From: Namhyung Kim <namhyung@gmail.com>
To: NeilBrown <neilb@suse.de>
Cc: linux-raid@vger.kernel.org
Subject: Re: [md PATCH 04/36] md: load/store badblock list from v1.x metadata
Date: Sat, 23 Jul 2011 01:34:47 +0900 [thread overview]
Message-ID: <87vcuu46l4.fsf@gmail.com> (raw)
In-Reply-To: <20110721025847.8422.27295.stgit@notabene.brown> (NeilBrown's message of "Thu, 21 Jul 2011 12:58:47 +1000")
NeilBrown <neilb@suse.de> writes:
> Space must have been allocated when array was created.
> A feature flag is set when the badblock list is non-empty, to
> ensure old kernels don't load and trust the whole device.
>
> We only update the on-disk badblocklist when it has changed.
> If the badblocklist (or other metadata) is stored on a bad block, we
> don't cope very well.
>
> If metadata has no room for bad block, flag bad-blocks as disabled,
> and do the same for 0.90 metadata.
>
> Signed-off-by: NeilBrown <neilb@suse.de>
> ---
>
> drivers/md/md.c | 111 +++++++++++++++++++++++++++++++++++++++++++--
> drivers/md/md.h | 5 ++
> include/linux/raid/md_p.h | 14 ++++--
> 3 files changed, 119 insertions(+), 11 deletions(-)
>
> diff --git a/drivers/md/md.c b/drivers/md/md.c
> index 9324635..18c3aab 100644
> --- a/drivers/md/md.c
> +++ b/drivers/md/md.c
> @@ -757,6 +757,10 @@ static void free_disk_sb(mdk_rdev_t * rdev)
> rdev->sb_start = 0;
> rdev->sectors = 0;
> }
> + if (rdev->bb_page) {
> + put_page(rdev->bb_page);
> + rdev->bb_page = NULL;
> + }
> }
>
>
> @@ -1395,6 +1399,8 @@ static __le32 calc_sb_1_csum(struct mdp_superblock_1 * sb)
> return cpu_to_le32(csum);
> }
>
> +static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors,
> + int acknowledged);
> static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
> {
> struct mdp_superblock_1 *sb;
> @@ -1473,6 +1479,47 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
> else
> rdev->desc_nr = le32_to_cpu(sb->dev_number);
>
> + if (!rdev->bb_page) {
> + rdev->bb_page = alloc_page(GFP_KERNEL);
> + if (!rdev->bb_page)
> + return -ENOMEM;
> + }
This will allocate ->bb_page's for unsupported arrays too. Checking
->bblog_offset here might be helpful.
> + if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BAD_BLOCKS) &&
> + rdev->badblocks.count == 0) {
> + /* need to load the bad block list.
> + * Currently we limit it to one page.
> + */
> + s32 offset;
> + sector_t bb_sector;
> + u64 *bbp;
> + int i;
> + int sectors = le16_to_cpu(sb->bblog_size);
> + if (sectors > (PAGE_SIZE / 512))
> + return -EINVAL;
> + offset = le32_to_cpu(sb->bblog_offset);
> + if (offset == 0)
> + return -EINVAL;
> + bb_sector = (long long)offset;
> + if (!sync_page_io(rdev, bb_sector, sectors << 9,
> + rdev->bb_page, READ, true))
> + return -EIO;
> + bbp = (u64 *)page_address(rdev->bb_page);
Unnecessary cast.
> + rdev->badblocks.shift = sb->bblog_shift;
> + for (i = 0 ; i < (sectors << (9-3)) ; i++, bbp++) {
> + u64 bb = le64_to_cpu(*bbp);
> + int count = bb & (0x3ff);
> + u64 sector = bb >> 10;
> + sector <<= sb->bblog_shift;
> + count <<= sb->bblog_shift;
> + if (bb + 1 == 0)
> + break;
This code probably needs comment.
> + if (md_set_badblocks(&rdev->badblocks,
> + sector, count, 1) == 0)
> + return -EINVAL;
> + }
> + } else if (sb->bblog_offset == 0)
> + rdev->badblocks.shift = -1;
->badblocks.page can be freed as well.
> +
> if (!refdev) {
> ret = 1;
> } else {
> @@ -1624,7 +1671,6 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
> sb->pad0 = 0;
> sb->recovery_offset = cpu_to_le64(0);
> memset(sb->pad1, 0, sizeof(sb->pad1));
> - memset(sb->pad2, 0, sizeof(sb->pad2));
> memset(sb->pad3, 0, sizeof(sb->pad3));
>
> sb->utime = cpu_to_le64((__u64)mddev->utime);
> @@ -1664,6 +1710,43 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
> sb->new_chunk = cpu_to_le32(mddev->new_chunk_sectors);
> }
>
> + if (rdev->badblocks.count == 0)
> + /* Nothing to do for bad blocks*/ ;
> + else if (sb->bblog_offset == 0)
> + /* Cannot record bad blocks on this device */
> + md_error(mddev, rdev);
> + else {
> + int havelock = 0;
> + struct badblocks *bb = &rdev->badblocks;
> + u64 *bbp = (u64 *)page_address(rdev->bb_page);
Unnecessary cast too.
> + u64 *p;
> + sb->feature_map |= cpu_to_le32(MD_FEATURE_BAD_BLOCKS);
> + if (bb->changed) {
> + memset(bbp, 0xff, PAGE_SIZE);
> +
> + rcu_read_lock();
> + p = rcu_dereference(bb->active_page);
> + if (!p) {
> + spin_lock_irq(&bb->lock);
> + p = bb->page;
> + havelock = 1;
> + }
> + for (i = 0 ; i < bb->count ; i++) {
> + u64 internal_bb = *p++;
> + u64 store_bb = ((BB_OFFSET(internal_bb) << 10)
> + | BB_LEN(internal_bb));
> + *bbp++ = cpu_to_le64(store_bb);
> + }
> + bb->sector = (rdev->sb_start +
> + (int)le32_to_cpu(sb->bblog_offset));
> + bb->size = le16_to_cpu(sb->bblog_size);
> + bb->changed = 0;
> + if (havelock)
> + spin_unlock_irq(&bb->lock);
> + rcu_read_unlock();
> + }
> + }
> +
> max_dev = 0;
> list_for_each_entry(rdev2, &mddev->disks, same_set)
> if (rdev2->desc_nr+1 > max_dev)
> @@ -2197,6 +2280,7 @@ static void md_update_sb(mddev_t * mddev, int force_change)
> mdk_rdev_t *rdev;
> int sync_req;
> int nospares = 0;
> + int any_badblocks_changed = 0;
>
> repeat:
> /* First make sure individual recovery_offsets are correct */
> @@ -2268,6 +2352,11 @@ repeat:
> MD_BUG();
> mddev->events --;
> }
> +
> + list_for_each_entry(rdev, &mddev->disks, same_set)
> + if (rdev->badblocks.changed)
> + any_badblocks_changed++;
> +
> sync_sbs(mddev, nospares);
> spin_unlock_irq(&mddev->write_lock);
>
> @@ -2293,6 +2382,13 @@ repeat:
> bdevname(rdev->bdev,b),
> (unsigned long long)rdev->sb_start);
> rdev->sb_events = mddev->events;
> + if (rdev->badblocks.size) {
> + md_super_write(mddev, rdev,
> + rdev->badblocks.sector,
> + rdev->badblocks.size << 9,
> + rdev->bb_page);
> + rdev->badblocks.size = 0;
> + }
>
> } else
> dprintk(")\n");
> @@ -2316,6 +2412,9 @@ repeat:
> if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
> sysfs_notify(&mddev->kobj, NULL, "sync_completed");
>
> + if (any_badblocks_changed)
> + list_for_each_entry(rdev, &mddev->disks, same_set)
> + md_ack_all_badblocks(&rdev->badblocks);
> }
>
> /* words written to sysfs files may, or may not, be \n terminated.
> @@ -2823,6 +2922,8 @@ int md_rdev_init(mdk_rdev_t *rdev)
> rdev->sb_events = 0;
> rdev->last_read_error.tv_sec = 0;
> rdev->last_read_error.tv_nsec = 0;
> + rdev->sb_loaded = 0;
> + rdev->bb_page = NULL;
> atomic_set(&rdev->nr_pending, 0);
> atomic_set(&rdev->read_errors, 0);
> atomic_set(&rdev->corrected_errors, 0);
> @@ -2912,11 +3013,9 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi
> return rdev;
>
> abort_free:
> - if (rdev->sb_page) {
> - if (rdev->bdev)
> - unlock_rdev(rdev);
> - free_disk_sb(rdev);
> - }
> + if (rdev->bdev)
> + unlock_rdev(rdev);
> + free_disk_sb(rdev);
> kfree(rdev);
> return ERR_PTR(err);
> }
> diff --git a/drivers/md/md.h b/drivers/md/md.h
> index d327734..834e46b 100644
> --- a/drivers/md/md.h
> +++ b/drivers/md/md.h
> @@ -55,7 +55,7 @@ struct mdk_rdev_s
> struct block_device *meta_bdev;
> struct block_device *bdev; /* block device handle */
>
> - struct page *sb_page;
> + struct page *sb_page, *bb_page;
> int sb_loaded;
> __u64 sb_events;
> sector_t data_offset; /* start of data in array */
> @@ -128,6 +128,9 @@ struct mdk_rdev_s
> u64 *active_page; /* either 'page' or 'NULL' */
> int changed;
> spinlock_t lock;
> +
> + sector_t sector;
> + sector_t size; /* in sectors */
Looks like 'int' is sufficient for 'size'. Anyway md_super_write()
treats it as int.
> } badblocks;
> };
>
> diff --git a/include/linux/raid/md_p.h b/include/linux/raid/md_p.h
> index 75cbf4f..9e65d9e 100644
> --- a/include/linux/raid/md_p.h
> +++ b/include/linux/raid/md_p.h
> @@ -245,10 +245,16 @@ struct mdp_superblock_1 {
> __u8 device_uuid[16]; /* user-space setable, ignored by kernel */
> __u8 devflags; /* per-device flags. Only one defined...*/
> #define WriteMostly1 1 /* mask for writemostly flag in above */
> - __u8 pad2[64-57]; /* set to 0 when writing */
> + /* Bad block log. If there are any bad blocks the feature flag is set.
> + * If offset and size are non-zero, that space is reserved and available
> + */
> + __u8 bblog_shift; /* shift from sectors to block size */
> + __le16 bblog_size; /* number of sectors reserved for list */
> + __le32 bblog_offset; /* sector offset from superblock to bblog,
> + * signed - not unsigned */
>
> /* array state information - 64 bytes */
> - __le64 utime; /* 40 bits second, 24 btes microseconds */
> + __le64 utime; /* 40 bits second, 24 bits microseconds */
> __le64 events; /* incremented when superblock updated */
> __le64 resync_offset; /* data before this offset (from data_offset) known to be in sync */
> __le32 sb_csum; /* checksum up to devs[max_dev] */
> @@ -270,8 +276,8 @@ struct mdp_superblock_1 {
> * must be honoured
> */
> #define MD_FEATURE_RESHAPE_ACTIVE 4
> +#define MD_FEATURE_BAD_BLOCKS 8 /* badblock list is not empty */
>
> -#define MD_FEATURE_ALL (1|2|4)
> +#define MD_FEATURE_ALL (1|2|4|8)
>
> #endif
> -
>
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-raid" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
next prev parent reply other threads:[~2011-07-22 16:34 UTC|newest]
Thread overview: 65+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-07-21 2:58 [md PATCH 00/36] md patches for 3.1 - part 2: bad block logs NeilBrown
2011-07-21 2:58 ` [md PATCH 03/36] md: don't allow arrays to contain devices with bad blocks NeilBrown
2011-07-22 15:47 ` Namhyung Kim
2011-07-21 2:58 ` [md PATCH 02/36] md/bad-block-log: add sysfs interface for accessing bad-block-log NeilBrown
2011-07-22 15:43 ` Namhyung Kim
2011-07-26 2:29 ` NeilBrown
2011-07-26 5:17 ` Namhyung Kim
2011-07-26 8:48 ` Namhyung Kim
2011-07-26 15:03 ` [PATCH v2] md: add documentation for bad block log Namhyung Kim
2011-07-27 1:05 ` [md PATCH 02/36] md/bad-block-log: add sysfs interface for accessing bad-block-log NeilBrown
2011-07-21 2:58 ` [md PATCH 04/36] md: load/store badblock list from v1.x metadata NeilBrown
2011-07-22 16:34 ` Namhyung Kim [this message]
2011-07-21 2:58 ` [md PATCH 01/36] md: beginnings of bad block management NeilBrown
2011-07-22 15:03 ` Namhyung Kim
2011-07-26 2:26 ` NeilBrown
2011-07-26 5:17 ` Namhyung Kim
2011-07-22 16:52 ` Namhyung Kim
2011-07-26 3:20 ` NeilBrown
2011-07-21 2:58 ` [md PATCH 09/36] md: make it easier to wait for bad blocks to be acknowledged NeilBrown
2011-07-26 16:04 ` Namhyung Kim
2011-07-27 1:18 ` NeilBrown
2011-07-21 2:58 ` [md PATCH 11/36] md/raid1: clear bad-block record when write succeeds NeilBrown
2011-07-27 5:05 ` Namhyung Kim
2011-07-21 2:58 ` [md PATCH 07/36] md/raid1: avoid reading known bad blocks during resync NeilBrown
2011-07-26 14:25 ` Namhyung Kim
2011-07-21 2:58 ` [md PATCH 10/36] md/raid1: avoid writing to known-bad blocks on known-bad drives NeilBrown
2011-07-27 4:09 ` Namhyung Kim
2011-07-27 4:19 ` NeilBrown
2011-07-21 2:58 ` [md PATCH 14/36] md/raid1: record badblocks found during resync etc NeilBrown
2011-07-27 15:39 ` Namhyung Kim
2011-07-21 2:58 ` [md PATCH 12/36] md/raid1: store behind-write pages in bi_vecs NeilBrown
2011-07-27 15:16 ` Namhyung Kim
2011-07-21 2:58 ` [md PATCH 06/36] md/raid1: avoid reading from known bad blocks NeilBrown
2011-07-26 14:06 ` Namhyung Kim
2011-07-21 2:58 ` [md PATCH 08/36] md: add 'write_error' flag to component devices NeilBrown
2011-07-26 15:22 ` Namhyung Kim
2011-07-21 2:58 ` [md PATCH 13/36] md/raid1: Handle write errors by updating badblock log NeilBrown
2011-07-27 15:28 ` Namhyung Kim
2011-07-21 2:58 ` [md PATCH 05/36] md: Disable bad blocks and v0.90 metadata NeilBrown
2011-07-22 17:02 ` Namhyung Kim
2011-07-21 2:58 ` [md PATCH 19/36] md/raid5: write errors should be recorded as bad blocks if possible NeilBrown
2011-07-21 2:58 ` [md PATCH 21/36] md/raid5: Clear bad blocks on successful write NeilBrown
2011-07-21 2:58 ` [md PATCH 17/36] md/raid5: avoid reading from known bad blocks NeilBrown
2011-07-21 2:58 ` [md PATCH 18/36] md/raid5: use bad-block log to improve handling of uncorrectable read errors NeilBrown
2011-07-21 2:58 ` [md PATCH 16/36] md/raid1: factor several functions out or raid1d() NeilBrown
2011-07-27 15:55 ` Namhyung Kim
2011-07-28 1:39 ` NeilBrown
2011-07-21 2:58 ` [md PATCH 22/36] md/raid10: simplify/reindent some loops NeilBrown
2011-07-21 2:58 ` [md PATCH 24/36] md/raid10: avoid reading from known bad blocks - part 1 NeilBrown
2011-07-21 2:58 ` [md PATCH 15/36] md/raid1: improve handling of read failure during recovery NeilBrown
2011-07-27 15:45 ` Namhyung Kim
2011-07-21 2:58 ` [md PATCH 23/36] md/raid10: Split handle_read_error out from raid10d NeilBrown
2011-07-21 2:58 ` [md PATCH 20/36] md/raid5. Don't write to known bad block on doubtful devices NeilBrown
2011-07-21 2:58 ` [md PATCH 31/36] md/raid10: Handle write errors by updating badblock log NeilBrown
2011-07-21 2:58 ` [md PATCH 30/36] md/raid10: clear bad-block record when write succeeds NeilBrown
2011-07-21 2:58 ` [md PATCH 29/36] md/raid10: avoid writing to known bad blocks on known bad drives NeilBrown
2011-07-21 2:58 ` [md PATCH 34/36] md/raid10: simplify read error handling during recovery NeilBrown
2011-07-21 2:58 ` [md PATCH 25/36] md/raid10: avoid reading from known bad blocks - part 2 NeilBrown
2011-07-21 2:58 ` [md PATCH 32/36] md/raid10: attempt to fix read errors during resync/check NeilBrown
2011-07-21 2:58 ` [md PATCH 33/36] md/raid10: record bad blocks due to write errors during resync/recovery NeilBrown
2011-07-21 2:58 ` [md PATCH 26/36] md/raid10 - avoid reading from known bad blocks - part 3 NeilBrown
2011-07-21 2:58 ` [md PATCH 27/36] md/raid10: avoid reading known bad blocks during resync/recovery NeilBrown
2011-07-21 2:58 ` [md PATCH 28/36] md/raid10 record bad blocks as needed during recovery NeilBrown
2011-07-21 2:58 ` [md PATCH 35/36] md/raid10: Handle read errors during recovery better NeilBrown
2011-07-21 2:58 ` [md PATCH 36/36] md/raid10: handle further errors during fix_read_error better NeilBrown
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=87vcuu46l4.fsf@gmail.com \
--to=namhyung@gmail.com \
--cc=linux-raid@vger.kernel.org \
--cc=neilb@suse.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.