start >>= 9;
len >>= 9;
- if (start + len > (bdev->bd_inode->i_size >> 9))
+ if (start + len > (i_size_read(bdev->bd_inode) >> 9))
return -EINVAL;
if (secure)
flags |= BLKDEV_DISCARD_SECURE;
* We need to set the startsect first, the driver may
* want to override it.
*/
+ memset(&geo, 0, sizeof(geo));
geo.start = get_start_sect(bdev);
ret = disk->fops->getgeo(bdev, &geo);
if (ret)
return -EINVAL;
if (get_user(n, (int __user *) arg))
return -EFAULT;
- if (!(mode & FMODE_EXCL) && bd_claim(bdev, &bdev) < 0)
+ if (!(mode & FMODE_EXCL) &&
+ blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
return -EBUSY;
ret = set_blocksize(bdev, n);
if (!(mode & FMODE_EXCL))
- bd_release(bdev);
+ blkdev_put(bdev, mode | FMODE_EXCL);
return ret;
case BLKPG:
ret = blkpg_ioctl(bdev, (struct blkpg_ioctl_arg __user *) arg);
ret = blkdev_reread_part(bdev);
break;
case BLKGETSIZE:
- size = bdev->bd_inode->i_size;
+ size = i_size_read(bdev->bd_inode);
if ((size >> 9) > ~0UL)
return -EFBIG;
return put_ulong(arg, size >> 9);
case BLKGETSIZE64:
- return put_u64(arg, bdev->bd_inode->i_size);
+ return put_u64(arg, i_size_read(bdev->bd_inode));
case BLKTRACESTART:
case BLKTRACESTOP:
case BLKTRACESETUP:
#define D_ASSERT(exp) if (!(exp)) \
dev_err(DEV, "ASSERT( " #exp " ) in %s:%d\n", __FILE__, __LINE__)
-#define ERR_IF(exp) if (({ \
- int _b = (exp) != 0; \
- if (_b) dev_err(DEV, "%s: (%s) in %s:%d\n", \
- __func__, #exp, __FILE__, __LINE__); \
- _b; \
+#define ERR_IF(exp) if (({ \
+ int _b = (exp) != 0; \
+ if (_b) dev_err(DEV, "ASSERT FAILED: %s: (%s) in %s:%d\n", \
+ __func__, #exp, __FILE__, __LINE__); \
+ _b; \
}))
/* Defines to control fault insertion */
/* drbd_epoch flag bits */
enum {
- DE_BARRIER_IN_NEXT_EPOCH_ISSUED,
- DE_BARRIER_IN_NEXT_EPOCH_DONE,
- DE_CONTAINS_A_BARRIER,
DE_HAVE_BARRIER_NUMBER,
- DE_IS_FINISHING,
};
enum epoch_event {
EV_PUT,
EV_GOT_BARRIER_NR,
- EV_BARRIER_DONE,
EV_BECAME_LAST,
EV_CLEANUP = 32, /* used as flag */
};
__EE_CALL_AL_COMPLETE_IO,
__EE_MAY_SET_IN_SYNC,
- /* This epoch entry closes an epoch using a barrier.
- * On sucessful completion, the epoch is released,
- * and the P_BARRIER_ACK send. */
- __EE_IS_BARRIER,
-
/* In case a barrier failed,
* we need to resubmit without the barrier flag. */
__EE_RESUBMITTED,
};
#define EE_CALL_AL_COMPLETE_IO (1<<__EE_CALL_AL_COMPLETE_IO)
#define EE_MAY_SET_IN_SYNC (1<<__EE_MAY_SET_IN_SYNC)
-#define EE_IS_BARRIER (1<<__EE_IS_BARRIER)
#define EE_RESUBMITTED (1<<__EE_RESUBMITTED)
#define EE_WAS_ERROR (1<<__EE_WAS_ERROR)
#define EE_HAS_DIGEST (1<<__EE_HAS_DIGEST)
* Gets cleared when the state.conn
* goes into C_CONNECTED state. */
WRITE_BM_AFTER_RESYNC, /* A kmalloc() during resync failed */
- NO_BARRIER_SUPP, /* underlying block device doesn't implement barriers */
CONSIDER_RESYNC,
- MD_NO_BARRIER, /* meta data device does not support barriers,
- so don't even try */
+ MD_NO_FUA, /* Users wants us to not use FUA/FLUSH on meta data dev */
SUSPEND_IO, /* suspend application io */
BITMAP_IO, /* suspend application io;
once no more io in flight, start bitmap io */
BITMAP_IO_QUEUED, /* Started bitmap IO */
- GO_DISKLESS, /* Disk failed, local_cnt reached zero, we are going diskless */
+ GO_DISKLESS, /* Disk is being detached, on io-error or admin request. */
+ WAS_IO_ERROR, /* Local disk failed returned IO error */
RESYNC_AFTER_NEG, /* Resync after online grow after the attach&negotiate finished. */
NET_CONGESTED, /* The data socket is congested */
struct drbd_backing_dev {
struct block_device *backing_bdev;
struct block_device *md_bdev;
- struct file *lo_file;
- struct file *md_file;
struct drbd_md md;
struct disk_conf dc; /* The user provided config... */
sector_t known_size; /* last known size of that backing device */
WO_none,
WO_drain_io,
WO_bdev_flush,
- WO_bio_barrier
};
struct fifo_buffer {
extern int drbd_bmio_clear_n_write(struct drbd_conf *mdev);
extern int drbd_bitmap_io(struct drbd_conf *mdev, int (*io_fn)(struct drbd_conf *), char *why);
extern void drbd_go_diskless(struct drbd_conf *mdev);
+extern void drbd_ldev_destroy(struct drbd_conf *mdev);
/* Meta data layout
case EP_PASS_ON:
if (!forcedetach) {
if (__ratelimit(&drbd_ratelimit_state))
- dev_err(DEV, "Local IO failed in %s."
- "Passing error on...\n", where);
+ dev_err(DEV, "Local IO failed in %s.\n", where);
break;
}
/* NOTE fall through to detach case if forcedetach set */
case EP_DETACH:
case EP_CALL_HELPER:
+ set_bit(WAS_IO_ERROR, &mdev->flags);
if (mdev->state.disk > D_FAILED) {
_drbd_set_state(_NS(mdev, disk, D_FAILED), CS_HARD, NULL);
- dev_err(DEV, "Local IO failed in %s."
- "Detaching...\n", where);
+ dev_err(DEV,
+ "Local IO failed in %s. Detaching...\n", where);
}
break;
}
static inline sector_t drbd_get_capacity(struct block_device *bdev)
{
/* return bdev ? get_capacity(bdev->bd_disk) : 0; */
- return bdev ? bdev->bd_inode->i_size >> 9 : 0;
+ return bdev ? i_size_read(bdev->bd_inode) >> 9 : 0;
}
/**
__release(local);
D_ASSERT(i >= 0);
if (i == 0) {
+ if (mdev->state.disk == D_DISKLESS)
+ /* even internal references gone, safe to destroy */
+ drbd_ldev_destroy(mdev);
if (mdev->state.disk == D_FAILED)
+ /* all application IO references gone. */
drbd_go_diskless(mdev);
wake_up(&mdev->misc_wait);
}
{
int io_allowed;
+ /* never get a reference while D_DISKLESS */
+ if (mdev->state.disk == D_DISKLESS)
+ return 0;
+
atomic_inc(&mdev->local_cnt);
io_allowed = (mdev->state.disk >= mins);
if (!io_allowed)
{
int r;
- if (test_bit(MD_NO_BARRIER, &mdev->flags))
+ if (test_bit(MD_NO_FUA, &mdev->flags))
return;
r = blkdev_issue_flush(mdev->ldev->md_bdev, GFP_KERNEL, NULL);
if (r) {
- set_bit(MD_NO_BARRIER, &mdev->flags);
+ set_bit(MD_NO_FUA, &mdev->flags);
dev_err(DEV, "meta data flush failed with status %d, disabling md-flushes\n", r);
}
}
ns.conn != C_UNCONNECTED && ns.conn != C_DISCONNECTING && ns.conn <= C_TEAR_DOWN)
ns.conn = os.conn;
+ /* we cannot fail (again) if we already detached */
+ if (ns.disk == D_FAILED && os.disk == D_DISKLESS)
+ ns.disk = D_DISKLESS;
+
+ /* if we are only D_ATTACHING yet,
+ * we can (and should) go directly to D_DISKLESS. */
+ if (ns.disk == D_FAILED && os.disk == D_ATTACHING)
+ ns.disk = D_DISKLESS;
+
/* After C_DISCONNECTING only C_STANDALONE may follow */
if (os.conn == C_DISCONNECTING && ns.conn != C_STANDALONE)
ns.conn = os.conn;
!test_and_set_bit(CONFIG_PENDING, &mdev->flags))
set_bit(DEVICE_DYING, &mdev->flags);
- mdev->state.i = ns.i;
+ /* if we are going -> D_FAILED or D_DISKLESS, grab one extra reference
+ * on the ldev here, to be sure the transition -> D_DISKLESS resp.
+ * drbd_ldev_destroy() won't happen before our corresponding
+ * after_state_ch works run, where we put_ldev again. */
+ if ((os.disk != D_FAILED && ns.disk == D_FAILED) ||
+ (os.disk != D_DISKLESS && ns.disk == D_DISKLESS))
+ atomic_inc(&mdev->local_cnt);
+
+ mdev->state = ns;
wake_up(&mdev->misc_wait);
wake_up(&mdev->state_wait);
if (test_bit(NEW_CUR_UUID, &mdev->flags)) {
drbd_uuid_new_current(mdev);
clear_bit(NEW_CUR_UUID, &mdev->flags);
- drbd_md_sync(mdev);
}
spin_lock_irq(&mdev->req_lock);
_drbd_set_state(_NS(mdev, susp_fen, 0), CS_VERBOSE, NULL);
os.disk > D_INCONSISTENT && ns.disk == D_INCONSISTENT)
drbd_queue_bitmap_io(mdev, &drbd_bmio_set_n_write, NULL, "set_n_write from invalidate");
- /* first half of local IO error */
- if (os.disk > D_FAILED && ns.disk == D_FAILED) {
- enum drbd_io_error_p eh = EP_PASS_ON;
+ /* first half of local IO error, failure to attach,
+ * or administrative detach */
+ if (os.disk != D_FAILED && ns.disk == D_FAILED) {
+ enum drbd_io_error_p eh;
+ int was_io_error;
+ /* corresponding get_ldev was in __drbd_set_state, to serialize
+ * our cleanup here with the transition to D_DISKLESS,
+ * so it is safe to dreference ldev here. */
+ eh = mdev->ldev->dc.on_io_error;
+ was_io_error = test_and_clear_bit(WAS_IO_ERROR, &mdev->flags);
+
+ /* current state still has to be D_FAILED,
+ * there is only one way out: to D_DISKLESS,
+ * and that may only happen after our put_ldev below. */
+ if (mdev->state.disk != D_FAILED)
+ dev_err(DEV,
+ "ASSERT FAILED: disk is %s during detach\n",
+ drbd_disk_str(mdev->state.disk));
if (drbd_send_state(mdev))
- dev_warn(DEV, "Notified peer that my disk is broken.\n");
+ dev_warn(DEV, "Notified peer that I am detaching my disk\n");
else
- dev_err(DEV, "Sending state for drbd_io_error() failed\n");
+ dev_err(DEV, "Sending state for detaching disk failed\n");
drbd_rs_cancel_all(mdev);
- if (get_ldev_if_state(mdev, D_FAILED)) {
- eh = mdev->ldev->dc.on_io_error;
- put_ldev(mdev);
- }
- if (eh == EP_CALL_HELPER)
+ /* In case we want to get something to stable storage still,
+ * this may be the last chance.
+ * Following put_ldev may transition to D_DISKLESS. */
+ drbd_md_sync(mdev);
+ put_ldev(mdev);
+
+ if (was_io_error && eh == EP_CALL_HELPER)
drbd_khelper(mdev, "local-io-error");
}
+ /* second half of local IO error, failure to attach,
+ * or administrative detach,
+ * after local_cnt references have reached zero again */
+ if (os.disk != D_DISKLESS && ns.disk == D_DISKLESS) {
+ /* We must still be diskless,
+ * re-attach has to be serialized with this! */
+ if (mdev->state.disk != D_DISKLESS)
+ dev_err(DEV,
+ "ASSERT FAILED: disk is %s while going diskless\n",
+ drbd_disk_str(mdev->state.disk));
- /* second half of local IO error handling,
- * after local_cnt references have reached zero: */
- if (os.disk == D_FAILED && ns.disk == D_DISKLESS) {
- mdev->rs_total = 0;
- mdev->rs_failed = 0;
- atomic_set(&mdev->rs_pending_cnt, 0);
- }
-
- if (os.disk > D_DISKLESS && ns.disk == D_DISKLESS) {
- /* We must still be diskless,
- * re-attach has to be serialized with this! */
- if (mdev->state.disk != D_DISKLESS)
- dev_err(DEV,
- "ASSERT FAILED: disk is %s while going diskless\n",
- drbd_disk_str(mdev->state.disk));
+ mdev->rs_total = 0;
+ mdev->rs_failed = 0;
+ atomic_set(&mdev->rs_pending_cnt, 0);
- /* we cannot assert local_cnt == 0 here, as get_ldev_if_state
- * will inc/dec it frequently. Since we became D_DISKLESS, no
- * one has touched the protected members anymore, though, so we
- * are safe to free them here. */
if (drbd_send_state(mdev))
- dev_warn(DEV, "Notified peer that I detached my disk.\n");
+ dev_warn(DEV, "Notified peer that I'm now diskless.\n");
else
- dev_err(DEV, "Sending state for detach failed\n");
-
- lc_destroy(mdev->resync);
- mdev->resync = NULL;
- lc_destroy(mdev->act_log);
- mdev->act_log = NULL;
- __no_warn(local,
- drbd_free_bc(mdev->ldev);
- mdev->ldev = NULL;);
-
- if (mdev->md_io_tmpp) {
- __free_page(mdev->md_io_tmpp);
- mdev->md_io_tmpp = NULL;
- }
+ dev_err(DEV, "Sending state for being diskless failed\n");
+ /* corresponding get_ldev in __drbd_set_state
+ * this may finaly trigger drbd_ldev_destroy. */
+ put_ldev(mdev);
}
/* Disks got bigger while they were detached */
drbd_set_defaults(mdev);
- /* for now, we do NOT yet support it,
- * even though we start some framework
- * to eventually support barriers */
- set_bit(NO_BARRIER_SUPP, &mdev->flags);
-
atomic_set(&mdev->ap_bio_cnt, 0);
atomic_set(&mdev->ap_pending_cnt, 0);
atomic_set(&mdev->rs_pending_cnt, 0);
drbd_thread_init(mdev, &mdev->asender, drbd_asender);
mdev->agreed_pro_version = PRO_VERSION_MAX;
- mdev->write_ordering = WO_bio_barrier;
+ mdev->write_ordering = WO_bdev_flush;
mdev->resync_wenr = LC_FREE;
}
D_ASSERT(list_empty(&mdev->resync_work.list));
D_ASSERT(list_empty(&mdev->unplug_work.list));
D_ASSERT(list_empty(&mdev->go_diskless.list));
-
}
if (ldev == NULL)
return;
- bd_release(ldev->backing_bdev);
- bd_release(ldev->md_bdev);
-
- fput(ldev->lo_file);
- fput(ldev->md_file);
+ blkdev_put(ldev->backing_bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
+ blkdev_put(ldev->md_bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
kfree(ldev);
}
get_random_bytes(&val, sizeof(u64));
_drbd_uuid_set(mdev, UI_CURRENT, val);
+ /* get it to stable storage _now_ */
+ drbd_md_sync(mdev);
}
void drbd_uuid_set_bm(struct drbd_conf *mdev, u64 val) __must_hold(local)
return 1;
}
+void drbd_ldev_destroy(struct drbd_conf *mdev)
+{
+ lc_destroy(mdev->resync);
+ mdev->resync = NULL;
+ lc_destroy(mdev->act_log);
+ mdev->act_log = NULL;
+ __no_warn(local,
+ drbd_free_bc(mdev->ldev);
+ mdev->ldev = NULL;);
+
+ if (mdev->md_io_tmpp) {
+ __free_page(mdev->md_io_tmpp);
+ mdev->md_io_tmpp = NULL;
+ }
+ clear_bit(GO_DISKLESS, &mdev->flags);
+}
+
static int w_go_diskless(struct drbd_conf *mdev, struct drbd_work *w, int unused)
{
D_ASSERT(mdev->state.disk == D_FAILED);
/* we cannot assert local_cnt == 0 here, as get_ldev_if_state will
* inc/dec it frequently. Once we are D_DISKLESS, no one will touch
- * the protected members anymore, though, so in the after_state_ch work
- * it will be safe to free them. */
+ * the protected members anymore, though, so once put_ldev reaches zero
+ * again, it will be safe to free them. */
drbd_force_state(mdev, NS(disk, D_DISKLESS));
- /* We need to wait for return of references checked out while we still
- * have been D_FAILED, though (drbd_md_sync, bitmap io). */
- wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt));
-
- clear_bit(GO_DISKLESS, &mdev->flags);
return 1;
}
D_ASSERT(mdev->state.disk == D_FAILED);
if (!test_and_set_bit(GO_DISKLESS, &mdev->flags))
drbd_queue_work(&mdev->data.work, &mdev->go_diskless);
- /* don't drbd_queue_work_front,
- * we need to serialize with the after_state_ch work
- * of the -> D_FAILED transition. */
}
/**
sector_t max_possible_sectors;
sector_t min_md_device_sectors;
struct drbd_backing_dev *nbc = NULL; /* new_backing_conf */
- struct inode *inode, *inode2;
+ struct block_device *bdev;
struct lru_cache *resync_lru = NULL;
union drbd_state ns, os;
unsigned int max_seg_s;
retcode = ERR_DISK_CONFIGURED;
goto fail;
}
+ /* It may just now have detached because of IO error. Make sure
+ * drbd_ldev_destroy is done already, we may end up here very fast,
+ * e.g. if someone calls attach from the on-io-error handler,
+ * to realize a "hot spare" feature (not that I'd recommend that) */
+ wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt));
/* allocation not in the IO path, cqueue thread context */
nbc = kzalloc(sizeof(struct drbd_backing_dev), GFP_KERNEL);
}
}
- nbc->lo_file = filp_open(nbc->dc.backing_dev, O_RDWR, 0);
- if (IS_ERR(nbc->lo_file)) {
+ bdev = blkdev_get_by_path(nbc->dc.backing_dev,
+ FMODE_READ | FMODE_WRITE | FMODE_EXCL, mdev);
+ if (IS_ERR(bdev)) {
dev_err(DEV, "open(\"%s\") failed with %ld\n", nbc->dc.backing_dev,
- PTR_ERR(nbc->lo_file));
- nbc->lo_file = NULL;
+ PTR_ERR(bdev));
retcode = ERR_OPEN_DISK;
goto fail;
}
-
- inode = nbc->lo_file->f_dentry->d_inode;
-
- if (!S_ISBLK(inode->i_mode)) {
- retcode = ERR_DISK_NOT_BDEV;
- goto fail;
- }
-
- nbc->md_file = filp_open(nbc->dc.meta_dev, O_RDWR, 0);
- if (IS_ERR(nbc->md_file)) {
+ nbc->backing_bdev = bdev;
+
+ /*
+ * meta_dev_idx >= 0: external fixed size, possibly multiple
+ * drbd sharing one meta device. TODO in that case, paranoia
+ * check that [md_bdev, meta_dev_idx] is not yet used by some
+ * other drbd minor! (if you use drbd.conf + drbdadm, that
+ * should check it for you already; but if you don't, or
+ * someone fooled it, we need to double check here)
+ */
+ bdev = blkdev_get_by_path(nbc->dc.meta_dev,
+ FMODE_READ | FMODE_WRITE | FMODE_EXCL,
+ (nbc->dc.meta_dev_idx < 0) ?
+ (void *)mdev : (void *)drbd_m_holder);
+ if (IS_ERR(bdev)) {
dev_err(DEV, "open(\"%s\") failed with %ld\n", nbc->dc.meta_dev,
- PTR_ERR(nbc->md_file));
- nbc->md_file = NULL;
+ PTR_ERR(bdev));
retcode = ERR_OPEN_MD_DISK;
goto fail;
}
+ nbc->md_bdev = bdev;
- inode2 = nbc->md_file->f_dentry->d_inode;
-
- if (!S_ISBLK(inode2->i_mode)) {
- retcode = ERR_MD_NOT_BDEV;
- goto fail;
- }
-
- nbc->backing_bdev = inode->i_bdev;
- if (bd_claim(nbc->backing_bdev, mdev)) {
- printk(KERN_ERR "drbd: bd_claim(%p,%p); failed [%p;%p;%u]\n",
- nbc->backing_bdev, mdev,
- nbc->backing_bdev->bd_holder,
- nbc->backing_bdev->bd_contains->bd_holder,
- nbc->backing_bdev->bd_holders);
- retcode = ERR_BDCLAIM_DISK;
+ if ((nbc->backing_bdev == nbc->md_bdev) !=
+ (nbc->dc.meta_dev_idx == DRBD_MD_INDEX_INTERNAL ||
+ nbc->dc.meta_dev_idx == DRBD_MD_INDEX_FLEX_INT)) {
+ retcode = ERR_MD_IDX_INVALID;
goto fail;
}
offsetof(struct bm_extent, lce));
if (!resync_lru) {
retcode = ERR_NOMEM;
- goto release_bdev_fail;
- }
-
- /* meta_dev_idx >= 0: external fixed size,
- * possibly multiple drbd sharing one meta device.
- * TODO in that case, paranoia check that [md_bdev, meta_dev_idx] is
- * not yet used by some other drbd minor!
- * (if you use drbd.conf + drbdadm,
- * that should check it for you already; but if you don't, or someone
- * fooled it, we need to double check here) */
- nbc->md_bdev = inode2->i_bdev;
- if (bd_claim(nbc->md_bdev, (nbc->dc.meta_dev_idx < 0) ? (void *)mdev
- : (void *) drbd_m_holder)) {
- retcode = ERR_BDCLAIM_MD_DISK;
- goto release_bdev_fail;
- }
-
- if ((nbc->backing_bdev == nbc->md_bdev) !=
- (nbc->dc.meta_dev_idx == DRBD_MD_INDEX_INTERNAL ||
- nbc->dc.meta_dev_idx == DRBD_MD_INDEX_FLEX_INT)) {
- retcode = ERR_MD_IDX_INVALID;
- goto release_bdev2_fail;
+ goto fail;
}
/* RT - for drbd_get_max_capacity() DRBD_MD_INDEX_FLEX_INT */
(unsigned long long) drbd_get_max_capacity(nbc),
(unsigned long long) nbc->dc.disk_size);
retcode = ERR_DISK_TO_SMALL;
- goto release_bdev2_fail;
+ goto fail;
}
if (nbc->dc.meta_dev_idx < 0) {
dev_warn(DEV, "refusing attach: md-device too small, "
"at least %llu sectors needed for this meta-disk type\n",
(unsigned long long) min_md_device_sectors);
- goto release_bdev2_fail;
+ goto fail;
}
/* Make sure the new disk is big enough
if (drbd_get_max_capacity(nbc) <
drbd_get_capacity(mdev->this_bdev)) {
retcode = ERR_DISK_TO_SMALL;
- goto release_bdev2_fail;
+ goto fail;
}
nbc->known_size = drbd_get_capacity(nbc->backing_bdev);
retcode = _drbd_request_state(mdev, NS(disk, D_ATTACHING), CS_VERBOSE);
drbd_resume_io(mdev);
if (retcode < SS_SUCCESS)
- goto release_bdev2_fail;
+ goto fail;
if (!get_ldev_if_state(mdev, D_ATTACHING))
goto force_diskless;
/* Reset the "barriers don't work" bits here, then force meta data to
* be written, to ensure we determine if barriers are supported. */
if (nbc->dc.no_md_flush)
- set_bit(MD_NO_BARRIER, &mdev->flags);
+ set_bit(MD_NO_FUA, &mdev->flags);
else
- clear_bit(MD_NO_BARRIER, &mdev->flags);
+ clear_bit(MD_NO_FUA, &mdev->flags);
/* Point of no return reached.
* Devices and memory are no longer released by error cleanup below.
nbc = NULL;
resync_lru = NULL;
- mdev->write_ordering = WO_bio_barrier;
- drbd_bump_write_ordering(mdev, WO_bio_barrier);
+ mdev->write_ordering = WO_bdev_flush;
+ drbd_bump_write_ordering(mdev, WO_bdev_flush);
if (drbd_md_test_flag(mdev->ldev, MDF_CRASHED_PRIMARY))
set_bit(CRASHED_PRIMARY, &mdev->flags);
force_diskless_dec:
put_ldev(mdev);
force_diskless:
- drbd_force_state(mdev, NS(disk, D_DISKLESS));
+ drbd_force_state(mdev, NS(disk, D_FAILED));
drbd_md_sync(mdev);
- release_bdev2_fail:
- if (nbc)
- bd_release(nbc->md_bdev);
- release_bdev_fail:
- if (nbc)
- bd_release(nbc->backing_bdev);
fail:
if (nbc) {
- if (nbc->lo_file)
- fput(nbc->lo_file);
- if (nbc->md_file)
- fput(nbc->md_file);
+ if (nbc->backing_bdev)
+ blkdev_put(nbc->backing_bdev,
+ FMODE_READ | FMODE_WRITE | FMODE_EXCL);
+ if (nbc->md_bdev)
+ blkdev_put(nbc->md_bdev,
+ FMODE_READ | FMODE_WRITE | FMODE_EXCL);
kfree(nbc);
}
lc_destroy(resync_lru);
return 0;
}
+/* Detaching the disk is a process in multiple stages. First we need to lock
+ * out application IO, in-flight IO, IO stuck in drbd_al_begin_io.
+ * Then we transition to D_DISKLESS, and wait for put_ldev() to return all
+ * internal references as well.
+ * Only then we have finally detached. */
static int drbd_nl_detach(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
struct drbd_nl_cfg_reply *reply)
{
+ drbd_suspend_io(mdev); /* so no-one is stuck in drbd_al_begin_io */
reply->ret_code = drbd_request_state(mdev, NS(disk, D_DISKLESS));
+ if (mdev->state.disk == D_DISKLESS)
+ wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt));
+ drbd_resume_io(mdev);
return 0;
}
if (test_bit(NEW_CUR_UUID, &mdev->flags)) {
drbd_uuid_new_current(mdev);
clear_bit(NEW_CUR_UUID, &mdev->flags);
- drbd_md_sync(mdev);
}
drbd_suspend_io(mdev);
reply->ret_code = drbd_request_state(mdev, NS3(susp, 0, susp_nod, 0, susp_fen, 0));
/* return the offset of the super block in 512byte sectors */
static inline sector_t calc_dev_sboffset(struct block_device *bdev)
{
- sector_t num_sectors = bdev->bd_inode->i_size / 512;
+ sector_t num_sectors = i_size_read(bdev->bd_inode) / 512;
return MD_NEW_SIZE_SECTORS(num_sectors);
}
*/
switch(minor_version) {
case 0:
- sb_start = rdev->bdev->bd_inode->i_size >> 9;
+ sb_start = i_size_read(rdev->bdev->bd_inode) >> 9;
sb_start -= 8*2;
sb_start &= ~(sector_t)(4*2-1);
break;
ret = 0;
}
if (minor_version)
- rdev->sectors = (rdev->bdev->bd_inode->i_size >> 9) -
+ rdev->sectors = (i_size_read(rdev->bdev->bd_inode) >> 9) -
le64_to_cpu(sb->data_offset);
else
rdev->sectors = rdev->sb_start;
return 0; /* component must fit device */
if (rdev->sb_start < rdev->data_offset) {
/* minor versions 1 and 2; superblock before data */
- max_sectors = rdev->bdev->bd_inode->i_size >> 9;
+ max_sectors = i_size_read(rdev->bdev->bd_inode) >> 9;
max_sectors -= rdev->data_offset;
if (!num_sectors || num_sectors > max_sectors)
num_sectors = max_sectors;
} else {
/* minor version 0; superblock after data */
sector_t sb_start;
- sb_start = (rdev->bdev->bd_inode->i_size >> 9) - 8*2;
+ sb_start = (i_size_read(rdev->bdev->bd_inode) >> 9) - 8*2;
sb_start &= ~(sector_t)(4*2 - 1);
max_sectors = rdev->sectors + sb_start - rdev->sb_start;
if (!num_sectors || num_sectors > max_sectors)
rdev->sysfs_state = sysfs_get_dirent_safe(rdev->kobj.sd, "state");
list_add_rcu(&rdev->same_set, &mddev->disks);
- bd_claim_by_disk(rdev->bdev, rdev->bdev->bd_holder, mddev->gendisk);
+ bd_link_disk_holder(rdev->bdev, mddev->gendisk);
/* May as well allow recovery to be retried once */
mddev->recovery_disabled = 0;
MD_BUG();
return;
}
- bd_release_from_disk(rdev->bdev, rdev->mddev->gendisk);
list_del_rcu(&rdev->same_set);
printk(KERN_INFO "md: unbind<%s>\n", bdevname(rdev->bdev,b));
rdev->mddev = NULL;
struct block_device *bdev;
char b[BDEVNAME_SIZE];
- bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
+ bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
+ shared ? (mdk_rdev_t *)lock_rdev : rdev);
if (IS_ERR(bdev)) {
printk(KERN_ERR "md: could not open %s.\n",
__bdevname(dev, b));
return PTR_ERR(bdev);
}
- err = bd_claim(bdev, shared ? (mdk_rdev_t *)lock_rdev : rdev);
- if (err) {
- printk(KERN_ERR "md: could not bd_claim %s.\n",
- bdevname(bdev, b));
- blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
- return err;
- }
if (!shared)
set_bit(AllReserved, &rdev->flags);
rdev->bdev = bdev;
rdev->bdev = NULL;
if (!bdev)
MD_BUG();
- bd_release(bdev);
- blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
+ blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
}
void md_autodetect_dev(dev_t dev);
if (!sectors)
return -EBUSY;
} else if (!sectors)
- sectors = (rdev->bdev->bd_inode->i_size >> 9) -
+ sectors = (i_size_read(rdev->bdev->bd_inode) >> 9) -
rdev->data_offset;
}
if (sectors < my_mddev->dev_sectors)
kobject_init(&rdev->kobj, &rdev_ktype);
- size = rdev->bdev->bd_inode->i_size >> BLOCK_SIZE_BITS;
+ size = i_size_read(rdev->bdev->bd_inode) >> BLOCK_SIZE_BITS;
if (!size) {
printk(KERN_WARNING
"md: %s has zero or unknown size, marking faulty!\n",
if (!mddev->persistent) {
printk(KERN_INFO "md: nonpersistent superblock ...\n");
- rdev->sb_start = rdev->bdev->bd_inode->i_size / 512;
- } else
+ rdev->sb_start = i_size_read(rdev->bdev->bd_inode) / 512;
+ } else
rdev->sb_start = calc_dev_sboffset(rdev->bdev);
rdev->sectors = rdev->sb_start;
if (mddev->persistent)
rdev->sb_start = calc_dev_sboffset(rdev->bdev);
else
- rdev->sb_start = rdev->bdev->bd_inode->i_size / 512;
+ rdev->sb_start = i_size_read(rdev->bdev->bd_inode) / 512;
rdev->sectors = rdev->sb_start;
return sprintf(buf, "%llu\n",(unsigned long long)p->nr_sects);
}
+ssize_t part_ro_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct hd_struct *p = dev_to_part(dev);
+ return sprintf(buf, "%d\n", p->policy ? 1 : 0);
+}
+
ssize_t part_alignment_offset_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
static DEVICE_ATTR(partition, S_IRUGO, part_partition_show, NULL);
static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL);
static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
+static DEVICE_ATTR(ro, S_IRUGO, part_ro_show, NULL);
static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL);
static DEVICE_ATTR(discard_alignment, S_IRUGO, part_discard_alignment_show,
NULL);
&dev_attr_partition.attr,
&dev_attr_start.attr,
&dev_attr_size.attr,
+ &dev_attr_ro.attr,
&dev_attr_alignment_offset.attr,
&dev_attr_discard_alignment.attr,
&dev_attr_stat.attr,
goto exit;
bdev->bd_invalidated = 1;
- err = blkdev_get(bdev, FMODE_READ);
+ err = blkdev_get(bdev, FMODE_READ, NULL);
if (err < 0)
goto exit;
blkdev_put(bdev, FMODE_READ);
mp->m_qflags &= ~XFS_OQUOTA_ENFD;
} else if (!strcmp(this_char, MNTOPT_DELAYLOG)) {
mp->m_flags |= XFS_MOUNT_DELAYLOG;
- cmn_err(CE_WARN,
- "Enabling EXPERIMENTAL delayed logging feature "
- "- use at your own risk.\n");
} else if (!strcmp(this_char, MNTOPT_NODELAYLOG)) {
mp->m_flags &= ~XFS_MOUNT_DELAYLOG;
} else if (!strcmp(this_char, "ihashsize")) {
{
int error = 0;
- *bdevp = open_bdev_exclusive(name, FMODE_READ|FMODE_WRITE, mp);
+ *bdevp = blkdev_get_by_path(name, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
+ mp);
if (IS_ERR(*bdevp)) {
error = PTR_ERR(*bdevp);
printk("XFS: Invalid device [%s], error=%d\n", name, error);
struct block_device *bdev)
{
if (bdev)
- close_bdev_exclusive(bdev, FMODE_READ|FMODE_WRITE);
+ blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
}
/*
projects / mv-sheeva.git / commitdiff