Merge tag 'md/4.2' of git://neil.brown.name/md

Pull md updates from Neil Brown:
 "A mixed bag

   - a few bug fixes
   - some performance improvement that decrease lock contention
   - some clean-up

  Nothing major"

* tag 'md/4.2' of git://neil.brown.name/md:
  md: clear Blocked flag on failed devices when array is read-only.
  md: unlock mddev_lock on an error path.
  md: clear mddev->private when it has been freed.
  md: fix a build warning
  md/raid5: ignore released_stripes check
  md/raid5: per hash value and exclusive wait_for_stripe
  md/raid5: split wait_for_stripe and introduce wait_for_quiescent
  wait: introduce wait_event_exclusive_cmd
  md: convert to kstrto*()
  md/raid10: make sync_request_write() call bio_copy_data()

drivers/md/md.c

@@ -2628,13 +2628,14 @@ errors_show(struct md_rdev *rdev, char *page)
 static ssize_t
 errors_store(struct md_rdev *rdev, const char *buf, size_t len)
 {
-	char *e;
-	unsigned long n = simple_strtoul(buf, &e, 10);
-	if (*buf && (*e == 0 || *e == '\n')) {
+	unsigned int n;
+	int rv;
+
+	rv = kstrtouint(buf, 10, &n);
+	if (rv < 0)
+		return rv;
 	atomic_set(&rdev->corrected_errors, n);
 	return len;
-	}
-	return -EINVAL;
 }
 static struct rdev_sysfs_entry rdev_errors =
 __ATTR(errors, S_IRUGO|S_IWUSR, errors_show, errors_store);
@@ -2651,13 +2652,16 @@ slot_show(struct md_rdev *rdev, char *page)
 static ssize_t
 slot_store(struct md_rdev *rdev, const char *buf, size_t len)
 {
-	char *e;
+	int slot;
 	int err;
-	int slot = simple_strtoul(buf, &e, 10);
+
 	if (strncmp(buf, "none", 4)==0)
 		slot = -1;
-	else if (e==buf || (*e && *e!= '\n'))
-		return -EINVAL;
+	else {
+		err = kstrtouint(buf, 10, (unsigned int *)&slot);
+		if (err < 0)
+			return err;
+	}
 	if (rdev->mddev->pers && slot == -1) {
 		/* Setting 'slot' on an active array requires also
 		 * updating the 'rd%d' link, and communicating
@@ -3542,12 +3546,12 @@ layout_show(struct mddev *mddev, char *page)
 static ssize_t
 layout_store(struct mddev *mddev, const char *buf, size_t len)
 {
-	char *e;
-	unsigned long n = simple_strtoul(buf, &e, 10);
+	unsigned int n;
 	int err;
 
-	if (!*buf || (*e && *e != '\n'))
-		return -EINVAL;
+	err = kstrtouint(buf, 10, &n);
+	if (err < 0)
+		return err;
 	err = mddev_lock(mddev);
 	if (err)
 		return err;
@@ -3591,12 +3595,12 @@ static int update_raid_disks(struct mddev *mddev, int raid_disks);
 static ssize_t
 raid_disks_store(struct mddev *mddev, const char *buf, size_t len)
 {
-	char *e;
+	unsigned int n;
 	int err;
-	unsigned long n = simple_strtoul(buf, &e, 10);
 
-	if (!*buf || (*e && *e != '\n'))
-		return -EINVAL;
+	err = kstrtouint(buf, 10, &n);
+	if (err < 0)
+		return err;
 
 	err = mddev_lock(mddev);
 	if (err)
@@ -3643,12 +3647,12 @@ chunk_size_show(struct mddev *mddev, char *page)
 static ssize_t
 chunk_size_store(struct mddev *mddev, const char *buf, size_t len)
 {
+	unsigned long n;
 	int err;
-	char *e;
-	unsigned long n = simple_strtoul(buf, &e, 10);
 
-	if (!*buf || (*e && *e != '\n'))
-		return -EINVAL;
+	err = kstrtoul(buf, 10, &n);
+	if (err < 0)
+		return err;
 
 	err = mddev_lock(mddev);
 	if (err)
@@ -3686,19 +3690,24 @@ resync_start_show(struct mddev *mddev, char *page)
 static ssize_t
 resync_start_store(struct mddev *mddev, const char *buf, size_t len)
 {
+	unsigned long long n;
 	int err;
-	char *e;
-	unsigned long long n = simple_strtoull(buf, &e, 10);
+
+	if (cmd_match(buf, "none"))
+		n = MaxSector;
+	else {
+		err = kstrtoull(buf, 10, &n);
+		if (err < 0)
+			return err;
+		if (n != (sector_t)n)
+			return -EINVAL;
+	}
 
 	err = mddev_lock(mddev);
 	if (err)
 		return err;
 	if (mddev->pers && !test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
 		err = -EBUSY;
-	else if (cmd_match(buf, "none"))
-		n = MaxSector;
-	else if (!*buf || (*e && *e != '\n'))
-		err = -EINVAL;
 
 	if (!err) {
 		mddev->recovery_cp = n;
@@ -3934,14 +3943,14 @@ max_corrected_read_errors_show(struct mddev *mddev, char *page) {
 static ssize_t
 max_corrected_read_errors_store(struct mddev *mddev, const char *buf, size_t len)
 {
-	char *e;
-	unsigned long n = simple_strtoul(buf, &e, 10);
+	unsigned int n;
+	int rv;
 
-	if (*buf && (*e == 0 || *e == '\n')) {
+	rv = kstrtouint(buf, 10, &n);
+	if (rv < 0)
+		return rv;
 	atomic_set(&mddev->max_corr_read_errors, n);
 	return len;
-	}
-	return -EINVAL;
 }
 
 static struct md_sysfs_entry max_corr_read_errors =
@@ -4003,8 +4012,10 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len)
 	else
 		rdev = md_import_device(dev, -1, -1);
 
-	if (IS_ERR(rdev))
+	if (IS_ERR(rdev)) {
+		mddev_unlock(mddev);
 		return PTR_ERR(rdev);
+	}
 	err = bind_rdev_to_array(rdev, mddev);
  out:
 	if (err)
@@ -4298,15 +4309,18 @@ sync_min_show(struct mddev *mddev, char *page)
 static ssize_t
 sync_min_store(struct mddev *mddev, const char *buf, size_t len)
 {
-	int min;
-	char *e;
+	unsigned int min;
+	int rv;
+
 	if (strncmp(buf, "system", 6)==0) {
-		mddev->sync_speed_min = 0;
-		return len;
-	}
-	min = simple_strtoul(buf, &e, 10);
-	if (buf == e || (*e && *e != '\n') || min <= 0)
+		min = 0;
+	} else {
+		rv = kstrtouint(buf, 10, &min);
+		if (rv < 0)
+			return rv;
+		if (min == 0)
 			return -EINVAL;
+	}
 	mddev->sync_speed_min = min;
 	return len;
 }
@@ -4324,15 +4338,18 @@ sync_max_show(struct mddev *mddev, char *page)
 static ssize_t
 sync_max_store(struct mddev *mddev, const char *buf, size_t len)
 {
-	int max;
-	char *e;
+	unsigned int max;
+	int rv;
+
 	if (strncmp(buf, "system", 6)==0) {
-		mddev->sync_speed_max = 0;
-		return len;
-	}
-	max = simple_strtoul(buf, &e, 10);
-	if (buf == e || (*e && *e != '\n') || max <= 0)
+		max = 0;
+	} else {
+		rv = kstrtouint(buf, 10, &max);
+		if (rv < 0)
+			return rv;
+		if (max == 0)
 			return -EINVAL;
+	}
 	mddev->sync_speed_max = max;
 	return len;
 }
@@ -4515,12 +4532,13 @@ suspend_lo_show(struct mddev *mddev, char *page)
 static ssize_t
 suspend_lo_store(struct mddev *mddev, const char *buf, size_t len)
 {
-	char *e;
-	unsigned long long new = simple_strtoull(buf, &e, 10);
-	unsigned long long old;
+	unsigned long long old, new;
 	int err;
 
-	if (buf == e || (*e && *e != '\n'))
+	err = kstrtoull(buf, 10, &new);
+	if (err < 0)
+		return err;
+	if (new != (sector_t)new)
 		return -EINVAL;
 
 	err = mddev_lock(mddev);
@@ -4557,12 +4575,13 @@ suspend_hi_show(struct mddev *mddev, char *page)
 static ssize_t
 suspend_hi_store(struct mddev *mddev, const char *buf, size_t len)
 {
-	char *e;
-	unsigned long long new = simple_strtoull(buf, &e, 10);
-	unsigned long long old;
+	unsigned long long old, new;
 	int err;
 
-	if (buf == e || (*e && *e != '\n'))
+	err = kstrtoull(buf, 10, &new);
+	if (err < 0)
+		return err;
+	if (new != (sector_t)new)
 		return -EINVAL;
 
 	err = mddev_lock(mddev);
@@ -4604,11 +4623,13 @@ static ssize_t
 reshape_position_store(struct mddev *mddev, const char *buf, size_t len)
 {
 	struct md_rdev *rdev;
-	char *e;
+	unsigned long long new;
 	int err;
-	unsigned long long new = simple_strtoull(buf, &e, 10);
 
-	if (buf == e || (*e && *e != '\n'))
+	err = kstrtoull(buf, 10, &new);
+	if (err < 0)
+		return err;
+	if (new != (sector_t)new)
 		return -EINVAL;
 	err = mddev_lock(mddev);
 	if (err)
@@ -5157,6 +5178,7 @@ int md_run(struct mddev *mddev)
 		mddev_detach(mddev);
 		if (mddev->private)
 			pers->free(mddev, mddev->private);
+		mddev->private = NULL;
 		module_put(pers->owner);
 		bitmap_destroy(mddev);
 		return err;
@@ -5292,6 +5314,7 @@ static void md_clean(struct mddev *mddev)
 	mddev->changed = 0;
 	mddev->degraded = 0;
 	mddev->safemode = 0;
+	mddev->private = NULL;
 	mddev->merge_check_needed = 0;
 	mddev->bitmap_info.offset = 0;
 	mddev->bitmap_info.default_offset = 0;
@@ -5364,6 +5387,7 @@ static void __md_stop(struct mddev *mddev)
 	mddev->pers = NULL;
 	spin_unlock(&mddev->lock);
 	pers->free(mddev, mddev->private);
+	mddev->private = NULL;
 	if (pers->sync_request && mddev->to_remove == NULL)
 		mddev->to_remove = &md_redundancy_group;
 	module_put(pers->owner);
@@ -6373,7 +6397,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 	    mddev->ctime         != info->ctime         ||
 	    mddev->level         != info->level         ||
 /*	    mddev->layout        != info->layout        || */
-	    !mddev->persistent	 != info->not_persistent||
+	    mddev->persistent	 != !info->not_persistent ||
 	    mddev->chunk_sectors != info->chunk_size >> 9 ||
 	    /* ignore bottom 8 bits of state, and allow SB_BITMAP_PRESENT to change */
 	    ((state^info->state) & 0xfffffe00)
@@ -8104,6 +8128,15 @@ void md_check_recovery(struct mddev *mddev)
 		int spares = 0;
 
 		if (mddev->ro) {
+			struct md_rdev *rdev;
+			if (!mddev->external && mddev->in_sync)
+				/* 'Blocked' flag not needed as failed devices
+				 * will be recorded if array switched to read/write.
+				 * Leaving it set will prevent the device
+				 * from being removed.
+				 */
+				rdev_for_each(rdev, mddev)
+					clear_bit(Blocked, &rdev->flags);
 			/* On a read-only array we can:
 			 * - remove failed devices
 			 * - add already-in_sync devices if the array itself
@@ -9011,13 +9044,7 @@ static int get_ro(char *buffer, struct kernel_param *kp)
 }
 static int set_ro(const char *val, struct kernel_param *kp)
 {
-	char *e;
-	int num = simple_strtoul(val, &e, 10);
-	if (*val && (*e == '\0' || *e == '\n')) {
-		start_readonly = num;
-		return 0;
-	}
-	return -EINVAL;
+	return kstrtouint(val, 10, (unsigned int *)&start_readonly);
 }
 
 module_param_call(start_ro, set_ro, get_ro, NULL, S_IRUSR|S_IWUSR);

drivers/md/raid10.c

@@ -2099,17 +2099,10 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 		tbio->bi_rw = WRITE;
 		tbio->bi_private = r10_bio;
 		tbio->bi_iter.bi_sector = r10_bio->devs[i].addr;
-
-		for (j=0; j < vcnt ; j++) {
-			tbio->bi_io_vec[j].bv_offset = 0;
-			tbio->bi_io_vec[j].bv_len = PAGE_SIZE;
-
-			memcpy(page_address(tbio->bi_io_vec[j].bv_page),
-			       page_address(fbio->bi_io_vec[j].bv_page),
-			       PAGE_SIZE);
-		}
 		tbio->bi_end_io = end_sync_write;
 
+		bio_copy_data(tbio, fbio);
+
 		d = r10_bio->devs[i].devnum;
 		atomic_inc(&conf->mirrors[d].rdev->nr_pending);
 		atomic_inc(&r10_bio->remaining);
@@ -2124,17 +2117,14 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 	 * that are active
 	 */
 	for (i = 0; i < conf->copies; i++) {
-		int j, d;
+		int d;
 
 		tbio = r10_bio->devs[i].repl_bio;
 		if (!tbio || !tbio->bi_end_io)
 			continue;
 		if (r10_bio->devs[i].bio->bi_end_io != end_sync_write
 		    && r10_bio->devs[i].bio != fbio)
-			for (j = 0; j < vcnt; j++)
-				memcpy(page_address(tbio->bi_io_vec[j].bv_page),
-				       page_address(fbio->bi_io_vec[j].bv_page),
-				       PAGE_SIZE);
+			bio_copy_data(tbio, fbio);
 		d = r10_bio->devs[i].devnum;
 		atomic_inc(&r10_bio->remaining);
 		md_sync_acct(conf->mirrors[d].replacement->bdev,

drivers/md/raid5.c

@@ -344,7 +344,8 @@ static void release_inactive_stripe_list(struct r5conf *conf,
 					 int hash)
 {
 	int size;
-	bool do_wakeup = false;
+	unsigned long do_wakeup = 0;
+	int i = 0;
 	unsigned long flags;
 
 	if (hash == NR_STRIPE_HASH_LOCKS) {
@@ -365,15 +366,21 @@ static void release_inactive_stripe_list(struct r5conf *conf,
 			    !list_empty(list))
 				atomic_dec(&conf->empty_inactive_list_nr);
 			list_splice_tail_init(list, conf->inactive_list + hash);
-			do_wakeup = true;
+			do_wakeup |= 1 << hash;
 			spin_unlock_irqrestore(conf->hash_locks + hash, flags);
 		}
 		size--;
 		hash--;
 	}
 
+	for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) {
+		if (do_wakeup & (1 << i))
+			wake_up(&conf->wait_for_stripe[i]);
+	}
+
 	if (do_wakeup) {
-		wake_up(&conf->wait_for_stripe);
+		if (atomic_read(&conf->active_stripes) == 0)
+			wake_up(&conf->wait_for_quiescent);
 		if (conf->retry_read_aligned)
 			md_wakeup_thread(conf->mddev->thread);
 	}
@@ -667,15 +674,15 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
 	spin_lock_irq(conf->hash_locks + hash);
 
 	do {
-		wait_event_lock_irq(conf->wait_for_stripe,
+		wait_event_lock_irq(conf->wait_for_quiescent,
 				    conf->quiesce == 0 || noquiesce,
 				    *(conf->hash_locks + hash));
 		sh = __find_stripe(conf, sector, conf->generation - previous);
 		if (!sh) {
 			if (!test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) {
 				sh = get_free_stripe(conf, hash);
-				if (!sh && llist_empty(&conf->released_stripes) &&
-				    !test_bit(R5_DID_ALLOC, &conf->cache_state))
+				if (!sh && !test_bit(R5_DID_ALLOC,
+						     &conf->cache_state))
 					set_bit(R5_ALLOC_MORE,
 						&conf->cache_state);
 			}
@@ -684,14 +691,15 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
 			if (!sh) {
 				set_bit(R5_INACTIVE_BLOCKED,
 					&conf->cache_state);
-				wait_event_lock_irq(
-					conf->wait_for_stripe,
+				wait_event_exclusive_cmd(
+					conf->wait_for_stripe[hash],
 					!list_empty(conf->inactive_list + hash) &&
 					(atomic_read(&conf->active_stripes)
 					 < (conf->max_nr_stripes * 3 / 4)
 					 || !test_bit(R5_INACTIVE_BLOCKED,
 						      &conf->cache_state)),
-					*(conf->hash_locks + hash));
+					spin_unlock_irq(conf->hash_locks + hash),
+					spin_lock_irq(conf->hash_locks + hash));
 				clear_bit(R5_INACTIVE_BLOCKED,
 					  &conf->cache_state);
 			} else {
@@ -716,6 +724,9 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
 		}
 	} while (sh == NULL);
 
+	if (!list_empty(conf->inactive_list + hash))
+		wake_up(&conf->wait_for_stripe[hash]);
+
 	spin_unlock_irq(conf->hash_locks + hash);
 	return sh;
 }
@@ -2177,7 +2188,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	cnt = 0;
 	list_for_each_entry(nsh, &newstripes, lru) {
 		lock_device_hash_lock(conf, hash);
-		wait_event_cmd(conf->wait_for_stripe,
+		wait_event_exclusive_cmd(conf->wait_for_stripe[hash],
 				    !list_empty(conf->inactive_list + hash),
 				    unlock_device_hash_lock(conf, hash),
 				    lock_device_hash_lock(conf, hash));
@@ -4760,7 +4771,7 @@ static void raid5_align_endio(struct bio *bi, int error)
 					 raid_bi, 0);
 		bio_endio(raid_bi, 0);
 		if (atomic_dec_and_test(&conf->active_aligned_reads))
-			wake_up(&conf->wait_for_stripe);
+			wake_up(&conf->wait_for_quiescent);
 		return;
 	}
 
@@ -4855,7 +4866,7 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 		align_bi->bi_iter.bi_sector += rdev->data_offset;
 
 		spin_lock_irq(&conf->device_lock);
-		wait_event_lock_irq(conf->wait_for_stripe,
+		wait_event_lock_irq(conf->wait_for_quiescent,
 				    conf->quiesce == 0,
 				    conf->device_lock);
 		atomic_inc(&conf->active_aligned_reads);
@@ -5699,7 +5710,7 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 		bio_endio(raid_bio, 0);
 	}
 	if (atomic_dec_and_test(&conf->active_aligned_reads))
-		wake_up(&conf->wait_for_stripe);
+		wake_up(&conf->wait_for_quiescent);
 	return handled;
 }
 
@@ -6433,7 +6444,10 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 		goto abort;
 	spin_lock_init(&conf->device_lock);
 	seqcount_init(&conf->gen_lock);
-	init_waitqueue_head(&conf->wait_for_stripe);
+	init_waitqueue_head(&conf->wait_for_quiescent);
+	for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) {
+		init_waitqueue_head(&conf->wait_for_stripe[i]);
+	}
 	init_waitqueue_head(&conf->wait_for_overlap);
 	INIT_LIST_HEAD(&conf->handle_list);
 	INIT_LIST_HEAD(&conf->hold_list);
@@ -7466,7 +7480,7 @@ static void raid5_quiesce(struct mddev *mddev, int state)
 		 * active stripes can drain
 		 */
 		conf->quiesce = 2;
-		wait_event_cmd(conf->wait_for_stripe,
+		wait_event_cmd(conf->wait_for_quiescent,
 				    atomic_read(&conf->active_stripes) == 0 &&
 				    atomic_read(&conf->active_aligned_reads) == 0,
 				    unlock_all_device_hash_locks_irq(conf),
@@ -7480,7 +7494,7 @@ static void raid5_quiesce(struct mddev *mddev, int state)
 	case 0: /* re-enable writes */
 		lock_all_device_hash_locks_irq(conf);
 		conf->quiesce = 0;
-		wake_up(&conf->wait_for_stripe);
+		wake_up(&conf->wait_for_quiescent);
 		wake_up(&conf->wait_for_overlap);
 		unlock_all_device_hash_locks_irq(conf);
 		break;

drivers/md/raid5.h

@@ -511,7 +511,8 @@ struct r5conf {
 	struct list_head	inactive_list[NR_STRIPE_HASH_LOCKS];
 	atomic_t		empty_inactive_list_nr;
 	struct llist_head	released_stripes;
-	wait_queue_head_t	wait_for_stripe;
+	wait_queue_head_t	wait_for_quiescent;
+	wait_queue_head_t	wait_for_stripe[NR_STRIPE_HASH_LOCKS];
 	wait_queue_head_t	wait_for_overlap;
 	unsigned long		cache_state;
 #define R5_INACTIVE_BLOCKED	1	/* release of inactive stripes blocked,

include/linux/wait.h

@@ -358,6 +358,19 @@ do {									\
 	__ret;								\
 })
 
+#define __wait_event_exclusive_cmd(wq, condition, cmd1, cmd2)		\
+	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 1, 0,	\
+			    cmd1; schedule(); cmd2)
+/*
+ * Just like wait_event_cmd(), except it sets exclusive flag
+ */
+#define wait_event_exclusive_cmd(wq, condition, cmd1, cmd2)		\
+do {									\
+	if (condition)							\
+		break;							\
+	__wait_event_exclusive_cmd(wq, condition, cmd1, cmd2);		\
+} while (0)
+
 #define __wait_event_cmd(wq, condition, cmd1, cmd2)			\
 	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
 			    cmd1; schedule(); cmd2)