Merge branch 'master' of /home/davem/src/GIT/linux-2.6/

1 files changed, 333 insertions, 122 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 5f154ef1e4be..dd3dfe42d5a9 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -39,11 +39,13 @@
 #include <linux/buffer_head.h> /* for invalidate_bdev */
 #include <linux/poll.h>
 #include <linux/ctype.h>
+#include <linux/string.h>
 #include <linux/hdreg.h>
 #include <linux/proc_fs.h>
 #include <linux/random.h>
 #include <linux/reboot.h>
 #include <linux/file.h>
+#include <linux/compat.h>
 #include <linux/delay.h>
 #include <linux/raid/md_p.h>
 #include <linux/raid/md_u.h>
@@ -68,6 +70,12 @@ static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
 #define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); }
 
 /*
+ * Default number of read corrections we'll attempt on an rdev
+ * before ejecting it from the array. We divide the read error
+ * count by 2 for every hour elapsed between read errors.
+ */
+#define MD_DEFAULT_MAX_CORRECTED_READ_ERRORS 20
+/*
  * Current RAID-1,4,5 parallel reconstruction 'guaranteed speed limit'
  * is 1000 KB/sec, so the extra system load does not show up that much.
  * Increase it if you want to have more _guaranteed_ speed. Note that
@@ -213,12 +221,12 @@ static int md_make_request(struct request_queue *q, struct bio *bio)
                 return 0;
         }
         rcu_read_lock();
-        if (mddev->suspended) {
+        if (mddev->suspended || mddev->barrier) {
                 DEFINE_WAIT(__wait);
                 for (;;) {
                         prepare_to_wait(&mddev->sb_wait, &__wait,
                                         TASK_UNINTERRUPTIBLE);
-                        if (!mddev->suspended)
+                        if (!mddev->suspended && !mddev->barrier)
                                 break;
                         rcu_read_unlock();
                         schedule();
@@ -260,10 +268,110 @@ static void mddev_resume(mddev_t *mddev)
 
 int mddev_congested(mddev_t *mddev, int bits)
 {
+        if (mddev->barrier)
+                return 1;
         return mddev->suspended;
 }
 EXPORT_SYMBOL(mddev_congested);
 
+/*
+ * Generic barrier handling for md
+ */
+
+#define POST_REQUEST_BARRIER ((void*)1)
+
+static void md_end_barrier(struct bio *bio, int err)
+{
+        mdk_rdev_t *rdev = bio->bi_private;
+        mddev_t *mddev = rdev->mddev;
+        if (err == -EOPNOTSUPP && mddev->barrier != POST_REQUEST_BARRIER)
+                set_bit(BIO_EOPNOTSUPP, &mddev->barrier->bi_flags);
+
+        rdev_dec_pending(rdev, mddev);
+
+        if (atomic_dec_and_test(&mddev->flush_pending)) {
+                if (mddev->barrier == POST_REQUEST_BARRIER) {
+                        /* This was a post-request barrier */
+                        mddev->barrier = NULL;
+                        wake_up(&mddev->sb_wait);
+                } else
+                        /* The pre-request barrier has finished */
+                        schedule_work(&mddev->barrier_work);
+        }
+        bio_put(bio);
+}
+
+static void submit_barriers(mddev_t *mddev)
+{
+        mdk_rdev_t *rdev;
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(rdev, &mddev->disks, same_set)
+                if (rdev->raid_disk >= 0 &&
+                    !test_bit(Faulty, &rdev->flags)) {
+                        /* Take two references, one is dropped
+                         * when request finishes, one after
+                         * we reclaim rcu_read_lock
+                         */
+                        struct bio *bi;
+                        atomic_inc(&rdev->nr_pending);
+                        atomic_inc(&rdev->nr_pending);
+                        rcu_read_unlock();
+                        bi = bio_alloc(GFP_KERNEL, 0);
+                        bi->bi_end_io = md_end_barrier;
+                        bi->bi_private = rdev;
+                        bi->bi_bdev = rdev->bdev;
+                        atomic_inc(&mddev->flush_pending);
+                        submit_bio(WRITE_BARRIER, bi);
+                        rcu_read_lock();
+                        rdev_dec_pending(rdev, mddev);
+                }
+        rcu_read_unlock();
+}
+
+static void md_submit_barrier(struct work_struct *ws)
+{
+        mddev_t *mddev = container_of(ws, mddev_t, barrier_work);
+        struct bio *bio = mddev->barrier;
+
+        atomic_set(&mddev->flush_pending, 1);
+
+        if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
+                bio_endio(bio, -EOPNOTSUPP);
+        else if (bio->bi_size == 0)
+                /* an empty barrier - all done */
+                bio_endio(bio, 0);
+        else {
+                bio->bi_rw &= ~(1<<BIO_RW_BARRIER);
+                if (mddev->pers->make_request(mddev->queue, bio))
+                        generic_make_request(bio);
+                mddev->barrier = POST_REQUEST_BARRIER;
+                submit_barriers(mddev);
+        }
+        if (atomic_dec_and_test(&mddev->flush_pending)) {
+                mddev->barrier = NULL;
+                wake_up(&mddev->sb_wait);
+        }
+}
+
+void md_barrier_request(mddev_t *mddev, struct bio *bio)
+{
+        spin_lock_irq(&mddev->write_lock);
+        wait_event_lock_irq(mddev->sb_wait,
+                            !mddev->barrier,
+                            mddev->write_lock, /*nothing*/);
+        mddev->barrier = bio;
+        spin_unlock_irq(&mddev->write_lock);
+
+        atomic_set(&mddev->flush_pending, 1);
+        INIT_WORK(&mddev->barrier_work, md_submit_barrier);
+
+        submit_barriers(mddev);
+
+        if (atomic_dec_and_test(&mddev->flush_pending))
+                schedule_work(&mddev->barrier_work);
+}
+EXPORT_SYMBOL(md_barrier_request);
 
 static inline mddev_t *mddev_get(mddev_t *mddev)
 {
@@ -278,7 +386,9 @@ static void mddev_put(mddev_t *mddev)
         if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
                 return;
         if (!mddev->raid_disks && list_empty(&mddev->disks) &&
-            !mddev->hold_active) {
+            mddev->ctime == 0 && !mddev->hold_active) {
+                /* Array is not configured at all, and not held active,
+                 * so destroy it */
                 list_del(&mddev->all_mddevs);
                 if (mddev->gendisk) {
                         /* we did a probe so need to clean up.
@@ -363,6 +473,7 @@ static mddev_t * mddev_find(dev_t unit)
 
         mutex_init(&new->open_mutex);
         mutex_init(&new->reconfig_mutex);
+        mutex_init(&new->bitmap_info.mutex);
         INIT_LIST_HEAD(&new->disks);
         INIT_LIST_HEAD(&new->all_mddevs);
         init_timer(&new->safemode_timer);
@@ -370,6 +481,7 @@ static mddev_t * mddev_find(dev_t unit)
         atomic_set(&new->openers, 0);
         atomic_set(&new->active_io, 0);
         spin_lock_init(&new->write_lock);
+        atomic_set(&new->flush_pending, 0);
         init_waitqueue_head(&new->sb_wait);
         init_waitqueue_head(&new->recovery_wait);
         new->reshape_position = MaxSector;
@@ -748,7 +860,7 @@ struct super_type  {
  */
 int md_check_no_bitmap(mddev_t *mddev)
 {
-        if (!mddev->bitmap_file && !mddev->bitmap_offset)
+        if (!mddev->bitmap_info.file && !mddev->bitmap_info.offset)
                 return 0;
         printk(KERN_ERR "%s: bitmaps are not supported for %s\n",
                 mdname(mddev), mddev->pers->name);
@@ -876,8 +988,8 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
                 mddev->raid_disks = sb->raid_disks;
                 mddev->dev_sectors = sb->size * 2;
                 mddev->events = ev1;
-                mddev->bitmap_offset = 0;
-                mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
+                mddev->bitmap_info.offset = 0;
+                mddev->bitmap_info.default_offset = MD_SB_BYTES >> 9;
 
                 if (mddev->minor_version >= 91) {
                         mddev->reshape_position = sb->reshape_position;
@@ -911,8 +1023,9 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
                 mddev->max_disks = MD_SB_DISKS;
 
                 if (sb->state & (1<<MD_SB_BITMAP_PRESENT) &&
-                    mddev->bitmap_file == NULL)
-                        mddev->bitmap_offset = mddev->default_bitmap_offset;
+                    mddev->bitmap_info.file == NULL)
+                        mddev->bitmap_info.offset =
+                                mddev->bitmap_info.default_offset;
 
         } else if (mddev->pers == NULL) {
                 /* Insist on good event counter while assembling */
@@ -1029,7 +1142,7 @@ static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev)
         sb->layout = mddev->layout;
         sb->chunk_size = mddev->chunk_sectors << 9;
 
-        if (mddev->bitmap && mddev->bitmap_file == NULL)
+        if (mddev->bitmap && mddev->bitmap_info.file == NULL)
                 sb->state |= (1<<MD_SB_BITMAP_PRESENT);
 
         sb->disks[0].state = (1<<MD_DISK_REMOVED);
@@ -1107,7 +1220,7 @@ super_90_rdev_size_change(mdk_rdev_t *rdev, sector_t num_sectors)
 {
         if (num_sectors && num_sectors < rdev->mddev->dev_sectors)
                 return 0; /* component must fit device */
-        if (rdev->mddev->bitmap_offset)
+        if (rdev->mddev->bitmap_info.offset)
                 return 0; /* can't move bitmap */
         rdev->sb_start = calc_dev_sboffset(rdev->bdev);
         if (!num_sectors || num_sectors > rdev->sb_start)
@@ -1286,8 +1399,8 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
                 mddev->raid_disks = le32_to_cpu(sb->raid_disks);
                 mddev->dev_sectors = le64_to_cpu(sb->size);
                 mddev->events = ev1;
-                mddev->bitmap_offset = 0;
-                mddev->default_bitmap_offset = 1024 >> 9;
+                mddev->bitmap_info.offset = 0;
+                mddev->bitmap_info.default_offset = 1024 >> 9;
                 
                 mddev->recovery_cp = le64_to_cpu(sb->resync_offset);
                 memcpy(mddev->uuid, sb->set_uuid, 16);
@@ -1295,8 +1408,9 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
                 mddev->max_disks =  (4096-256)/2;
 
                 if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET) &&
-                    mddev->bitmap_file == NULL )
-                        mddev->bitmap_offset = (__s32)le32_to_cpu(sb->bitmap_offset);
+                    mddev->bitmap_info.file == NULL )
+                        mddev->bitmap_info.offset =
+                                (__s32)le32_to_cpu(sb->bitmap_offset);
 
                 if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) {
                         mddev->reshape_position = le64_to_cpu(sb->reshape_position);
@@ -1390,19 +1504,17 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
         sb->level = cpu_to_le32(mddev->level);
         sb->layout = cpu_to_le32(mddev->layout);
 
-        if (mddev->bitmap && mddev->bitmap_file == NULL) {
-                sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_offset);
+        if (mddev->bitmap && mddev->bitmap_info.file == NULL) {
+                sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_info.offset);
                 sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
         }
 
         if (rdev->raid_disk >= 0 &&
             !test_bit(In_sync, &rdev->flags)) {
-                if (rdev->recovery_offset > 0) {
-                        sb->feature_map |=
-                                cpu_to_le32(MD_FEATURE_RECOVERY_OFFSET);
-                        sb->recovery_offset =
-                                cpu_to_le64(rdev->recovery_offset);
-                }
+                sb->feature_map |=
+                        cpu_to_le32(MD_FEATURE_RECOVERY_OFFSET);
+                sb->recovery_offset =
+                        cpu_to_le64(rdev->recovery_offset);
         }
 
         if (mddev->reshape_position != MaxSector) {
@@ -1436,7 +1548,7 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
                         sb->dev_roles[i] = cpu_to_le16(0xfffe);
                 else if (test_bit(In_sync, &rdev2->flags))
                         sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
-                else if (rdev2->raid_disk >= 0 && rdev2->recovery_offset > 0)
+                else if (rdev2->raid_disk >= 0)
                         sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
                 else
                         sb->dev_roles[i] = cpu_to_le16(0xffff);
@@ -1458,7 +1570,7 @@ super_1_rdev_size_change(mdk_rdev_t *rdev, sector_t num_sectors)
                 max_sectors -= rdev->data_offset;
                 if (!num_sectors || num_sectors > max_sectors)
                         num_sectors = max_sectors;
-        } else if (rdev->mddev->bitmap_offset) {
+        } else if (rdev->mddev->bitmap_info.offset) {
                 /* minor version 0 with bitmap we can't move */
                 return 0;
         } else {
@@ -1826,15 +1938,11 @@ static void print_sb_1(struct mdp_superblock_1 *sb)
 
         uuid = sb->set_uuid;
         printk(KERN_INFO
-               "md:  SB: (V:%u) (F:0x%08x) Array-ID:<%02x%02x%02x%02x"
-               ":%02x%02x:%02x%02x:%02x%02x:%02x%02x%02x%02x%02x%02x>\n"
+               "md:  SB: (V:%u) (F:0x%08x) Array-ID:<%pU>\n"
                "md:    Name: \"%s\" CT:%llu\n",
                 le32_to_cpu(sb->major_version),
                 le32_to_cpu(sb->feature_map),
-                uuid[0], uuid[1], uuid[2], uuid[3],
-                uuid[4], uuid[5], uuid[6], uuid[7],
-                uuid[8], uuid[9], uuid[10], uuid[11],
-                uuid[12], uuid[13], uuid[14], uuid[15],
+                uuid,
                 sb->set_name,
                 (unsigned long long)le64_to_cpu(sb->ctime)
                        & MD_SUPERBLOCK_1_TIME_SEC_MASK);
@@ -1843,8 +1951,7 @@ static void print_sb_1(struct mdp_superblock_1 *sb)
         printk(KERN_INFO
                "md:       L%u SZ%llu RD:%u LO:%u CS:%u DO:%llu DS:%llu SO:%llu"
                         " RO:%llu\n"
-               "md:     Dev:%08x UUID: %02x%02x%02x%02x:%02x%02x:%02x%02x:%02x%02x"
-                        ":%02x%02x%02x%02x%02x%02x\n"
+               "md:     Dev:%08x UUID: %pU\n"
                "md:       (F:0x%08x) UT:%llu Events:%llu ResyncOffset:%llu CSUM:0x%08x\n"
                "md:         (MaxDev:%u) \n",
                 le32_to_cpu(sb->level),
@@ -1857,10 +1964,7 @@ static void print_sb_1(struct mdp_superblock_1 *sb)
                 (unsigned long long)le64_to_cpu(sb->super_offset),
                 (unsigned long long)le64_to_cpu(sb->recovery_offset),
                 le32_to_cpu(sb->dev_number),
-                uuid[0], uuid[1], uuid[2], uuid[3],
-                uuid[4], uuid[5], uuid[6], uuid[7],
-                uuid[8], uuid[9], uuid[10], uuid[11],
-                uuid[12], uuid[13], uuid[14], uuid[15],
+                uuid,
                 sb->devflags,
                 (unsigned long long)le64_to_cpu(sb->utime) & MD_SUPERBLOCK_1_TIME_SEC_MASK,
                 (unsigned long long)le64_to_cpu(sb->events),
@@ -2442,12 +2546,49 @@ rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 static struct rdev_sysfs_entry rdev_size =
 __ATTR(size, S_IRUGO|S_IWUSR, rdev_size_show, rdev_size_store);
 
+
+static ssize_t recovery_start_show(mdk_rdev_t *rdev, char *page)
+{
+        unsigned long long recovery_start = rdev->recovery_offset;
+
+        if (test_bit(In_sync, &rdev->flags) ||
+            recovery_start == MaxSector)
+                return sprintf(page, "none\n");
+
+        return sprintf(page, "%llu\n", recovery_start);
+}
+
+static ssize_t recovery_start_store(mdk_rdev_t *rdev, const char *buf, size_t len)
+{
+        unsigned long long recovery_start;
+
+        if (cmd_match(buf, "none"))
+                recovery_start = MaxSector;
+        else if (strict_strtoull(buf, 10, &recovery_start))
+                return -EINVAL;
+
+        if (rdev->mddev->pers &&
+            rdev->raid_disk >= 0)
+                return -EBUSY;
+
+        rdev->recovery_offset = recovery_start;
+        if (recovery_start == MaxSector)
+                set_bit(In_sync, &rdev->flags);
+        else
+                clear_bit(In_sync, &rdev->flags);
+        return len;
+}
+
+static struct rdev_sysfs_entry rdev_recovery_start =
+__ATTR(recovery_start, S_IRUGO|S_IWUSR, recovery_start_show, recovery_start_store);
+
 static struct attribute *rdev_default_attrs[] = {
         &rdev_state.attr,
         &rdev_errors.attr,
         &rdev_slot.attr,
         &rdev_offset.attr,
         &rdev_size.attr,
+        &rdev_recovery_start.attr,
         NULL,
 };
 static ssize_t
@@ -2549,6 +2690,8 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi
         rdev->flags = 0;
         rdev->data_offset = 0;
         rdev->sb_events = 0;
+        rdev->last_read_error.tv_sec  = 0;
+        rdev->last_read_error.tv_nsec = 0;
         atomic_set(&rdev->nr_pending, 0);
         atomic_set(&rdev->read_errors, 0);
         atomic_set(&rdev->corrected_errors, 0);
@@ -2659,6 +2802,47 @@ static void analyze_sbs(mddev_t * mddev)
         }
 }
 
+/* Read a fixed-point number.
+ * Numbers in sysfs attributes should be in "standard" units where
+ * possible, so time should be in seconds.
+ * However we internally use a a much smaller unit such as 
+ * milliseconds or jiffies.
+ * This function takes a decimal number with a possible fractional
+ * component, and produces an integer which is the result of
+ * multiplying that number by 10^'scale'.
+ * all without any floating-point arithmetic.
+ */
+int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale)
+{
+        unsigned long result = 0;
+        long decimals = -1;
+        while (isdigit(*cp) || (*cp == '.' && decimals < 0)) {
+                if (*cp == '.')
+                        decimals = 0;
+                else if (decimals < scale) {
+                        unsigned int value;
+                        value = *cp - '0';
+                        result = result * 10 + value;
+                        if (decimals >= 0)
+                                decimals++;
+                }
+                cp++;
+        }
+        if (*cp == '\n')
+                cp++;
+        if (*cp)
+                return -EINVAL;
+        if (decimals < 0)
+                decimals = 0;
+        while (decimals < scale) {
+                result *= 10;
+                decimals ++;
+        }
+        *res = result;
+        return 0;
+}
+
+
 static void md_safemode_timeout(unsigned long data);
 
 static ssize_t
@@ -2670,31 +2854,10 @@ safe_delay_show(mddev_t *mddev, char *page)
 static ssize_t
 safe_delay_store(mddev_t *mddev, const char *cbuf, size_t len)
 {
-        int scale=1;
-        int dot=0;
-        int i;
         unsigned long msec;
-        char buf[30];
 
-        /* remove a period, and count digits after it */
-        if (len >= sizeof(buf))
+        if (strict_strtoul_scaled(cbuf, &msec, 3) < 0)
                 return -EINVAL;
-        strlcpy(buf, cbuf, sizeof(buf));
-        for (i=0; i<len; i++) {
-                if (dot) {
-                        if (isdigit(buf[i])) {
-                                buf[i-1] = buf[i];
-                                scale *= 10;
-                        }
-                        buf[i] = 0;
-                } else if (buf[i] == '.') {
-                        dot=1;
-                        buf[i] = 0;
-                }
-        }
-        if (strict_strtoul(buf, 10, &msec) < 0)
-                return -EINVAL;
-        msec = (msec * 1000) / scale;
         if (msec == 0)
                 mddev->safemode_delay = 0;
         else {
@@ -2970,7 +3133,9 @@ resync_start_store(mddev_t *mddev, const char *buf, size_t len)
 
         if (mddev->pers)
                 return -EBUSY;
-        if (!*buf || (*e && *e != '\n'))
+        if (cmd_match(buf, "none"))
+                n = MaxSector;
+        else if (!*buf || (*e && *e != '\n'))
                 return -EINVAL;
 
         mddev->recovery_cp = n;
@@ -3166,6 +3331,29 @@ static struct md_sysfs_entry md_array_state =
 __ATTR(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store);
 
 static ssize_t
+max_corrected_read_errors_show(mddev_t *mddev, char *page) {
+        return sprintf(page, "%d\n",
+                       atomic_read(&mddev->max_corr_read_errors));
+}
+
+static ssize_t
+max_corrected_read_errors_store(mddev_t *mddev, const char *buf, size_t len)
+{
+        char *e;
+        unsigned long n = simple_strtoul(buf, &e, 10);
+
+        if (*buf && (*e == 0 || *e == '\n')) {
+                atomic_set(&mddev->max_corr_read_errors, n);
+                return len;
+        }
+        return -EINVAL;
+}
+
+static struct md_sysfs_entry max_corr_read_errors =
+__ATTR(max_read_errors, S_IRUGO|S_IWUSR, max_corrected_read_errors_show,
+        max_corrected_read_errors_store);
+
+static ssize_t
 null_show(mddev_t *mddev, char *page)
 {
         return -EINVAL;
@@ -3246,8 +3434,7 @@ bitmap_store(mddev_t *mddev, const char *buf, size_t len)
                 }
                 if (*end && !isspace(*end)) break;
                 bitmap_dirty_bits(mddev->bitmap, chunk, end_chunk);
-                buf = end;
-                while (isspace(*buf)) buf++;
+                buf = skip_spaces(end);
         }
         bitmap_unplug(mddev->bitmap); /* flush the bits to disk */
 out:
@@ -3790,6 +3977,7 @@ static struct attribute *md_default_attrs[] = {
         &md_array_state.attr,
         &md_reshape_position.attr,
         &md_array_size.attr,
+        &max_corr_read_errors.attr,
         NULL,
 };
 
@@ -3894,6 +4082,7 @@ static void mddev_delayed_delete(struct work_struct *ws)
                 mddev->sysfs_action = NULL;
                 mddev->private = NULL;
         }
+        sysfs_remove_group(&mddev->kobj, &md_bitmap_group);
         kobject_del(&mddev->kobj);
         kobject_put(&mddev->kobj);
 }
@@ -3985,6 +4174,8 @@ static int md_alloc(dev_t dev, char *name)
                        disk->disk_name);
                 error = 0;
         }
+        if (sysfs_create_group(&mddev->kobj, &md_bitmap_group))
+                printk(KERN_DEBUG "pointless warning\n");
  abort:
         mutex_unlock(&disks_mutex);
         if (!error) {
@@ -4166,7 +4357,7 @@ static int do_md_run(mddev_t * mddev)
         mddev->barriers_work = 1;
         mddev->ok_start_degraded = start_dirty_degraded;
 
-        if (start_readonly)
+        if (start_readonly && mddev->ro == 0)
                 mddev->ro = 2; /* read-only, but switch on first write */
 
         err = mddev->pers->run(mddev);
@@ -4206,6 +4397,8 @@ static int do_md_run(mddev_t * mddev)
                 mddev->ro = 0;
 
         atomic_set(&mddev->writes_pending,0);
+        atomic_set(&mddev->max_corr_read_errors,
+                   MD_DEFAULT_MAX_CORRECTED_READ_ERRORS);
         mddev->safemode = 0;
         mddev->safemode_timer.function = md_safemode_timeout;
         mddev->safemode_timer.data = (unsigned long) mddev;
@@ -4228,33 +4421,6 @@ static int do_md_run(mddev_t * mddev)
 
         set_capacity(disk, mddev->array_sectors);
 
-        /* If there is a partially-recovered drive we need to
-         * start recovery here.  If we leave it to md_check_recovery,
-         * it will remove the drives and not do the right thing
-         */
-        if (mddev->degraded && !mddev->sync_thread) {
-                int spares = 0;
-                list_for_each_entry(rdev, &mddev->disks, same_set)
-                        if (rdev->raid_disk >= 0 &&
-                            !test_bit(In_sync, &rdev->flags) &&
-                            !test_bit(Faulty, &rdev->flags))
-                                /* complete an interrupted recovery */
-                                spares++;
-                if (spares && mddev->pers->sync_request) {
-                        mddev->recovery = 0;
-                        set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-                        mddev->sync_thread = md_register_thread(md_do_sync,
-                                                                mddev,
-                                                                "resync");
-                        if (!mddev->sync_thread) {
-                                printk(KERN_ERR "%s: could not start resync"
-                                       " thread...\n",
-                                       mdname(mddev));
-                                /* leave the spares where they are, it shouldn't hurt */
-                                mddev->recovery = 0;
-                        }
-                }
-        }
         md_wakeup_thread(mddev->thread);
         md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
@@ -4310,7 +4476,7 @@ static int deny_bitmap_write_access(struct file * file)
         return 0;
 }
 
-static void restore_bitmap_write_access(struct file *file)
+void restore_bitmap_write_access(struct file *file)
 {
         struct inode *inode = file->f_mapping->host;
 
@@ -4405,12 +4571,12 @@ out:
                 printk(KERN_INFO "md: %s stopped.\n", mdname(mddev));
 
                 bitmap_destroy(mddev);
-                if (mddev->bitmap_file) {
-                        restore_bitmap_write_access(mddev->bitmap_file);
-                        fput(mddev->bitmap_file);
-                        mddev->bitmap_file = NULL;
+                if (mddev->bitmap_info.file) {
+                        restore_bitmap_write_access(mddev->bitmap_info.file);
+                        fput(mddev->bitmap_info.file);
+                        mddev->bitmap_info.file = NULL;
                 }
-                mddev->bitmap_offset = 0;
+                mddev->bitmap_info.offset = 0;
 
                 /* make sure all md_delayed_delete calls have finished */
                 flush_scheduled_work();
@@ -4451,6 +4617,11 @@ out:
                 mddev->degraded = 0;
                 mddev->barriers_work = 0;
                 mddev->safemode = 0;
+                mddev->bitmap_info.offset = 0;
+                mddev->bitmap_info.default_offset = 0;
+                mddev->bitmap_info.chunksize = 0;
+                mddev->bitmap_info.daemon_sleep = 0;
+                mddev->bitmap_info.max_write_behind = 0;
                 kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
                 if (mddev->hold_active == UNTIL_STOP)
                         mddev->hold_active = 0;
@@ -4636,7 +4807,7 @@ static int get_array_info(mddev_t * mddev, void __user * arg)
         info.state         = 0;
         if (mddev->in_sync)
                 info.state = (1<<MD_SB_CLEAN);
-        if (mddev->bitmap && mddev->bitmap_offset)
+        if (mddev->bitmap && mddev->bitmap_info.offset)
                 info.state = (1<<MD_SB_BITMAP_PRESENT);
         info.active_disks  = insync;
         info.working_disks = working;
@@ -4994,23 +5165,23 @@ static int set_bitmap_file(mddev_t *mddev, int fd)
         if (fd >= 0) {
                 if (mddev->bitmap)
                         return -EEXIST; /* cannot add when bitmap is present */
-                mddev->bitmap_file = fget(fd);
+                mddev->bitmap_info.file = fget(fd);
 
-                if (mddev->bitmap_file == NULL) {
+                if (mddev->bitmap_info.file == NULL) {
                         printk(KERN_ERR "%s: error: failed to get bitmap file\n",
                                mdname(mddev));
                         return -EBADF;
                 }
 
-                err = deny_bitmap_write_access(mddev->bitmap_file);
+                err = deny_bitmap_write_access(mddev->bitmap_info.file);
                 if (err) {
                         printk(KERN_ERR "%s: error: bitmap file is already in use\n",
                                mdname(mddev));
-                        fput(mddev->bitmap_file);
-                        mddev->bitmap_file = NULL;
+                        fput(mddev->bitmap_info.file);
+                        mddev->bitmap_info.file = NULL;
                         return err;
                 }
-                mddev->bitmap_offset = 0; /* file overrides offset */
+                mddev->bitmap_info.offset = 0; /* file overrides offset */
         } else if (mddev->bitmap == NULL)
                 return -ENOENT; /* cannot remove what isn't there */
         err = 0;
@@ -5025,11 +5196,11 @@ static int set_bitmap_file(mddev_t *mddev, int fd)
                 mddev->pers->quiesce(mddev, 0);
         }
         if (fd < 0) {
-                if (mddev->bitmap_file) {
-                        restore_bitmap_write_access(mddev->bitmap_file);
-                        fput(mddev->bitmap_file);
+                if (mddev->bitmap_info.file) {
+                        restore_bitmap_write_access(mddev->bitmap_info.file);
+                        fput(mddev->bitmap_info.file);
                 }
-                mddev->bitmap_file = NULL;
+                mddev->bitmap_info.file = NULL;
         }
 
         return err;
@@ -5066,6 +5237,10 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info)
                 mddev->minor_version = info->minor_version;
                 mddev->patch_version = info->patch_version;
                 mddev->persistent = !info->not_persistent;
+                /* ensure mddev_put doesn't delete this now that there
+                 * is some minimal configuration.
+                 */
+                mddev->ctime         = get_seconds();
                 return 0;
         }
         mddev->major_version = MD_MAJOR_VERSION;
@@ -5096,8 +5271,8 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info)
                 mddev->flags         = 0;
         set_bit(MD_CHANGE_DEVS, &mddev->flags);
 
-        mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
-        mddev->bitmap_offset = 0;
+        mddev->bitmap_info.default_offset = MD_SB_BYTES >> 9;
+        mddev->bitmap_info.offset = 0;
 
         mddev->reshape_position = MaxSector;
 
@@ -5197,7 +5372,7 @@ static int update_array_info(mddev_t *mddev, mdu_array_info_t *info)
         int state = 0;
 
         /* calculate expected state,ignoring low bits */
-        if (mddev->bitmap && mddev->bitmap_offset)
+        if (mddev->bitmap && mddev->bitmap_info.offset)
                 state |= (1 << MD_SB_BITMAP_PRESENT);
 
         if (mddev->major_version != info->major_version ||
@@ -5256,9 +5431,10 @@ static int update_array_info(mddev_t *mddev, mdu_array_info_t *info)
                         /* add the bitmap */
                         if (mddev->bitmap)
                                 return -EEXIST;
-                        if (mddev->default_bitmap_offset == 0)
+                        if (mddev->bitmap_info.default_offset == 0)
                                 return -EINVAL;
-                        mddev->bitmap_offset = mddev->default_bitmap_offset;
+                        mddev->bitmap_info.offset =
+                                mddev->bitmap_info.default_offset;
                         mddev->pers->quiesce(mddev, 1);
                         rv = bitmap_create(mddev);
                         if (rv)
@@ -5273,7 +5449,7 @@ static int update_array_info(mddev_t *mddev, mdu_array_info_t *info)
                         mddev->pers->quiesce(mddev, 1);
                         bitmap_destroy(mddev);
                         mddev->pers->quiesce(mddev, 0);
-                        mddev->bitmap_offset = 0;
+                        mddev->bitmap_info.offset = 0;
                 }
         }
         md_update_sb(mddev, 1);
@@ -5524,6 +5700,25 @@ done:
 abort:
         return err;
 }
+#ifdef CONFIG_COMPAT
+static int md_compat_ioctl(struct block_device *bdev, fmode_t mode,
+                    unsigned int cmd, unsigned long arg)
+{
+        switch (cmd) {
+        case HOT_REMOVE_DISK:
+        case HOT_ADD_DISK:
+        case SET_DISK_FAULTY:
+        case SET_BITMAP_FILE:
+                /* These take in integer arg, do not convert */
+                break;
+        default:
+                arg = (unsigned long)compat_ptr(arg);
+                break;
+        }
+
+        return md_ioctl(bdev, mode, cmd, arg);
+}
+#endif /* CONFIG_COMPAT */
 
 static int md_open(struct block_device *bdev, fmode_t mode)
 {
@@ -5589,6 +5784,9 @@ static const struct block_device_operations md_fops =
         .open           = md_open,
         .release        = md_release,
         .ioctl          = md_ioctl,
+#ifdef CONFIG_COMPAT
+        .compat_ioctl   = md_compat_ioctl,
+#endif
         .getgeo         = md_getgeo,
         .media_changed  = md_media_changed,
         .revalidate_disk= md_revalidate,
@@ -5982,14 +6180,14 @@ static int md_seq_show(struct seq_file *seq, void *v)
                         unsigned long chunk_kb;
                         unsigned long flags;
                         spin_lock_irqsave(&bitmap->lock, flags);
-                        chunk_kb = bitmap->chunksize >> 10;
+                        chunk_kb = mddev->bitmap_info.chunksize >> 10;
                         seq_printf(seq, "bitmap: %lu/%lu pages [%luKB], "
                                 "%lu%s chunk",
                                 bitmap->pages - bitmap->missing_pages,
                                 bitmap->pages,
                                 (bitmap->pages - bitmap->missing_pages)
                                         << (PAGE_SHIFT - 10),
-                                chunk_kb ? chunk_kb : bitmap->chunksize,
+                                chunk_kb ? chunk_kb : mddev->bitmap_info.chunksize,
                                 chunk_kb ? "KB" : "B");
                         if (bitmap->file) {
                                 seq_printf(seq, ", file: ");
@@ -6275,10 +6473,11 @@ void md_do_sync(mddev_t *mddev)
                 mddev->curr_resync = 2;
 
         try_again:
-                if (kthread_should_stop()) {
+                if (kthread_should_stop())
                         set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+
+                if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
                         goto skip;
-                }
                 for_each_mddev(mddev2, tmp) {
                         if (mddev2 == mddev)
                                 continue;
@@ -6338,12 +6537,14 @@ void md_do_sync(mddev_t *mddev)
                 /* recovery follows the physical size of devices */
                 max_sectors = mddev->dev_sectors;
                 j = MaxSector;
-                list_for_each_entry(rdev, &mddev->disks, same_set)
+                rcu_read_lock();
+                list_for_each_entry_rcu(rdev, &mddev->disks, same_set)
                         if (rdev->raid_disk >= 0 &&
                             !test_bit(Faulty, &rdev->flags) &&
                             !test_bit(In_sync, &rdev->flags) &&
                             rdev->recovery_offset < j)
                                 j = rdev->recovery_offset;
+                rcu_read_unlock();
         }
 
         printk(KERN_INFO "md: %s of RAID array %s\n", desc, mdname(mddev));
@@ -6380,6 +6581,7 @@ void md_do_sync(mddev_t *mddev)
                        desc, mdname(mddev));
                 mddev->curr_resync = j;
         }
+        mddev->curr_resync_completed = mddev->curr_resync;
 
         while (j < max_sectors) {
                 sector_t sectors;
@@ -6512,22 +6714,29 @@ void md_do_sync(mddev_t *mddev)
                 } else {
                         if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery))
                                 mddev->curr_resync = MaxSector;
-                        list_for_each_entry(rdev, &mddev->disks, same_set)
+                        rcu_read_lock();
+                        list_for_each_entry_rcu(rdev, &mddev->disks, same_set)
                                 if (rdev->raid_disk >= 0 &&
                                     !test_bit(Faulty, &rdev->flags) &&
                                     !test_bit(In_sync, &rdev->flags) &&
                                     rdev->recovery_offset < mddev->curr_resync)
                                         rdev->recovery_offset = mddev->curr_resync;
+                        rcu_read_unlock();
                 }
         }
         set_bit(MD_CHANGE_DEVS, &mddev->flags);
 
  skip:
+        if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+                /* We completed so min/max setting can be forgotten if used. */
+                if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+                        mddev->resync_min = 0;
+                mddev->resync_max = MaxSector;
+        } else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+                mddev->resync_min = mddev->curr_resync_completed;
         mddev->curr_resync = 0;
-        mddev->curr_resync_completed = 0;
         if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery))
-                /* We completed so max setting can be forgotten. */
-                mddev->resync_max = MaxSector;
+                mddev->curr_resync_completed = 0;
         sysfs_notify(&mddev->kobj, NULL, "sync_completed");
         wake_up(&resync_wait);
         set_bit(MD_RECOVERY_DONE, &mddev->recovery);
@@ -6590,6 +6799,7 @@ static int remove_and_add_spares(mddev_t *mddev)
                                                        nm, mdname(mddev));
                                         spares++;
                                         md_new_event(mddev);
+                                        set_bit(MD_CHANGE_DEVS, &mddev->flags);
                                 } else
                                         break;
                         }
@@ -6625,7 +6835,7 @@ void md_check_recovery(mddev_t *mddev)
 
 
         if (mddev->bitmap)
-                bitmap_daemon_work(mddev->bitmap);
+                bitmap_daemon_work(mddev);
 
         if (mddev->ro)
                 return;
@@ -6995,5 +7205,6 @@ EXPORT_SYMBOL(md_unregister_thread);
 EXPORT_SYMBOL(md_wakeup_thread);
 EXPORT_SYMBOL(md_check_recovery);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MD RAID framework");
 MODULE_ALIAS("md");
 MODULE_ALIAS_BLOCKDEV_MAJOR(MD_MAJOR);