Merge branch 'md-next' into md-linus

#include <linux/mount.h>

#include <linux/buffer_head.h>

#include <linux/seq_file.h>

#include <trace/events/block.h>

#include "md.h"

#include "bitmap.h"

static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)

{

	struct md_rdev *rdev = NULL;

	struct md_rdev *rdev;

	struct block_device *bdev;

	struct mddev *mddev = bitmap->mddev;

	struct bitmap_storage *store = &bitmap->storage;

restart:

	rdev = NULL;

	while ((rdev = next_active_rdev(rdev, mddev)) != NULL) {

		int size = PAGE_SIZE;

		loff_t offset = mddev->bitmap_info.offset;

			       page);

	}

	if (wait)

		md_super_wait(mddev);

	if (wait && md_super_wait(mddev) < 0)

		goto restart;

	return 0;

 bad_alignment:

		ret = -EIO;

out:

	if (ret)

		printk(KERN_ALERT "md: bitmap read error: (%dB @ %llu): %d\n",

		pr_err("md: bitmap read error: (%dB @ %llu): %d\n",

		       (int)PAGE_SIZE,

		       (unsigned long long)index << PAGE_SHIFT,

		       ret);

 * bitmap file superblock operations

 */

/*

 * bitmap_wait_writes() should be called before writing any bitmap

 * blocks, to ensure previous writes, particularly from

 * bitmap_daemon_work(), have completed.

 */

static void bitmap_wait_writes(struct bitmap *bitmap)

{

	if (bitmap->storage.file)

		wait_event(bitmap->write_wait,

			   atomic_read(&bitmap->pending_writes)==0);

	else

		/* Note that we ignore the return value.  The writes

		 * might have failed, but that would just mean that

		 * some bits which should be cleared haven't been,

		 * which is safe.  The relevant bitmap blocks will

		 * probably get written again, but there is no great

		 * loss if they aren't.

		 */

		md_super_wait(bitmap->mddev);

}

/* update the event counter and sync the superblock to disk */

void bitmap_update_sb(struct bitmap *bitmap)

{

	if (!bitmap || !bitmap->storage.sb_page)

		return;

	sb = kmap_atomic(bitmap->storage.sb_page);

	printk(KERN_DEBUG "%s: bitmap file superblock:\n", bmname(bitmap));

	printk(KERN_DEBUG "         magic: %08x\n", le32_to_cpu(sb->magic));

	printk(KERN_DEBUG "       version: %d\n", le32_to_cpu(sb->version));

	printk(KERN_DEBUG "          uuid: %08x.%08x.%08x.%08x\n",

	pr_debug("%s: bitmap file superblock:\n", bmname(bitmap));

	pr_debug("         magic: %08x\n", le32_to_cpu(sb->magic));

	pr_debug("       version: %d\n", le32_to_cpu(sb->version));

	pr_debug("          uuid: %08x.%08x.%08x.%08x\n",

		 *(__u32 *)(sb->uuid+0),

		 *(__u32 *)(sb->uuid+4),

		 *(__u32 *)(sb->uuid+8),

		 *(__u32 *)(sb->uuid+12));

	printk(KERN_DEBUG "        events: %llu\n",

	pr_debug("        events: %llu\n",

		 (unsigned long long) le64_to_cpu(sb->events));

	printk(KERN_DEBUG "events cleared: %llu\n",

	pr_debug("events cleared: %llu\n",

		 (unsigned long long) le64_to_cpu(sb->events_cleared));

	printk(KERN_DEBUG "         state: %08x\n", le32_to_cpu(sb->state));

	printk(KERN_DEBUG "     chunksize: %d B\n", le32_to_cpu(sb->chunksize));

	printk(KERN_DEBUG "  daemon sleep: %ds\n", le32_to_cpu(sb->daemon_sleep));

	printk(KERN_DEBUG "     sync size: %llu KB\n",

	pr_debug("         state: %08x\n", le32_to_cpu(sb->state));

	pr_debug("     chunksize: %d B\n", le32_to_cpu(sb->chunksize));

	pr_debug("  daemon sleep: %ds\n", le32_to_cpu(sb->daemon_sleep));

	pr_debug("     sync size: %llu KB\n",

		 (unsigned long long)le64_to_cpu(sb->sync_size)/2);

	printk(KERN_DEBUG "max write behind: %d\n", le32_to_cpu(sb->write_behind));

	pr_debug("max write behind: %d\n", le32_to_cpu(sb->write_behind));

	kunmap_atomic(sb);

}

	BUG_ON(!chunksize);

	if (!is_power_of_2(chunksize)) {

		kunmap_atomic(sb);

		printk(KERN_ERR "bitmap chunksize not a power of 2\n");

		pr_warn("bitmap chunksize not a power of 2\n");

		return -EINVAL;

	}

	sb->chunksize = cpu_to_le32(chunksize);

	daemon_sleep = bitmap->mddev->bitmap_info.daemon_sleep;

	if (!daemon_sleep || (daemon_sleep > MAX_SCHEDULE_TIMEOUT)) {

		printk(KERN_INFO "Choosing daemon_sleep default (5 sec)\n");

		pr_debug("Choosing daemon_sleep default (5 sec)\n");

		daemon_sleep = 5 * HZ;

	}

	sb->daemon_sleep = cpu_to_le32(daemon_sleep);

		/* to 4k blocks */

		bm_blocks = DIV_ROUND_UP_SECTOR_T(bm_blocks, 4096);

		offset = bitmap->mddev->bitmap_info.offset + (bitmap->cluster_slot * (bm_blocks << 3));

		pr_info("%s:%d bm slot: %d offset: %llu\n", __func__, __LINE__,

		pr_debug("%s:%d bm slot: %d offset: %llu\n", __func__, __LINE__,

			bitmap->cluster_slot, offset);

	}

	else if (write_behind > COUNTER_MAX)

		reason = "write-behind limit out of range (0 - 16383)";

	if (reason) {

		printk(KERN_INFO "%s: invalid bitmap file superblock: %s\n",

		pr_warn("%s: invalid bitmap file superblock: %s\n",

			bmname(bitmap), reason);

		goto out;

	}

		 * bitmap's UUID and event counter to the mddev's

		 */

		if (memcmp(sb->uuid, bitmap->mddev->uuid, 16)) {

			printk(KERN_INFO

			       "%s: bitmap superblock UUID mismatch\n",

			pr_warn("%s: bitmap superblock UUID mismatch\n",

				bmname(bitmap));

			goto out;

		}

		events = le64_to_cpu(sb->events);

		if (!nodes && (events < bitmap->mddev->events)) {

			printk(KERN_INFO

			       "%s: bitmap file is out of date (%llu < %llu) "

			       "-- forcing full recovery\n",

			pr_warn("%s: bitmap file is out of date (%llu < %llu) -- forcing full recovery\n",

				bmname(bitmap), events,

				(unsigned long long) bitmap->mddev->events);

			set_bit(BITMAP_STALE, &bitmap->flags);

	if (err == 0 && nodes && (bitmap->cluster_slot < 0)) {

		err = md_setup_cluster(bitmap->mddev, nodes);

		if (err) {

			pr_err("%s: Could not setup cluster service (%d)\n",

			pr_warn("%s: Could not setup cluster service (%d)\n",

				bmname(bitmap), err);

			goto out_no_sb;

		}

				ptr = file_path(bitmap->storage.file,

					     path, PAGE_SIZE);

			printk(KERN_ALERT

			      "%s: kicking failed bitmap file %s from array!\n",

			pr_warn("%s: kicking failed bitmap file %s from array!\n",

				bmname(bitmap), IS_ERR(ptr) ? "" : ptr);

			kfree(path);

		} else

			printk(KERN_ALERT

			       "%s: disabling internal bitmap due to errors\n",

			pr_warn("%s: disabling internal bitmap due to errors\n",

				bmname(bitmap));

	}

}

{

	unsigned long i;

	int dirty, need_write;

	int writing = 0;

	if (!bitmap || !bitmap->storage.filemap ||

	    test_bit(BITMAP_STALE, &bitmap->flags))

		need_write = test_and_clear_page_attr(bitmap, i,

						      BITMAP_PAGE_NEEDWRITE);

		if (dirty || need_write) {

			if (!writing) {

				bitmap_wait_writes(bitmap);

				if (bitmap->mddev->queue)

					blk_add_trace_msg(bitmap->mddev->queue,

							  "md bitmap_unplug");

			}

			clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING);

			write_page(bitmap, bitmap->storage.filemap[i], 0);

			writing = 1;

		}

	}

	if (bitmap->storage.file)

		wait_event(bitmap->write_wait,

			   atomic_read(&bitmap->pending_writes)==0);

	else

		md_super_wait(bitmap->mddev);

	if (writing)

		bitmap_wait_writes(bitmap);

	if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags))

		bitmap_file_kick(bitmap);

	outofdate = test_bit(BITMAP_STALE, &bitmap->flags);

	if (outofdate)

		printk(KERN_INFO "%s: bitmap file is out of date, doing full "

			"recovery\n", bmname(bitmap));

		pr_warn("%s: bitmap file is out of date, doing full recovery\n", bmname(bitmap));

	if (file && i_size_read(file->f_mapping->host) < store->bytes) {

		printk(KERN_INFO "%s: bitmap file too short %lu < %lu\n",

		pr_warn("%s: bitmap file too short %lu < %lu\n",

			bmname(bitmap),

			(unsigned long) i_size_read(file->f_mapping->host),

			store->bytes);

		offset = 0;

	}

	printk(KERN_INFO "%s: bitmap initialized from disk: "

	       "read %lu pages, set %lu of %lu bits\n",

	pr_debug("%s: bitmap initialized from disk: read %lu pages, set %lu of %lu bits\n",

		 bmname(bitmap), store->file_pages,

		 bit_cnt, chunks);

	return 0;

 err:

	printk(KERN_INFO "%s: bitmap initialisation failed: %d\n",

	pr_warn("%s: bitmap initialisation failed: %d\n",

		bmname(bitmap), ret);

	return ret;

}

	}

	bitmap->allclean = 1;

	if (bitmap->mddev->queue)

		blk_add_trace_msg(bitmap->mddev->queue,

				  "md bitmap_daemon_work");

	/* Any file-page which is PENDING now needs to be written.

	 * So set NEEDWRITE now, then after we make any last-minute changes

	 * we will write it.

	}

	spin_unlock_irq(&counts->lock);

	bitmap_wait_writes(bitmap);

	/* Now start writeout on any page in NEEDWRITE that isn't DIRTY.

	 * DIRTY pages need to be written by bitmap_unplug so it can wait

	 * for them.

		   atomic_read(&bitmap->mddev->recovery_active) == 0);

	bitmap->mddev->curr_resync_completed = sector;

	set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);

	set_bit(MD_SB_CHANGE_CLEAN, &bitmap->mddev->sb_flags);

	sector &= ~((1ULL << bitmap->counts.chunkshift) - 1);

	s = 0;

	while (s < sector && s < bitmap->mddev->resync_max_sectors) {

	if (err)

		goto error;

	printk(KERN_INFO "created bitmap (%lu pages) for device %s\n",

	pr_debug("created bitmap (%lu pages) for device %s\n",

		 bitmap->counts.pages, bmname(bitmap));

	err = test_bit(BITMAP_WRITE_ERROR, &bitmap->flags) ? -EIO : 0;

					   !bitmap->mddev->bitmap_info.external,

					   mddev_is_clustered(bitmap->mddev)

					   ? bitmap->cluster_slot : 0);

	if (ret)

	if (ret) {

		bitmap_file_unmap(&store);

		goto err;

	}

	pages = DIV_ROUND_UP(chunks, PAGE_COUNTER_RATIO);

				bitmap->mddev->bitmap_info.chunksize = 1 << (old_counts.chunkshift +

									     BITMAP_BLOCK_SHIFT);

				blocks = old_counts.chunks << old_counts.chunkshift;

				pr_err("Could not pre-allocate in-memory bitmap for cluster raid\n");

				pr_warn("Could not pre-allocate in-memory bitmap for cluster raid\n");

				break;

			} else

				bitmap->counts.bp[page].count += 1;

		/* Ensure new bitmap info is stored in

		 * metadata promptly.

		 */

		set_bit(MD_CHANGE_DEVS, &mddev->flags);

		set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);

		md_wakeup_thread(mddev->thread);

	}

	rv = 0;

		sb->compat_features = cpu_to_le32(FEATURE_FLAG_SUPPORTS_V190);

		/* Force writing of superblocks to disk */

		set_bit(MD_CHANGE_DEVS, &rdev->mddev->flags);

		set_bit(MD_SB_CHANGE_DEVS, &rdev->mddev->sb_flags);

		/* Any superblock is better than none, choose that if given */

		return refdev ? 0 : 1;

	struct mddev *mddev = &rs->md;

	int ro = mddev->ro;

	set_bit(MD_CHANGE_DEVS, &mddev->flags);

	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);

	mddev->ro = 0;

	md_update_sb(mddev, 1);

	mddev->ro = ro;

#include <linux/seq_file.h>

#include <linux/module.h>

#include <linux/slab.h>

#include <trace/events/block.h>

#include "md.h"

#include "linear.h"

		sector_t sectors;

		if (j < 0 || j >= raid_disks || disk->rdev) {

			printk(KERN_ERR "md/linear:%s: disk numbering problem. Aborting!\n",

			pr_warn("md/linear:%s: disk numbering problem. Aborting!\n",

				mdname(mddev));

			goto out;

		}

			discard_supported = true;

	}

	if (cnt != raid_disks) {

		printk(KERN_ERR "md/linear:%s: not enough drives present. Aborting!\n",

		pr_warn("md/linear:%s: not enough drives present. Aborting!\n",

			mdname(mddev));

		goto out;

	}

	}

	do {

		tmp_dev = which_dev(mddev, bio->bi_iter.bi_sector);

		sector_t bio_sector = bio->bi_iter.bi_sector;

		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;

		bio->bi_bdev = tmp_dev->rdev->bdev;

		if (unlikely(bio->bi_iter.bi_sector >= end_sector ||

			     bio->bi_iter.bi_sector < start_sector))

		if (unlikely(bio_sector >= end_sector ||

			     bio_sector < start_sector))

			goto out_of_bounds;

		if (unlikely(bio_end_sector(bio) > end_sector)) {

			/* This bio crosses a device boundary, so we have to

			 * split it.

			 */

			split = bio_split(bio, end_sector -

					  bio->bi_iter.bi_sector,

			split = bio_split(bio, end_sector - bio_sector,

					  GFP_NOIO, fs_bio_set);

			bio_chain(split, bio);

		} else {

			 !blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {

			/* Just ignore it */

			bio_endio(split);

		} else

		} else {

			if (mddev->gendisk)

				trace_block_bio_remap(bdev_get_queue(split->bi_bdev),

						      split, disk_devt(mddev->gendisk),

						      bio_sector);

			generic_make_request(split);

		}

	} while (split != bio);

	return;

out_of_bounds:

	printk(KERN_ERR

	       "md/linear:%s: make_request: Sector %llu out of bounds on "

	       "dev %s: %llu sectors, offset %llu\n",

	pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %s: %llu sectors, offset %llu\n",

	       mdname(mddev),

	       (unsigned long long)bio->bi_iter.bi_sector,

	       bdevname(tmp_dev->rdev->bdev, b),

static void linear_status (struct seq_file *seq, struct mddev *mddev)

{

	seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2);

}

#define MaxSector (~(sector_t)0)

/*

 * These flags should really be called "NO_RETRY" rather than

 * "FAILFAST" because they don't make any promise about time lapse,

 * only about the number of retries, which will be zero.

 * REQ_FAILFAST_DRIVER is not included because

 * Commit: 4a27446f3e39 ("[SCSI] modify scsi to handle new fail fast flags.")

 * seems to suggest that the errors it avoids retrying should usually

 * be retried.

 */

#define	MD_FAILFAST	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT)

/*

 * MD's 'extended' device

 */

				 * so it is safe to remove without

				 * another synchronize_rcu() call.

				 */

	ExternalBbl,            /* External metadata provides bad

				 * block management for a disk

				 */

	FailFast,		/* Minimal retries should be attempted on

				 * this device, so use REQ_FAILFAST_DEV.

				 * Also don't try to repair failed reads.

				 * It is expects that no bad block log

				 * is present.

				 */

	LastDev,		/* Seems to be the last working dev as

				 * it didn't fail, so don't use FailFast

				 * any more for metadata

				 */

};

static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,

				int is_new);

struct md_cluster_info;

enum mddev_flags {

	MD_ARRAY_FIRST_USE,	/* First use of array, needs initialization */

	MD_CLOSING,		/* If set, we are closing the array, do not open

				 * it then */

	MD_JOURNAL_CLEAN,	/* A raid with journal is already clean */

	MD_HAS_JOURNAL,		/* The raid array has journal feature set */

	MD_RELOAD_SB,		/* Reload the superblock because another node

				 * updated it.

				 */

	MD_CLUSTER_RESYNC_LOCKED, /* cluster raid only, which means node

				   * already took resync lock, need to

				   * release the lock */

	MD_FAILFAST_SUPPORTED,	/* Using MD_FAILFAST on metadata writes is

				 * supported as calls to md_error() will

				 * never cause the array to become failed.

				 */

};

enum mddev_sb_flags {

	MD_SB_CHANGE_DEVS,		/* Some device status has changed */

	MD_SB_CHANGE_CLEAN,	/* transition to or from 'clean' */

	MD_SB_CHANGE_PENDING,	/* switch from 'clean' to 'active' in progress */

	MD_SB_NEED_REWRITE,	/* metadata write needs to be repeated */

};

struct mddev {

	void				*private;

	struct md_personality		*pers;

	int				md_minor;

	struct list_head		disks;

	unsigned long			flags;

#define MD_CHANGE_DEVS	0	/* Some device status has changed */

#define MD_CHANGE_CLEAN 1	/* transition to or from 'clean' */

#define MD_CHANGE_PENDING 2	/* switch from 'clean' to 'active' in progress */

#define MD_UPDATE_SB_FLAGS (1 | 2 | 4)	/* If these are set, md_update_sb needed */

#define MD_ARRAY_FIRST_USE 3    /* First use of array, needs initialization */

#define MD_CLOSING	4	/* If set, we are closing the array, do not open

				 * it then */

#define MD_JOURNAL_CLEAN 5	/* A raid with journal is already clean */

#define MD_HAS_JOURNAL	6	/* The raid array has journal feature set */

#define MD_RELOAD_SB	7	/* Reload the superblock because another node

				 * updated it.

				 */

#define MD_CLUSTER_RESYNC_LOCKED 8 /* cluster raid only, which means node

				    * already took resync lock, need to

				    * release the lock */

	unsigned long			sb_flags;

	int				suspended;

	atomic_t			active_io;

	int				parallel_resync;

	int				ok_start_degraded;

	/* recovery/resync flags

	 * NEEDED:   we might need to start a resync/recover

	 * RUNNING:  a thread is running, or about to be started

	 * SYNC:     actually doing a resync, not a recovery

	 * RECOVER:  doing recovery, or need to try it.

	 * INTR:     resync needs to be aborted for some reason

	 * DONE:     thread is done and is waiting to be reaped

	 * REQUEST:  user-space has requested a sync (used with SYNC)

	 * CHECK:    user-space request for check-only, no repair

	 * RESHAPE:  A reshape is happening

	 * ERROR:    sync-action interrupted because io-error

	 *

	 * If neither SYNC or RESHAPE are set, then it is a recovery.

	 */

#define	MD_RECOVERY_RUNNING	0

#define	MD_RECOVERY_SYNC	1

#define	MD_RECOVERY_RECOVER	2

#define	MD_RECOVERY_INTR	3

#define	MD_RECOVERY_DONE	4

#define	MD_RECOVERY_NEEDED	5

#define	MD_RECOVERY_REQUESTED	6

#define	MD_RECOVERY_CHECK	7

#define MD_RECOVERY_RESHAPE	8

#define	MD_RECOVERY_FROZEN	9

#define	MD_RECOVERY_ERROR	10

	unsigned long			recovery;

	/* If a RAID personality determines that recovery (of a particular

	unsigned int			good_device_nr;	/* good device num within cluster raid */

};

enum recovery_flags {

	/*

	 * If neither SYNC or RESHAPE are set, then it is a recovery.

	 */

	MD_RECOVERY_RUNNING,	/* a thread is running, or about to be started */

	MD_RECOVERY_SYNC,	/* actually doing a resync, not a recovery */

	MD_RECOVERY_RECOVER,	/* doing recovery, or need to try it. */

	MD_RECOVERY_INTR,	/* resync needs to be aborted for some reason */

	MD_RECOVERY_DONE,	/* thread is done and is waiting to be reaped */

	MD_RECOVERY_NEEDED,	/* we might need to start a resync/recover */

	MD_RECOVERY_REQUESTED,	/* user-space has requested a sync (used with SYNC) */

	MD_RECOVERY_CHECK,	/* user-space request for check-only, no repair */

	MD_RECOVERY_RESHAPE,	/* A reshape is happening */

	MD_RECOVERY_FROZEN,	/* User request to abort, and not restart, any action */

	MD_RECOVERY_ERROR,	/* sync-action interrupted because io-error */

};

static inline int __must_check mddev_lock(struct mddev *mddev)

{

	return mutex_lock_interruptible(&mddev->reconfig_mutex);

extern void md_flush_request(struct mddev *mddev, struct bio *bio);

extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,

			   sector_t sector, int size, struct page *page);

extern void md_super_wait(struct mddev *mddev);

extern int md_super_wait(struct mddev *mddev);

extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,

			struct page *page, int op, int op_flags,

			bool metadata_op);