1 files changed, 129 insertions, 9 deletions

diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index a09bdc000e64..114927da9cc9 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -26,6 +26,8 @@
 #define AUTOCOMMIT_BLOCKS_SSD		65536
 #define AUTOCOMMIT_BLOCKS_PMEM		64
 #define AUTOCOMMIT_MSEC			1000
+#define MAX_AGE_DIV			16
+#define MAX_AGE_UNSPECIFIED		-1UL
 
 #define BITMAP_GRANULARITY	65536
 #if BITMAP_GRANULARITY < PAGE_SIZE
@@ -88,6 +90,7 @@ struct wc_entry {
 		:47
 #endif
 	;
+	unsigned long age;
 #ifdef DM_WRITECACHE_HANDLE_HARDWARE_ERRORS
 	uint64_t original_sector;
 	uint64_t seq_count;
@@ -119,6 +122,7 @@ struct dm_writecache {
 	size_t writeback_size;
 	size_t freelist_high_watermark;
 	size_t freelist_low_watermark;
+	unsigned long max_age;
 
 	unsigned uncommitted_blocks;
 	unsigned autocommit_blocks;
@@ -130,6 +134,8 @@ struct dm_writecache {
 	struct timer_list autocommit_timer;
 	struct wait_queue_head freelist_wait;
 
+	struct timer_list max_age_timer;
+
 	atomic_t bio_in_progress[2];
 	struct wait_queue_head bio_in_progress_wait[2];
 
@@ -160,6 +166,7 @@ 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;
@@ -502,6 +509,34 @@ static void ssd_commit_flushed(struct dm_writecache *wc, bool wait_for_ios)
 	memset(wc->dirty_bitmap, 0, wc->dirty_bitmap_size);
 }
 
+static void ssd_commit_superblock(struct dm_writecache *wc)
+{
+	int r;
+	struct dm_io_region region;
+	struct dm_io_request req;
+
+	region.bdev = wc->ssd_dev->bdev;
+	region.sector = 0;
+	region.count = PAGE_SIZE;
+
+	if (unlikely(region.sector + region.count > wc->metadata_sectors))
+		region.count = wc->metadata_sectors - region.sector;
+
+	region.sector += wc->start_sector;
+
+	req.bi_op = REQ_OP_WRITE;
+	req.bi_op_flags = REQ_SYNC | REQ_FUA;
+	req.mem.type = DM_IO_VMA;
+	req.mem.ptr.vma = (char *)wc->memory_map;
+	req.client = wc->dm_io;
+	req.notify.fn = NULL;
+	req.notify.context = NULL;
+
+	r = dm_io(&req, 1, &region, NULL);
+	if (unlikely(r))
+		writecache_error(wc, r, "error writing superblock");
+}
+
 static void writecache_commit_flushed(struct dm_writecache *wc, bool wait_for_ios)
 {
 	if (WC_MODE_PMEM(wc))
@@ -596,6 +631,7 @@ static void writecache_insert_entry(struct dm_writecache *wc, struct wc_entry *i
 	rb_link_node(&ins->rb_node, parent, node);
 	rb_insert_color(&ins->rb_node, &wc->tree);
 	list_add(&ins->lru, &wc->lru);
+	ins->age = jiffies;
 }
 
 static void writecache_unlink(struct dm_writecache *wc, struct wc_entry *e)
@@ -631,6 +667,16 @@ static inline void writecache_verify_watermark(struct dm_writecache *wc)
 		queue_work(wc->writeback_wq, &wc->writeback_work);
 }
 
+static void writecache_max_age_timer(struct timer_list *t)
+{
+	struct dm_writecache *wc = from_timer(wc, t, max_age_timer);
+
+	if (!dm_suspended(wc->ti) && !writecache_has_error(wc)) {
+		queue_work(wc->writeback_wq, &wc->writeback_work);
+		mod_timer(&wc->max_age_timer, jiffies + wc->max_age / MAX_AGE_DIV);
+	}
+}
+
 static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc, sector_t expected_sector)
 {
 	struct wc_entry *e;
@@ -741,8 +787,10 @@ static void writecache_flush(struct dm_writecache *wc)
 
 	wc->seq_count++;
 	pmem_assign(sb(wc)->seq_count, cpu_to_le64(wc->seq_count));
-	writecache_flush_region(wc, &sb(wc)->seq_count, sizeof sb(wc)->seq_count);
-	writecache_commit_flushed(wc, false);
+	if (WC_MODE_PMEM(wc))
+		writecache_commit_flushed(wc, false);
+	else
+		ssd_commit_superblock(wc);
 
 	wc->overwrote_committed = false;
 
@@ -837,6 +885,7 @@ static void writecache_suspend(struct dm_target *ti)
 	bool flush_on_suspend;
 
 	del_timer_sync(&wc->autocommit_timer);
+	del_timer_sync(&wc->max_age_timer);
 
 	wc_lock(wc);
 	writecache_flush(wc);
@@ -876,6 +925,7 @@ static int writecache_alloc_entries(struct dm_writecache *wc)
 		struct wc_entry *e = &wc->entries[b];
 		e->index = b;
 		e->write_in_progress = false;
+		cond_resched();
 	}
 
 	return 0;
@@ -930,6 +980,7 @@ static void writecache_resume(struct dm_target *ti)
 			e->original_sector = le64_to_cpu(wme.original_sector);
 			e->seq_count = le64_to_cpu(wme.seq_count);
 		}
+		cond_resched();
 	}
 #endif
 	for (b = 0; b < wc->n_blocks; b++) {
@@ -973,6 +1024,9 @@ erase_this:
 
 	writecache_verify_watermark(wc);
 
+	if (wc->max_age != MAX_AGE_UNSPECIFIED)
+		mod_timer(&wc->max_age_timer, jiffies + wc->max_age / MAX_AGE_DIV);
+
 	wc_unlock(wc);
 }
 
@@ -1021,6 +1075,28 @@ 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 +1107,8 @@ 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]);
 
@@ -1194,6 +1272,7 @@ read_next_block:
 		}
 	} else {
 		do {
+			bool found_entry = false;
 			if (writecache_has_error(wc))
 				goto unlock_error;
 			e = writecache_find_entry(wc, bio->bi_iter.bi_sector, 0);
@@ -1204,9 +1283,25 @@ read_next_block:
 					wc->overwrote_committed = true;
 					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;
+						BUG_ON(!next_boundary);
+						if (next_boundary < bio->bi_iter.bi_size >> SECTOR_SHIFT) {
+							dm_accept_partial_bio(bio, next_boundary);
+						}
+					}
+					goto unlock_remap_origin;
+				}
 				writecache_wait_on_freelist(wc);
 				continue;
 			}
@@ -1619,7 +1714,9 @@ restart:
 	wbl.size = 0;
 	while (!list_empty(&wc->lru) &&
 	       (wc->writeback_all ||
-		wc->freelist_size + wc->writeback_size <= wc->freelist_low_watermark)) {
+		wc->freelist_size + wc->writeback_size <= wc->freelist_low_watermark ||
+		(jiffies - container_of(wc->lru.prev, struct wc_entry, lru)->age >=
+		 wc->max_age - wc->max_age / MAX_AGE_DIV))) {
 
 		n_walked++;
 		if (unlikely(n_walked > WRITEBACK_LATENCY) &&
@@ -1791,8 +1888,10 @@ static int init_memory(struct dm_writecache *wc)
 	pmem_assign(sb(wc)->n_blocks, cpu_to_le64(wc->n_blocks));
 	pmem_assign(sb(wc)->seq_count, cpu_to_le64(0));
 
-	for (b = 0; b < wc->n_blocks; b++)
+	for (b = 0; b < wc->n_blocks; b++) {
 		write_original_sector_seq_count(wc, &wc->entries[b], -1, -1);
+		cond_resched();
+	}
 
 	writecache_flush_all_metadata(wc);
 	writecache_commit_flushed(wc, false);
@@ -1882,9 +1981,11 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	wc->ti = ti;
 
 	mutex_init(&wc->lock);
+	wc->max_age = MAX_AGE_UNSPECIFIED;
 	writecache_poison_lists(wc);
 	init_waitqueue_head(&wc->freelist_wait);
 	timer_setup(&wc->autocommit_timer, writecache_autocommit_timer, 0);
+	timer_setup(&wc->max_age_timer, writecache_max_age_timer, 0);
 
 	for (i = 0; i < 2; i++) {
 		atomic_set(&wc->bio_in_progress[i], 0);
@@ -2058,6 +2159,16 @@ 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, "max_age") && opt_params >= 1) {
+			unsigned max_age_msecs;
+			string = dm_shift_arg(&as), opt_params--;
+			if (sscanf(string, "%u%c", &max_age_msecs, &dummy) != 1)
+				goto invalid_optional;
+			if (max_age_msecs > 86400000)
+				goto invalid_optional;
+			wc->max_age = msecs_to_jiffies(max_age_msecs);
+		} else if (!strcasecmp(string, "cleaner")) {
+			wc->cleaner = true;
 		} else if (!strcasecmp(string, "fua")) {
 			if (WC_MODE_PMEM(wc)) {
 				wc->writeback_fua = true;
@@ -2235,6 +2346,9 @@ overflow:
 	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";
@@ -2278,9 +2392,9 @@ 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;
@@ -2288,19 +2402,21 @@ 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);
@@ -2312,6 +2428,10 @@ 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->max_age != MAX_AGE_UNSPECIFIED)
+			DMEMIT(" max_age %u", jiffies_to_msecs(wc->max_age));
+		if (wc->cleaner)
+			DMEMIT(" cleaner");
 		if (wc->writeback_fua_set)
 			DMEMIT(" %sfua", wc->writeback_fua ? "" : "no");
 		break;
@@ -2320,7 +2440,7 @@ 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,