Merge tag 'md-6.14-20250113' of https://git.kernel.org/pub/scm/linux/kernel/git/mdraid/linux into for-6.14/block

Pull MD updates from Song:

"1. Reintroduce md-linear, by Yu Kuai.
 2. md-bitmap refactor and fix, by Yu Kuai.
 3. Replace kmap_atomic with kmap_local_page, by David Reaver."

* tag 'md-6.14-20250113' of https://git.kernel.org/pub/scm/linux/kernel/git/mdraid/linux:
  md/md-bitmap: move bitmap_{start, end}write to md upper layer
  md/raid5: implement pers->bitmap_sector()
  md: add a new callback pers->bitmap_sector()
  md/md-bitmap: remove the last parameter for bimtap_ops->endwrite()
  md/md-bitmap: factor behind write counters out from bitmap_{start/end}write()
  md: Replace deprecated kmap_atomic() with kmap_local_page()
  md: reintroduce md-linear

drivers/md/Kconfig

@@ -61,6 +61,19 @@ config MD_BITMAP_FILE
 	  various kernel APIs and can only work with files on a file system not
 	  actually sitting on the MD device.
 
+config MD_LINEAR
+	tristate "Linear (append) mode"
+	depends on BLK_DEV_MD
+	help
+	  If you say Y here, then your multiple devices driver will be able to
+	  use the so-called linear mode, i.e. it will combine the hard disk
+	  partitions by simply appending one to the other.
+
+	  To compile this as a module, choose M here: the module
+	  will be called linear.
+
+	  If unsure, say Y.
+
 config MD_RAID0
 	tristate "RAID-0 (striping) mode"
 	depends on BLK_DEV_MD

drivers/md/Makefile

@@ -29,12 +29,14 @@ dm-zoned-y	+= dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o
 
 md-mod-y	+= md.o md-bitmap.o
 raid456-y	+= raid5.o raid5-cache.o raid5-ppl.o
+linear-y       += md-linear.o
 
 # Note: link order is important.  All raid personalities
 # and must come before md.o, as they each initialise
 # themselves, and md.o may use the personalities when it
 # auto-initialised.
 
+obj-$(CONFIG_MD_LINEAR)		+= linear.o
 obj-$(CONFIG_MD_RAID0)		+= raid0.o
 obj-$(CONFIG_MD_RAID1)		+= raid1.o
 obj-$(CONFIG_MD_RAID10)		+= raid10.o

drivers/md/md-autodetect.c

@@ -49,6 +49,7 @@ static int md_setup_ents __initdata;
  *             instead of just one.  -- KTK
  * 18May2000: Added support for persistent-superblock arrays:
  *             md=n,0,factor,fault,device-list   uses RAID0 for device n
+ *             md=n,-1,factor,fault,device-list  uses LINEAR for device n
  *             md=n,device-list      reads a RAID superblock from the devices
  *             elements in device-list are read by name_to_kdev_t so can be
  *             a hex number or something like /dev/hda1 /dev/sdb
@@ -87,7 +88,7 @@ static int __init md_setup(char *str)
 		md_setup_ents++;
 	switch (get_option(&str, &level)) {	/* RAID level */
 	case 2: /* could be 0 or -1.. */
-		if (level == 0) {
+		if (level == 0 || level == LEVEL_LINEAR) {
 			if (get_option(&str, &factor) != 2 ||	/* Chunk Size */
 					get_option(&str, &fault) != 2) {
 				printk(KERN_WARNING "md: Too few arguments supplied to md=.\n");
@@ -95,7 +96,10 @@ static int __init md_setup(char *str)
 			}
 			md_setup_args[ent].level = level;
 			md_setup_args[ent].chunk = 1 << (factor+12);
-			pername = "raid0";
+			if (level ==  LEVEL_LINEAR)
+				pername = "linear";
+			else
+				pername = "raid0";
 			break;
 		}
 		fallthrough;

drivers/md/md-bitmap.c

@@ -682,7 +682,7 @@ static void bitmap_update_sb(void *data)
 		return;
 	if (!bitmap->storage.sb_page) /* no superblock */
 		return;
-	sb = kmap_atomic(bitmap->storage.sb_page);
+	sb = kmap_local_page(bitmap->storage.sb_page);
 	sb->events = cpu_to_le64(bitmap->mddev->events);
 	if (bitmap->mddev->events < bitmap->events_cleared)
 		/* rocking back to read-only */
@@ -702,7 +702,7 @@ static void bitmap_update_sb(void *data)
 	sb->nodes = cpu_to_le32(bitmap->mddev->bitmap_info.nodes);
 	sb->sectors_reserved = cpu_to_le32(bitmap->mddev->
 					   bitmap_info.space);
-	kunmap_atomic(sb);
+	kunmap_local(sb);
 
 	if (bitmap->storage.file)
 		write_file_page(bitmap, bitmap->storage.sb_page, 1);
@@ -717,7 +717,7 @@ static void bitmap_print_sb(struct bitmap *bitmap)
 
 	if (!bitmap || !bitmap->storage.sb_page)
 		return;
-	sb = kmap_atomic(bitmap->storage.sb_page);
+	sb = kmap_local_page(bitmap->storage.sb_page);
 	pr_debug("%s: bitmap file superblock:\n", bmname(bitmap));
 	pr_debug("         magic: %08x\n", le32_to_cpu(sb->magic));
 	pr_debug("       version: %u\n", le32_to_cpu(sb->version));
@@ -736,7 +736,7 @@ static void bitmap_print_sb(struct bitmap *bitmap)
 	pr_debug("     sync size: %llu KB\n",
 		 (unsigned long long)le64_to_cpu(sb->sync_size)/2);
 	pr_debug("max write behind: %u\n", le32_to_cpu(sb->write_behind));
-	kunmap_atomic(sb);
+	kunmap_local(sb);
 }
 
 /*
@@ -760,7 +760,7 @@ static int md_bitmap_new_disk_sb(struct bitmap *bitmap)
 		return -ENOMEM;
 	bitmap->storage.sb_index = 0;
 
-	sb = kmap_atomic(bitmap->storage.sb_page);
+	sb = kmap_local_page(bitmap->storage.sb_page);
 
 	sb->magic = cpu_to_le32(BITMAP_MAGIC);
 	sb->version = cpu_to_le32(BITMAP_MAJOR_HI);
@@ -768,7 +768,7 @@ static int md_bitmap_new_disk_sb(struct bitmap *bitmap)
 	chunksize = bitmap->mddev->bitmap_info.chunksize;
 	BUG_ON(!chunksize);
 	if (!is_power_of_2(chunksize)) {
-		kunmap_atomic(sb);
+		kunmap_local(sb);
 		pr_warn("bitmap chunksize not a power of 2\n");
 		return -EINVAL;
 	}
@@ -803,7 +803,7 @@ static int md_bitmap_new_disk_sb(struct bitmap *bitmap)
 	sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
 	bitmap->mddev->bitmap_info.nodes = 0;
 
-	kunmap_atomic(sb);
+	kunmap_local(sb);
 
 	return 0;
 }
@@ -865,7 +865,7 @@ static int md_bitmap_read_sb(struct bitmap *bitmap)
 		return err;
 
 	err = -EINVAL;
-	sb = kmap_atomic(sb_page);
+	sb = kmap_local_page(sb_page);
 
 	chunksize = le32_to_cpu(sb->chunksize);
 	daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ;
@@ -932,7 +932,7 @@ static int md_bitmap_read_sb(struct bitmap *bitmap)
 	err = 0;
 
 out:
-	kunmap_atomic(sb);
+	kunmap_local(sb);
 	if (err == 0 && nodes && (bitmap->cluster_slot < 0)) {
 		/* Assigning chunksize is required for "re_read" */
 		bitmap->mddev->bitmap_info.chunksize = chunksize;
@@ -1161,12 +1161,12 @@ static void md_bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 	bit = file_page_offset(&bitmap->storage, chunk);
 
 	/* set the bit */
-	kaddr = kmap_atomic(page);
+	kaddr = kmap_local_page(page);
 	if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags))
 		set_bit(bit, kaddr);
 	else
 		set_bit_le(bit, kaddr);
-	kunmap_atomic(kaddr);
+	kunmap_local(kaddr);
 	pr_debug("set file bit %lu page %lu\n", bit, index);
 	/* record page number so it gets flushed to disk when unplug occurs */
 	set_page_attr(bitmap, index - node_offset, BITMAP_PAGE_DIRTY);
@@ -1190,12 +1190,12 @@ static void md_bitmap_file_clear_bit(struct bitmap *bitmap, sector_t block)
 	if (!page)
 		return;
 	bit = file_page_offset(&bitmap->storage, chunk);
-	paddr = kmap_atomic(page);
+	paddr = kmap_local_page(page);
 	if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags))
 		clear_bit(bit, paddr);
 	else
 		clear_bit_le(bit, paddr);
-	kunmap_atomic(paddr);
+	kunmap_local(paddr);
 	if (!test_page_attr(bitmap, index - node_offset, BITMAP_PAGE_NEEDWRITE)) {
 		set_page_attr(bitmap, index - node_offset, BITMAP_PAGE_PENDING);
 		bitmap->allclean = 0;
@@ -1214,12 +1214,12 @@ static int md_bitmap_file_test_bit(struct bitmap *bitmap, sector_t block)
 	if (!page)
 		return -EINVAL;
 	bit = file_page_offset(&bitmap->storage, chunk);
-	paddr = kmap_atomic(page);
+	paddr = kmap_local_page(page);
 	if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags))
 		set = test_bit(bit, paddr);
 	else
 		set = test_bit_le(bit, paddr);
-	kunmap_atomic(paddr);
+	kunmap_local(paddr);
 	return set;
 }
 
@@ -1388,9 +1388,9 @@ static int md_bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 			 * If the bitmap is out of date, dirty the whole page
 			 * and write it out
 			 */
-			paddr = kmap_atomic(page);
+			paddr = kmap_local_page(page);
 			memset(paddr + offset, 0xff, PAGE_SIZE - offset);
-			kunmap_atomic(paddr);
+			kunmap_local(paddr);
 
 			filemap_write_page(bitmap, i, true);
 			if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags)) {
@@ -1406,12 +1406,12 @@ static int md_bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 		void *paddr;
 		bool was_set;
 
-		paddr = kmap_atomic(page);
+		paddr = kmap_local_page(page);
 		if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags))
 			was_set = test_bit(bit, paddr);
 		else
 			was_set = test_bit_le(bit, paddr);
-		kunmap_atomic(paddr);
+		kunmap_local(paddr);
 
 		if (was_set) {
 			/* if the disk bit is set, set the memory bit */
@@ -1546,10 +1546,10 @@ static void bitmap_daemon_work(struct mddev *mddev)
 		bitmap_super_t *sb;
 		bitmap->need_sync = 0;
 		if (bitmap->storage.filemap) {
-			sb = kmap_atomic(bitmap->storage.sb_page);
+			sb = kmap_local_page(bitmap->storage.sb_page);
 			sb->events_cleared =
 				cpu_to_le64(bitmap->events_cleared);
-			kunmap_atomic(sb);
+			kunmap_local(sb);
 			set_page_attr(bitmap, 0,
 				      BITMAP_PAGE_NEEDWRITE);
 		}
@@ -1671,24 +1671,13 @@ __acquires(bitmap->lock)
 }
 
 static int bitmap_startwrite(struct mddev *mddev, sector_t offset,
-			     unsigned long sectors, bool behind)
+			     unsigned long sectors)
 {
 	struct bitmap *bitmap = mddev->bitmap;
 
 	if (!bitmap)
 		return 0;
 
-	if (behind) {
-		int bw;
-		atomic_inc(&bitmap->behind_writes);
-		bw = atomic_read(&bitmap->behind_writes);
-		if (bw > bitmap->behind_writes_used)
-			bitmap->behind_writes_used = bw;
-
-		pr_debug("inc write-behind count %d/%lu\n",
-			 bw, bitmap->mddev->bitmap_info.max_write_behind);
-	}
-
 	while (sectors) {
 		sector_t blocks;
 		bitmap_counter_t *bmc;
@@ -1737,21 +1726,13 @@ static int bitmap_startwrite(struct mddev *mddev, sector_t offset,
 }
 
 static void bitmap_endwrite(struct mddev *mddev, sector_t offset,
-			    unsigned long sectors, bool success, bool behind)
+			    unsigned long sectors)
 {
 	struct bitmap *bitmap = mddev->bitmap;
 
 	if (!bitmap)
 		return;
 
-	if (behind) {
-		if (atomic_dec_and_test(&bitmap->behind_writes))
-			wake_up(&bitmap->behind_wait);
-		pr_debug("dec write-behind count %d/%lu\n",
-			 atomic_read(&bitmap->behind_writes),
-			 bitmap->mddev->bitmap_info.max_write_behind);
-	}
-
 	while (sectors) {
 		sector_t blocks;
 		unsigned long flags;
@@ -1764,15 +1745,16 @@ static void bitmap_endwrite(struct mddev *mddev, sector_t offset,
 			return;
 		}
 
-		if (success && !bitmap->mddev->degraded &&
-		    bitmap->events_cleared < bitmap->mddev->events) {
-			bitmap->events_cleared = bitmap->mddev->events;
-			bitmap->need_sync = 1;
-			sysfs_notify_dirent_safe(bitmap->sysfs_can_clear);
-		}
-
-		if (!success && !NEEDED(*bmc))
+		if (!bitmap->mddev->degraded) {
+			if (bitmap->events_cleared < bitmap->mddev->events) {
+				bitmap->events_cleared = bitmap->mddev->events;
+				bitmap->need_sync = 1;
+				sysfs_notify_dirent_safe(
+						bitmap->sysfs_can_clear);
+			}
+		} else if (!NEEDED(*bmc)) {
 			*bmc |= NEEDED_MASK;
+		}
 
 		if (COUNTER(*bmc) == COUNTER_MAX)
 			wake_up(&bitmap->overflow_wait);
@@ -2062,6 +2044,37 @@ static void md_bitmap_free(void *data)
 	kfree(bitmap);
 }
 
+static void bitmap_start_behind_write(struct mddev *mddev)
+{
+	struct bitmap *bitmap = mddev->bitmap;
+	int bw;
+
+	if (!bitmap)
+		return;
+
+	atomic_inc(&bitmap->behind_writes);
+	bw = atomic_read(&bitmap->behind_writes);
+	if (bw > bitmap->behind_writes_used)
+		bitmap->behind_writes_used = bw;
+
+	pr_debug("inc write-behind count %d/%lu\n",
+		 bw, bitmap->mddev->bitmap_info.max_write_behind);
+}
+
+static void bitmap_end_behind_write(struct mddev *mddev)
+{
+	struct bitmap *bitmap = mddev->bitmap;
+
+	if (!bitmap)
+		return;
+
+	if (atomic_dec_and_test(&bitmap->behind_writes))
+		wake_up(&bitmap->behind_wait);
+	pr_debug("dec write-behind count %d/%lu\n",
+		 atomic_read(&bitmap->behind_writes),
+		 bitmap->mddev->bitmap_info.max_write_behind);
+}
+
 static void bitmap_wait_behind_writes(struct mddev *mddev)
 {
 	struct bitmap *bitmap = mddev->bitmap;
@@ -2981,6 +2994,9 @@ static struct bitmap_operations bitmap_ops = {
 	.dirty_bits		= bitmap_dirty_bits,
 	.unplug			= bitmap_unplug,
 	.daemon_work		= bitmap_daemon_work,
+
+	.start_behind_write	= bitmap_start_behind_write,
+	.end_behind_write	= bitmap_end_behind_write,
 	.wait_behind_writes	= bitmap_wait_behind_writes,
 
 	.startwrite		= bitmap_startwrite,

drivers/md/md-bitmap.h

@@ -84,12 +84,15 @@ struct bitmap_operations {
 			   unsigned long e);
 	void (*unplug)(struct mddev *mddev, bool sync);
 	void (*daemon_work)(struct mddev *mddev);
+
+	void (*start_behind_write)(struct mddev *mddev);
+	void (*end_behind_write)(struct mddev *mddev);
 	void (*wait_behind_writes)(struct mddev *mddev);
 
 	int (*startwrite)(struct mddev *mddev, sector_t offset,
-			  unsigned long sectors, bool behind);
+			  unsigned long sectors);
 	void (*endwrite)(struct mddev *mddev, sector_t offset,
-			 unsigned long sectors, bool success, bool behind);
+			 unsigned long sectors);
 	bool (*start_sync)(struct mddev *mddev, sector_t offset,
 			   sector_t *blocks, bool degraded);
 	void (*end_sync)(struct mddev *mddev, sector_t offset, sector_t *blocks);

drivers/md/md-linear.c

@@ -0,0 +1,354 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * linear.c : Multiple Devices driver for Linux Copyright (C) 1994-96 Marc
+ * ZYNGIER <zyngier@ufr-info-p7.ibp.fr> or <maz@gloups.fdn.fr>
+ */
+
+#include <linux/blkdev.h>
+#include <linux/raid/md_u.h>
+#include <linux/seq_file.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <trace/events/block.h>
+#include "md.h"
+
+struct dev_info {
+	struct md_rdev	*rdev;
+	sector_t	end_sector;
+};
+
+struct linear_conf {
+	struct rcu_head         rcu;
+	sector_t                array_sectors;
+	/* a copy of mddev->raid_disks */
+	int                     raid_disks;
+	struct dev_info         disks[] __counted_by(raid_disks);
+};
+
+/*
+ * find which device holds a particular offset
+ */
+static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
+{
+	int lo, mid, hi;
+	struct linear_conf *conf;
+
+	lo = 0;
+	hi = mddev->raid_disks - 1;
+	conf = mddev->private;
+
+	/*
+	 * Binary Search
+	 */
+
+	while (hi > lo) {
+
+		mid = (hi + lo) / 2;
+		if (sector < conf->disks[mid].end_sector)
+			hi = mid;
+		else
+			lo = mid + 1;
+	}
+
+	return conf->disks + lo;
+}
+
+static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks)
+{
+	struct linear_conf *conf;
+	sector_t array_sectors;
+
+	conf = mddev->private;
+	WARN_ONCE(sectors || raid_disks,
+		  "%s does not support generic reshape\n", __func__);
+	array_sectors = conf->array_sectors;
+
+	return array_sectors;
+}
+
+static int linear_set_limits(struct mddev *mddev)
+{
+	struct queue_limits lim;
+	int err;
+
+	md_init_stacking_limits(&lim);
+	lim.max_hw_sectors = mddev->chunk_sectors;
+	lim.max_write_zeroes_sectors = mddev->chunk_sectors;
+	lim.io_min = mddev->chunk_sectors << 9;
+	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
+	if (err) {
+		queue_limits_cancel_update(mddev->gendisk->queue);
+		return err;
+	}
+
+	return queue_limits_set(mddev->gendisk->queue, &lim);
+}
+
+static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
+{
+	struct linear_conf *conf;
+	struct md_rdev *rdev;
+	int ret = -EINVAL;
+	int cnt;
+	int i;
+
+	conf = kzalloc(struct_size(conf, disks, raid_disks), GFP_KERNEL);
+	if (!conf)
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * conf->raid_disks is copy of mddev->raid_disks. The reason to
+	 * keep a copy of mddev->raid_disks in struct linear_conf is,
+	 * mddev->raid_disks may not be consistent with pointers number of
+	 * conf->disks[] when it is updated in linear_add() and used to
+	 * iterate old conf->disks[] earray in linear_congested().
+	 * Here conf->raid_disks is always consitent with number of
+	 * pointers in conf->disks[] array, and mddev->private is updated
+	 * with rcu_assign_pointer() in linear_addr(), such race can be
+	 * avoided.
+	 */
+	conf->raid_disks = raid_disks;
+
+	cnt = 0;
+	conf->array_sectors = 0;
+
+	rdev_for_each(rdev, mddev) {
+		int j = rdev->raid_disk;
+		struct dev_info *disk = conf->disks + j;
+		sector_t sectors;
+
+		if (j < 0 || j >= raid_disks || disk->rdev) {
+			pr_warn("md/linear:%s: disk numbering problem. Aborting!\n",
+				mdname(mddev));
+			goto out;
+		}
+
+		disk->rdev = rdev;
+		if (mddev->chunk_sectors) {
+			sectors = rdev->sectors;
+			sector_div(sectors, mddev->chunk_sectors);
+			rdev->sectors = sectors * mddev->chunk_sectors;
+		}
+
+		conf->array_sectors += rdev->sectors;
+		cnt++;
+	}
+	if (cnt != raid_disks) {
+		pr_warn("md/linear:%s: not enough drives present. Aborting!\n",
+			mdname(mddev));
+		goto out;
+	}
+
+	/*
+	 * Here we calculate the device offsets.
+	 */
+	conf->disks[0].end_sector = conf->disks[0].rdev->sectors;
+
+	for (i = 1; i < raid_disks; i++)
+		conf->disks[i].end_sector =
+			conf->disks[i-1].end_sector +
+			conf->disks[i].rdev->sectors;
+
+	if (!mddev_is_dm(mddev)) {
+		ret = linear_set_limits(mddev);
+		if (ret)
+			goto out;
+	}
+
+	return conf;
+
+out:
+	kfree(conf);
+	return ERR_PTR(ret);
+}
+
+static int linear_run(struct mddev *mddev)
+{
+	struct linear_conf *conf;
+	int ret;
+
+	if (md_check_no_bitmap(mddev))
+		return -EINVAL;
+
+	conf = linear_conf(mddev, mddev->raid_disks);
+	if (IS_ERR(conf))
+		return PTR_ERR(conf);
+
+	mddev->private = conf;
+	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
+
+	ret =  md_integrity_register(mddev);
+	if (ret) {
+		kfree(conf);
+		mddev->private = NULL;
+	}
+	return ret;
+}
+
+static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
+{
+	/* Adding a drive to a linear array allows the array to grow.
+	 * It is permitted if the new drive has a matching superblock
+	 * already on it, with raid_disk equal to raid_disks.
+	 * It is achieved by creating a new linear_private_data structure
+	 * and swapping it in in-place of the current one.
+	 * The current one is never freed until the array is stopped.
+	 * This avoids races.
+	 */
+	struct linear_conf *newconf, *oldconf;
+
+	if (rdev->saved_raid_disk != mddev->raid_disks)
+		return -EINVAL;
+
+	rdev->raid_disk = rdev->saved_raid_disk;
+	rdev->saved_raid_disk = -1;
+
+	newconf = linear_conf(mddev, mddev->raid_disks + 1);
+	if (!newconf)
+		return -ENOMEM;
+
+	/* newconf->raid_disks already keeps a copy of * the increased
+	 * value of mddev->raid_disks, WARN_ONCE() is just used to make
+	 * sure of this. It is possible that oldconf is still referenced
+	 * in linear_congested(), therefore kfree_rcu() is used to free
+	 * oldconf until no one uses it anymore.
+	 */
+	oldconf = rcu_dereference_protected(mddev->private,
+			lockdep_is_held(&mddev->reconfig_mutex));
+	mddev->raid_disks++;
+	WARN_ONCE(mddev->raid_disks != newconf->raid_disks,
+		"copied raid_disks doesn't match mddev->raid_disks");
+	rcu_assign_pointer(mddev->private, newconf);
+	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
+	set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
+	kfree_rcu(oldconf, rcu);
+	return 0;
+}
+
+static void linear_free(struct mddev *mddev, void *priv)
+{
+	struct linear_conf *conf = priv;
+
+	kfree(conf);
+}
+
+static bool linear_make_request(struct mddev *mddev, struct bio *bio)
+{
+	struct dev_info *tmp_dev;
+	sector_t start_sector, end_sector, data_offset;
+	sector_t bio_sector = bio->bi_iter.bi_sector;
+
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
+		return true;
+
+	tmp_dev = which_dev(mddev, bio_sector);
+	start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
+	end_sector = tmp_dev->end_sector;
+	data_offset = tmp_dev->rdev->data_offset;
+
+	if (unlikely(bio_sector >= end_sector ||
+		     bio_sector < start_sector))
+		goto out_of_bounds;
+
+	if (unlikely(is_rdev_broken(tmp_dev->rdev))) {
+		md_error(mddev, tmp_dev->rdev);
+		bio_io_error(bio);
+		return true;
+	}
+
+	if (unlikely(bio_end_sector(bio) > end_sector)) {
+		/* This bio crosses a device boundary, so we have to split it */
+		struct bio *split = bio_split(bio, end_sector - bio_sector,
+					      GFP_NOIO, &mddev->bio_set);
+
+		if (IS_ERR(split)) {
+			bio->bi_status = errno_to_blk_status(PTR_ERR(split));
+			bio_endio(bio);
+			return true;
+		}
+
+		bio_chain(split, bio);
+		submit_bio_noacct(bio);
+		bio = split;
+	}
+
+	md_account_bio(mddev, &bio);
+	bio_set_dev(bio, tmp_dev->rdev->bdev);
+	bio->bi_iter.bi_sector = bio->bi_iter.bi_sector -
+		start_sector + data_offset;
+
+	if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
+		     !bdev_max_discard_sectors(bio->bi_bdev))) {
+		/* Just ignore it */
+		bio_endio(bio);
+	} else {
+		if (mddev->gendisk)
+			trace_block_bio_remap(bio, disk_devt(mddev->gendisk),
+					      bio_sector);
+		mddev_check_write_zeroes(mddev, bio);
+		submit_bio_noacct(bio);
+	}
+	return true;
+
+out_of_bounds:
+	pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %pg: %llu sectors, offset %llu\n",
+	       mdname(mddev),
+	       (unsigned long long)bio->bi_iter.bi_sector,
+	       tmp_dev->rdev->bdev,
+	       (unsigned long long)tmp_dev->rdev->sectors,
+	       (unsigned long long)start_sector);
+	bio_io_error(bio);
+	return true;
+}
+
+static void linear_status(struct seq_file *seq, struct mddev *mddev)
+{
+	seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2);
+}
+
+static void linear_error(struct mddev *mddev, struct md_rdev *rdev)
+{
+	if (!test_and_set_bit(MD_BROKEN, &mddev->flags)) {
+		char *md_name = mdname(mddev);
+
+		pr_crit("md/linear%s: Disk failure on %pg detected, failing array.\n",
+			md_name, rdev->bdev);
+	}
+}
+
+static void linear_quiesce(struct mddev *mddev, int state)
+{
+}
+
+static struct md_personality linear_personality = {
+	.name		= "linear",
+	.level		= LEVEL_LINEAR,
+	.owner		= THIS_MODULE,
+	.make_request	= linear_make_request,
+	.run		= linear_run,
+	.free		= linear_free,
+	.status		= linear_status,
+	.hot_add_disk	= linear_add,
+	.size		= linear_size,
+	.quiesce	= linear_quiesce,
+	.error_handler	= linear_error,
+};
+
+static int __init linear_init(void)
+{
+	return register_md_personality(&linear_personality);
+}
+
+static void linear_exit(void)
+{
+	unregister_md_personality(&linear_personality);
+}
+
+module_init(linear_init);
+module_exit(linear_exit);
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Linear device concatenation personality for MD (deprecated)");
+MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/
+MODULE_ALIAS("md-linear");
+MODULE_ALIAS("md-level--1");

drivers/md/md.c

@@ -8124,7 +8124,7 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev)
 		return;
 	mddev->pers->error_handler(mddev, rdev);
 
-	if (mddev->pers->level == 0)
+	if (mddev->pers->level == 0 || mddev->pers->level == LEVEL_LINEAR)
 		return;
 
 	if (mddev->degraded && !test_bit(MD_BROKEN, &mddev->flags))
@@ -8745,12 +8745,32 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 }
 EXPORT_SYMBOL_GPL(md_submit_discard_bio);
 
+static void md_bitmap_start(struct mddev *mddev,
+			    struct md_io_clone *md_io_clone)
+{
+	if (mddev->pers->bitmap_sector)
+		mddev->pers->bitmap_sector(mddev, &md_io_clone->offset,
+					   &md_io_clone->sectors);
+
+	mddev->bitmap_ops->startwrite(mddev, md_io_clone->offset,
+				      md_io_clone->sectors);
+}
+
+static void md_bitmap_end(struct mddev *mddev, struct md_io_clone *md_io_clone)
+{
+	mddev->bitmap_ops->endwrite(mddev, md_io_clone->offset,
+				    md_io_clone->sectors);
+}
+
 static void md_end_clone_io(struct bio *bio)
 {
 	struct md_io_clone *md_io_clone = bio->bi_private;
 	struct bio *orig_bio = md_io_clone->orig_bio;
 	struct mddev *mddev = md_io_clone->mddev;
 
+	if (bio_data_dir(orig_bio) == WRITE && mddev->bitmap)
+		md_bitmap_end(mddev, md_io_clone);
+
 	if (bio->bi_status && !orig_bio->bi_status)
 		orig_bio->bi_status = bio->bi_status;
 
@@ -8775,6 +8795,12 @@ static void md_clone_bio(struct mddev *mddev, struct bio **bio)
 	if (blk_queue_io_stat(bdev->bd_disk->queue))
 		md_io_clone->start_time = bio_start_io_acct(*bio);
 
+	if (bio_data_dir(*bio) == WRITE && mddev->bitmap) {
+		md_io_clone->offset = (*bio)->bi_iter.bi_sector;
+		md_io_clone->sectors = bio_sectors(*bio);
+		md_bitmap_start(mddev, md_io_clone);
+	}
+
 	clone->bi_end_io = md_end_clone_io;
 	clone->bi_private = md_io_clone;
 	*bio = clone;
@@ -8793,6 +8819,9 @@ void md_free_cloned_bio(struct bio *bio)
 	struct bio *orig_bio = md_io_clone->orig_bio;
 	struct mddev *mddev = md_io_clone->mddev;
 
+	if (bio_data_dir(orig_bio) == WRITE && mddev->bitmap)
+		md_bitmap_end(mddev, md_io_clone);
+
 	if (bio->bi_status && !orig_bio->bi_status)
 		orig_bio->bi_status = bio->bi_status;
 

drivers/md/md.h

@@ -746,6 +746,9 @@ struct md_personality
 	void *(*takeover) (struct mddev *mddev);
 	/* Changes the consistency policy of an active array. */
 	int (*change_consistency_policy)(struct mddev *mddev, const char *buf);
+	/* convert io ranges from array to bitmap */
+	void (*bitmap_sector)(struct mddev *mddev, sector_t *offset,
+			      unsigned long *sectors);
 };
 
 struct md_sysfs_entry {
@@ -828,6 +831,8 @@ struct md_io_clone {
 	struct mddev	*mddev;
 	struct bio	*orig_bio;
 	unsigned long	start_time;
+	sector_t	offset;
+	unsigned long	sectors;
 	struct bio	bio_clone;
 };
 

drivers/md/raid1.c

@@ -420,10 +420,8 @@ static void close_write(struct r1bio *r1_bio)
 		r1_bio->behind_master_bio = NULL;
 	}
 
-	/* clear the bitmap if all writes complete successfully */
-	mddev->bitmap_ops->endwrite(mddev, r1_bio->sector, r1_bio->sectors,
-				    !test_bit(R1BIO_Degraded, &r1_bio->state),
-				    test_bit(R1BIO_BehindIO, &r1_bio->state));
+	if (test_bit(R1BIO_BehindIO, &r1_bio->state))
+		mddev->bitmap_ops->end_behind_write(mddev);
 	md_write_end(mddev);
 }
 
@@ -480,8 +478,6 @@ static void raid1_end_write_request(struct bio *bio)
 		if (!test_bit(Faulty, &rdev->flags))
 			set_bit(R1BIO_WriteError, &r1_bio->state);
 		else {
-			/* Fail the request */
-			set_bit(R1BIO_Degraded, &r1_bio->state);
 			/* Finished with this branch */
 			r1_bio->bios[mirror] = NULL;
 			to_put = bio;
@@ -1535,11 +1531,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			write_behind = true;
 
 		r1_bio->bios[i] = NULL;
-		if (!rdev || test_bit(Faulty, &rdev->flags)) {
-			if (i < conf->raid_disks)
-				set_bit(R1BIO_Degraded, &r1_bio->state);
+		if (!rdev || test_bit(Faulty, &rdev->flags))
 			continue;
-		}
 
 		atomic_inc(&rdev->nr_pending);
 		if (test_bit(WriteErrorSeen, &rdev->flags)) {
@@ -1558,16 +1551,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 					 */
 					max_sectors = bad_sectors;
 				rdev_dec_pending(rdev, mddev);
-				/* We don't set R1BIO_Degraded as that
-				 * only applies if the disk is
-				 * missing, so it might be re-added,
-				 * and we want to know to recover this
-				 * chunk.
-				 * In this case the device is here,
-				 * and the fact that this chunk is not
-				 * in-sync is recorded in the bad
-				 * block log
-				 */
 				continue;
 			}
 			if (is_bad) {
@@ -1645,9 +1628,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			    stats.behind_writes < max_write_behind)
 				alloc_behind_master_bio(r1_bio, bio);
 
-			mddev->bitmap_ops->startwrite(
-				mddev, r1_bio->sector, r1_bio->sectors,
-				test_bit(R1BIO_BehindIO, &r1_bio->state));
+			if (test_bit(R1BIO_BehindIO, &r1_bio->state))
+				mddev->bitmap_ops->start_behind_write(mddev);
 			first_clone = 0;
 		}
 
@@ -2614,12 +2596,10 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
 			 * errors.
 			 */
 			fail = true;
-			if (!narrow_write_error(r1_bio, m)) {
+			if (!narrow_write_error(r1_bio, m))
 				md_error(conf->mddev,
 					 conf->mirrors[m].rdev);
 				/* an I/O failed, we can't clear the bitmap */
-				set_bit(R1BIO_Degraded, &r1_bio->state);
-			}
 			rdev_dec_pending(conf->mirrors[m].rdev,
 					 conf->mddev);
 		}
@@ -2710,8 +2690,6 @@ static void raid1d(struct md_thread *thread)
 			list_del(&r1_bio->retry_list);
 			idx = sector_to_idx(r1_bio->sector);
 			atomic_dec(&conf->nr_queued[idx]);
-			if (mddev->degraded)
-				set_bit(R1BIO_Degraded, &r1_bio->state);
 			if (test_bit(R1BIO_WriteError, &r1_bio->state))
 				close_write(r1_bio);
 			raid_end_bio_io(r1_bio);

drivers/md/raid1.h

@@ -188,7 +188,6 @@ struct r1bio {
 enum r1bio_state {
 	R1BIO_Uptodate,
 	R1BIO_IsSync,
-	R1BIO_Degraded,
 	R1BIO_BehindIO,
 /* Set ReadError on bios that experience a readerror so that
  * raid1d knows what to do with them.

drivers/md/raid10.c

@@ -428,10 +428,6 @@ static void close_write(struct r10bio *r10_bio)
 {
 	struct mddev *mddev = r10_bio->mddev;
 
-	/* clear the bitmap if all writes complete successfully */
-	mddev->bitmap_ops->endwrite(mddev, r10_bio->sector, r10_bio->sectors,
-				    !test_bit(R10BIO_Degraded, &r10_bio->state),
-				    false);
 	md_write_end(mddev);
 }
 
@@ -501,7 +497,6 @@ static void raid10_end_write_request(struct bio *bio)
 				set_bit(R10BIO_WriteError, &r10_bio->state);
 			else {
 				/* Fail the request */
-				set_bit(R10BIO_Degraded, &r10_bio->state);
 				r10_bio->devs[slot].bio = NULL;
 				to_put = bio;
 				dec_rdev = 1;
@@ -1438,10 +1433,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 		r10_bio->devs[i].bio = NULL;
 		r10_bio->devs[i].repl_bio = NULL;
 
-		if (!rdev && !rrdev) {
-			set_bit(R10BIO_Degraded, &r10_bio->state);
+		if (!rdev && !rrdev)
 			continue;
-		}
 		if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
 			sector_t first_bad;
 			sector_t dev_sector = r10_bio->devs[i].addr;
@@ -1458,14 +1451,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 					 * to other devices yet
 					 */
 					max_sectors = bad_sectors;
-				/* We don't set R10BIO_Degraded as that
-				 * only applies if the disk is missing,
-				 * so it might be re-added, and we want to
-				 * know to recover this chunk.
-				 * In this case the device is here, and the
-				 * fact that this chunk is not in-sync is
-				 * recorded in the bad block log.
-				 */
 				continue;
 			}
 			if (is_bad) {
@@ -1519,8 +1504,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 	md_account_bio(mddev, &bio);
 	r10_bio->master_bio = bio;
 	atomic_set(&r10_bio->remaining, 1);
-	mddev->bitmap_ops->startwrite(mddev, r10_bio->sector, r10_bio->sectors,
-				      false);
 
 	for (i = 0; i < conf->copies; i++) {
 		if (r10_bio->devs[i].bio)
@@ -2966,11 +2949,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 				rdev_dec_pending(rdev, conf->mddev);
 			} else if (bio != NULL && bio->bi_status) {
 				fail = true;
-				if (!narrow_write_error(r10_bio, m)) {
+				if (!narrow_write_error(r10_bio, m))
 					md_error(conf->mddev, rdev);
-					set_bit(R10BIO_Degraded,
-						&r10_bio->state);
-				}
 				rdev_dec_pending(rdev, conf->mddev);
 			}
 			bio = r10_bio->devs[m].repl_bio;
@@ -3029,8 +3009,6 @@ static void raid10d(struct md_thread *thread)
 			r10_bio = list_first_entry(&tmp, struct r10bio,
 						   retry_list);
 			list_del(&r10_bio->retry_list);
-			if (mddev->degraded)
-				set_bit(R10BIO_Degraded, &r10_bio->state);
 
 			if (test_bit(R10BIO_WriteError,
 				     &r10_bio->state))

drivers/md/raid10.h

@@ -161,7 +161,6 @@ enum r10bio_state {
 	R10BIO_IsSync,
 	R10BIO_IsRecover,
 	R10BIO_IsReshape,
-	R10BIO_Degraded,
 /* Set ReadError on bios that experience a read error
  * so that raid10d knows what to do with them.
  */

drivers/md/raid5-cache.c

@@ -313,10 +313,6 @@ void r5c_handle_cached_data_endio(struct r5conf *conf,
 		if (sh->dev[i].written) {
 			set_bit(R5_UPTODATE, &sh->dev[i].flags);
 			r5c_return_dev_pending_writes(conf, &sh->dev[i]);
-			conf->mddev->bitmap_ops->endwrite(conf->mddev,
-					sh->sector, RAID5_STRIPE_SECTORS(conf),
-					!test_bit(STRIPE_DEGRADED, &sh->state),
-					false);
 		}
 	}
 }
@@ -1023,10 +1019,10 @@ int r5l_write_stripe(struct r5l_log *log, struct stripe_head *sh)
 		/* checksum is already calculated in last run */
 		if (test_bit(STRIPE_LOG_TRAPPED, &sh->state))
 			continue;
-		addr = kmap_atomic(sh->dev[i].page);
+		addr = kmap_local_page(sh->dev[i].page);
 		sh->dev[i].log_checksum = crc32c_le(log->uuid_checksum,
 						    addr, PAGE_SIZE);
-		kunmap_atomic(addr);
+		kunmap_local(addr);
 	}
 	parity_pages = 1 + !!(sh->qd_idx >= 0);
 	data_pages = write_disks - parity_pages;
@@ -1979,9 +1975,9 @@ r5l_recovery_verify_data_checksum(struct r5l_log *log,
 	u32 checksum;
 
 	r5l_recovery_read_page(log, ctx, page, log_offset);
-	addr = kmap_atomic(page);
+	addr = kmap_local_page(page);
 	checksum = crc32c_le(log->uuid_checksum, addr, PAGE_SIZE);
-	kunmap_atomic(addr);
+	kunmap_local(addr);
 	return (le32_to_cpu(log_checksum) == checksum) ? 0 : -EINVAL;
 }
 
@@ -2381,11 +2377,11 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log,
 				payload->size = cpu_to_le32(BLOCK_SECTORS);
 				payload->location = cpu_to_le64(
 					raid5_compute_blocknr(sh, i, 0));
-				addr = kmap_atomic(dev->page);
+				addr = kmap_local_page(dev->page);
 				payload->checksum[0] = cpu_to_le32(
 					crc32c_le(log->uuid_checksum, addr,
 						  PAGE_SIZE));
-				kunmap_atomic(addr);
+				kunmap_local(addr);
 				sync_page_io(log->rdev, write_pos, PAGE_SIZE,
 					     dev->page, REQ_OP_WRITE, false);
 				write_pos = r5l_ring_add(log, write_pos,
@@ -2888,10 +2884,10 @@ int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh)
 
 		if (!test_bit(R5_Wantwrite, &sh->dev[i].flags))
 			continue;
-		addr = kmap_atomic(sh->dev[i].page);
+		addr = kmap_local_page(sh->dev[i].page);
 		sh->dev[i].log_checksum = crc32c_le(log->uuid_checksum,
 						    addr, PAGE_SIZE);
-		kunmap_atomic(addr);
+		kunmap_local(addr);
 		pages++;
 	}
 	WARN_ON(pages == 0);

drivers/md/raid5.c

@@ -906,8 +906,7 @@ static bool stripe_can_batch(struct stripe_head *sh)
 	if (raid5_has_log(conf) || raid5_has_ppl(conf))
 		return false;
 	return test_bit(STRIPE_BATCH_READY, &sh->state) &&
-		!test_bit(STRIPE_BITMAP_PENDING, &sh->state) &&
-		is_full_stripe_write(sh);
+	       is_full_stripe_write(sh);
 }
 
 /* we only do back search */
@@ -1345,8 +1344,6 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 				submit_bio_noacct(rbi);
 		}
 		if (!rdev && !rrdev) {
-			if (op_is_write(op))
-				set_bit(STRIPE_DEGRADED, &sh->state);
 			pr_debug("skip op %d on disc %d for sector %llu\n",
 				bi->bi_opf, i, (unsigned long long)sh->sector);
 			clear_bit(R5_LOCKED, &sh->dev[i].flags);
@@ -2884,7 +2881,6 @@ static void raid5_end_write_request(struct bio *bi)
 			set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
 	} else {
 		if (bi->bi_status) {
-			set_bit(STRIPE_DEGRADED, &sh->state);
 			set_bit(WriteErrorSeen, &rdev->flags);
 			set_bit(R5_WriteError, &sh->dev[i].flags);
 			if (!test_and_set_bit(WantReplacement, &rdev->flags))
@@ -3548,29 +3544,9 @@ static void __add_stripe_bio(struct stripe_head *sh, struct bio *bi,
 		 (*bip)->bi_iter.bi_sector, sh->sector, dd_idx,
 		 sh->dev[dd_idx].sector);
 
-	if (conf->mddev->bitmap && firstwrite) {
-		/* Cannot hold spinlock over bitmap_startwrite,
-		 * but must ensure this isn't added to a batch until
-		 * we have added to the bitmap and set bm_seq.
-		 * So set STRIPE_BITMAP_PENDING to prevent
-		 * batching.
-		 * If multiple __add_stripe_bio() calls race here they
-		 * much all set STRIPE_BITMAP_PENDING.  So only the first one
-		 * to complete "bitmap_startwrite" gets to set
-		 * STRIPE_BIT_DELAY.  This is important as once a stripe
-		 * is added to a batch, STRIPE_BIT_DELAY cannot be changed
-		 * any more.
-		 */
-		set_bit(STRIPE_BITMAP_PENDING, &sh->state);
-		spin_unlock_irq(&sh->stripe_lock);
-		conf->mddev->bitmap_ops->startwrite(conf->mddev, sh->sector,
-					RAID5_STRIPE_SECTORS(conf), false);
-		spin_lock_irq(&sh->stripe_lock);
-		clear_bit(STRIPE_BITMAP_PENDING, &sh->state);
-		if (!sh->batch_head) {
-			sh->bm_seq = conf->seq_flush+1;
-			set_bit(STRIPE_BIT_DELAY, &sh->state);
-		}
+	if (conf->mddev->bitmap && firstwrite && !sh->batch_head) {
+		sh->bm_seq = conf->seq_flush+1;
+		set_bit(STRIPE_BIT_DELAY, &sh->state);
 	}
 }
 
@@ -3621,7 +3597,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 	BUG_ON(sh->batch_head);
 	for (i = disks; i--; ) {
 		struct bio *bi;
-		int bitmap_end = 0;
 
 		if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
 			struct md_rdev *rdev = conf->disks[i].rdev;
@@ -3646,8 +3621,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		sh->dev[i].towrite = NULL;
 		sh->overwrite_disks = 0;
 		spin_unlock_irq(&sh->stripe_lock);
-		if (bi)
-			bitmap_end = 1;
 
 		log_stripe_write_finished(sh);
 
@@ -3662,11 +3635,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			bio_io_error(bi);
 			bi = nextbi;
 		}
-		if (bitmap_end)
-			conf->mddev->bitmap_ops->endwrite(conf->mddev,
-					sh->sector, RAID5_STRIPE_SECTORS(conf),
-					false, false);
-		bitmap_end = 0;
 		/* and fail all 'written' */
 		bi = sh->dev[i].written;
 		sh->dev[i].written = NULL;
@@ -3675,7 +3643,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			sh->dev[i].page = sh->dev[i].orig_page;
 		}
 
-		if (bi) bitmap_end = 1;
 		while (bi && bi->bi_iter.bi_sector <
 		       sh->dev[i].sector + RAID5_STRIPE_SECTORS(conf)) {
 			struct bio *bi2 = r5_next_bio(conf, bi, sh->dev[i].sector);
@@ -3709,10 +3676,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 				bi = nextbi;
 			}
 		}
-		if (bitmap_end)
-			conf->mddev->bitmap_ops->endwrite(conf->mddev,
-					sh->sector, RAID5_STRIPE_SECTORS(conf),
-					false, false);
 		/* If we were in the middle of a write the parity block might
 		 * still be locked - so just clear all R5_LOCKED flags
 		 */
@@ -4061,10 +4024,7 @@ static void handle_stripe_clean_event(struct r5conf *conf,
 					bio_endio(wbi);
 					wbi = wbi2;
 				}
-				conf->mddev->bitmap_ops->endwrite(conf->mddev,
-					sh->sector, RAID5_STRIPE_SECTORS(conf),
-					!test_bit(STRIPE_DEGRADED, &sh->state),
-					false);
+
 				if (head_sh->batch_head) {
 					sh = list_first_entry(&sh->batch_list,
 							      struct stripe_head,
@@ -4341,7 +4301,6 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh,
 		s->locked++;
 		set_bit(R5_Wantwrite, &dev->flags);
 
-		clear_bit(STRIPE_DEGRADED, &sh->state);
 		set_bit(STRIPE_INSYNC, &sh->state);
 		break;
 	case check_state_run:
@@ -4498,7 +4457,6 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh,
 			clear_bit(R5_Wantwrite, &dev->flags);
 			s->locked--;
 		}
-		clear_bit(STRIPE_DEGRADED, &sh->state);
 
 		set_bit(STRIPE_INSYNC, &sh->state);
 		break;
@@ -4891,8 +4849,7 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
 					  (1 << STRIPE_COMPUTE_RUN)  |
 					  (1 << STRIPE_DISCARD) |
 					  (1 << STRIPE_BATCH_READY) |
-					  (1 << STRIPE_BATCH_ERR) |
-					  (1 << STRIPE_BITMAP_PENDING)),
+					  (1 << STRIPE_BATCH_ERR)),
 			"stripe state: %lx\n", sh->state);
 		WARN_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) |
 					      (1 << STRIPE_REPLACED)),
@@ -4900,7 +4857,6 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
 
 		set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
 					    (1 << STRIPE_PREREAD_ACTIVE) |
-					    (1 << STRIPE_DEGRADED) |
 					    (1 << STRIPE_ON_UNPLUG_LIST)),
 			      head_sh->state & (1 << STRIPE_INSYNC));
 
@@ -5784,10 +5740,6 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 		}
 		spin_unlock_irq(&sh->stripe_lock);
 		if (conf->mddev->bitmap) {
-			for (d = 0; d < conf->raid_disks - conf->max_degraded;
-			     d++)
-				mddev->bitmap_ops->startwrite(mddev, sh->sector,
-					RAID5_STRIPE_SECTORS(conf), false);
 			sh->bm_seq = conf->seq_flush + 1;
 			set_bit(STRIPE_BIT_DELAY, &sh->state);
 		}
@@ -5928,6 +5880,54 @@ static enum reshape_loc get_reshape_loc(struct mddev *mddev,
 	return LOC_BEHIND_RESHAPE;
 }
 
+static void raid5_bitmap_sector(struct mddev *mddev, sector_t *offset,
+				unsigned long *sectors)
+{
+	struct r5conf *conf = mddev->private;
+	sector_t start = *offset;
+	sector_t end = start + *sectors;
+	sector_t prev_start = start;
+	sector_t prev_end = end;
+	int sectors_per_chunk;
+	enum reshape_loc loc;
+	int dd_idx;
+
+	sectors_per_chunk = conf->chunk_sectors *
+		(conf->raid_disks - conf->max_degraded);
+	start = round_down(start, sectors_per_chunk);
+	end = round_up(end, sectors_per_chunk);
+
+	start = raid5_compute_sector(conf, start, 0, &dd_idx, NULL);
+	end = raid5_compute_sector(conf, end, 0, &dd_idx, NULL);
+
+	/*
+	 * For LOC_INSIDE_RESHAPE, this IO will wait for reshape to make
+	 * progress, hence it's the same as LOC_BEHIND_RESHAPE.
+	 */
+	loc = get_reshape_loc(mddev, conf, prev_start);
+	if (likely(loc != LOC_AHEAD_OF_RESHAPE)) {
+		*offset = start;
+		*sectors = end - start;
+		return;
+	}
+
+	sectors_per_chunk = conf->prev_chunk_sectors *
+		(conf->previous_raid_disks - conf->max_degraded);
+	prev_start = round_down(prev_start, sectors_per_chunk);
+	prev_end = round_down(prev_end, sectors_per_chunk);
+
+	prev_start = raid5_compute_sector(conf, prev_start, 1, &dd_idx, NULL);
+	prev_end = raid5_compute_sector(conf, prev_end, 1, &dd_idx, NULL);
+
+	/*
+	 * for LOC_AHEAD_OF_RESHAPE, reshape can make progress before this IO
+	 * is handled in make_stripe_request(), we can't know this here hence
+	 * we set bits for both.
+	 */
+	*offset = min(start, prev_start);
+	*sectors = max(end, prev_end) - *offset;
+}
+
 static enum stripe_result make_stripe_request(struct mddev *mddev,
 		struct r5conf *conf, struct stripe_request_ctx *ctx,
 		sector_t logical_sector, struct bio *bi)
@@ -8976,6 +8976,7 @@ static struct md_personality raid6_personality =
 	.takeover	= raid6_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
 	.prepare_suspend = raid5_prepare_suspend,
+	.bitmap_sector	= raid5_bitmap_sector,
 };
 static struct md_personality raid5_personality =
 {
@@ -9001,6 +9002,7 @@ static struct md_personality raid5_personality =
 	.takeover	= raid5_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
 	.prepare_suspend = raid5_prepare_suspend,
+	.bitmap_sector	= raid5_bitmap_sector,
 };
 
 static struct md_personality raid4_personality =
@@ -9027,6 +9029,7 @@ static struct md_personality raid4_personality =
 	.takeover	= raid4_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
 	.prepare_suspend = raid5_prepare_suspend,
+	.bitmap_sector	= raid5_bitmap_sector,
 };
 
 static int __init raid5_init(void)

drivers/md/raid5.h

@@ -358,7 +358,6 @@ enum {
 	STRIPE_REPLACED,
 	STRIPE_PREREAD_ACTIVE,
 	STRIPE_DELAYED,
-	STRIPE_DEGRADED,
 	STRIPE_BIT_DELAY,
 	STRIPE_EXPANDING,
 	STRIPE_EXPAND_SOURCE,
@@ -372,9 +371,6 @@ enum {
 	STRIPE_ON_RELEASE_LIST,
 	STRIPE_BATCH_READY,
 	STRIPE_BATCH_ERR,
-	STRIPE_BITMAP_PENDING,	/* Being added to bitmap, don't add
-				 * to batch yet.
-				 */
 	STRIPE_LOG_TRAPPED,	/* trapped into log (see raid5-cache.c)
 				 * this bit is used in two scenarios:
 				 *

include/uapi/linux/raid/md_p.h

@@ -233,7 +233,7 @@ struct mdp_superblock_1 {
 	char	set_name[32];	/* set and interpreted by user-space */
 
 	__le64	ctime;		/* lo 40 bits are seconds, top 24 are microseconds or 0*/
-	__le32	level;		/* 0,1,4,5 */
+	__le32	level;		/* 0,1,4,5, -1 (linear) */
 	__le32	layout;		/* only for raid5 and raid10 currently */
 	__le64	size;		/* used size of component devices, in 512byte sectors */
 

include/uapi/linux/raid/md_u.h

@@ -103,6 +103,8 @@ typedef struct mdu_array_info_s {
 
 } mdu_array_info_t;
 
+#define LEVEL_LINEAR		(-1)
+
 /* we need a value for 'no level specified' and 0
  * means 'raid0', so we need something else.  This is
  * for internal use only