.2.3-Print-error-message-if-failing-to-write-super-for-1..patch
 Patch11:     mdadm-3.2.3-Incremental-fix-adding-devices-with-incremental.patch
-Patch19:     mdadm-3.2.3-udev.patch
+Patch12:     mdadm-3.2.3-FIX-External-metadata-sometimes-is-not-updated.patch
-Patch20:     mdadm-2.5.2-static.patch
+Patch13:     mdadm-3.2.3-FIX-mdmon-check-in-reshape_container-can-cause-a-pro.patch
+Patch14:     mdadm-3.2.3-imsm-display-fd-in-error-trace-when-when-store_imsm_.patch
+Patch15:     mdadm-3.2.3-FIX-NULL-pointer-to-strdup-can-be-passed.patch
+Patch16:     mdadm-3.2.3-imsm-FIX-No-new-missing-disks-are-allowed-during-gen.patch
+Patch17:     mdadm-3.2.3-FIX-Array-is-not-run-when-expansion-disks-are-added.patch
+Patch18:     mdadm-3.2.3-imsm-FIX-imsm_get_allowed_degradation-doesn-t-count-.patch
+Patch19:     mdadm-3.2.3-Fix-Sometimes-mdmon-throws-core-dump-during-reshape.patch
+Patch20:     mdadm-3.2.3-Flush-mdmon-before-next-reshape-step-during-containe.patch
+Patch21:     mdadm-3.2.3-imsm-FIX-Chunk-size-migration-problem.patch
+Patch22:     mdadm-3.2.3-FIX-use-md-position-to-reshape-restart.patch
+Patch23:     mdadm-3.2.3-imsm-FIX-use-md-position-to-reshape-restart.patch
+Patch24:     mdadm-3.2.3-imsm-FIX-Clear-migration-record-when-migration-switc.patch
+Patch25:     mdadm-3.2.3-FIX-restart-reshape-when-reshape-process-is-stopped-.patch
+Patch26:     mdadm-3.2.3-FIX-Do-not-try-to-continue-reshape-using-inactive-ar.patch
+Patch27:     mdadm-3.2.3-FIX-Changes-in-0-case-for-reshape-position-verificat.patch
+Patch98:     mdadm-3.2.3-udev.patch
+Patch99:     mdadm-2.5.2-static.patch
 URL:         http://www.kernel.org/pub/linux/utils/raid/mdadm/
 License:     GPLv2+
 Group:       System Environment/Base
@@ -67,8 +83,26 @@ is not used as the system init process.
 %patch9 -p1 -b .double
 %patch10 -p1 -b .print
 %patch11 -p1 -b .incremental
-%patch19 -p1 -b .udev
+%patch12 -p1 -b .update
-%patch20 -p1 -b .static
+%patch13 -p1 -b .mdmon
+%patch14 -p1 -b .display
+%patch15 -p1 -b .strdup
+%patch16 -p1 -b .missing
+%patch17 -p1 -b .exp
+%patch18 -p1 -b .allowed
+%patch19 -p1 -b .core
+%patch20 -p1 -b .flush
+%patch21 -p1 -b .chunk
+%patch22 -p1 -b .position
+%patch23 -p1 -b .reshape
+%patch24 -p1 -b .record
+%patch25 -p1 -b .restart
+%patch26 -p1 -b .nocontinue
+%patch27 -p1 -b .0case
+
+# Fedora customization patches
+%patch98 -p1 -b .udev
+%patch99 -p1 -b .static
 
 %build
 make %{?_smp_mflags} CXFLAGS="$RPM_OPT_FLAGS" SYSCONFDIR="%{_sysconfdir}" mdadm mdmon
@@ -141,6 +175,11 @@ fi
 %{_initrddir}/*
 
 %changelog
+* Mon Apr 30 2012 Jes Sorensen <Jes.Sorensen@redhat.com> - 3.2.3-8
+- Fix bug where IMSM arrays stay inactive in case a reboot is
+- performed during the reshape process.
+- Resolves: bz817522 (f17) bz817535 (f16) bz817537 (f15)
+
 * Wed Mar 28 2012 Jes Sorensen <Jes.Sorensen@redhat.com> - 3.2.3-7
 - Fix issue when re-adding drive to a raid1 array with bitmap
 - Resolves: bz807743 (f17) bz769323 (f16) bz791159 (f15)