1 files changed, 285 insertions, 61 deletions

diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c
index 1ed0094f064..b953db6cc22 100644
--- a/drivers/md/dm-log-userspace-base.c
+++ b/drivers/md/dm-log-userspace-base.c
@@ -9,17 +9,30 @@
 #include <linux/dm-dirty-log.h>
 #include <linux/device-mapper.h>
 #include <linux/dm-log-userspace.h>
+#include <linux/module.h>
+#include <linux/workqueue.h>
 
 #include "dm-log-userspace-transfer.h"
 
+#define DM_LOG_USERSPACE_VSN "1.3.0"
+
 struct flush_entry {
 	int type;
 	region_t region;
 	struct list_head list;
 };
 
+/*
+ * This limit on the number of mark and clear request is, to a degree,
+ * arbitrary.  However, there is some basis for the choice in the limits
+ * imposed on the size of data payload by dm-log-userspace-transfer.c:
+ * dm_consult_userspace().
+ */
+#define MAX_FLUSH_GROUP_COUNT 32
+
 struct log_c {
 	struct dm_target *ti;
+	struct dm_dev *log_dev;
 	uint32_t region_size;
 	region_t region_count;
 	uint64_t luid;
@@ -37,8 +50,27 @@ struct log_c {
 	 */
 	uint64_t in_sync_hint;
 
+	/*
+	 * Mark and clear requests are held until a flush is issued
+	 * so that we can group, and thereby limit, the amount of
+	 * network traffic between kernel and userspace.  The 'flush_lock'
+	 * is used to protect these lists.
+	 */
 	spinlock_t flush_lock;
-	struct list_head flush_list;  /* only for clear and mark requests */
+	struct list_head mark_list;
+	struct list_head clear_list;
+
+	/*
+	 * Workqueue for flush of clear region requests.
+	 */
+	struct workqueue_struct *dmlog_wq;
+	struct delayed_work flush_log_work;
+	atomic_t sched_flush;
+
+	/*
+	 * Combine userspace flush and mark requests for efficiency.
+	 */
+	uint32_t integrated_flush;
 };
 
 static mempool_t *flush_entry_pool;
@@ -103,6 +135,9 @@ static int build_constructor_string(struct dm_target *ti,
 
 	*ctr_str = NULL;
 
+	/*
+	 * Determine overall size of the string.
+	 */
 	for (i = 0, str_size = 0; i < argc; i++)
 		str_size += strlen(argv[i]) + 1; /* +1 for space between args */
 
@@ -122,18 +157,39 @@ static int build_constructor_string(struct dm_target *ti,
 	return str_size;
 }
 
+static void do_flush(struct work_struct *work)
+{
+	int r;
+	struct log_c *lc = container_of(work, struct log_c, flush_log_work.work);
+
+	atomic_set(&lc->sched_flush, 0);
+
+	r = userspace_do_request(lc, lc->uuid, DM_ULOG_FLUSH, NULL, 0, NULL, NULL);
+
+	if (r)
+		dm_table_event(lc->ti->table);
+}
+
 /*
  * userspace_ctr
  *
  * argv contains:
- *	<UUID> <other args>
- * Where 'other args' is the userspace implementation specific log
- * arguments.  An example might be:
- *	<UUID> clustered_disk <arg count> <log dev> <region_size> [[no]sync]
+ *	<UUID> [integrated_flush] <other args>
+ * Where 'other args' are the userspace implementation-specific log
+ * arguments.
+ *
+ * Example:
+ *	<UUID> [integrated_flush] clustered-disk <arg count> <log dev>
+ *	<region_size> [[no]sync]
+ *
+ * This module strips off the <UUID> and uses it for identification
+ * purposes when communicating with userspace about a log.
  *
- * So, this module will strip off the <UUID> for identification purposes
- * when communicating with userspace about a log; but will pass on everything
- * else.
+ * If integrated_flush is defined, the kernel combines flush
+ * and mark requests.
+ *
+ * The rest of the line, beginning with 'clustered-disk', is passed
+ * to the userspace ctr function.
  */
 static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 			 unsigned argc, char **argv)
@@ -144,13 +200,15 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 	struct log_c *lc = NULL;
 	uint64_t rdata;
 	size_t rdata_size = sizeof(rdata);
+	char *devices_rdata = NULL;
+	size_t devices_rdata_size = DM_NAME_LEN;
 
 	if (argc < 3) {
 		DMWARN("Too few arguments to userspace dirty log");
 		return -EINVAL;
 	}
 
-	lc = kmalloc(sizeof(*lc), GFP_KERNEL);
+	lc = kzalloc(sizeof(*lc), GFP_KERNEL);
 	if (!lc) {
 		DMWARN("Unable to allocate userspace log context.");
 		return -ENOMEM;
@@ -167,22 +225,46 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 		return -EINVAL;
 	}
 
+	lc->usr_argc = argc;
+
 	strncpy(lc->uuid, argv[0], DM_UUID_LEN);
+	argc--;
+	argv++;
 	spin_lock_init(&lc->flush_lock);
-	INIT_LIST_HEAD(&lc->flush_list);
+	INIT_LIST_HEAD(&lc->mark_list);
+	INIT_LIST_HEAD(&lc->clear_list);
+
+	if (!strcasecmp(argv[0], "integrated_flush")) {
+		lc->integrated_flush = 1;
+		argc--;
+		argv++;
+	}
 
-	str_size = build_constructor_string(ti, argc - 1, argv + 1, &ctr_str);
+	str_size = build_constructor_string(ti, argc, argv, &ctr_str);
 	if (str_size < 0) {
 		kfree(lc);
 		return str_size;
 	}
 
-	/* Send table string */
-	r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_CTR,
-				 ctr_str, str_size, NULL, NULL);
+	devices_rdata = kzalloc(devices_rdata_size, GFP_KERNEL);
+	if (!devices_rdata) {
+		DMERR("Failed to allocate memory for device information");
+		r = -ENOMEM;
+		goto out;
+	}
 
-	if (r == -ESRCH) {
-		DMERR("Userspace log server not found");
+	/*
+	 * Send table string and get back any opened device.
+	 */
+	r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_CTR,
+				 ctr_str, str_size,
+				 devices_rdata, &devices_rdata_size);
+
+	if (r < 0) {
+		if (r == -ESRCH)
+			DMERR("Userspace log server not found");
+		else
+			DMERR("Userspace log server failed to create log");
 		goto out;
 	}
 
@@ -199,13 +281,38 @@ 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);
 
+	if (devices_rdata_size) {
+		if (devices_rdata[devices_rdata_size - 1] != '\0') {
+			DMERR("DM_ULOG_CTR device return string not properly terminated");
+			r = -EINVAL;
+			goto out;
+		}
+		r = dm_get_device(ti, devices_rdata,
+				  dm_table_get_mode(ti->table), &lc->log_dev);
+		if (r)
+			DMERR("Failed to register %s with device-mapper",
+			      devices_rdata);
+	}
+
+	if (lc->integrated_flush) {
+		lc->dmlog_wq = alloc_workqueue("dmlogd", WQ_MEM_RECLAIM, 0);
+		if (!lc->dmlog_wq) {
+			DMERR("couldn't start dmlogd");
+			r = -ENOMEM;
+			goto out;
+		}
+
+		INIT_DELAYED_WORK(&lc->flush_log_work, do_flush);
+		atomic_set(&lc->sched_flush, 0);
+	}
+
 out:
+	kfree(devices_rdata);
 	if (r) {
 		kfree(lc);
 		kfree(ctr_str);
 	} else {
 		lc->usr_argv_str = ctr_str;
-		lc->usr_argc = argc;
 		log->context = lc;
 	}
 
@@ -214,12 +321,21 @@ out:
 
 static void userspace_dtr(struct dm_dirty_log *log)
 {
-	int r;
 	struct log_c *lc = log->context;
 
-	r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_DTR,
-				 NULL, 0,
-				 NULL, NULL);
+	if (lc->integrated_flush) {
+		/* flush workqueue */
+		if (atomic_read(&lc->sched_flush))
+			flush_delayed_work(&lc->flush_log_work);
+
+		destroy_workqueue(lc->dmlog_wq);
+	}
+
+	(void) dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_DTR,
+				    NULL, 0, NULL, NULL);
+
+	if (lc->log_dev)
+		dm_put_device(lc->ti, lc->log_dev);
 
 	kfree(lc->usr_argv_str);
 	kfree(lc);
@@ -233,8 +349,7 @@ static int userspace_presuspend(struct dm_dirty_log *log)
 	struct log_c *lc = log->context;
 
 	r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_PRESUSPEND,
-				 NULL, 0,
-				 NULL, NULL);
+				 NULL, 0, NULL, NULL);
 
 	return r;
 }
@@ -244,9 +359,14 @@ static int userspace_postsuspend(struct dm_dirty_log *log)
 	int r;
 	struct log_c *lc = log->context;
 
+	/*
+	 * Run planned flush earlier.
+	 */
+	if (lc->integrated_flush && atomic_read(&lc->sched_flush))
+		flush_delayed_work(&lc->flush_log_work);
+
 	r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_POSTSUSPEND,
-				 NULL, 0,
-				 NULL, NULL);
+				 NULL, 0, NULL, NULL);
 
 	return r;
 }
@@ -258,8 +378,7 @@ static int userspace_resume(struct dm_dirty_log *log)
 
 	lc->in_sync_hint = 0;
 	r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_RESUME,
-				 NULL, 0,
-				 NULL, NULL);
+				 NULL, 0, NULL, NULL);
 
 	return r;
 }
@@ -338,6 +457,85 @@ static int userspace_in_sync(struct dm_dirty_log *log, region_t region,
 	return (r) ? 0 : (int)in_sync;
 }
 
+static int flush_one_by_one(struct log_c *lc, struct list_head *flush_list)
+{
+	int r = 0;
+	struct flush_entry *fe;
+
+	list_for_each_entry(fe, flush_list, list) {
+		r = userspace_do_request(lc, lc->uuid, fe->type,
+					 (char *)&fe->region,
+					 sizeof(fe->region),
+					 NULL, NULL);
+		if (r)
+			break;
+	}
+
+	return r;
+}
+
+static int flush_by_group(struct log_c *lc, struct list_head *flush_list,
+			  int flush_with_payload)
+{
+	int r = 0;
+	int count;
+	uint32_t type = 0;
+	struct flush_entry *fe, *tmp_fe;
+	LIST_HEAD(tmp_list);
+	uint64_t group[MAX_FLUSH_GROUP_COUNT];
+
+	/*
+	 * Group process the requests
+	 */
+	while (!list_empty(flush_list)) {
+		count = 0;
+
+		list_for_each_entry_safe(fe, tmp_fe, flush_list, list) {
+			group[count] = fe->region;
+			count++;
+
+			list_move(&fe->list, &tmp_list);
+
+			type = fe->type;
+			if (count >= MAX_FLUSH_GROUP_COUNT)
+				break;
+		}
+
+		if (flush_with_payload) {
+			r = userspace_do_request(lc, lc->uuid, DM_ULOG_FLUSH,
+						 (char *)(group),
+						 count * sizeof(uint64_t),
+						 NULL, NULL);
+			/*
+			 * Integrated flush failed.
+			 */
+			if (r)
+				break;
+		} else {
+			r = userspace_do_request(lc, lc->uuid, type,
+						 (char *)(group),
+						 count * sizeof(uint64_t),
+						 NULL, NULL);
+			if (r) {
+				/*
+				 * Group send failed.  Attempt one-by-one.
+				 */
+				list_splice_init(&tmp_list, flush_list);
+				r = flush_one_by_one(lc, flush_list);
+				break;
+			}
+		}
+	}
+
+	/*
+	 * Must collect flush_entrys that were successfully processed
+	 * as a group so that they will be free'd by the caller.
+	 */
+	list_splice_init(&tmp_list, flush_list);
+
+	return r;
+}
+
 /*
  * userspace_flush
  *
@@ -360,42 +558,70 @@ static int userspace_flush(struct dm_dirty_log *log)
 	int r = 0;
 	unsigned long flags;
 	struct log_c *lc = log->context;
-	LIST_HEAD(flush_list);
+	LIST_HEAD(mark_list);
+	LIST_HEAD(clear_list);
+	int mark_list_is_empty;
+	int clear_list_is_empty;
 	struct flush_entry *fe, *tmp_fe;
 
 	spin_lock_irqsave(&lc->flush_lock, flags);
-	list_splice_init(&lc->flush_list, &flush_list);
+	list_splice_init(&lc->mark_list, &mark_list);
+	list_splice_init(&lc->clear_list, &clear_list);
 	spin_unlock_irqrestore(&lc->flush_lock, flags);
 
-	if (list_empty(&flush_list))
+	mark_list_is_empty = list_empty(&mark_list);
+	clear_list_is_empty = list_empty(&clear_list);
+
+	if (mark_list_is_empty && clear_list_is_empty)
 		return 0;
 
-	/*
-	 * FIXME: Count up requests, group request types,
-	 * allocate memory to stick all requests in and
-	 * send to server in one go.  Failing the allocation,
-	 * do it one by one.
-	 */
+	r = flush_by_group(lc, &clear_list, 0);
+	if (r)
+		goto out;
 
-	list_for_each_entry(fe, &flush_list, list) {
-		r = userspace_do_request(lc, lc->uuid, fe->type,
-					 (char *)&fe->region,
-					 sizeof(fe->region),
-					 NULL, NULL);
+	if (!lc->integrated_flush) {
+		r = flush_by_group(lc, &mark_list, 0);
 		if (r)
-			goto fail;
+			goto out;
+		r = userspace_do_request(lc, lc->uuid, DM_ULOG_FLUSH,
+					 NULL, 0, NULL, NULL);
+		goto out;
 	}
 
-	r = userspace_do_request(lc, lc->uuid, DM_ULOG_FLUSH,
-				 NULL, 0, NULL, NULL);
+	/*
+	 * Send integrated flush request with mark_list as payload.
+	 */
+	r = flush_by_group(lc, &mark_list, 1);
+	if (r)
+		goto out;
+
+	if (mark_list_is_empty && !atomic_read(&lc->sched_flush)) {
+		/*
+		 * When there are only clear region requests,
+		 * we schedule a flush in the future.
+		 */
+		queue_delayed_work(lc->dmlog_wq, &lc->flush_log_work, 3 * HZ);
+		atomic_set(&lc->sched_flush, 1);
+	} else {
+		/*
+		 * Cancel pending flush because we
+		 * have already flushed in mark_region.
+		 */
+		cancel_delayed_work(&lc->flush_log_work);
+		atomic_set(&lc->sched_flush, 0);
+	}
 
-fail:
+out:
 	/*
-	 * We can safely remove these entries, even if failure.
+	 * We can safely remove these entries, even after failure.
 	 * Calling code will receive an error and will know that
 	 * the log facility has failed.
 	 */
-	list_for_each_entry_safe(fe, tmp_fe, &flush_list, list) {
+	list_for_each_entry_safe(fe, tmp_fe, &mark_list, list) {
+		list_del(&fe->list);
+		mempool_free(fe, flush_entry_pool);
+	}
+	list_for_each_entry_safe(fe, tmp_fe, &clear_list, list) {
 		list_del(&fe->list);
 		mempool_free(fe, flush_entry_pool);
 	}
@@ -425,7 +651,7 @@ static void userspace_mark_region(struct dm_dirty_log *log, region_t region)
 	spin_lock_irqsave(&lc->flush_lock, flags);
 	fe->type = DM_ULOG_MARK_REGION;
 	fe->region = region;
-	list_add(&fe->list, &lc->flush_list);
+	list_add(&fe->list, &lc->mark_list);
 	spin_unlock_irqrestore(&lc->flush_lock, flags);
 
 	return;
@@ -462,7 +688,7 @@ static void userspace_clear_region(struct dm_dirty_log *log, region_t region)
 	spin_lock_irqsave(&lc->flush_lock, flags);
 	fe->type = DM_ULOG_CLEAR_REGION;
 	fe->region = region;
-	list_add(&fe->list, &lc->flush_list);
+	list_add(&fe->list, &lc->clear_list);
 	spin_unlock_irqrestore(&lc->flush_lock, flags);
 
 	return;
@@ -491,8 +717,7 @@ static int userspace_get_resync_work(struct dm_dirty_log *log, region_t *region)
 
 	rdata_size = sizeof(pkg);
 	r = userspace_do_request(lc, lc->uuid, DM_ULOG_GET_RESYNC_WORK,
-				 NULL, 0,
-				 (char *)&pkg, &rdata_size);
+				 NULL, 0, (char *)&pkg, &rdata_size);
 
 	*region = pkg.r;
 	return (r) ? r : (int)pkg.i;
@@ -518,8 +743,7 @@ static void userspace_set_region_sync(struct dm_dirty_log *log,
 	pkg.i = (int64_t)in_sync;
 
 	r = userspace_do_request(lc, lc->uuid, DM_ULOG_SET_REGION_SYNC,
-				 (char *)&pkg, sizeof(pkg),
-				 NULL, NULL);
+				 (char *)&pkg, sizeof(pkg), NULL, NULL);
 
 	/*
 	 * It would be nice to be able to report failures.
@@ -545,8 +769,7 @@ static region_t userspace_get_sync_count(struct dm_dirty_log *log)
 
 	rdata_size = sizeof(sync_count);
 	r = userspace_do_request(lc, lc->uuid, DM_ULOG_GET_SYNC_COUNT,
-				 NULL, 0,
-				 (char *)&sync_count, &rdata_size);
+				 NULL, 0, (char *)&sync_count, &rdata_size);
 
 	if (r)
 		return 0;
@@ -573,8 +796,7 @@ static int userspace_status(struct dm_dirty_log *log, status_type_t status_type,
 	switch (status_type) {
 	case STATUSTYPE_INFO:
 		r = userspace_do_request(lc, lc->uuid, DM_ULOG_STATUS_INFO,
-					 NULL, 0,
-					 result, &sz);
+					 NULL, 0, result, &sz);
 
 		if (r) {
 			sz = 0;
@@ -587,8 +809,10 @@ static int userspace_status(struct dm_dirty_log *log, status_type_t status_type,
 		BUG_ON(!table_args); /* There will always be a ' ' */
 		table_args++;
 
-		DMEMIT("%s %u %s %s ", log->type->name, lc->usr_argc,
-		       lc->uuid, table_args);
+		DMEMIT("%s %u %s ", log->type->name, lc->usr_argc, lc->uuid);
+		if (lc->integrated_flush)
+			DMEMIT("integrated_flush ");
+		DMEMIT("%s ", table_args);
 		break;
 	}
 	return (r) ? 0 : (int)sz;
@@ -684,7 +908,7 @@ static int __init userspace_dirty_log_init(void)
 		return r;
 	}
 
-	DMINFO("version 1.0.0 loaded");
+	DMINFO("version " DM_LOG_USERSPACE_VSN " loaded");
 	return 0;
 }
 
@@ -694,7 +918,7 @@ static void __exit userspace_dirty_log_exit(void)
 	dm_ulog_tfr_exit();
 	mempool_destroy(flush_entry_pool);
 
-	DMINFO("version 1.0.0 unloaded");
+	DMINFO("version " DM_LOG_USERSPACE_VSN " unloaded");
 	return;
 }