From: Mikulas Patocka <mpatocka@redhat.com>
Date: Mon, 24 Feb 2020 10:20:32 +0100
Subject: [PATCH] dm writecache: implement the "cleaner" policy
Git-commit: 93de44eb3fc8c3566f5315b0210630cc361526a7
Patch-mainline: v5.7-rc1
References: bsc#1175995,jsc#SLE-15608

The "flush" or "flush_on_suspend" messages flush the whole cache. However,
these flushing methods can take some time and the process is left in
an interruptible state during the flush.

Implement a "cleaner" option that offers an alternate flushing method.
When this option is activated (either by a message or in the constructor
arguments), the cache will not promote new writes (however, writes to
already cached blocks are promoted, to avoid data corruption due to
misordered writes) and it will gradually writeback any cached data. The
userspace can then monitor the cleaning process with "dmsetup status".
When the number of cached bloks drops to zero, the userspace can unload
the dm-writecache target and replace it with dm-linear or other targets.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Hannes Reinecke <hare@suse.com>
---
 drivers/md/dm-writecache.c | 48 +++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 43 insertions(+), 5 deletions(-)

diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index dc1e10c6ecd7..3f17dcc6b73e 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -160,6 +160,7 @@ struct dm_writecache {
 	bool autocommit_time_set:1;
 	bool writeback_fua_set:1;
 	bool flush_on_suspend:1;
+	bool cleaner:1;
 
 	unsigned writeback_all;
 	struct workqueue_struct *writeback_wq;
@@ -1021,6 +1022,28 @@ static int process_flush_on_suspend_mesg(unsigned argc, char **argv, struct dm_w
 	return 0;
 }
 
+static void activate_cleaner(struct dm_writecache *wc)
+{
+	wc->flush_on_suspend = true;
+	wc->cleaner = true;
+	wc->freelist_high_watermark = wc->n_blocks;
+	wc->freelist_low_watermark = wc->n_blocks;
+}
+
+static int process_cleaner_mesg(unsigned argc, char **argv, struct dm_writecache *wc)
+{
+	if (argc != 1)
+		return -EINVAL;
+
+	wc_lock(wc);
+	activate_cleaner(wc);
+	if (!dm_suspended(wc->ti))
+		writecache_verify_watermark(wc);
+	wc_unlock(wc);
+
+	return 0;
+}
+
 static int writecache_message(struct dm_target *ti, unsigned argc, char **argv,
 			      char *result, unsigned maxlen)
 {
@@ -1031,6 +1054,8 @@ static int writecache_message(struct dm_target *ti, unsigned argc, char **argv,
 		r = process_flush_mesg(argc, argv, wc);
 	else if (!strcasecmp(argv[0], "flush_on_suspend"))
 		r = process_flush_on_suspend_mesg(argc, argv, wc);
+	else if (!strcasecmp(argv[0], "cleaner"))
+		r = process_cleaner_mesg(argc, argv, wc);
 	else
 		DMERR("unrecognised message received: %s", argv[0]);
 
@@ -1206,10 +1231,14 @@ static int writecache_map(struct dm_target *ti, struct bio *bio)
 					goto bio_copy;
 				}
 				found_entry = true;
+			} else {
+				if (unlikely(wc->cleaner))
+					goto direct_write;
 			}
 			e = writecache_pop_from_freelist(wc, (sector_t)-1);
 			if (unlikely(!e)) {
 				if (!found_entry) {
+direct_write:
 					e = writecache_find_entry(wc, bio->bi_iter.bi_sector, WFE_RETURN_FOLLOWING);
 					if (e) {
 						sector_t next_boundary = read_original_sector(wc, e) - bio->bi_iter.bi_sector;
@@ -2071,6 +2100,8 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
 				goto invalid_optional;
 			wc->autocommit_jiffies = msecs_to_jiffies(autocommit_msecs);
 			wc->autocommit_time_set = true;
+		} else if (!strcasecmp(string, "cleaner")) {
+			wc->cleaner = true;
 		} else if (!strcasecmp(string, "fua")) {
 			if (WC_MODE_PMEM(wc)) {
 				wc->writeback_fua = true;
@@ -2248,6 +2279,9 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	do_div(x, 100);
 	wc->freelist_low_watermark = x;
 
+	if (wc->cleaner)
+		activate_cleaner(wc);
+
 	r = writecache_alloc_entries(wc);
 	if (r) {
 		ti->error = "Cannot allocate memory";
@@ -2291,9 +2325,9 @@ static void writecache_status(struct dm_target *ti, status_type_t type,
 		extra_args = 0;
 		if (wc->start_sector)
 			extra_args += 2;
-		if (wc->high_wm_percent_set)
+		if (wc->high_wm_percent_set && !wc->cleaner)
 			extra_args += 2;
-		if (wc->low_wm_percent_set)
+		if (wc->low_wm_percent_set && !wc->cleaner)
 			extra_args += 2;
 		if (wc->max_writeback_jobs_set)
 			extra_args += 2;
@@ -2301,19 +2335,21 @@ static void writecache_status(struct dm_target *ti, status_type_t type,
 			extra_args += 2;
 		if (wc->autocommit_time_set)
 			extra_args += 2;
+		if (wc->cleaner)
+			extra_args++;
 		if (wc->writeback_fua_set)
 			extra_args++;
 
 		DMEMIT("%u", extra_args);
 		if (wc->start_sector)
 			DMEMIT(" start_sector %llu", (unsigned long long)wc->start_sector);
-		if (wc->high_wm_percent_set) {
+		if (wc->high_wm_percent_set && !wc->cleaner) {
 			x = (uint64_t)wc->freelist_high_watermark * 100;
 			x += wc->n_blocks / 2;
 			do_div(x, (size_t)wc->n_blocks);
 			DMEMIT(" high_watermark %u", 100 - (unsigned)x);
 		}
-		if (wc->low_wm_percent_set) {
+		if (wc->low_wm_percent_set && !wc->cleaner) {
 			x = (uint64_t)wc->freelist_low_watermark * 100;
 			x += wc->n_blocks / 2;
 			do_div(x, (size_t)wc->n_blocks);
@@ -2325,6 +2361,8 @@ static void writecache_status(struct dm_target *ti, status_type_t type,
 			DMEMIT(" autocommit_blocks %u", wc->autocommit_blocks);
 		if (wc->autocommit_time_set)
 			DMEMIT(" autocommit_time %u", jiffies_to_msecs(wc->autocommit_jiffies));
+		if (wc->cleaner)
+			DMEMIT(" cleaner");
 		if (wc->writeback_fua_set)
 			DMEMIT(" %sfua", wc->writeback_fua ? "" : "no");
 		break;
@@ -2333,7 +2371,7 @@ static void writecache_status(struct dm_target *ti, status_type_t type,
 
 static struct target_type writecache_target = {
 	.name			= "writecache",
-	.version		= {1, 2, 0},
+	.version		= {1, 3, 0},
 	.module			= THIS_MODULE,
 	.ctr			= writecache_ctr,
 	.dtr			= writecache_dtr,
-- 
2.16.4