The DM part of dm-raid45

445 lines not on this page · raw message

index d54f901..0e3922a 100644
@@ -17,6 +17,7 @@ struct raid_set {
 	struct dm_target *ti;
 	struct mddev_s md;
 	struct raid_type *raid_type;
+	struct target_callbacks callbacks;
 	struct raid_dev dev[0];
 };
 

@@ -146,6 +147,13 @@ static void do_table_event(struct work_struct *ws)
 	dm_table_event(rs->ti->table);
 }
 
+static int raid_is_congested(void *v, int bits)
+{
+	struct target_callbacks *cb = v;
+	struct raid_set *rs = container_of(cb, struct raid_set,
+					   callbacks);
+	return md_raid5_congested(&rs->md, bits);
+}
 /*
  * Construct a RAID4/5/6 mapping:
  * Args:

@@ -309,6 +317,10 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 
 	if (errnum)
 		goto err;
+
+	rs->callbacks.congested_fn = raid_is_congested;
+	dm_table_add_callbacks(ti->table, &rs->callbacks);
+
 	return 0;
 err:
 	if (rs)

@@ -321,6 +333,7 @@ static void raid_dtr(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
 
+	list_del_init(&rs->callbacks.list);
 	md_stop(&rs->md);
 	context_free(rs);
 }

index 9924ea2..b856340 100644
@@ -68,6 +68,8 @@ struct dm_table {
 	void (*event_fn)(void *);
 	void *event_context;
 
+	struct list_head target_callbacks;
+
 	struct dm_md_mempools *mempools;
 };
 

@@ -202,6 +204,7 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&t->devices);
+	INIT_LIST_HEAD(&t->target_callbacks);
 	atomic_set(&t->holders, 0);
 
 	if (!num_targets)

@@ -1174,10 +1177,18 @@ int dm_table_resume_targets(struct dm_table *t)
 	return 0;
 }
 
+void dm_table_add_callbacks(struct dm_table *t,
+			    struct target_callbacks *cb)
+{
+	list_add(&cb->list, &t->target_callbacks);
+}
+EXPORT_SYMBOL_GPL(dm_table_add_callbacks);
+
 int dm_table_any_congested(struct dm_table *t, int bdi_bits)
 {
 	struct dm_dev_internal *dd;
 	struct list_head *devices = dm_table_get_devices(t);
+	struct target_callbacks *cb;
 	int r = 0;
 
 	list_for_each_entry(dd, devices, list) {

@@ -1192,6 +1203,10 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits)
 				     bdevname(dd->dm_dev.bdev, b));
 	}
 
+	list_for_each_entry(cb, &t->target_callbacks, list)
+		if (cb->congested_fn)
+			r |= cb->congested_fn(cb, bdi_bits);
+
 	return r;
 }
 

index 1381cd9..2b0f538 100644
@@ -187,6 +187,12 @@ struct dm_target {
 	char *error;
 };
 
+/* Each target can link one of these into the table */
+struct target_callbacks {
+	struct list_head list;
+	congested_fn *congested_fn;
+};
+
 int dm_register_target(struct target_type *t);
 void dm_unregister_target(struct target_type *t);
 

@@ -263,6 +269,12 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 			sector_t start, sector_t len, char *params);
 
 /*
+ * Target_ctr should call this if they need to add any
+ * callback
+ */
+void dm_table_add_callbacks(struct dm_table *t,
+			    struct target_callbacks *cb);
+/*
  * Finally call this to make the table ready for use.
  */
 int dm_table_complete(struct dm_table *t);

index 0e3922a..47db9d4 100644
@@ -154,6 +154,14 @@ static int raid_is_congested(void *v, int bits)
 					   callbacks);
 	return md_raid5_congested(&rs->md, bits);
 }
+static void raid_unplug(void *v)
+{
+	struct target_callbacks *cb = v;
+	struct raid_set *rs = container_of(cb, struct raid_set,
+					   callbacks);
+	md_raid5_unplug_device(rs->md.private);
+}
+
 /*
  * Construct a RAID4/5/6 mapping:
  * Args:

@@ -289,6 +297,7 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 			goto err;
 		clear_bit(In_sync, &rs->dev[rebuildA].rdev.flags);
 		rs->dev[rebuildA].rdev.recovery_offset = 0;
+	rs->callbacks.unplug_fn = raid_unplug;
 	}
 	if (rebuildB >= 0) {
 		if (rs->dev[rebuildB].dev == NULL)

index b856340..cad4992 100644
@@ -1228,6 +1228,7 @@ void dm_table_unplug_all(struct dm_table *t)
 {
 	struct dm_dev_internal *dd;
 	struct list_head *devices = dm_table_get_devices(t);
+	struct target_callbacks *cb;
 
 	list_for_each_entry(dd, devices, list) {
 		struct request_queue *q = bdev_get_queue(dd->dm_dev.bdev);

@@ -1240,6 +1241,9 @@ void dm_table_unplug_all(struct dm_table *t)
 				     dm_device_name(t->md),
 				     bdevname(dd->dm_dev.bdev, b));
 	}
+	list_for_each_entry(cb, &t->target_callbacks, list)
+		if (cb->unplug_fn)
+			cb->unplug_fn(cb);
 }
 
 struct mapped_device *dm_table_get_md(struct dm_table *t)

index 2b0f538..5b8ac19 100644
@@ -191,6 +191,7 @@ struct dm_target {
 struct target_callbacks {
 	struct list_head list;
 	congested_fn *congested_fn;
+	void (*unplug_fn)(void *);
 };
 
 int dm_register_target(struct target_type *t);

index 47db9d4..4ffd654 100644
@@ -435,6 +435,37 @@ static int raid_status(struct dm_target *ti, status_type_t type,
 	return 0;
 }
 
+static int raid_iterate_devices(struct dm_target *ti,
+				iterate_devices_callout_fn fn,
+				void *data)
+{
+	struct raid_set *rs = ti->private;
+	int ret = 0;
+	unsigned i = 0;
+
+	for (i = 0; !ret && i < rs->md.raid_disks; i++)
+		if (rs->dev[i].dev)
+			ret = fn(ti,
+				 rs->dev[i].dev,
+				 rs->dev[i].rdev.data_offset,
+				 rs->md.dev_sectors,
+				 data);
+
+	return ret;
+}
+
+static void raid_io_hints(struct dm_target *ti,
+			  struct queue_limits *limits)
+{
+	struct raid_set *rs = ti->private;
+	unsigned chunk_size = rs->md.chunk_sectors << 9;
+	raid5_conf_t *conf = rs->md.private;
+
+	blk_limits_io_min(limits, chunk_size);
+	blk_limits_io_opt(limits, chunk_size *
+			  (conf->raid_disks - conf->max_degraded));
+}
+
 static struct target_type raid_target = {
 	.name = "raid45",
 	.version = {1, 0, 0},

@@ -443,6 +474,8 @@ static struct target_type raid_target = {
 	.dtr = raid_dtr,
 	.map = raid_map,
 	.status = raid_status,
+	.iterate_devices = raid_iterate_devices,
+	.io_hints = raid_io_hints,
 };
 
 static int __init dm_raid_init(void)

index 4ffd654..e2546fc 100644
@@ -466,6 +466,25 @@ static void raid_io_hints(struct dm_target *ti,
 			  (conf->raid_disks - conf->max_degraded));
 }
 
+static void raid_presuspend(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+	md_stop_writes(&rs->md);
+}
+
+static void raid_postsuspend(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+	mddev_suspend(&rs->md);
+}
+
+static void raid_resume(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+
+	mddev_resume(&rs->md);
+}
+
 static struct target_type raid_target = {
 	.name = "raid45",
 	.version = {1, 0, 0},

@@ -476,6 +495,9 @@ static struct target_type raid_target = {
 	.status = raid_status,
 	.iterate_devices = raid_iterate_devices,
 	.io_hints = raid_io_hints,
+	.presuspend = raid_presuspend,
+	.postsuspend = raid_postsuspend,
+	.resume = raid_resume,
 };
 
 static int __init dm_raid_init(void)

index e2546fc..a2567b0 100644
@@ -485,6 +485,31 @@ static void raid_resume(struct dm_target *ti)
 	mddev_resume(&rs->md);
 }
 
+/* Parse and handle a message from userspace
+ * Messages are:
+ *    stripecache  N  (pages per devices)
+ *    minspeed  N          (kibibytes per seconds)
+ */
+static int raid_message(struct dm_target *ti, unsigned argc, char **argv)
+{
+	struct raid_set *rs = ti->private;
+
+	if (argc == 2 && strcmp(argv[0], "stripecache") == 0) {
+		unsigned long size;
+		if (strict_strtoul(argv[1], 10, &size))
+			return -EINVAL;
+		return raid5_set_cache_size(&rs->md, size);
+	}
+	if (argc == 2 && strcmp(argv[0], "minspeed") == 0) {
+		unsigned long speed;
+		if (strict_strtoul(argv[1], 10, &speed))
+			return -EINVAL;
+		rs->md.sync_speed_min = speed;
+		return 0;
+	}
+	return -EINVAL;
+}
+
 static struct target_type raid_target = {
 	.name = "raid45",
 	.version = {1, 0, 0},

@@ -498,6 +523,7 @@ static struct target_type raid_target = {
 	.presuspend = raid_presuspend,
 	.postsuspend = raid_postsuspend,
 	.resume = raid_resume,
+	.message = raid_message,
 };
 
 static int __init dm_raid_init(void)

index 1ed0094..935a49b 100644
@@ -94,7 +94,7 @@ retry:
 	return -ESRCH;
 }
 
-static int build_constructor_string(struct dm_target *ti,
+static int build_constructor_string(sector_t log_size,
 				    unsigned argc, char **argv,
 				    char **ctr_str)
 {

@@ -114,7 +114,7 @@ static int build_constructor_string(struct dm_target *ti,
 		return -ENOMEM;
 	}
 
-	str_size = sprintf(str, "%llu", (unsigned long long)ti->len);
+	str_size = sprintf(str, "%llu", (unsigned long long)log_size);
 	for (i = 0; i < argc; i++)
 		str_size += sprintf(str + str_size, " %s", argv[i]);
 

@@ -136,6 +136,7 @@ static int build_constructor_string(struct dm_target *ti,
  * else.
  */
 static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
+			 sector_t log_size,
 			 unsigned argc, char **argv)
 {
 	int r = 0;

@@ -171,7 +172,9 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 	spin_lock_init(&lc->flush_lock);
 	INIT_LIST_HEAD(&lc->flush_list);
 
-	str_size = build_constructor_string(ti, argc - 1, argv + 1, &ctr_str);
+	str_size = build_constructor_string(log_size,
+					    argc - 1, argv + 1,
+					    &ctr_str);
 	if (str_size < 0) {
 		kfree(lc);
 		return str_size;

@@ -197,7 +200,7 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 	}
 
 	lc->region_size = (uint32_t)rdata;
-	lc->region_count = dm_sector_div_up(ti->len, lc->region_size);
+	lc->region_count = dm_sector_div_up(log_size, lc->region_size);
 
 out:
 	if (r) {

index 5a08be0..a232c14 100644
@@ -146,6 +146,7 @@ EXPORT_SYMBOL(dm_dirty_log_type_unregister);
 
 struct dm_dirty_log *dm_dirty_log_create(const char *type_name,
 			struct dm_target *ti,
+			sector_t log_size,
 			int (*flush_callback_fn)(struct dm_target *ti),
 			unsigned int argc, char **argv)
 {

@@ -164,7 +165,7 @@ struct dm_dirty_log *dm_dirty_log_create(const char *type_name,
 
 	log->flush_callback_fn = flush_callback_fn;
 	log->type = type;
-	if (type->ctr(log, ti, argc, argv)) {
+	if (type->ctr(log, ti, log_size, argc, argv)) {
 		kfree(log);
 		put_type(type);
 		return NULL;

@@ -335,9 +336,9 @@ static int read_header(struct log_c *log)
 	return 0;
 }
 
-static int _check_region_size(struct dm_target *ti, uint32_t region_size)
+static int _check_region_size(sector_t log_size, uint32_t region_size)
 {
-	if (region_size < 2 || region_size > ti->len)
+	if (region_size < 2 || region_size > log_size)
 		return 0;
 
 	if (!is_power_of_2(region_size))

@@ -353,6 +354,7 @@ static int _check_region_size(struct dm_target *ti, uint32_t region_size)
  *--------------------------------------------------------------*/
 #define BYTE_SHIFT 3
 static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
+			      sector_t log_size,
 			      unsigned int argc, char **argv,
 			      struct dm_dev *dev)
 {

@@ -382,12 +384,12 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 	}
 
 	if (sscanf(argv[0], "%u", &region_size) != 1 ||
-	    !_check_region_size(ti, region_size)) {
+	    !_check_region_size(log_size, region_size)) {
 		DMWARN("invalid region size %s", argv[0]);
 		return -EINVAL;
 	}
 
-	region_count = dm_sector_div_up(ti->len, region_size);
+	region_count = dm_sector_div_up(log_size, region_size);
 
 	lc = kmalloc(sizeof(*lc), GFP_KERNEL);
 	if (!lc) {

@@ -507,9 +509,10 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 }
 
 static int core_ctr(struct dm_dirty_log *log, struct dm_target *ti,
+		    sector_t log_size,
 		    unsigned int argc, char **argv)
 {
-	return create_log_context(log, ti, argc, argv, NULL);
+	return create_log_context(log, ti, log_size, argc, argv, NULL);
 }
 
 static void destroy_log_context(struct log_c *lc)

@@ -533,6 +536,7 @@ static void core_dtr(struct dm_dirty_log *log)
  * argv contains log_device region_size followed optionally by [no]sync
  *--------------------------------------------------------------*/
 static int disk_ctr(struct dm_dirty_log *log, struct dm_target *ti,
+		    sector_t log_size,
 		    unsigned int argc, char **argv)
 {
 	int r;

@@ -547,7 +551,7 @@ static int disk_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 	if (r)
 		return r;
 
-	r = create_log_context(log, ti, argc - 1, argv + 1, dev);
+	r = create_log_context(log, ti, log_size, argc - 1, argv + 1, dev);
 	if (r) {
 		dm_put_device(ti, dev);
 		return r;

index ddda531..ea732fc 100644
@@ -968,8 +968,8 @@ static struct dm_dirty_log *create_dirty_log(struct dm_target *ti,
 		return NULL;
 	}
 
-	dl = dm_dirty_log_create(argv[0], ti, mirror_flush, param_count,
-				 argv + 2);
+	dl = dm_dirty_log_create(argv[0], ti, ti->len, mirror_flush,
+				 param_count, argv + 2);
 	if (!dl) {
 		ti->error = "Error creating mirror dirty log";
 		return NULL;

index 7084503..641419f 100644
@@ -33,6 +33,7 @@ struct dm_dirty_log_type {
 	struct list_head list;
 
 	int (*ctr)(struct dm_dirty_log *log, struct dm_target *ti,
+		   sector_t log_size,
 		   unsigned argc, char **argv);
 	void (*dtr)(struct dm_dirty_log *log);
 

@@ -137,7 +138,7 @@ int dm_dirty_log_type_unregister(struct dm_dirty_log_type *type);
  * type->constructor/destructor() directly.
  */
 struct dm_dirty_log *dm_dirty_log_create(const char *type_name,
-			struct dm_target *ti,
+			struct dm_target *ti, sector_t log_size,
 			int (*flush_callback_fn)(struct dm_target *ti),
 			unsigned argc, char **argv);
 void dm_dirty_log_destroy(struct dm_dirty_log *log);

index a2567b0..5355342 100644
@@ -7,6 +7,8 @@
 #include "md.h"
 #include "raid5.h"
 #include "dm.h"
+#include "bitmap.h"
+#include <linux/dm-dirty-log.h>
 
 struct raid_dev {
 	struct dm_dev *dev;

@@ -183,7 +185,8 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 {
 	char *err = NULL;
 	int errnum = -EINVAL;
-	unsigned long cnt;
+	unsigned long cnt, log_cnt;
+	char **log_argv;
 	struct raid_type *rt;
 	unsigned long chunk_size;
 	int recovery = 1;

@@ -192,16 +195,18 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	sector_t sectors_per_dev, chunks;
 	struct raid_set *rs = NULL;
 	int in_sync, i;
+	struct dm_dirty_log *log = NULL;
 
-	/* log type - core XXX [no]sync */
+	/* log type - type arg-count args */
 	err = "Cannot parse log type";
 	if (argc < 2 ||
-	    strcmp(argv[0], "core") != 0 ||
 	    strict_strtoul(argv[1], 10, &cnt) < 0 ||
 	    cnt + 2 > argc)
 		goto err;
-	if (cnt >= 2 && strcmp(argv[3], "sync") == 0)
-		recovery = 0;
+
+	log_cnt = cnt;
+	log_argv = argv;
+
 	argc -= cnt+2;
 	argv += cnt+2;
 

@@ -276,6 +281,11 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	if (sector_div(chunks, chunk_size))
 		goto err;
 
+	log = dm_dirty_log_create(log_argv[0], ti, sectors_per_dev,
+				  NULL, log_cnt, log_argv+2);
+	err = "Error creating dirty log";
+	if (!log)
+		goto err;
 
 	/* Now the devices: three words each */
 	rs = context_alloc(rt, chunk_size, recovery,

@@ -318,6 +328,11 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	ti->split_io = rs->md.chunk_sectors;
 	ti->private = rs;
 
+	rs->md.bitmap_info.log = log;
+	rs->md.bitmap_info.daemon_sleep = 10 * HZ;
+	rs->md.bitmap_info.chunksize = log->type->get_region_size(log) * 512;
+	rs->md.bitmap_info.external = 1;
+
 	mutex_lock(&rs->md.reconfig_mutex);
 	err = "Fail to run raid array";
 	errnum = md_run(&rs->md);

@@ -332,6 +347,8 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 
 	return 0;
 err:
+	if (log)
+		dm_dirty_log_destroy(log);
 	if (rs)
 		context_free(rs);
 	ti->error = err;

@@ -343,6 +360,7 @@ static void raid_dtr(struct dm_target *ti)
 	struct raid_set *rs = ti->private;
 
 	list_del_init(&rs->callbacks.list);
+	dm_dirty_log_destroy(rs->md.bitmap_info.log);
 	md_stop(&rs->md);
 	context_free(rs);
 }

@@ -362,6 +380,7 @@ static int raid_status(struct dm_target *ti, status_type_t type,
 {
 	struct raid_set *rs = ti->private;
 	struct raid5_private_data *conf = rs->md.private;
+	struct dm_dirty_log *log = conf->mddev->bitmap_info.log;
 	int sz = 0;
 	int rbcnt;
 	int i;

@@ -394,14 +413,14 @@ static int raid_status(struct dm_target *ti, status_type_t type,
 		DMEMIT("%llu/%llu ",
 		       (unsigned long long) sync,
 		       (unsigned long long) rs->md.resync_max_sectors);
-		DMEMIT("1 core");
+
+		sz += log->type->status(log, type, result + sz, maxlen - sz);
 
 		break;
 	case STATUSTYPE_TABLE:
 		/* The string you would use to construct this array */
-		/* Pretend to use a core log with a region size of 1 sector */
-		DMEMIT("core 2 %u %ssync ", 1,
-		       rs->md.recovery_cp == MaxSector ? "" : "no");
+		sz += log->type->status(log, type, result + sz, maxlen - sz);
+
 		DMEMIT("%s ", rs->raid_type->name);
 		DMEMIT("1 %u ", rs->md.chunk_sectors);
 

@@ -469,19 +488,28 @@ static void raid_io_hints(struct dm_target *ti,
 static void raid_presuspend(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
+	struct dm_dirty_log *log = rs->md.bitmap_info.log;
+
 	md_stop_writes(&rs->md);
+	log->type->presuspend(log);
 }
 
 static void raid_postsuspend(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
+	struct dm_dirty_log *log = rs->md.bitmap_info.log;
+
 	mddev_suspend(&rs->md);
+	log->type->postsuspend(log);
 }
 
 static void raid_resume(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
+	struct dm_dirty_log *log = rs->md.bitmap_info.log;
 
+	log->type->resume(log);
+	bitmap_load(&rs->md);
 	mddev_resume(&rs->md);
 }