typedef struct mddev_s mddev_t;
typedef struct mdk_rdev_s mdk_rdev_t;
+/* Bad block numbers are stored sorted in a single page.
+ * 64bits is used for each block or extent.
+ * 54 bits are sector number, 9 bits are extent size,
+ * 1 bit is an 'acknowledged' flag.
+ */
+#define MD_MAX_BADBLOCKS (PAGE_SIZE/8)
+
/*
* MD's 'extended' device
*/
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 */
#define In_sync 2 /* device is in_sync with rest of array */
#define WriteMostly 4 /* Avoid reading if at all possible */
#define AutoDetected 7 /* added by auto-detect */
-#define Blocked 8 /* An error occurred on an externally
- * managed array, don't allow writes
+#define Blocked 8 /* An error occurred but has not yet
+ * been acknowledged by the metadata
+ * handler, so don't allow writes
* until it is cleared */
+#define WriteErrorSeen 9 /* A write error has been seen on this
+ * device
+ */
+#define FaultRecorded 10 /* Intermediate state for clearing
+ * Blocked. The Fault is/will-be
+ * recorded in the metadata, but that
+ * metadata hasn't been stored safely
+ * on disk yet.
+ */
+#define BlockedBadBlocks 11 /* A writer is blocked because they
+ * found an unacknowledged bad-block.
+ * This can safely be cleared at any
+ * time, and the writer will re-check.
+ * It may be set at any time, and at
+ * worst the writer will timeout and
+ * re-check. So setting it as
+ * accurately as possible is good, but
+ * not absolutely critical.
+ */
wait_queue_head_t blocked_wait;
int desc_nr; /* descriptor index in the superblock */
struct sysfs_dirent *sysfs_state; /* handle for 'state'
* sysfs entry */
+
+ struct badblocks {
+ int count; /* count of bad blocks */
+ int unacked_exist; /* there probably are unacknowledged
+ * bad blocks. This is only cleared
+ * when a read discovers none
+ */
+ int shift; /* shift from sectors to block size
+ * a -ve shift means badblocks are
+ * disabled.*/
+ u64 *page; /* badblock list */
+ int changed;
+ seqlock_t lock;
+
+ sector_t sector;
+ sector_t size; /* in sectors */
+ } badblocks;
};
+#define BB_LEN_MASK (0x00000000000001FFULL)
+#define BB_OFFSET_MASK (0x7FFFFFFFFFFFFE00ULL)
+#define BB_ACK_MASK (0x8000000000000000ULL)
+#define BB_MAX_LEN 512
+#define BB_OFFSET(x) (((x) & BB_OFFSET_MASK) >> 9)
+#define BB_LEN(x) (((x) & BB_LEN_MASK) + 1)
+#define BB_ACK(x) (!!((x) & BB_ACK_MASK))
+#define BB_MAKE(a, l, ack) (((a)<<9) | ((l)-1) | ((u64)(!!(ack)) << 63))
+
+extern int md_is_badblock(struct badblocks *bb, sector_t s, int sectors,
+ sector_t *first_bad, int *bad_sectors);
+static inline int is_badblock(mdk_rdev_t *rdev, sector_t s, int sectors,
+ sector_t *first_bad, int *bad_sectors)
+{
+ if (unlikely(rdev->badblocks.count)) {
+ int rv = md_is_badblock(&rdev->badblocks, rdev->data_offset + s,
+ sectors,
+ first_bad, bad_sectors);
+ if (rv)
+ *first_bad -= rdev->data_offset;
+ return rv;
+ }
+ return 0;
+}
+extern int rdev_set_badblocks(mdk_rdev_t *rdev, sector_t s, int sectors,
+ int acknowledged);
+extern int rdev_clear_badblocks(mdk_rdev_t *rdev, sector_t s, int sectors);
+extern void md_ack_all_badblocks(struct badblocks *bb);
+
struct mddev_s
{
void *private;
#define MD_RECOVERY_FROZEN 9
unsigned long recovery;
- int recovery_disabled; /* if we detect that recovery
- * will always fail, set this
- * so we don't loop trying */
+ /* If a RAID personality determines that recovery (of a particular
+ * device) will fail due to a read error on the source device, it
+ * takes a copy of this number and does not attempt recovery again
+ * until this number changes.
+ */
+ int recovery_disabled;
int in_sync; /* know to not need resync */
/* 'open_mutex' avoids races between 'md_open' and 'do_md_stop', so
* hot-adding a bitmap. It should
* eventually be settable by sysfs.
*/
- /* When md is serving under dm, it might use a
- * dirty_log to store the bits.
- */
- struct dm_dirty_log *log;
-
struct mutex mutex;
unsigned long chunksize;
unsigned long daemon_sleep; /* how many jiffies between updates? */
return mddev->gendisk ? mddev->gendisk->disk_name : "mdX";
}
+static inline int sysfs_link_rdev(mddev_t *mddev, mdk_rdev_t *rdev)
+{
+ char nm[20];
+ sprintf(nm, "rd%d", rdev->raid_disk);
+ return sysfs_create_link(&mddev->kobj, &rdev->kobj, nm);
+}
+
+static inline void sysfs_unlink_rdev(mddev_t *mddev, mdk_rdev_t *rdev)
+{
+ char nm[20];
+ sprintf(nm, "rd%d", rdev->raid_disk);
+ sysfs_remove_link(&mddev->kobj, nm);
+}
+
/*
* iterates through some rdev ringlist. It's safe to remove the
* current 'rdev'. Dont touch 'tmp' though.
extern int md_run(mddev_t *mddev);
extern void md_stop(mddev_t *mddev);
extern void md_stop_writes(mddev_t *mddev);
-extern void md_rdev_init(mdk_rdev_t *rdev);
+extern int md_rdev_init(mdk_rdev_t *rdev);
extern void mddev_suspend(mddev_t *mddev);
extern void mddev_resume(mddev_t *mddev);
extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
mddev_t *mddev);
extern int mddev_check_plugged(mddev_t *mddev);
+extern void md_trim_bio(struct bio *bio, int offset, int size);
#endif /* _MD_MD_H */
git.openpandora.org / pandora-kernel.git / blobdiff