Merge tag 'md/3.15' of git://neil.brown.name/md

Pull md updates from Neil Brown:
 "Just a few md patches for the 3.15 merge window.

  Not much happening in md/raid at the moment.  Just a few bug fixes
  (one for -stable) and a couple of performance tweaks"

* tag 'md/3.15' of git://neil.brown.name/md:
  raid5: get_active_stripe avoids device_lock
  raid5: make_request does less prepare wait
  md: avoid oops on unload if some process is in poll or select.
  md/raid1: r1buf_pool_alloc: free allocate pages when subsequent allocation fails.
  md/bitmap: don't abuse i_writecount for bitmap files.

5 files changed, 61 insertions, 51 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 4195a01b153..9a8e66ae04f 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1988,7 +1988,6 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 		if (mddev->bitmap_info.file) {
 			struct file *f = mddev->bitmap_info.file;
 			mddev->bitmap_info.file = NULL;
-			restore_bitmap_write_access(f);
 			fput(f);
 		}
 	} else {
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4ad5cc4e63e..8fda38d23e3 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5181,32 +5181,6 @@ static int restart_array(struct mddev *mddev)
 	return 0;
 }
 
-/* similar to deny_write_access, but accounts for our holding a reference
- * to the file ourselves */
-static int deny_bitmap_write_access(struct file * file)
-{
-	struct inode *inode = file->f_mapping->host;
-
-	spin_lock(&inode->i_lock);
-	if (atomic_read(&inode->i_writecount) > 1) {
-		spin_unlock(&inode->i_lock);
-		return -ETXTBSY;
-	}
-	atomic_set(&inode->i_writecount, -1);
-	spin_unlock(&inode->i_lock);
-
-	return 0;
-}
-
-void restore_bitmap_write_access(struct file *file)
-{
-	struct inode *inode = file->f_mapping->host;
-
-	spin_lock(&inode->i_lock);
-	atomic_set(&inode->i_writecount, 1);
-	spin_unlock(&inode->i_lock);
-}
-
 static void md_clean(struct mddev *mddev)
 {
 	mddev->array_sectors = 0;
@@ -5427,7 +5401,6 @@ static int do_md_stop(struct mddev * mddev, int mode,
 
 		bitmap_destroy(mddev);
 		if (mddev->bitmap_info.file) {
-			restore_bitmap_write_access(mddev->bitmap_info.file);
 			fput(mddev->bitmap_info.file);
 			mddev->bitmap_info.file = NULL;
 		}
@@ -5979,7 +5952,7 @@ abort_export:
 
 static int set_bitmap_file(struct mddev *mddev, int fd)
 {
-	int err;
+	int err = 0;
 
 	if (mddev->pers) {
 		if (!mddev->pers->quiesce)
@@ -5991,6 +5964,7 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
 
 
 	if (fd >= 0) {
+		struct inode *inode;
 		if (mddev->bitmap)
 			return -EEXIST; /* cannot add when bitmap is present */
 		mddev->bitmap_info.file = fget(fd);
@@ -6001,10 +5975,21 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
 			return -EBADF;
 		}
 
-		err = deny_bitmap_write_access(mddev->bitmap_info.file);
-		if (err) {
+		inode = mddev->bitmap_info.file->f_mapping->host;
+		if (!S_ISREG(inode->i_mode)) {
+			printk(KERN_ERR "%s: error: bitmap file must be a regular file\n",
+			       mdname(mddev));
+			err = -EBADF;
+		} else if (!(mddev->bitmap_info.file->f_mode & FMODE_WRITE)) {
+			printk(KERN_ERR "%s: error: bitmap file must open for write\n",
+			       mdname(mddev));
+			err = -EBADF;
+		} else if (atomic_read(&inode->i_writecount) != 1) {
 			printk(KERN_ERR "%s: error: bitmap file is already in use\n",
 			       mdname(mddev));
+			err = -EBUSY;
+		}
+		if (err) {
 			fput(mddev->bitmap_info.file);
 			mddev->bitmap_info.file = NULL;
 			return err;
@@ -6027,10 +6012,8 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
 		mddev->pers->quiesce(mddev, 0);
 	}
 	if (fd < 0) {
-		if (mddev->bitmap_info.file) {
-			restore_bitmap_write_access(mddev->bitmap_info.file);
+		if (mddev->bitmap_info.file)
 			fput(mddev->bitmap_info.file);
-		}
 		mddev->bitmap_info.file = NULL;
 	}
 
@@ -7182,11 +7165,14 @@ static int md_seq_open(struct inode *inode, struct file *file)
 	return error;
 }
 
+static int md_unloading;
 static unsigned int mdstat_poll(struct file *filp, poll_table *wait)
 {
 	struct seq_file *seq = filp->private_data;
 	int mask;
 
+	if (md_unloading)
+		return POLLIN|POLLRDNORM|POLLERR|POLLPRI;;
 	poll_wait(filp, &md_event_waiters, wait);
 
 	/* always allow read */
@@ -8672,6 +8658,7 @@ static __exit void md_exit(void)
 {
 	struct mddev *mddev;
 	struct list_head *tmp;
+	int delay = 1;
 
 	blk_unregister_region(MKDEV(MD_MAJOR,0), 1U << MINORBITS);
 	blk_unregister_region(MKDEV(mdp_major,0), 1U << MINORBITS);
@@ -8680,7 +8667,19 @@ static __exit void md_exit(void)
 	unregister_blkdev(mdp_major, "mdp");
 	unregister_reboot_notifier(&md_notifier);
 	unregister_sysctl_table(raid_table_header);
+
+	/* We cannot unload the modules while some process is
+	 * waiting for us in select() or poll() - wake them up
+	 */
+	md_unloading = 1;
+	while (waitqueue_active(&md_event_waiters)) {
+		/* not safe to leave yet */
+		wake_up(&md_event_waiters);
+		msleep(delay);
+		delay += delay;
+	}
 	remove_proc_entry("mdstat", NULL);
+
 	for_each_mddev(mddev, tmp) {
 		export_array(mddev);
 		mddev->hold_active = 0;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 07bba96de26..a49d991f3fe 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -605,7 +605,6 @@ extern int md_check_no_bitmap(struct mddev *mddev);
 extern int md_integrity_register(struct mddev *mddev);
 extern void md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev);
 extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale);
-extern void restore_bitmap_write_access(struct file *file);
 
 extern void mddev_init(struct mddev *mddev);
 extern int md_run(struct mddev *mddev);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 4a6ca1cb2e7..56e24c072b6 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -97,6 +97,7 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 	struct pool_info *pi = data;
 	struct r1bio *r1_bio;
 	struct bio *bio;
+	int need_pages;
 	int i, j;
 
 	r1_bio = r1bio_pool_alloc(gfp_flags, pi);
@@ -119,15 +120,15 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 	 * RESYNC_PAGES for each bio.
 	 */
 	if (test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery))
-		j = pi->raid_disks;
+		need_pages = pi->raid_disks;
 	else
-		j = 1;
-	while(j--) {
+		need_pages = 1;
+	for (j = 0; j < need_pages; j++) {
 		bio = r1_bio->bios[j];
 		bio->bi_vcnt = RESYNC_PAGES;
 
 		if (bio_alloc_pages(bio, gfp_flags))
-			goto out_free_bio;
+			goto out_free_pages;
 	}
 	/* If not user-requests, copy the page pointers to all bios */
 	if (!test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) {
@@ -141,6 +142,14 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 
 	return r1_bio;
 
+out_free_pages:
+	while (--j >= 0) {
+		struct bio_vec *bv;
+
+		bio_for_each_segment_all(bv, r1_bio->bios[j], i)
+			__free_page(bv->bv_page);
+	}
+
 out_free_bio:
 	while (++j < pi->raid_disks)
 		bio_put(r1_bio->bios[j]);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 16f5c21963d..25247a85291 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -679,14 +679,9 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
 				init_stripe(sh, sector, previous);
 				atomic_inc(&sh->count);
 			}
-		} else {
+		} else if (!atomic_inc_not_zero(&sh->count)) {
 			spin_lock(&conf->device_lock);
-			if (atomic_read(&sh->count)) {
-				BUG_ON(!list_empty(&sh->lru)
-				    && !test_bit(STRIPE_EXPANDING, &sh->state)
-				    && !test_bit(STRIPE_ON_UNPLUG_LIST, &sh->state)
-					);
-			} else {
+			if (!atomic_read(&sh->count)) {
 				if (!test_bit(STRIPE_HANDLE, &sh->state))
 					atomic_inc(&conf->active_stripes);
 				BUG_ON(list_empty(&sh->lru) &&
@@ -4552,6 +4547,8 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 	struct stripe_head *sh;
 	const int rw = bio_data_dir(bi);
 	int remaining;
+	DEFINE_WAIT(w);
+	bool do_prepare;
 
 	if (unlikely(bi->bi_rw & REQ_FLUSH)) {
 		md_flush_request(mddev, bi);
@@ -4575,15 +4572,18 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 	bi->bi_next = NULL;
 	bi->bi_phys_segments = 1;	/* over-loaded to count active stripes */
 
+	prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
 	for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) {
-		DEFINE_WAIT(w);
 		int previous;
 		int seq;
 
+		do_prepare = false;
 	retry:
 		seq = read_seqcount_begin(&conf->gen_lock);
 		previous = 0;
-		prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
+		if (do_prepare)
+			prepare_to_wait(&conf->wait_for_overlap, &w,
+				TASK_UNINTERRUPTIBLE);
 		if (unlikely(conf->reshape_progress != MaxSector)) {
 			/* spinlock is needed as reshape_progress may be
 			 * 64bit on a 32bit platform, and so it might be
@@ -4604,6 +4604,7 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 				    : logical_sector >= conf->reshape_safe) {
 					spin_unlock_irq(&conf->device_lock);
 					schedule();
+					do_prepare = true;
 					goto retry;
 				}
 			}
@@ -4640,6 +4641,7 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 				if (must_retry) {
 					release_stripe(sh);
 					schedule();
+					do_prepare = true;
 					goto retry;
 				}
 			}
@@ -4663,8 +4665,10 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 				prepare_to_wait(&conf->wait_for_overlap,
 						&w, TASK_INTERRUPTIBLE);
 				if (logical_sector >= mddev->suspend_lo &&
-				    logical_sector < mddev->suspend_hi)
+				    logical_sector < mddev->suspend_hi) {
 					schedule();
+					do_prepare = true;
+				}
 				goto retry;
 			}
 
@@ -4677,9 +4681,9 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 				md_wakeup_thread(mddev->thread);
 				release_stripe(sh);
 				schedule();
+				do_prepare = true;
 				goto retry;
 			}
-			finish_wait(&conf->wait_for_overlap, &w);
 			set_bit(STRIPE_HANDLE, &sh->state);
 			clear_bit(STRIPE_DELAYED, &sh->state);
 			if ((bi->bi_rw & REQ_SYNC) &&
@@ -4689,10 +4693,10 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 		} else {
 			/* cannot get stripe for read-ahead, just give-up */
 			clear_bit(BIO_UPTODATE, &bi->bi_flags);
-			finish_wait(&conf->wait_for_overlap, &w);
 			break;
 		}
 	}
+	finish_wait(&conf->wait_for_overlap, &w);
 
 	remaining = raid5_dec_bi_active_stripes(bi);
 	if (remaining == 0) {