From 12724c018c964596aa277489fd287d5c3506361a Mon Sep 17 00:00:00 2001
From: Tkaczyk Mariusz <mariusz.tkaczyk@intel.com>
Date: Fri, 17 Apr 2020 13:55:55 +0200
Subject: [RHEL7.9 PATCH 70/71] Manage, imsm: Write metadata before add

New drive in container always appears as spare. Manager is able to
handle that, and queues appropriative update to monitor.
No update from mdadm side has to be processed, just insert the drive and
ping the mdmon. Metadata has to be written if no mdmon is running (case
for Raid0 or container without arrays).

If bare drive is added very early on startup (by custom bare rule),
there is possiblity that mdmon was not restarted after switch root. Old
one is not able to handle new drive. New one fails because there is
drive without metadata in container and metadata cannot be loaded.

To prevent this, write spare metadata before adding device
to container. Mdmon will overwrite it (same case as spare migration,
if drive appears it writes the most recent metadata).
Metadata has to be written only on new drive before sysfs_add_disk(),
don't race with mdmon if running.

Signed-off-by: Tkaczyk Mariusz <mariusz.tkaczyk@intel.com>
Signed-off-by: Jes Sorensen <jsorensen@fb.com>
---
 Manage.c      |  6 +-----
 super-intel.c | 66 ++++++++++++++++++++++++++++++++++++++---------------------
 2 files changed, 44 insertions(+), 28 deletions(-)

diff --git a/Manage.c b/Manage.c
index b22c396..0a5f09b 100644
--- a/Manage.c
+++ b/Manage.c
@@ -994,17 +994,13 @@ int Manage_add(int fd, int tfd, struct mddev_dev *dv,
 
 		Kill(dv->devname, NULL, 0, -1, 0);
 		dfd = dev_open(dv->devname, O_RDWR | O_EXCL|O_DIRECT);
-		if (mdmon_running(tst->container_devnm))
-			tst->update_tail = &tst->updates;
 		if (tst->ss->add_to_super(tst, &disc, dfd,
 					  dv->devname, INVALID_SECTORS)) {
 			close(dfd);
 			close(container_fd);
 			return -1;
 		}
-		if (tst->update_tail)
-			flush_metadata_updates(tst);
-		else
+		if (!mdmon_running(tst->container_devnm))
 			tst->ss->sync_metadata(tst);
 
 		sra = sysfs_read(container_fd, NULL, 0);
diff --git a/super-intel.c b/super-intel.c
index 562a58c..3a73d2b 100644
--- a/super-intel.c
+++ b/super-intel.c
@@ -5809,6 +5809,9 @@ int mark_spare(struct dl *disk)
 	return ret_val;
 }
 
+
+static int write_super_imsm_spare(struct intel_super *super, struct dl *d);
+
 static int add_to_super_imsm(struct supertype *st, mdu_disk_info_t *dk,
 			     int fd, char *devname,
 			     unsigned long long data_offset)
@@ -5938,9 +5941,13 @@ static int add_to_super_imsm(struct supertype *st, mdu_disk_info_t *dk,
 		dd->next = super->disk_mgmt_list;
 		super->disk_mgmt_list = dd;
 	} else {
+		/* this is called outside of mdmon
+		 * write initial spare metadata
+		 * mdmon will overwrite it.
+		 */
 		dd->next = super->disks;
 		super->disks = dd;
-		super->updates_pending++;
+		write_super_imsm_spare(super, dd);
 	}
 
 	return 0;
@@ -5979,15 +5986,15 @@ static union {
 	struct imsm_super anchor;
 } spare_record __attribute__ ((aligned(MAX_SECTOR_SIZE)));
 
-/* spare records have their own family number and do not have any defined raid
- * devices
- */
-static int write_super_imsm_spares(struct intel_super *super, int doclose)
+
+static int write_super_imsm_spare(struct intel_super *super, struct dl *d)
 {
 	struct imsm_super *mpb = super->anchor;
 	struct imsm_super *spare = &spare_record.anchor;
 	__u32 sum;
-	struct dl *d;
+
+	if (d->index != -1)
+		return 1;
 
 	spare->mpb_size = __cpu_to_le32(sizeof(struct imsm_super));
 	spare->generation_num = __cpu_to_le32(1UL);
@@ -6000,28 +6007,41 @@ static int write_super_imsm_spares(struct intel_super *super, int doclose)
 	snprintf((char *) spare->sig, MAX_SIGNATURE_LENGTH,
 		 MPB_SIGNATURE MPB_VERSION_RAID0);
 
-	for (d = super->disks; d; d = d->next) {
-		if (d->index != -1)
-			continue;
+	spare->disk[0] = d->disk;
+	if (__le32_to_cpu(d->disk.total_blocks_hi) > 0)
+		spare->attributes |= MPB_ATTRIB_2TB_DISK;
 
-		spare->disk[0] = d->disk;
-		if (__le32_to_cpu(d->disk.total_blocks_hi) > 0)
-			spare->attributes |= MPB_ATTRIB_2TB_DISK;
+	if (super->sector_size == 4096)
+		convert_to_4k_imsm_disk(&spare->disk[0]);
 
-		if (super->sector_size == 4096)
-			convert_to_4k_imsm_disk(&spare->disk[0]);
+	sum = __gen_imsm_checksum(spare);
+	spare->family_num = __cpu_to_le32(sum);
+	spare->orig_family_num = 0;
+	sum = __gen_imsm_checksum(spare);
+	spare->check_sum = __cpu_to_le32(sum);
 
-		sum = __gen_imsm_checksum(spare);
-		spare->family_num = __cpu_to_le32(sum);
-		spare->orig_family_num = 0;
-		sum = __gen_imsm_checksum(spare);
-		spare->check_sum = __cpu_to_le32(sum);
+	if (store_imsm_mpb(d->fd, spare)) {
+		pr_err("failed for device %d:%d %s\n",
+			d->major, d->minor, strerror(errno));
+		return 1;
+	}
+
+	return 0;
+}
+/* spare records have their own family number and do not have any defined raid
+ * devices
+ */
+static int write_super_imsm_spares(struct intel_super *super, int doclose)
+{
+	struct dl *d;
+
+	for (d = super->disks; d; d = d->next) {
+		if (d->index != -1)
+			continue;
 
-		if (store_imsm_mpb(d->fd, spare)) {
-			pr_err("failed for device %d:%d %s\n",
-				d->major, d->minor, strerror(errno));
+		if (write_super_imsm_spare(super, d))
 			return 1;
-		}
+
 		if (doclose) {
 			close(d->fd);
 			d->fd = -1;
-- 
2.7.5