46 files changed, 826 insertions, 393 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1aba036dcabf..26e5f5026620 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -376,7 +376,7 @@ int blkdev_fsync(struct file *filp, struct dentry *dentry, int datasync)
          */
         mutex_unlock(&bd_inode->i_mutex);
 
-        error = blkdev_issue_flush(bdev, NULL);
+        error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL, BLKDEV_IFL_WAIT);
         if (error == -EOPNOTSUPP)
                 error = 0;
 
@@ -627,41 +627,209 @@ void bd_forget(struct inode *inode)
                 iput(bdev->bd_inode);
 }
 
-int bd_claim(struct block_device *bdev, void *holder)
+/**
+ * bd_may_claim - test whether a block device can be claimed
+ * @bdev: block device of interest
+ * @whole: whole block device containing @bdev, may equal @bdev
+ * @holder: holder trying to claim @bdev
+ *
+ * Test whther @bdev can be claimed by @holder.
+ *
+ * CONTEXT:
+ * spin_lock(&bdev_lock).
+ *
+ * RETURNS:
+ * %true if @bdev can be claimed, %false otherwise.
+ */
+static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
+                         void *holder)
 {
-        int res;
-        spin_lock(&bdev_lock);
-
-        /* first decide result */
         if (bdev->bd_holder == holder)
-                res = 0;         /* already a holder */
+                return true;     /* already a holder */
         else if (bdev->bd_holder != NULL)
-                res = -EBUSY;    /* held by someone else */
+                return false;    /* held by someone else */
         else if (bdev->bd_contains == bdev)
-                res = 0;         /* is a whole device which isn't held */
+                return true;     /* is a whole device which isn't held */
 
-        else if (bdev->bd_contains->bd_holder == bd_claim)
-                res = 0;         /* is a partition of a device that is being partitioned */
-        else if (bdev->bd_contains->bd_holder != NULL)
-                res = -EBUSY;    /* is a partition of a held device */
+        else if (whole->bd_holder == bd_claim)
+                return true;     /* is a partition of a device that is being partitioned */
+        else if (whole->bd_holder != NULL)
+                return false;    /* is a partition of a held device */
         else
-                res = 0;         /* is a partition of an un-held device */
+                return true;     /* is a partition of an un-held device */
+}
+
+/**
+ * bd_prepare_to_claim - prepare to claim a block device
+ * @bdev: block device of interest
+ * @whole: the whole device containing @bdev, may equal @bdev
+ * @holder: holder trying to claim @bdev
+ *
+ * Prepare to claim @bdev.  This function fails if @bdev is already
+ * claimed by another holder and waits if another claiming is in
+ * progress.  This function doesn't actually claim.  On successful
+ * return, the caller has ownership of bd_claiming and bd_holder[s].
+ *
+ * CONTEXT:
+ * spin_lock(&bdev_lock).  Might release bdev_lock, sleep and regrab
+ * it multiple times.
+ *
+ * RETURNS:
+ * 0 if @bdev can be claimed, -EBUSY otherwise.
+ */
+static int bd_prepare_to_claim(struct block_device *bdev,
+                               struct block_device *whole, void *holder)
+{
+retry:
+        /* if someone else claimed, fail */
+        if (!bd_may_claim(bdev, whole, holder))
+                return -EBUSY;
+
+        /* if someone else is claiming, wait for it to finish */
+        if (whole->bd_claiming && whole->bd_claiming != holder) {
+                wait_queue_head_t *wq = bit_waitqueue(&whole->bd_claiming, 0);
+                DEFINE_WAIT(wait);
+
+                prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
+                spin_unlock(&bdev_lock);
+                schedule();
+                finish_wait(wq, &wait);
+                spin_lock(&bdev_lock);
+                goto retry;
+        }
+
+        /* yay, all mine */
+        return 0;
+}
+
+/**
+ * bd_start_claiming - start claiming a block device
+ * @bdev: block device of interest
+ * @holder: holder trying to claim @bdev
+ *
+ * @bdev is about to be opened exclusively.  Check @bdev can be opened
+ * exclusively and mark that an exclusive open is in progress.  Each
+ * successful call to this function must be matched with a call to
+ * either bd_claim() or bd_abort_claiming().  If this function
+ * succeeds, the matching bd_claim() is guaranteed to succeed.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * Pointer to the block device containing @bdev on success, ERR_PTR()
+ * value on failure.
+ */
+static struct block_device *bd_start_claiming(struct block_device *bdev,
+                                              void *holder)
+{
+        struct gendisk *disk;
+        struct block_device *whole;
+        int partno, err;
+
+        might_sleep();
+
+        /*
+         * @bdev might not have been initialized properly yet, look up
+         * and grab the outer block device the hard way.
+         */
+        disk = get_gendisk(bdev->bd_dev, &partno);
+        if (!disk)
+                return ERR_PTR(-ENXIO);
+
+        whole = bdget_disk(disk, 0);
+        put_disk(disk);
+        if (!whole)
+                return ERR_PTR(-ENOMEM);
+
+        /* prepare to claim, if successful, mark claiming in progress */
+        spin_lock(&bdev_lock);
+
+        err = bd_prepare_to_claim(bdev, whole, holder);
+        if (err == 0) {
+                whole->bd_claiming = holder;
+                spin_unlock(&bdev_lock);
+                return whole;
+        } else {
+                spin_unlock(&bdev_lock);
+                bdput(whole);
+                return ERR_PTR(err);
+        }
+}
 
-        /* now impose change */
-        if (res==0) {
+/* releases bdev_lock */
+static void __bd_abort_claiming(struct block_device *whole, void *holder)
+{
+        BUG_ON(whole->bd_claiming != holder);
+        whole->bd_claiming = NULL;
+        wake_up_bit(&whole->bd_claiming, 0);
+
+        spin_unlock(&bdev_lock);
+        bdput(whole);
+}
+
+/**
+ * bd_abort_claiming - abort claiming a block device
+ * @whole: whole block device returned by bd_start_claiming()
+ * @holder: holder trying to claim @bdev
+ *
+ * Abort a claiming block started by bd_start_claiming().  Note that
+ * @whole is not the block device to be claimed but the whole device
+ * returned by bd_start_claiming().
+ *
+ * CONTEXT:
+ * Grabs and releases bdev_lock.
+ */
+static void bd_abort_claiming(struct block_device *whole, void *holder)
+{
+        spin_lock(&bdev_lock);
+        __bd_abort_claiming(whole, holder);             /* releases bdev_lock */
+}
+
+/**
+ * bd_claim - claim a block device
+ * @bdev: block device to claim
+ * @holder: holder trying to claim @bdev
+ *
+ * Try to claim @bdev which must have been opened successfully.  This
+ * function may be called with or without preceding
+ * blk_start_claiming().  In the former case, this function is always
+ * successful and terminates the claiming block.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * 0 if successful, -EBUSY if @bdev is already claimed.
+ */
+int bd_claim(struct block_device *bdev, void *holder)
+{
+        struct block_device *whole = bdev->bd_contains;
+        int res;
+
+        might_sleep();
+
+        spin_lock(&bdev_lock);
+
+        res = bd_prepare_to_claim(bdev, whole, holder);
+        if (res == 0) {
                 /* note that for a whole device bd_holders
                  * will be incremented twice, and bd_holder will
                  * be set to bd_claim before being set to holder
                  */
-                bdev->bd_contains->bd_holders ++;
-                bdev->bd_contains->bd_holder = bd_claim;
+                whole->bd_holders++;
+                whole->bd_holder = bd_claim;
                 bdev->bd_holders++;
                 bdev->bd_holder = holder;
         }
-        spin_unlock(&bdev_lock);
+
+        if (whole->bd_claiming)
+                __bd_abort_claiming(whole, holder);     /* releases bdev_lock */
+        else
+                spin_unlock(&bdev_lock);
+
         return res;
 }
-
 EXPORT_SYMBOL(bd_claim);
 
 void bd_release(struct block_device *bdev)
@@ -1275,6 +1443,7 @@ EXPORT_SYMBOL(blkdev_get);
 
 static int blkdev_open(struct inode * inode, struct file * filp)
 {
+        struct block_device *whole = NULL;
         struct block_device *bdev;
         int res;
 
@@ -1297,22 +1466,25 @@ static int blkdev_open(struct inode * inode, struct file * filp)
         if (bdev == NULL)
                 return -ENOMEM;
 
+        if (filp->f_mode & FMODE_EXCL) {
+                whole = bd_start_claiming(bdev, filp);
+                if (IS_ERR(whole)) {
+                        bdput(bdev);
+                        return PTR_ERR(whole);
+                }
+        }
+
         filp->f_mapping = bdev->bd_inode->i_mapping;
 
         res = blkdev_get(bdev, filp->f_mode);
-        if (res)
-                return res;
 
-        if (filp->f_mode & FMODE_EXCL) {
-                res = bd_claim(bdev, filp);
-                if (res)
-                        goto out_blkdev_put;
+        if (whole) {
+                if (res == 0)
+                        BUG_ON(bd_claim(bdev, filp) != 0);
+                else
+                        bd_abort_claiming(whole, filp);
         }
 
-        return 0;
-
- out_blkdev_put:
-        blkdev_put(bdev, filp->f_mode);
         return res;
 }
 
@@ -1523,27 +1695,34 @@ EXPORT_SYMBOL(lookup_bdev);
  */
 struct block_device *open_bdev_exclusive(const char *path, fmode_t mode, void *holder)
 {
-        struct block_device *bdev;
-        int error = 0;
+        struct block_device *bdev, *whole;
+        int error;
 
         bdev = lookup_bdev(path);
         if (IS_ERR(bdev))
                 return bdev;
 
+        whole = bd_start_claiming(bdev, holder);
+        if (IS_ERR(whole)) {
+                bdput(bdev);
+                return whole;
+        }
+
         error = blkdev_get(bdev, mode);
         if (error)
-                return ERR_PTR(error);
+                goto out_abort_claiming;
+
         error = -EACCES;
         if ((mode & FMODE_WRITE) && bdev_read_only(bdev))
-                goto blkdev_put;
-        error = bd_claim(bdev, holder);
-        if (error)
-                goto blkdev_put;
+                goto out_blkdev_put;
 
+        BUG_ON(bd_claim(bdev, holder) != 0);
         return bdev;
-        
-blkdev_put:
+
+out_blkdev_put:
         blkdev_put(bdev, mode);
+out_abort_claiming:
+        bd_abort_claiming(whole, holder);
         return ERR_PTR(error);
 }
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index b34d32fdaaec..c6a4f459ad76 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1589,7 +1589,7 @@ static void btrfs_issue_discard(struct block_device *bdev,
                                 u64 start, u64 len)
 {
         blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL,
-                             DISCARD_FL_BARRIER);
+                        BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
 }
 
 static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
diff --git a/fs/buffer.c b/fs/buffer.c
index 2914d9adfb50..e8aa7081d25c 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -275,6 +275,7 @@ void invalidate_bdev(struct block_device *bdev)
                 return;
 
         invalidate_bh_lrus();
+        lru_add_drain_all();    /* make sure all lru add caches are flushed */
         invalidate_mapping_pages(mapping, 0, -1);
 }
 EXPORT_SYMBOL(invalidate_bdev);
diff --git a/fs/ext3/fsync.c b/fs/ext3/fsync.c
index 26289e8f4163..fcf7487734b6 100644
--- a/fs/ext3/fsync.c
+++ b/fs/ext3/fsync.c
@@ -90,6 +90,7 @@ int ext3_sync_file(struct file * file, struct dentry *dentry, int datasync)
          * storage
          */
         if (needs_barrier)
-                blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
+                blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL,
+                                BLKDEV_IFL_WAIT);
         return ret;
 }
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 0d0c3239c1cd..ef3d980e67cb 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -100,9 +100,11 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
                 if (ext4_should_writeback_data(inode) &&
                     (journal->j_fs_dev != journal->j_dev) &&
                     (journal->j_flags & JBD2_BARRIER))
-                        blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
+                        blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL,
+                                        NULL, BLKDEV_IFL_WAIT);
                 jbd2_log_wait_commit(journal, commit_tid);
         } else if (journal->j_flags & JBD2_BARRIER)
-                blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
+                blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL,
+                        BLKDEV_IFL_WAIT);
         return ret;
 }
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 0a140741b39e..f74d270ba155 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -14,6 +14,7 @@
 #include <linux/dnotify.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/pipe_fs_i.h>
 #include <linux/security.h>
 #include <linux/ptrace.h>
 #include <linux/signal.h>
@@ -412,6 +413,10 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
         case F_NOTIFY:
                 err = fcntl_dirnotify(fd, filp, arg);
                 break;
+        case F_SETPIPE_SZ:
+        case F_GETPIPE_SZ:
+                err = pipe_fcntl(filp, cmd, arg);
+                break;
         default:
                 break;
         }
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 24e85ce11891..5c4161f1fd9a 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -45,6 +45,7 @@ struct wb_writeback_args {
         unsigned int for_kupdate:1;
         unsigned int range_cyclic:1;
         unsigned int for_background:1;
+        unsigned int sb_pinned:1;
 };
 
 /*
@@ -192,7 +193,8 @@ static void bdi_wait_on_work_clear(struct bdi_work *work)
 }
 
 static void bdi_alloc_queue_work(struct backing_dev_info *bdi,
-                                 struct wb_writeback_args *args)
+                                 struct wb_writeback_args *args,
+                                 int wait)
 {
         struct bdi_work *work;
 
@@ -204,6 +206,8 @@ static void bdi_alloc_queue_work(struct backing_dev_info *bdi,
         if (work) {
                 bdi_work_init(work, args);
                 bdi_queue_work(bdi, work);
+                if (wait)
+                        bdi_wait_on_work_clear(work);
         } else {
                 struct bdi_writeback *wb = &bdi->wb;
 
@@ -230,6 +234,11 @@ static void bdi_sync_writeback(struct backing_dev_info *bdi,
                 .sync_mode      = WB_SYNC_ALL,
                 .nr_pages       = LONG_MAX,
                 .range_cyclic   = 0,
+                /*
+                 * Setting sb_pinned is not necessary for WB_SYNC_ALL, but
+                 * lets make it explicitly clear.
+                 */
+                .sb_pinned      = 1,
         };
         struct bdi_work work;
 
@@ -245,21 +254,23 @@ static void bdi_sync_writeback(struct backing_dev_info *bdi,
  * @bdi: the backing device to write from
  * @sb: write inodes from this super_block
  * @nr_pages: the number of pages to write
+ * @sb_locked: caller already holds sb umount sem.
  *
  * Description:
  *   This does WB_SYNC_NONE opportunistic writeback. The IO is only
  *   started when this function returns, we make no guarentees on
- *   completion. Caller need not hold sb s_umount semaphore.
+ *   completion. Caller specifies whether sb umount sem is held already or not.
  *
  */
 void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb,
-                         long nr_pages)
+                         long nr_pages, int sb_locked)
 {
         struct wb_writeback_args args = {
                 .sb             = sb,
                 .sync_mode      = WB_SYNC_NONE,
                 .nr_pages       = nr_pages,
                 .range_cyclic   = 1,
+                .sb_pinned      = sb_locked,
         };
 
         /*
@@ -271,7 +282,7 @@ void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb,
                 args.for_background = 1;
         }
 
-        bdi_alloc_queue_work(bdi, &args);
+        bdi_alloc_queue_work(bdi, &args, sb_locked);
 }
 
 /*
@@ -452,11 +463,9 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 
         BUG_ON(inode->i_state & I_SYNC);
 
-        /* Set I_SYNC, reset I_DIRTY */
-        dirty = inode->i_state & I_DIRTY;
+        /* Set I_SYNC, reset I_DIRTY_PAGES */
         inode->i_state |= I_SYNC;
-        inode->i_state &= ~I_DIRTY;
-
+        inode->i_state &= ~I_DIRTY_PAGES;
         spin_unlock(&inode_lock);
 
         ret = do_writepages(mapping, wbc);
@@ -472,6 +481,15 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
                         ret = err;
         }
 
+        /*
+         * Some filesystems may redirty the inode during the writeback
+         * due to delalloc, clear dirty metadata flags right before
+         * write_inode()
+         */
+        spin_lock(&inode_lock);
+        dirty = inode->i_state & I_DIRTY;
+        inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC);
+        spin_unlock(&inode_lock);
         /* Don't write the inode if only I_DIRTY_PAGES was set */
         if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
                 int err = write_inode(inode, wbc);
@@ -577,7 +595,7 @@ static enum sb_pin_state pin_sb_for_writeback(struct writeback_control *wbc,
         /*
          * Caller must already hold the ref for this
          */
-        if (wbc->sync_mode == WB_SYNC_ALL) {
+        if (wbc->sync_mode == WB_SYNC_ALL || wbc->sb_pinned) {
                 WARN_ON(!rwsem_is_locked(&sb->s_umount));
                 return SB_NOT_PINNED;
         }
@@ -751,6 +769,7 @@ static long wb_writeback(struct bdi_writeback *wb,
                 .for_kupdate            = args->for_kupdate,
                 .for_background         = args->for_background,
                 .range_cyclic           = args->range_cyclic,
+                .sb_pinned              = args->sb_pinned,
         };
         unsigned long oldest_jif;
         long wrote = 0;
@@ -852,6 +871,12 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb)
         unsigned long expired;
         long nr_pages;
 
+        /*
+         * When set to zero, disable periodic writeback
+         */
+        if (!dirty_writeback_interval)
+                return 0;
+
         expired = wb->last_old_flush +
                         msecs_to_jiffies(dirty_writeback_interval * 10);
         if (time_before(jiffies, expired))
@@ -887,6 +912,7 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 
         while ((work = get_next_work_item(bdi, wb)) != NULL) {
                 struct wb_writeback_args args = work->args;
+                int post_clear;
 
                 /*
                  * Override sync mode, in case we must wait for completion
@@ -894,11 +920,13 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
                 if (force_wait)
                         work->args.sync_mode = args.sync_mode = WB_SYNC_ALL;
 
+                post_clear = WB_SYNC_ALL || args.sb_pinned;
+
                 /*
                  * If this isn't a data integrity operation, just notify
                  * that we have seen this work and we are now starting it.
                  */
-                if (args.sync_mode == WB_SYNC_NONE)
+                if (!post_clear)
                         wb_clear_pending(wb, work);
 
                 wrote += wb_writeback(wb, &args);
@@ -907,7 +935,7 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
                  * This is a data integrity writeback, so only do the
                  * notification when we have completed the work.
                  */
-                if (args.sync_mode == WB_SYNC_ALL)
+                if (post_clear)
                         wb_clear_pending(wb, work);
         }
 
@@ -947,8 +975,17 @@ int bdi_writeback_task(struct bdi_writeback *wb)
                                 break;
                 }
 
-                wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10);
-                schedule_timeout_interruptible(wait_jiffies);
+                if (dirty_writeback_interval) {
+                        wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10);
+                        schedule_timeout_interruptible(wait_jiffies);
+                } else {
+                        set_current_state(TASK_INTERRUPTIBLE);
+                        if (list_empty_careful(&wb->bdi->work_list) &&
+                            !kthread_should_stop())
+                                schedule();
+                        __set_current_state(TASK_RUNNING);
+                }
+
                 try_to_freeze();
         }
 
@@ -974,7 +1011,7 @@ static void bdi_writeback_all(struct super_block *sb, long nr_pages)
                 if (!bdi_has_dirty_io(bdi))
                         continue;
 
-                bdi_alloc_queue_work(bdi, &args);
+                bdi_alloc_queue_work(bdi, &args, 0);
         }
 
         rcu_read_unlock();
@@ -1183,6 +1220,18 @@ static void wait_sb_inodes(struct super_block *sb)
         iput(old_inode);
 }
 
+static void __writeback_inodes_sb(struct super_block *sb, int sb_locked)
+{
+        unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
+        unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
+        long nr_to_write;
+
+        nr_to_write = nr_dirty + nr_unstable +
+                        (inodes_stat.nr_inodes - inodes_stat.nr_unused);
+
+        bdi_start_writeback(sb->s_bdi, sb, nr_to_write, sb_locked);
+}
+
 /**
  * writeback_inodes_sb  -       writeback dirty inodes from given super_block
  * @sb: the superblock
@@ -1194,18 +1243,23 @@ static void wait_sb_inodes(struct super_block *sb)
  */
 void writeback_inodes_sb(struct super_block *sb)
 {
-        unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
-        unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
-        long nr_to_write;
-
-        nr_to_write = nr_dirty + nr_unstable +
-                        (inodes_stat.nr_inodes - inodes_stat.nr_unused);
-
-        bdi_start_writeback(sb->s_bdi, sb, nr_to_write);
+        __writeback_inodes_sb(sb, 0);
 }
 EXPORT_SYMBOL(writeback_inodes_sb);
 
 /**
+ * writeback_inodes_sb_locked   - writeback dirty inodes from given super_block
+ * @sb: the superblock
+ *
+ * Like writeback_inodes_sb(), except the caller already holds the
+ * sb umount sem.
+ */
+void writeback_inodes_sb_locked(struct super_block *sb)
+{
+        __writeback_inodes_sb(sb, 1);
+}
+
+/**
  * writeback_inodes_sb_if_idle  -       start writeback if none underway
  * @sb: the superblock
  *
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 8bce73ed4d8e..117fa4171f62 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -854,7 +854,8 @@ static void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
                                 if ((start + nr_sects) != blk) {
                                         rv = blkdev_issue_discard(bdev, start,
                                                             nr_sects, GFP_NOFS,
-                                                            DISCARD_FL_BARRIER);
+                                                            BLKDEV_IFL_WAIT |
+                                                            BLKDEV_IFL_BARRIER);
                                         if (rv)
                                                 goto fail;
                                         nr_sects = 0;
@@ -869,7 +870,7 @@ start_new_extent:
         }
         if (nr_sects) {
                 rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS,
-                                         DISCARD_FL_BARRIER);
+                                         BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
                 if (rv)
                         goto fail;
         }
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 30beb11ef928..076d1cc44f95 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -530,7 +530,8 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
          */
         if ((journal->j_fs_dev != journal->j_dev) &&
             (journal->j_flags & JBD2_BARRIER))
-                blkdev_issue_flush(journal->j_fs_dev, NULL);
+                blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL,
+                        BLKDEV_IFL_WAIT);
         if (!(journal->j_flags & JBD2_ABORT))
                 jbd2_journal_update_superblock(journal, 1);
         return 0;
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 671da7fb7ffd..75716d3d2be0 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -717,7 +717,8 @@ start_journal_io:
         if (commit_transaction->t_flushed_data_blocks &&
             (journal->j_fs_dev != journal->j_dev) &&
             (journal->j_flags & JBD2_BARRIER))
-                blkdev_issue_flush(journal->j_fs_dev, NULL);
+                blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL,
+                        BLKDEV_IFL_WAIT);
 
         /* Done it all: now write the commit record asynchronously. */
         if (JBD2_HAS_INCOMPAT_FEATURE(journal,
@@ -727,7 +728,8 @@ start_journal_io:
                 if (err)
                         __jbd2_journal_abort_hard(journal);
                 if (journal->j_flags & JBD2_BARRIER)
-                        blkdev_issue_flush(journal->j_dev, NULL);
+                        blkdev_issue_flush(journal->j_dev, GFP_KERNEL, NULL,
+                                BLKDEV_IFL_WAIT);
         }
 
         err = journal_finish_inode_data_buffers(journal, commit_transaction);
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index a756168a21c2..8c1097327abc 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -674,7 +674,7 @@ int nilfs_discard_segments(struct the_nilfs *nilfs, __u64 *segnump,
                                                    start * sects_per_block,
                                                    nblocks * sects_per_block,
                                                    GFP_NOFS,
-                                                   DISCARD_FL_BARRIER);
+                                                   BLKDEV_IFL_BARRIER);
                         if (ret < 0)
                                 return ret;
                         nblocks = 0;
@@ -684,7 +684,7 @@ int nilfs_discard_segments(struct the_nilfs *nilfs, __u64 *segnump,
                 ret = blkdev_issue_discard(nilfs->ns_bdev,
                                            start * sects_per_block,
                                            nblocks * sects_per_block,
-                                           GFP_NOFS, DISCARD_FL_BARRIER);
+                                           GFP_NOFS, BLKDEV_IFL_BARRIER);
         return ret;
 }
 
diff --git a/fs/partitions/acorn.c b/fs/partitions/acorn.c
index a97b477ac0fc..6921e7890be6 100644
--- a/fs/partitions/acorn.c
+++ b/fs/partitions/acorn.c
@@ -70,14 +70,14 @@ struct riscix_record {
 
 #if defined(CONFIG_ACORN_PARTITION_CUMANA) || \
         defined(CONFIG_ACORN_PARTITION_ADFS)
-static int
-riscix_partition(struct parsed_partitions *state, struct block_device *bdev,
-                unsigned long first_sect, int slot, unsigned long nr_sects)
+static int riscix_partition(struct parsed_partitions *state,
+                            unsigned long first_sect, int slot,
+                            unsigned long nr_sects)
 {
         Sector sect;
         struct riscix_record *rr;
         
-        rr = (struct riscix_record *)read_dev_sector(bdev, first_sect, &sect);
+        rr = read_part_sector(state, first_sect, &sect);
         if (!rr)
                 return -1;
 
@@ -123,9 +123,9 @@ struct linux_part {
 
 #if defined(CONFIG_ACORN_PARTITION_CUMANA) || \
         defined(CONFIG_ACORN_PARTITION_ADFS)
-static int
-linux_partition(struct parsed_partitions *state, struct block_device *bdev,
-                unsigned long first_sect, int slot, unsigned long nr_sects)
+static int linux_partition(struct parsed_partitions *state,
+                           unsigned long first_sect, int slot,
+                           unsigned long nr_sects)
 {
         Sector sect;
         struct linux_part *linuxp;
@@ -135,7 +135,7 @@ linux_partition(struct parsed_partitions *state, struct block_device *bdev,
 
         put_partition(state, slot++, first_sect, size);
 
-        linuxp = (struct linux_part *)read_dev_sector(bdev, first_sect, &sect);
+        linuxp = read_part_sector(state, first_sect, &sect);
         if (!linuxp)
                 return -1;
 
@@ -157,8 +157,7 @@ linux_partition(struct parsed_partitions *state, struct block_device *bdev,
 #endif
 
 #ifdef CONFIG_ACORN_PARTITION_CUMANA
-int
-adfspart_check_CUMANA(struct parsed_partitions *state, struct block_device *bdev)
+int adfspart_check_CUMANA(struct parsed_partitions *state)
 {
         unsigned long first_sector = 0;
         unsigned int start_blk = 0;
@@ -185,7 +184,7 @@ adfspart_check_CUMANA(struct parsed_partitions *state, struct block_device *bdev
                 struct adfs_discrecord *dr;
                 unsigned int nr_sects;
 
-                data = read_dev_sector(bdev, start_blk * 2 + 6, &sect);
+                data = read_part_sector(state, start_blk * 2 + 6, &sect);
                 if (!data)
                         return -1;
 
@@ -217,14 +216,14 @@ adfspart_check_CUMANA(struct parsed_partitions *state, struct block_device *bdev
 #ifdef CONFIG_ACORN_PARTITION_RISCIX
                 case PARTITION_RISCIX_SCSI:
                         /* RISCiX - we don't know how to find the next one. */
-                        slot = riscix_partition(state, bdev, first_sector,
-                                                 slot, nr_sects);
+                        slot = riscix_partition(state, first_sector, slot,
+                                                nr_sects);
                         break;
 #endif
 
                 case PARTITION_LINUX:
-                        slot = linux_partition(state, bdev, first_sector,
-                                                slot, nr_sects);
+                        slot = linux_partition(state, first_sector, slot,
+                                               nr_sects);
                         break;
                 }
                 put_dev_sector(sect);
@@ -249,8 +248,7 @@ adfspart_check_CUMANA(struct parsed_partitions *state, struct block_device *bdev
  *          hda1 = ADFS partition on first drive.
  *          hda2 = non-ADFS partition.
  */
-int
-adfspart_check_ADFS(struct parsed_partitions *state, struct block_device *bdev)
+int adfspart_check_ADFS(struct parsed_partitions *state)
 {
         unsigned long start_sect, nr_sects, sectscyl, heads;
         Sector sect;
@@ -259,7 +257,7 @@ adfspart_check_ADFS(struct parsed_partitions *state, struct block_device *bdev)
         unsigned char id;
         int slot = 1;
 
-        data = read_dev_sector(bdev, 6, &sect);
+        data = read_part_sector(state, 6, &sect);
         if (!data)
                 return -1;
 
@@ -278,21 +276,21 @@ adfspart_check_ADFS(struct parsed_partitions *state, struct block_device *bdev)
         /*
          * Work out start of non-adfs partition.
          */
-        nr_sects = (bdev->bd_inode->i_size >> 9) - start_sect;
+        nr_sects = (state->bdev->bd_inode->i_size >> 9) - start_sect;
 
         if (start_sect) {
                 switch (id) {
 #ifdef CONFIG_ACORN_PARTITION_RISCIX
                 case PARTITION_RISCIX_SCSI:
                 case PARTITION_RISCIX_MFM:
-                        slot = riscix_partition(state, bdev, start_sect,
-                                                 slot, nr_sects);
+                        slot = riscix_partition(state, start_sect, slot,
+                                                nr_sects);
                         break;
 #endif
 
                 case PARTITION_LINUX:
-                        slot = linux_partition(state, bdev, start_sect,
-                                                slot, nr_sects);
+                        slot = linux_partition(state, start_sect, slot,
+                                               nr_sects);
                         break;
                 }
         }
@@ -308,10 +306,11 @@ struct ics_part {
         __le32 size;
 };
 
-static int adfspart_check_ICSLinux(struct block_device *bdev, unsigned long block)
+static int adfspart_check_ICSLinux(struct parsed_partitions *state,
+                                   unsigned long block)
 {
         Sector sect;
-        unsigned char *data = read_dev_sector(bdev, block, &sect);
+        unsigned char *data = read_part_sector(state, block, &sect);
         int result = 0;
 
         if (data) {
@@ -349,8 +348,7 @@ static inline int valid_ics_sector(const unsigned char *data)
  *          hda2 = ADFS partition 1 on first drive.
  *              ..etc..
  */
-int
-adfspart_check_ICS(struct parsed_partitions *state, struct block_device *bdev)
+int adfspart_check_ICS(struct parsed_partitions *state)
 {
         const unsigned char *data;
         const struct ics_part *p;
@@ -360,7 +358,7 @@ adfspart_check_ICS(struct parsed_partitions *state, struct block_device *bdev)
         /*
          * Try ICS style partitions - sector 0 contains partition info.
          */
-        data = read_dev_sector(bdev, 0, &sect);
+        data = read_part_sector(state, 0, &sect);
         if (!data)
                 return -1;
 
@@ -392,7 +390,7 @@ adfspart_check_ICS(struct parsed_partitions *state, struct block_device *bdev)
                          * partition is.  We must not make this visible
                          * to the filesystem.
                          */
-                        if (size > 1 && adfspart_check_ICSLinux(bdev, start)) {
+                        if (size > 1 && adfspart_check_ICSLinux(state, start)) {
                                 start += 1;
                                 size -= 1;
                         }
@@ -446,8 +444,7 @@ static inline int valid_ptec_sector(const unsigned char *data)
  *          hda2 = ADFS partition 1 on first drive.
  *              ..etc..
  */
-int
-adfspart_check_POWERTEC(struct parsed_partitions *state, struct block_device *bdev)
+int adfspart_check_POWERTEC(struct parsed_partitions *state)
 {
         Sector sect;
         const unsigned char *data;
@@ -455,7 +452,7 @@ adfspart_check_POWERTEC(struct parsed_partitions *state, struct block_device *bd
         int slot = 1;
         int i;
 
-        data = read_dev_sector(bdev, 0, &sect);
+        data = read_part_sector(state, 0, &sect);
         if (!data)
                 return -1;
 
@@ -508,8 +505,7 @@ static const char eesox_name[] = {
  *  1. The individual ADFS boot block entries that are placed on the disk.
  *  2. The start address of the next entry.
  */
-int
-adfspart_check_EESOX(struct parsed_partitions *state, struct block_device *bdev)
+int adfspart_check_EESOX(struct parsed_partitions *state)
 {
         Sector sect;
         const unsigned char *data;
@@ -518,7 +514,7 @@ adfspart_check_EESOX(struct parsed_partitions *state, struct block_device *bdev)
         sector_t start = 0;
         int i, slot = 1;
 
-        data = read_dev_sector(bdev, 7, &sect);
+        data = read_part_sector(state, 7, &sect);
         if (!data)
                 return -1;
 
@@ -545,7 +541,7 @@ adfspart_check_EESOX(struct parsed_partitions *state, struct block_device *bdev)
         if (i != 0) {
                 sector_t size;
 
-                size = get_capacity(bdev->bd_disk);
+                size = get_capacity(state->bdev->bd_disk);
                 put_partition(state, slot++, start, size - start);
                 printk("\n");
         }
diff --git a/fs/partitions/acorn.h b/fs/partitions/acorn.h
index 81fd50ecc080..ede828529692 100644
--- a/fs/partitions/acorn.h
+++ b/fs/partitions/acorn.h
@@ -7,8 +7,8 @@
  *  format, and everyone stick to it?
  */
 
-int adfspart_check_CUMANA(struct parsed_partitions *state, struct block_device *bdev);
-int adfspart_check_ADFS(struct parsed_partitions *state, struct block_device *bdev);
-int adfspart_check_ICS(struct parsed_partitions *state, struct block_device *bdev);
-int adfspart_check_POWERTEC(struct parsed_partitions *state, struct block_device *bdev);
-int adfspart_check_EESOX(struct parsed_partitions *state, struct block_device *bdev);
+int adfspart_check_CUMANA(struct parsed_partitions *state);
+int adfspart_check_ADFS(struct parsed_partitions *state);
+int adfspart_check_ICS(struct parsed_partitions *state);
+int adfspart_check_POWERTEC(struct parsed_partitions *state);
+int adfspart_check_EESOX(struct parsed_partitions *state);
diff --git a/fs/partitions/amiga.c b/fs/partitions/amiga.c
index 9917a8c360f2..ba443d4229f8 100644
--- a/fs/partitions/amiga.c
+++ b/fs/partitions/amiga.c
@@ -23,8 +23,7 @@ checksum_block(__be32 *m, int size)
         return sum;
 }
 
-int
-amiga_partition(struct parsed_partitions *state, struct block_device *bdev)
+int amiga_partition(struct parsed_partitions *state)
 {
         Sector sect;
         unsigned char *data;
@@ -38,11 +37,11 @@ amiga_partition(struct parsed_partitions *state, struct block_device *bdev)
         for (blk = 0; ; blk++, put_dev_sector(sect)) {
                 if (blk == RDB_ALLOCATION_LIMIT)
                         goto rdb_done;
-                data = read_dev_sector(bdev, blk, &sect);
+                data = read_part_sector(state, blk, &sect);
                 if (!data) {
                         if (warn_no_part)
                                 printk("Dev %s: unable to read RDB block %d\n",
-                                       bdevname(bdev, b), blk);
+                                       bdevname(state->bdev, b), blk);
                         res = -1;
                         goto rdb_done;
                 }
@@ -64,7 +63,7 @@ amiga_partition(struct parsed_partitions *state, struct block_device *bdev)
                 }
 
                 printk("Dev %s: RDB in block %d has bad checksum\n",
-                               bdevname(bdev, b), blk);
+                       bdevname(state->bdev, b), blk);
         }
 
         /* blksize is blocks per 512 byte standard block */
@@ -75,11 +74,11 @@ amiga_partition(struct parsed_partitions *state, struct block_device *bdev)
         put_dev_sector(sect);
         for (part = 1; blk>0 && part<=16; part++, put_dev_sector(sect)) {
                 blk *= blksize; /* Read in terms partition table understands */
-                data = read_dev_sector(bdev, blk, &sect);
+                data = read_part_sector(state, blk, &sect);
                 if (!data) {
                         if (warn_no_part)
                                 printk("Dev %s: unable to read partition block %d\n",
-                                       bdevname(bdev, b), blk);
+                                       bdevname(state->bdev, b), blk);
                         res = -1;
                         goto rdb_done;
                 }
diff --git a/fs/partitions/amiga.h b/fs/partitions/amiga.h
index 2f3e9ce22d53..d094585cadaa 100644
--- a/fs/partitions/amiga.h
+++ b/fs/partitions/amiga.h
@@ -2,5 +2,5 @@
  *  fs/partitions/amiga.h
  */
 
-int amiga_partition(struct parsed_partitions *state, struct block_device *bdev);
+int amiga_partition(struct parsed_partitions *state);
 
diff --git a/fs/partitions/atari.c b/fs/partitions/atari.c
index 1f3572d5b755..4439ff1b6cec 100644
--- a/fs/partitions/atari.c
+++ b/fs/partitions/atari.c
@@ -30,7 +30,7 @@ static inline int OK_id(char *s)
                 memcmp (s, "RAW", 3) == 0 ;
 }
 
-int atari_partition(struct parsed_partitions *state, struct block_device *bdev)
+int atari_partition(struct parsed_partitions *state)
 {
         Sector sect;
         struct rootsector *rs;
@@ -42,12 +42,12 @@ int atari_partition(struct parsed_partitions *state, struct block_device *bdev)
         int part_fmt = 0; /* 0:unknown, 1:AHDI, 2:ICD/Supra */
 #endif
 
-        rs = (struct rootsector *) read_dev_sector(bdev, 0, &sect);
+        rs = read_part_sector(state, 0, &sect);
         if (!rs)
                 return -1;
 
         /* Verify this is an Atari rootsector: */
-        hd_size = bdev->bd_inode->i_size >> 9;
+        hd_size = state->bdev->bd_inode->i_size >> 9;
         if (!VALID_PARTITION(&rs->part[0], hd_size) &&
             !VALID_PARTITION(&rs->part[1], hd_size) &&
             !VALID_PARTITION(&rs->part[2], hd_size) &&
@@ -84,7 +84,7 @@ int atari_partition(struct parsed_partitions *state, struct block_device *bdev)
                 printk(" XGM<");
                 partsect = extensect = be32_to_cpu(pi->st);
                 while (1) {
-                        xrs = (struct rootsector *)read_dev_sector(bdev, partsect, &sect2);
+                        xrs = read_part_sector(state, partsect, &sect2);
                         if (!xrs) {
                                 printk (" block %ld read failed\n", partsect);
                                 put_dev_sector(sect);
diff --git a/fs/partitions/atari.h b/fs/partitions/atari.h
index 63186b00e135..fe2d32a89f36 100644
--- a/fs/partitions/atari.h
+++ b/fs/partitions/atari.h
@@ -31,4 +31,4 @@ struct rootsector
   u16 checksum;                 /* checksum for bootable disks */
 } __attribute__((__packed__));
 
-int atari_partition(struct parsed_partitions *state, struct block_device *bdev);
+int atari_partition(struct parsed_partitions *state);
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index e238ab23a9e7..5dcd4b0c5533 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -45,7 +45,7 @@ extern void md_autodetect_dev(dev_t dev);
 
 int warn_no_part = 1; /*This is ugly: should make genhd removable media aware*/
 
-static int (*check_part[])(struct parsed_partitions *, struct block_device *) = {
+static int (*check_part[])(struct parsed_partitions *) = {
         /*
          * Probe partition formats with tables at disk address 0
          * that also have an ADFS boot block at 0xdc0.
@@ -161,10 +161,11 @@ check_partition(struct gendisk *hd, struct block_device *bdev)
         struct parsed_partitions *state;
         int i, res, err;
 
-        state = kmalloc(sizeof(struct parsed_partitions), GFP_KERNEL);
+        state = kzalloc(sizeof(struct parsed_partitions), GFP_KERNEL);
         if (!state)
                 return NULL;
 
+        state->bdev = bdev;
         disk_name(hd, 0, state->name);
         printk(KERN_INFO " %s:", state->name);
         if (isdigit(state->name[strlen(state->name)-1]))
@@ -174,7 +175,7 @@ check_partition(struct gendisk *hd, struct block_device *bdev)
         i = res = err = 0;
         while (!res && check_part[i]) {
                 memset(&state->parts, 0, sizeof(state->parts));
-                res = check_part[i++](state, bdev);
+                res = check_part[i++](state);
                 if (res < 0) {
                         /* We have hit an I/O error which we don't report now.
                         * But record it, and let the others do their job.
@@ -186,6 +187,8 @@ check_partition(struct gendisk *hd, struct block_device *bdev)
         }
         if (res > 0)
                 return state;
+        if (state->access_beyond_eod)
+                err = -ENOSPC;
         if (err)
         /* The partition is unrecognized. So report I/O errors if there were any */
                 res = err;
@@ -538,12 +541,33 @@ exit:
         disk_part_iter_exit(&piter);
 }
 
+static bool disk_unlock_native_capacity(struct gendisk *disk)
+{
+        const struct block_device_operations *bdops = disk->fops;
+
+        if (bdops->unlock_native_capacity &&
+            !(disk->flags & GENHD_FL_NATIVE_CAPACITY)) {
+                printk(KERN_CONT "enabling native capacity\n");
+                bdops->unlock_native_capacity(disk);
+                disk->flags |= GENHD_FL_NATIVE_CAPACITY;
+                return true;
+        } else {
+                printk(KERN_CONT "truncated\n");
+                return false;
+        }
+}
+
 int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
 {
+        struct parsed_partitions *state = NULL;
         struct disk_part_iter piter;
         struct hd_struct *part;
-        struct parsed_partitions *state;
         int p, highest, res;
+rescan:
+        if (state && !IS_ERR(state)) {
+                kfree(state);
+                state = NULL;
+        }
 
         if (bdev->bd_part_count)
                 return -EBUSY;
@@ -562,8 +586,32 @@ int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
         bdev->bd_invalidated = 0;
         if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))
                 return 0;
-        if (IS_ERR(state))      /* I/O error reading the partition table */
+        if (IS_ERR(state)) {
+                /*
+                 * I/O error reading the partition table.  If any
+                 * partition code tried to read beyond EOD, retry
+                 * after unlocking native capacity.
+                 */
+                if (PTR_ERR(state) == -ENOSPC) {
+                        printk(KERN_WARNING "%s: partition table beyond EOD, ",
+                               disk->disk_name);
+                        if (disk_unlock_native_capacity(disk))
+                                goto rescan;
+                }
                 return -EIO;
+        }
+        /*
+         * If any partition code tried to read beyond EOD, try
+         * unlocking native capacity even if partition table is
+         * sucessfully read as we could be missing some partitions.
+         */
+        if (state->access_beyond_eod) {
+                printk(KERN_WARNING
+                       "%s: partition table partially beyond EOD, ",
+                       disk->disk_name);
+                if (disk_unlock_native_capacity(disk))
+                        goto rescan;
+        }
 
         /* tell userspace that the media / partition table may have changed */
         kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
@@ -581,7 +629,7 @@ int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
         /* add partitions */
         for (p = 1; p < state->limit; p++) {
                 sector_t size, from;
-try_scan:
+
                 size = state->parts[p].size;
                 if (!size)
                         continue;
@@ -589,30 +637,21 @@ try_scan:
                 from = state->parts[p].from;
                 if (from >= get_capacity(disk)) {
                         printk(KERN_WARNING
-                               "%s: p%d ignored, start %llu is behind the end of the disk\n",
+                               "%s: p%d start %llu is beyond EOD, ",
                                disk->disk_name, p, (unsigned long long) from);
+                        if (disk_unlock_native_capacity(disk))
+                                goto rescan;
                         continue;
                 }
 
                 if (from + size > get_capacity(disk)) {
-                        const struct block_device_operations *bdops = disk->fops;
-                        unsigned long long capacity;
-
                         printk(KERN_WARNING
-                               "%s: p%d size %llu exceeds device capacity, ",
+                               "%s: p%d size %llu extends beyond EOD, ",
                                disk->disk_name, p, (unsigned long long) size);
 
-                        if (bdops->set_capacity &&
-                            (disk->flags & GENHD_FL_NATIVE_CAPACITY) == 0) {
-                                printk(KERN_CONT "enabling native capacity\n");
-                                capacity = bdops->set_capacity(disk, ~0ULL);
-                                disk->flags |= GENHD_FL_NATIVE_CAPACITY;
-                                if (capacity > get_capacity(disk)) {
-                                        set_capacity(disk, capacity);
-                                        check_disk_size_change(disk, bdev);
-                                        bdev->bd_invalidated = 0;
-                                }
-                                goto try_scan;
+                        if (disk_unlock_native_capacity(disk)) {
+                                /* free state and restart */
+                                goto rescan;
                         } else {
                                 /*
                                  * we can not ignore partitions of broken tables
@@ -620,7 +659,6 @@ try_scan:
                                  * we limit them to the end of the disk to avoid
                                  * creating invalid block devices
                                  */
-                                printk(KERN_CONT "limited to end of disk\n");
                                 size = get_capacity(disk) - from;
                         }
                 }
diff --git a/fs/partitions/check.h b/fs/partitions/check.h
index 98dbe1a84528..52f8bd399396 100644
--- a/fs/partitions/check.h
+++ b/fs/partitions/check.h
@@ -6,6 +6,7 @@
  * description.
  */
 struct parsed_partitions {
+        struct block_device *bdev;
         char name[BDEVNAME_SIZE];
         struct {
                 sector_t from;
@@ -14,8 +15,19 @@ struct parsed_partitions {
         } parts[DISK_MAX_PARTS];
         int next;
         int limit;
+        bool access_beyond_eod;
 };
 
+static inline void *read_part_sector(struct parsed_partitions *state,
+                                     sector_t n, Sector *p)
+{
+        if (n >= get_capacity(state->bdev->bd_disk)) {
+                state->access_beyond_eod = true;
+                return NULL;
+        }
+        return read_dev_sector(state->bdev, n, p);
+}
+
 static inline void
 put_partition(struct parsed_partitions *p, int n, sector_t from, sector_t size)
 {
diff --git a/fs/partitions/efi.c b/fs/partitions/efi.c
index f5867f8ed214..9efb2cfe2410 100644
--- a/fs/partitions/efi.c
+++ b/fs/partitions/efi.c
@@ -140,8 +140,7 @@ efi_crc32(const void *buf, unsigned long len)
  *  the part[0] entry for this disk, and is the number of
  *  physical sectors available on the disk.
  */
-static u64
-last_lba(struct block_device *bdev)
+static u64 last_lba(struct block_device *bdev)
 {
         if (!bdev || !bdev->bd_inode)
                 return 0;
@@ -181,27 +180,28 @@ is_pmbr_valid(legacy_mbr *mbr)
 
 /**
  * read_lba(): Read bytes from disk, starting at given LBA
- * @bdev
+ * @state
  * @lba
  * @buffer
  * @size_t
  *
- * Description:  Reads @count bytes from @bdev into @buffer.
+ * Description: Reads @count bytes from @state->bdev into @buffer.
  * Returns number of bytes read on success, 0 on error.
  */
-static size_t
-read_lba(struct block_device *bdev, u64 lba, u8 * buffer, size_t count)
+static size_t read_lba(struct parsed_partitions *state,
+                       u64 lba, u8 *buffer, size_t count)
 {
         size_t totalreadcount = 0;
+        struct block_device *bdev = state->bdev;
         sector_t n = lba * (bdev_logical_block_size(bdev) / 512);
 
-        if (!bdev || !buffer || lba > last_lba(bdev))
+        if (!buffer || lba > last_lba(bdev))
                 return 0;
 
         while (count) {
                 int copied = 512;
                 Sector sect;
-                unsigned char *data = read_dev_sector(bdev, n++, &sect);
+                unsigned char *data = read_part_sector(state, n++, &sect);
                 if (!data)
                         break;
                 if (copied > count)
@@ -217,19 +217,20 @@ read_lba(struct block_device *bdev, u64 lba, u8 * buffer, size_t count)
 
 /**
  * alloc_read_gpt_entries(): reads partition entries from disk
- * @bdev
+ * @state
  * @gpt - GPT header
  * 
  * Description: Returns ptes on success,  NULL on error.
  * Allocates space for PTEs based on information found in @gpt.
  * Notes: remember to free pte when you're done!
  */
-static gpt_entry *
-alloc_read_gpt_entries(struct block_device *bdev, gpt_header *gpt)
+static gpt_entry *alloc_read_gpt_entries(struct parsed_partitions *state,
+                                         gpt_header *gpt)
 {
         size_t count;
         gpt_entry *pte;
-        if (!bdev || !gpt)
+
+        if (!gpt)
                 return NULL;
 
         count = le32_to_cpu(gpt->num_partition_entries) *
@@ -240,7 +241,7 @@ alloc_read_gpt_entries(struct block_device *bdev, gpt_header *gpt)
         if (!pte)
                 return NULL;
 
-        if (read_lba(bdev, le64_to_cpu(gpt->partition_entry_lba),
+        if (read_lba(state, le64_to_cpu(gpt->partition_entry_lba),
                      (u8 *) pte,
                      count) < count) {
                 kfree(pte);
@@ -252,27 +253,24 @@ alloc_read_gpt_entries(struct block_device *bdev, gpt_header *gpt)
 
 /**
  * alloc_read_gpt_header(): Allocates GPT header, reads into it from disk
- * @bdev
+ * @state
  * @lba is the Logical Block Address of the partition table
  * 
  * Description: returns GPT header on success, NULL on error.   Allocates
- * and fills a GPT header starting at @ from @bdev.
+ * and fills a GPT header starting at @ from @state->bdev.
  * Note: remember to free gpt when finished with it.
  */
-static gpt_header *
-alloc_read_gpt_header(struct block_device *bdev, u64 lba)
+static gpt_header *alloc_read_gpt_header(struct parsed_partitions *state,
+                                         u64 lba)
 {
         gpt_header *gpt;
-        unsigned ssz = bdev_logical_block_size(bdev);
-
-        if (!bdev)
-                return NULL;
+        unsigned ssz = bdev_logical_block_size(state->bdev);
 
         gpt = kzalloc(ssz, GFP_KERNEL);
         if (!gpt)
                 return NULL;
 
-        if (read_lba(bdev, lba, (u8 *) gpt, ssz) < ssz) {
+        if (read_lba(state, lba, (u8 *) gpt, ssz) < ssz) {
                 kfree(gpt);
                 gpt=NULL;
                 return NULL;
@@ -283,7 +281,7 @@ alloc_read_gpt_header(struct block_device *bdev, u64 lba)
 
 /**
  * is_gpt_valid() - tests one GPT header and PTEs for validity
- * @bdev
+ * @state
  * @lba is the logical block address of the GPT header to test
  * @gpt is a GPT header ptr, filled on return.
  * @ptes is a PTEs ptr, filled on return.
@@ -291,16 +289,15 @@ alloc_read_gpt_header(struct block_device *bdev, u64 lba)
  * Description: returns 1 if valid,  0 on error.
  * If valid, returns pointers to newly allocated GPT header and PTEs.
  */
-static int
-is_gpt_valid(struct block_device *bdev, u64 lba,
-             gpt_header **gpt, gpt_entry **ptes)
+static int is_gpt_valid(struct parsed_partitions *state, u64 lba,
+                        gpt_header **gpt, gpt_entry **ptes)
 {
         u32 crc, origcrc;
         u64 lastlba;
 
-        if (!bdev || !gpt || !ptes)
+        if (!ptes)
                 return 0;
-        if (!(*gpt = alloc_read_gpt_header(bdev, lba)))
+        if (!(*gpt = alloc_read_gpt_header(state, lba)))
                 return 0;
 
         /* Check the GUID Partition Table signature */
@@ -336,7 +333,7 @@ is_gpt_valid(struct block_device *bdev, u64 lba,
         /* Check the first_usable_lba and last_usable_lba are
          * within the disk.
          */
-        lastlba = last_lba(bdev);
+        lastlba = last_lba(state->bdev);
         if (le64_to_cpu((*gpt)->first_usable_lba) > lastlba) {
                 pr_debug("GPT: first_usable_lba incorrect: %lld > %lld\n",
                          (unsigned long long)le64_to_cpu((*gpt)->first_usable_lba),
@@ -350,7 +347,7 @@ is_gpt_valid(struct block_device *bdev, u64 lba,
                 goto fail;
         }
 
-        if (!(*ptes = alloc_read_gpt_entries(bdev, *gpt)))
+        if (!(*ptes = alloc_read_gpt_entries(state, *gpt)))
                 goto fail;
 
         /* Check the GUID Partition Entry Array CRC */
@@ -495,7 +492,7 @@ compare_gpts(gpt_header *pgpt, gpt_header *agpt, u64 lastlba)
 
 /**
  * find_valid_gpt() - Search disk for valid GPT headers and PTEs
- * @bdev
+ * @state
  * @gpt is a GPT header ptr, filled on return.
  * @ptes is a PTEs ptr, filled on return.
  * Description: Returns 1 if valid, 0 on error.
@@ -508,24 +505,25 @@ compare_gpts(gpt_header *pgpt, gpt_header *agpt, u64 lastlba)
  * This protects against devices which misreport their size, and forces
  * the user to decide to use the Alternate GPT.
  */
-static int
-find_valid_gpt(struct block_device *bdev, gpt_header **gpt, gpt_entry **ptes)
+static int find_valid_gpt(struct parsed_partitions *state, gpt_header **gpt,
+                          gpt_entry **ptes)
 {
         int good_pgpt = 0, good_agpt = 0, good_pmbr = 0;
         gpt_header *pgpt = NULL, *agpt = NULL;
         gpt_entry *pptes = NULL, *aptes = NULL;
         legacy_mbr *legacymbr;
         u64 lastlba;
-        if (!bdev || !gpt || !ptes)
+
+        if (!ptes)
                 return 0;
 
-        lastlba = last_lba(bdev);
+        lastlba = last_lba(state->bdev);
         if (!force_gpt) {
                 /* This will be added to the EFI Spec. per Intel after v1.02. */
                 legacymbr = kzalloc(sizeof (*legacymbr), GFP_KERNEL);
                 if (legacymbr) {
-                        read_lba(bdev, 0, (u8 *) legacymbr,
-                                 sizeof (*legacymbr));
+                        read_lba(state, 0, (u8 *) legacymbr,
+                                 sizeof (*legacymbr));
                         good_pmbr = is_pmbr_valid(legacymbr);
                         kfree(legacymbr);
                 }
@@ -533,15 +531,14 @@ find_valid_gpt(struct block_device *bdev, gpt_header **gpt, gpt_entry **ptes)
                         goto fail;
         }
 
-        good_pgpt = is_gpt_valid(bdev, GPT_PRIMARY_PARTITION_TABLE_LBA,
+        good_pgpt = is_gpt_valid(state, GPT_PRIMARY_PARTITION_TABLE_LBA,
                                  &pgpt, &pptes);
         if (good_pgpt)
-                good_agpt = is_gpt_valid(bdev,
+                good_agpt = is_gpt_valid(state,
                                          le64_to_cpu(pgpt->alternate_lba),
                                          &agpt, &aptes);
         if (!good_agpt && force_gpt)
-                good_agpt = is_gpt_valid(bdev, lastlba,
-                                         &agpt, &aptes);
+                good_agpt = is_gpt_valid(state, lastlba, &agpt, &aptes);
 
         /* The obviously unsuccessful case */
         if (!good_pgpt && !good_agpt)
@@ -583,9 +580,8 @@ find_valid_gpt(struct block_device *bdev, gpt_header **gpt, gpt_entry **ptes)
 }
 
 /**
- * efi_partition(struct parsed_partitions *state, struct block_device *bdev)
+ * efi_partition(struct parsed_partitions *state)
  * @state
- * @bdev
  *
  * Description: called from check.c, if the disk contains GPT
  * partitions, sets up partition entries in the kernel.
@@ -602,15 +598,14 @@ find_valid_gpt(struct block_device *bdev, gpt_header **gpt, gpt_entry **ptes)
  *  1 if successful
  *
  */
-int
-efi_partition(struct parsed_partitions *state, struct block_device *bdev)
+int efi_partition(struct parsed_partitions *state)
 {
         gpt_header *gpt = NULL;
         gpt_entry *ptes = NULL;
         u32 i;
-        unsigned ssz = bdev_logical_block_size(bdev) / 512;
+        unsigned ssz = bdev_logical_block_size(state->bdev) / 512;
 
-        if (!find_valid_gpt(bdev, &gpt, &ptes) || !gpt || !ptes) {
+        if (!find_valid_gpt(state, &gpt, &ptes) || !gpt || !ptes) {
                 kfree(gpt);
                 kfree(ptes);
                 return 0;
@@ -623,7 +618,7 @@ efi_partition(struct parsed_partitions *state, struct block_device *bdev)
                 u64 size = le64_to_cpu(ptes[i].ending_lba) -
                            le64_to_cpu(ptes[i].starting_lba) + 1ULL;
 
-                if (!is_pte_valid(&ptes[i], last_lba(bdev)))
+                if (!is_pte_valid(&ptes[i], last_lba(state->bdev)))
                         continue;
 
                 put_partition(state, i+1, start * ssz, size * ssz);
diff --git a/fs/partitions/efi.h b/fs/partitions/efi.h
index 6998b589abf9..b69ab729558f 100644
--- a/fs/partitions/efi.h
+++ b/fs/partitions/efi.h
@@ -110,7 +110,7 @@ typedef struct _legacy_mbr {
 } __attribute__ ((packed)) legacy_mbr;
 
 /* Functions */
-extern int efi_partition(struct parsed_partitions *state, struct block_device *bdev);
+extern int efi_partition(struct parsed_partitions *state);
 
 #endif
 
diff --git a/fs/partitions/ibm.c b/fs/partitions/ibm.c
index fc71aab08460..3e73de5967ff 100644
--- a/fs/partitions/ibm.c
+++ b/fs/partitions/ibm.c
@@ -58,9 +58,9 @@ cchhb2blk (struct vtoc_cchhb *ptr, struct hd_geometry *geo) {
 
 /*
  */
-int
-ibm_partition(struct parsed_partitions *state, struct block_device *bdev)
+int ibm_partition(struct parsed_partitions *state)
 {
+        struct block_device *bdev = state->bdev;
         int blocksize, res;
         loff_t i_size, offset, size, fmt_size;
         dasd_information2_t *info;
@@ -100,7 +100,8 @@ ibm_partition(struct parsed_partitions *state, struct block_device *bdev)
         /*
          * Get volume label, extract name and type.
          */
-        data = read_dev_sector(bdev, info->label_block*(blocksize/512), &sect);
+        data = read_part_sector(state, info->label_block*(blocksize/512),
+                                &sect);
         if (data == NULL)
                 goto out_readerr;
 
@@ -193,8 +194,8 @@ ibm_partition(struct parsed_partitions *state, struct block_device *bdev)
                          */
                         blk = cchhb2blk(&label->vol.vtoc, geo) + 1;
                         counter = 0;
-                        data = read_dev_sector(bdev, blk * (blocksize/512),
-                                               &sect);
+                        data = read_part_sector(state, blk * (blocksize/512),
+                                                &sect);
                         while (data != NULL) {
                                 struct vtoc_format1_label f1;
 
@@ -208,9 +209,8 @@ ibm_partition(struct parsed_partitions *state, struct block_device *bdev)
                                     || f1.DS1FMTID == _ascebc['7']
                                     || f1.DS1FMTID == _ascebc['9']) {
                                         blk++;
-                                        data = read_dev_sector(bdev, blk *
-                                                               (blocksize/512),
-                                                                &sect);
+                                        data = read_part_sector(state,
+                                                blk * (blocksize/512), &sect);
                                         continue;
                                 }
 
@@ -230,9 +230,8 @@ ibm_partition(struct parsed_partitions *state, struct block_device *bdev)
                                               size * (blocksize >> 9));
                                 counter++;
                                 blk++;
-                                data = read_dev_sector(bdev,
-                                                       blk * (blocksize/512),
-                                                       &sect);
+                                data = read_part_sector(state,
+                                                blk * (blocksize/512), &sect);
                         }
 
                         if (!data)
diff --git a/fs/partitions/ibm.h b/fs/partitions/ibm.h
index 31f85a6ac459..08fb0804a812 100644
--- a/fs/partitions/ibm.h
+++ b/fs/partitions/ibm.h
@@ -1 +1 @@
-int ibm_partition(struct parsed_partitions *, struct block_device *);
+int ibm_partition(struct parsed_partitions *);
diff --git a/fs/partitions/karma.c b/fs/partitions/karma.c
index 176d89bcf123..1cc928bb762f 100644
--- a/fs/partitions/karma.c
+++ b/fs/partitions/karma.c
@@ -9,7 +9,7 @@
 #include "check.h"
 #include "karma.h"
 
-int karma_partition(struct parsed_partitions *state, struct block_device *bdev)
+int karma_partition(struct parsed_partitions *state)
 {
         int i;
         int slot = 1;
@@ -29,7 +29,7 @@ int karma_partition(struct parsed_partitions *state, struct block_device *bdev)
         } __attribute__((packed)) *label;
         struct d_partition *p;
 
-        data = read_dev_sector(bdev, 0, &sect);
+        data = read_part_sector(state, 0, &sect);
         if (!data)
                 return -1;
 
diff --git a/fs/partitions/karma.h b/fs/partitions/karma.h
index ecf7d3f2a3d8..c764b2e9df21 100644
--- a/fs/partitions/karma.h
+++ b/fs/partitions/karma.h
@@ -4,5 +4,5 @@
 
 #define KARMA_LABEL_MAGIC               0xAB56
 
-int karma_partition(struct parsed_partitions *state, struct block_device *bdev);
+int karma_partition(struct parsed_partitions *state);
 
diff --git a/fs/partitions/ldm.c b/fs/partitions/ldm.c
index 8652fb99e962..3ceca05b668c 100644
--- a/fs/partitions/ldm.c
+++ b/fs/partitions/ldm.c
@@ -309,7 +309,7 @@ static bool ldm_compare_tocblocks (const struct tocblock *toc1,
 
 /**
  * ldm_validate_privheads - Compare the primary privhead with its backups
- * @bdev:  Device holding the LDM Database
+ * @state: Partition check state including device holding the LDM Database
  * @ph1:   Memory struct to fill with ph contents
  *
  * Read and compare all three privheads from disk.
@@ -321,8 +321,8 @@ static bool ldm_compare_tocblocks (const struct tocblock *toc1,
  * Return:  'true'   Success
  *          'false'  Error
  */
-static bool ldm_validate_privheads (struct block_device *bdev,
-                                    struct privhead *ph1)
+static bool ldm_validate_privheads(struct parsed_partitions *state,
+                                   struct privhead *ph1)
 {
         static const int off[3] = { OFF_PRIV1, OFF_PRIV2, OFF_PRIV3 };
         struct privhead *ph[3] = { ph1 };
@@ -332,7 +332,7 @@ static bool ldm_validate_privheads (struct block_device *bdev,
         long num_sects;
         int i;
 
-        BUG_ON (!bdev || !ph1);
+        BUG_ON (!state || !ph1);
 
         ph[1] = kmalloc (sizeof (*ph[1]), GFP_KERNEL);
         ph[2] = kmalloc (sizeof (*ph[2]), GFP_KERNEL);
@@ -346,8 +346,8 @@ static bool ldm_validate_privheads (struct block_device *bdev,
 
         /* Read and parse privheads */
         for (i = 0; i < 3; i++) {
-                data = read_dev_sector (bdev,
-                        ph[0]->config_start + off[i], &sect);
+                data = read_part_sector(state, ph[0]->config_start + off[i],
+                                        &sect);
                 if (!data) {
                         ldm_crit ("Disk read failed.");
                         goto out;
@@ -363,7 +363,7 @@ static bool ldm_validate_privheads (struct block_device *bdev,
                 }
         }
 
-        num_sects = bdev->bd_inode->i_size >> 9;
+        num_sects = state->bdev->bd_inode->i_size >> 9;
 
         if ((ph[0]->config_start > num_sects) ||
            ((ph[0]->config_start + ph[0]->config_size) > num_sects)) {
@@ -397,20 +397,20 @@ out:
 
 /**
  * ldm_validate_tocblocks - Validate the table of contents and its backups
- * @bdev:  Device holding the LDM Database
- * @base:  Offset, into @bdev, of the database
+ * @state: Partition check state including device holding the LDM Database
+ * @base:  Offset, into @state->bdev, of the database
  * @ldb:   Cache of the database structures
  *
  * Find and compare the four tables of contents of the LDM Database stored on
- * @bdev and return the parsed information into @toc1.
+ * @state->bdev and return the parsed information into @toc1.
  *
  * The offsets and sizes of the configs are range-checked against a privhead.
  *
  * Return:  'true'   @toc1 contains validated TOCBLOCK info
  *          'false'  @toc1 contents are undefined
  */
-static bool ldm_validate_tocblocks(struct block_device *bdev,
-        unsigned long base, struct ldmdb *ldb)
+static bool ldm_validate_tocblocks(struct parsed_partitions *state,
+                                   unsigned long base, struct ldmdb *ldb)
 {
         static const int off[4] = { OFF_TOCB1, OFF_TOCB2, OFF_TOCB3, OFF_TOCB4};
         struct tocblock *tb[4];
@@ -420,7 +420,7 @@ static bool ldm_validate_tocblocks(struct block_device *bdev,
         int i, nr_tbs;
         bool result = false;
 
-        BUG_ON(!bdev || !ldb);
+        BUG_ON(!state || !ldb);
         ph = &ldb->ph;
         tb[0] = &ldb->toc;
         tb[1] = kmalloc(sizeof(*tb[1]) * 3, GFP_KERNEL);
@@ -437,7 +437,7 @@ static bool ldm_validate_tocblocks(struct block_device *bdev,
          * skip any that fail as long as we get at least one valid TOCBLOCK.
          */
         for (nr_tbs = i = 0; i < 4; i++) {
-                data = read_dev_sector(bdev, base + off[i], &sect);
+                data = read_part_sector(state, base + off[i], &sect);
                 if (!data) {
                         ldm_error("Disk read failed for TOCBLOCK %d.", i);
                         continue;
@@ -473,7 +473,7 @@ err:
 
 /**
  * ldm_validate_vmdb - Read the VMDB and validate it
- * @bdev:  Device holding the LDM Database
+ * @state: Partition check state including device holding the LDM Database
  * @base:  Offset, into @bdev, of the database
  * @ldb:   Cache of the database structures
  *
@@ -483,8 +483,8 @@ err:
  * Return:  'true'   @ldb contains validated VBDB info
  *          'false'  @ldb contents are undefined
  */
-static bool ldm_validate_vmdb (struct block_device *bdev, unsigned long base,
-                               struct ldmdb *ldb)
+static bool ldm_validate_vmdb(struct parsed_partitions *state,
+                              unsigned long base, struct ldmdb *ldb)
 {
         Sector sect;
         u8 *data;
@@ -492,12 +492,12 @@ static bool ldm_validate_vmdb (struct block_device *bdev, unsigned long base,
         struct vmdb *vm;
         struct tocblock *toc;
 
-        BUG_ON (!bdev || !ldb);
+        BUG_ON (!state || !ldb);
 
         vm  = &ldb->vm;
         toc = &ldb->toc;
 
-        data = read_dev_sector (bdev, base + OFF_VMDB, &sect);
+        data = read_part_sector(state, base + OFF_VMDB, &sect);
         if (!data) {
                 ldm_crit ("Disk read failed.");
                 return false;
@@ -534,21 +534,21 @@ out:
 
 /**
  * ldm_validate_partition_table - Determine whether bdev might be a dynamic disk
- * @bdev:  Device holding the LDM Database
+ * @state: Partition check state including device holding the LDM Database
  *
  * This function provides a weak test to decide whether the device is a dynamic
  * disk or not.  It looks for an MS-DOS-style partition table containing at
  * least one partition of type 0x42 (formerly SFS, now used by Windows for
  * dynamic disks).
  *
- * N.B.  The only possible error can come from the read_dev_sector and that is
+ * N.B.  The only possible error can come from the read_part_sector and that is
  *       only likely to happen if the underlying device is strange.  If that IS
  *       the case we should return zero to let someone else try.
  *
- * Return:  'true'   @bdev is a dynamic disk
- *          'false'  @bdev is not a dynamic disk, or an error occurred
+ * Return:  'true'   @state->bdev is a dynamic disk
+ *          'false'  @state->bdev is not a dynamic disk, or an error occurred
  */
-static bool ldm_validate_partition_table (struct block_device *bdev)
+static bool ldm_validate_partition_table(struct parsed_partitions *state)
 {
         Sector sect;
         u8 *data;
@@ -556,9 +556,9 @@ static bool ldm_validate_partition_table (struct block_device *bdev)
         int i;
         bool result = false;
 
-        BUG_ON (!bdev);
+        BUG_ON(!state);
 
-        data = read_dev_sector (bdev, 0, &sect);
+        data = read_part_sector(state, 0, &sect);
         if (!data) {
                 ldm_crit ("Disk read failed.");
                 return false;
@@ -1391,8 +1391,8 @@ static bool ldm_frag_commit (struct list_head *frags, struct ldmdb *ldb)
 
 /**
  * ldm_get_vblks - Read the on-disk database of VBLKs into memory
- * @bdev:  Device holding the LDM Database
- * @base:  Offset, into @bdev, of the database
+ * @state: Partition check state including device holding the LDM Database
+ * @base:  Offset, into @state->bdev, of the database
  * @ldb:   Cache of the database structures
  *
  * To use the information from the VBLKs, they need to be read from the disk,
@@ -1401,8 +1401,8 @@ static bool ldm_frag_commit (struct list_head *frags, struct ldmdb *ldb)
  * Return:  'true'   All the VBLKs were read successfully
  *          'false'  An error occurred
  */
-static bool ldm_get_vblks (struct block_device *bdev, unsigned long base,
-                           struct ldmdb *ldb)
+static bool ldm_get_vblks(struct parsed_partitions *state, unsigned long base,
+                          struct ldmdb *ldb)
 {
         int size, perbuf, skip, finish, s, v, recs;
         u8 *data = NULL;
@@ -1410,7 +1410,7 @@ static bool ldm_get_vblks (struct block_device *bdev, unsigned long base,
         bool result = false;
         LIST_HEAD (frags);
 
-        BUG_ON (!bdev || !ldb);
+        BUG_ON(!state || !ldb);
 
         size   = ldb->vm.vblk_size;
         perbuf = 512 / size;
@@ -1418,7 +1418,7 @@ static bool ldm_get_vblks (struct block_device *bdev, unsigned long base,
         finish = (size * ldb->vm.last_vblk_seq) >> 9;
 
         for (s = skip; s < finish; s++) {               /* For each sector */
-                data = read_dev_sector (bdev, base + OFF_VMDB + s, &sect);
+                data = read_part_sector(state, base + OFF_VMDB + s, &sect);
                 if (!data) {
                         ldm_crit ("Disk read failed.");
                         goto out;
@@ -1474,8 +1474,7 @@ static void ldm_free_vblks (struct list_head *lh)
 
 /**
  * ldm_partition - Find out whether a device is a dynamic disk and handle it
- * @pp:    List of the partitions parsed so far
- * @bdev:  Device holding the LDM Database
+ * @state: Partition check state including device holding the LDM Database
  *
  * This determines whether the device @bdev is a dynamic disk and if so creates
  * the partitions necessary in the gendisk structure pointed to by @hd.
@@ -1485,21 +1484,21 @@ static void ldm_free_vblks (struct list_head *lh)
  * example, if the device is hda, we would have: hda1: LDM database, hda2, hda3,
  * and so on: the actual data containing partitions.
  *
- * Return:  1 Success, @bdev is a dynamic disk and we handled it
- *          0 Success, @bdev is not a dynamic disk
+ * Return:  1 Success, @state->bdev is a dynamic disk and we handled it
+ *          0 Success, @state->bdev is not a dynamic disk
  *         -1 An error occurred before enough information had been read
- *            Or @bdev is a dynamic disk, but it may be corrupted
+ *            Or @state->bdev is a dynamic disk, but it may be corrupted
  */
-int ldm_partition (struct parsed_partitions *pp, struct block_device *bdev)
+int ldm_partition(struct parsed_partitions *state)
 {
         struct ldmdb  *ldb;
         unsigned long base;
         int result = -1;
 
-        BUG_ON (!pp || !bdev);
+        BUG_ON(!state);
 
         /* Look for signs of a Dynamic Disk */
-        if (!ldm_validate_partition_table (bdev))
+        if (!ldm_validate_partition_table(state))
                 return 0;
 
         ldb = kmalloc (sizeof (*ldb), GFP_KERNEL);
@@ -1509,15 +1508,15 @@ int ldm_partition (struct parsed_partitions *pp, struct block_device *bdev)
         }
 
         /* Parse and check privheads. */
-        if (!ldm_validate_privheads (bdev, &ldb->ph))
+        if (!ldm_validate_privheads(state, &ldb->ph))
                 goto out;               /* Already logged */
 
         /* All further references are relative to base (database start). */
         base = ldb->ph.config_start;
 
         /* Parse and check tocs and vmdb. */
-        if (!ldm_validate_tocblocks (bdev, base, ldb) ||
-            !ldm_validate_vmdb      (bdev, base, ldb))
+        if (!ldm_validate_tocblocks(state, base, ldb) ||
+            !ldm_validate_vmdb(state, base, ldb))
                 goto out;               /* Already logged */
 
         /* Initialize vblk lists in ldmdb struct */
@@ -1527,13 +1526,13 @@ int ldm_partition (struct parsed_partitions *pp, struct block_device *bdev)
         INIT_LIST_HEAD (&ldb->v_comp);
         INIT_LIST_HEAD (&ldb->v_part);
 
-        if (!ldm_get_vblks (bdev, base, ldb)) {
+        if (!ldm_get_vblks(state, base, ldb)) {
                 ldm_crit ("Failed to read the VBLKs from the database.");
                 goto cleanup;
         }
 
         /* Finally, create the data partition devices. */
-        if (ldm_create_data_partitions (pp, ldb)) {
+        if (ldm_create_data_partitions(state, ldb)) {
                 ldm_debug ("Parsed LDM database successfully.");
                 result = 1;
         }
diff --git a/fs/partitions/ldm.h b/fs/partitions/ldm.h
index 30e08e809c1d..d1fb50b28d86 100644
--- a/fs/partitions/ldm.h
+++ b/fs/partitions/ldm.h
@@ -209,7 +209,7 @@ struct ldmdb {				/* Cache of the database */
         struct list_head v_part;
 };
 
-int ldm_partition (struct parsed_partitions *state, struct block_device *bdev);
+int ldm_partition(struct parsed_partitions *state);
 
 #endif /* _FS_PT_LDM_H_ */
 
diff --git a/fs/partitions/mac.c b/fs/partitions/mac.c
index dece9b4c881f..74465ff7c263 100644
--- a/fs/partitions/mac.c
+++ b/fs/partitions/mac.c
@@ -27,7 +27,7 @@ static inline void mac_fix_string(char *stg, int len)
                 stg[i] = 0;
 }
 
-int mac_partition(struct parsed_partitions *state, struct block_device *bdev)
+int mac_partition(struct parsed_partitions *state)
 {
         int slot = 1;
         Sector sect;
@@ -42,7 +42,7 @@ int mac_partition(struct parsed_partitions *state, struct block_device *bdev)
         struct mac_driver_desc *md;
 
         /* Get 0th block and look at the first partition map entry. */
-        md = (struct mac_driver_desc *) read_dev_sector(bdev, 0, &sect);
+        md = read_part_sector(state, 0, &sect);
         if (!md)
                 return -1;
         if (be16_to_cpu(md->signature) != MAC_DRIVER_MAGIC) {
@@ -51,7 +51,7 @@ int mac_partition(struct parsed_partitions *state, struct block_device *bdev)
         }
         secsize = be16_to_cpu(md->block_size);
         put_dev_sector(sect);
-        data = read_dev_sector(bdev, secsize/512, &sect);
+        data = read_part_sector(state, secsize/512, &sect);
         if (!data)
                 return -1;
         part = (struct mac_partition *) (data + secsize%512);
@@ -64,7 +64,7 @@ int mac_partition(struct parsed_partitions *state, struct block_device *bdev)
         for (blk = 1; blk <= blocks_in_map; ++blk) {
                 int pos = blk * secsize;
                 put_dev_sector(sect);
-                data = read_dev_sector(bdev, pos/512, &sect);
+                data = read_part_sector(state, pos/512, &sect);
                 if (!data)
                         return -1;
                 part = (struct mac_partition *) (data + pos%512);
@@ -123,7 +123,8 @@ int mac_partition(struct parsed_partitions *state, struct block_device *bdev)
         }
 #ifdef CONFIG_PPC_PMAC
         if (found_root_goodness)
-                note_bootable_part(bdev->bd_dev, found_root, found_root_goodness);
+                note_bootable_part(state->bdev->bd_dev, found_root,
+                                   found_root_goodness);
 #endif
 
         put_dev_sector(sect);
diff --git a/fs/partitions/mac.h b/fs/partitions/mac.h
index bbf26e1386fa..3c7d98436380 100644
--- a/fs/partitions/mac.h
+++ b/fs/partitions/mac.h
@@ -41,4 +41,4 @@ struct mac_driver_desc {
     /* ... more stuff */
 };
 
-int mac_partition(struct parsed_partitions *state, struct block_device *bdev);
+int mac_partition(struct parsed_partitions *state);
diff --git a/fs/partitions/msdos.c b/fs/partitions/msdos.c
index efe3df75f84d..15bfb7b1e044 100644
--- a/fs/partitions/msdos.c
+++ b/fs/partitions/msdos.c
@@ -64,7 +64,7 @@ msdos_magic_present(unsigned char *p)
 #define AIX_LABEL_MAGIC2        0xC2
 #define AIX_LABEL_MAGIC3        0xD4
 #define AIX_LABEL_MAGIC4        0xC1
-static int aix_magic_present(unsigned char *p, struct block_device *bdev)
+static int aix_magic_present(struct parsed_partitions *state, unsigned char *p)
 {
         struct partition *pt = (struct partition *) (p + 0x1be);
         Sector sect;
@@ -85,7 +85,7 @@ static int aix_magic_present(unsigned char *p, struct block_device *bdev)
                         is_extended_partition(pt))
                         return 0;
         }
-        d = read_dev_sector(bdev, 7, &sect);
+        d = read_part_sector(state, 7, &sect);
         if (d) {
                 if (d[0] == '_' && d[1] == 'L' && d[2] == 'V' && d[3] == 'M')
                         ret = 1;
@@ -105,15 +105,14 @@ static int aix_magic_present(unsigned char *p, struct block_device *bdev)
  * only for the actual data partitions.
  */
 
-static void
-parse_extended(struct parsed_partitions *state, struct block_device *bdev,
-                        sector_t first_sector, sector_t first_size)
+static void parse_extended(struct parsed_partitions *state,
+                           sector_t first_sector, sector_t first_size)
 {
         struct partition *p;
         Sector sect;
         unsigned char *data;
         sector_t this_sector, this_size;
-        sector_t sector_size = bdev_logical_block_size(bdev) / 512;
+        sector_t sector_size = bdev_logical_block_size(state->bdev) / 512;
         int loopct = 0;         /* number of links followed
                                    without finding a data partition */
         int i;
@@ -126,7 +125,7 @@ parse_extended(struct parsed_partitions *state, struct block_device *bdev,
                         return;
                 if (state->next == state->limit)
                         return;
-                data = read_dev_sector(bdev, this_sector, &sect);
+                data = read_part_sector(state, this_sector, &sect);
                 if (!data)
                         return;
 
@@ -198,9 +197,8 @@ done:
 /* james@bpgc.com: Solaris has a nasty indicator: 0x82 which also
    indicates linux swap.  Be careful before believing this is Solaris. */
 
-static void
-parse_solaris_x86(struct parsed_partitions *state, struct block_device *bdev,
-                        sector_t offset, sector_t size, int origin)
+static void parse_solaris_x86(struct parsed_partitions *state,
+                              sector_t offset, sector_t size, int origin)
 {
 #ifdef CONFIG_SOLARIS_X86_PARTITION
         Sector sect;
@@ -208,7 +206,7 @@ parse_solaris_x86(struct parsed_partitions *state, struct block_device *bdev,
         int i;
         short max_nparts;
 
-        v = (struct solaris_x86_vtoc *)read_dev_sector(bdev, offset+1, &sect);
+        v = read_part_sector(state, offset + 1, &sect);
         if (!v)
                 return;
         if (le32_to_cpu(v->v_sanity) != SOLARIS_X86_VTOC_SANE) {
@@ -245,16 +243,15 @@ parse_solaris_x86(struct parsed_partitions *state, struct block_device *bdev,
  * Create devices for BSD partitions listed in a disklabel, under a
  * dos-like partition. See parse_extended() for more information.
  */
-static void
-parse_bsd(struct parsed_partitions *state, struct block_device *bdev,
-                sector_t offset, sector_t size, int origin, char *flavour,
-                int max_partitions)
+static void parse_bsd(struct parsed_partitions *state,
+                      sector_t offset, sector_t size, int origin, char *flavour,
+                      int max_partitions)
 {
         Sector sect;
         struct bsd_disklabel *l;
         struct bsd_partition *p;
 
-        l = (struct bsd_disklabel *)read_dev_sector(bdev, offset+1, &sect);
+        l = read_part_sector(state, offset + 1, &sect);
         if (!l)
                 return;
         if (le32_to_cpu(l->d_magic) != BSD_DISKMAGIC) {
@@ -291,33 +288,28 @@ parse_bsd(struct parsed_partitions *state, struct block_device *bdev,
 }
 #endif
 
-static void
-parse_freebsd(struct parsed_partitions *state, struct block_device *bdev,
-                sector_t offset, sector_t size, int origin)
+static void parse_freebsd(struct parsed_partitions *state,
+                          sector_t offset, sector_t size, int origin)
 {
 #ifdef CONFIG_BSD_DISKLABEL
-        parse_bsd(state, bdev, offset, size, origin,
-                        "bsd", BSD_MAXPARTITIONS);
+        parse_bsd(state, offset, size, origin, "bsd", BSD_MAXPARTITIONS);
 #endif
 }
 
-static void
-parse_netbsd(struct parsed_partitions *state, struct block_device *bdev,
-                sector_t offset, sector_t size, int origin)
+static void parse_netbsd(struct parsed_partitions *state,
+                         sector_t offset, sector_t size, int origin)
 {
 #ifdef CONFIG_BSD_DISKLABEL
-        parse_bsd(state, bdev, offset, size, origin,
-                        "netbsd", BSD_MAXPARTITIONS);
+        parse_bsd(state, offset, size, origin, "netbsd", BSD_MAXPARTITIONS);
 #endif
 }
 
-static void
-parse_openbsd(struct parsed_partitions *state, struct block_device *bdev,
-                sector_t offset, sector_t size, int origin)
+static void parse_openbsd(struct parsed_partitions *state,
+                          sector_t offset, sector_t size, int origin)
 {
 #ifdef CONFIG_BSD_DISKLABEL
-        parse_bsd(state, bdev, offset, size, origin,
-                        "openbsd", OPENBSD_MAXPARTITIONS);
+        parse_bsd(state, offset, size, origin, "openbsd",
+                  OPENBSD_MAXPARTITIONS);
 #endif
 }
 
@@ -325,16 +317,15 @@ parse_openbsd(struct parsed_partitions *state, struct block_device *bdev,
  * Create devices for Unixware partitions listed in a disklabel, under a
  * dos-like partition. See parse_extended() for more information.
  */
-static void
-parse_unixware(struct parsed_partitions *state, struct block_device *bdev,
-                sector_t offset, sector_t size, int origin)
+static void parse_unixware(struct parsed_partitions *state,
+                           sector_t offset, sector_t size, int origin)
 {
 #ifdef CONFIG_UNIXWARE_DISKLABEL
         Sector sect;
         struct unixware_disklabel *l;
         struct unixware_slice *p;
 
-        l = (struct unixware_disklabel *)read_dev_sector(bdev, offset+29, &sect);
+        l = read_part_sector(state, offset + 29, &sect);
         if (!l)
                 return;
         if (le32_to_cpu(l->d_magic) != UNIXWARE_DISKMAGIC ||
@@ -365,9 +356,8 @@ parse_unixware(struct parsed_partitions *state, struct block_device *bdev,
  * Anand Krishnamurthy <anandk@wiproge.med.ge.com>
  * Rajeev V. Pillai    <rajeevvp@yahoo.com>
  */
-static void
-parse_minix(struct parsed_partitions *state, struct block_device *bdev,
-                sector_t offset, sector_t size, int origin)
+static void parse_minix(struct parsed_partitions *state,
+                        sector_t offset, sector_t size, int origin)
 {
 #ifdef CONFIG_MINIX_SUBPARTITION
         Sector sect;
@@ -375,7 +365,7 @@ parse_minix(struct parsed_partitions *state, struct block_device *bdev,
         struct partition *p;
         int i;
 
-        data = read_dev_sector(bdev, offset, &sect);
+        data = read_part_sector(state, offset, &sect);
         if (!data)
                 return;
 
@@ -404,8 +394,7 @@ parse_minix(struct parsed_partitions *state, struct block_device *bdev,
 
 static struct {
         unsigned char id;
-        void (*parse)(struct parsed_partitions *, struct block_device *,
-                        sector_t, sector_t, int);
+        void (*parse)(struct parsed_partitions *, sector_t, sector_t, int);
 } subtypes[] = {
         {FREEBSD_PARTITION, parse_freebsd},
         {NETBSD_PARTITION, parse_netbsd},
@@ -417,16 +406,16 @@ static struct {
         {0, NULL},
 };
  
-int msdos_partition(struct parsed_partitions *state, struct block_device *bdev)
+int msdos_partition(struct parsed_partitions *state)
 {
-        sector_t sector_size = bdev_logical_block_size(bdev) / 512;
+        sector_t sector_size = bdev_logical_block_size(state->bdev) / 512;
         Sector sect;
         unsigned char *data;
         struct partition *p;
         struct fat_boot_sector *fb;
         int slot;
 
-        data = read_dev_sector(bdev, 0, &sect);
+        data = read_part_sector(state, 0, &sect);
         if (!data)
                 return -1;
         if (!msdos_magic_present(data + 510)) {
@@ -434,7 +423,7 @@ int msdos_partition(struct parsed_partitions *state, struct block_device *bdev)
                 return 0;
         }
 
-        if (aix_magic_present(data, bdev)) {
+        if (aix_magic_present(state, data)) {
                 put_dev_sector(sect);
                 printk( " [AIX]");
                 return 0;
@@ -503,7 +492,7 @@ int msdos_partition(struct parsed_partitions *state, struct block_device *bdev)
                         put_partition(state, slot, start, n);
 
                         printk(" <");
-                        parse_extended(state, bdev, start, size);
+                        parse_extended(state, start, size);
                         printk(" >");
                         continue;
                 }
@@ -532,8 +521,8 @@ int msdos_partition(struct parsed_partitions *state, struct block_device *bdev)
 
                 if (!subtypes[n].parse)
                         continue;
-                subtypes[n].parse(state, bdev, start_sect(p)*sector_size,
-                                                nr_sects(p)*sector_size, slot);
+                subtypes[n].parse(state, start_sect(p) * sector_size,
+                                  nr_sects(p) * sector_size, slot);
         }
         put_dev_sector(sect);
         return 1;
diff --git a/fs/partitions/msdos.h b/fs/partitions/msdos.h
index 01e5e0b6902d..38c781c490b3 100644
--- a/fs/partitions/msdos.h
+++ b/fs/partitions/msdos.h
@@ -4,5 +4,5 @@
 
 #define MSDOS_LABEL_MAGIC               0xAA55
 
-int msdos_partition(struct parsed_partitions *state, struct block_device *bdev);
+int msdos_partition(struct parsed_partitions *state);
 
diff --git a/fs/partitions/osf.c b/fs/partitions/osf.c
index c05c17bc5df3..fc22b85d436a 100644
--- a/fs/partitions/osf.c
+++ b/fs/partitions/osf.c
@@ -10,7 +10,7 @@
 #include "check.h"
 #include "osf.h"
 
-int osf_partition(struct parsed_partitions *state, struct block_device *bdev)
+int osf_partition(struct parsed_partitions *state)
 {
         int i;
         int slot = 1;
@@ -49,7 +49,7 @@ int osf_partition(struct parsed_partitions *state, struct block_device *bdev)
         } * label;
         struct d_partition * partition;
 
-        data = read_dev_sector(bdev, 0, &sect);
+        data = read_part_sector(state, 0, &sect);
         if (!data)
                 return -1;
 
diff --git a/fs/partitions/osf.h b/fs/partitions/osf.h
index 427b8eab314b..20ed2315ec16 100644
--- a/fs/partitions/osf.h
+++ b/fs/partitions/osf.h
@@ -4,4 +4,4 @@
 
 #define DISKLABELMAGIC (0x82564557UL)
 
-int osf_partition(struct parsed_partitions *state, struct block_device *bdev);
+int osf_partition(struct parsed_partitions *state);
diff --git a/fs/partitions/sgi.c b/fs/partitions/sgi.c
index ed5ac83fe83a..43b1df9aa16c 100644
--- a/fs/partitions/sgi.c
+++ b/fs/partitions/sgi.c
@@ -27,7 +27,7 @@ struct sgi_disklabel {
         __be32 _unused1;                        /* Padding */
 };
 
-int sgi_partition(struct parsed_partitions *state, struct block_device *bdev)
+int sgi_partition(struct parsed_partitions *state)
 {
         int i, csum;
         __be32 magic;
@@ -39,7 +39,7 @@ int sgi_partition(struct parsed_partitions *state, struct block_device *bdev)
         struct sgi_partition *p;
         char b[BDEVNAME_SIZE];
 
-        label = (struct sgi_disklabel *) read_dev_sector(bdev, 0, &sect);
+        label = read_part_sector(state, 0, &sect);
         if (!label)
                 return -1;
         p = &label->partitions[0];
@@ -57,7 +57,7 @@ int sgi_partition(struct parsed_partitions *state, struct block_device *bdev)
         }
         if(csum) {
                 printk(KERN_WARNING "Dev %s SGI disklabel: csum bad, label corrupted\n",
-                       bdevname(bdev, b));
+                       bdevname(state->bdev, b));
                 put_dev_sector(sect);
                 return 0;
         }
diff --git a/fs/partitions/sgi.h b/fs/partitions/sgi.h
index 5d5595c09928..b9553ebdd5a9 100644
--- a/fs/partitions/sgi.h
+++ b/fs/partitions/sgi.h
@@ -2,7 +2,7 @@
  *  fs/partitions/sgi.h
  */
 
-extern int sgi_partition(struct parsed_partitions *state, struct block_device *bdev);
+extern int sgi_partition(struct parsed_partitions *state);
 
 #define SGI_LABEL_MAGIC 0x0be5a941
 
diff --git a/fs/partitions/sun.c b/fs/partitions/sun.c
index c95e6a62c01d..a32660e25f7f 100644
--- a/fs/partitions/sun.c
+++ b/fs/partitions/sun.c
@@ -10,7 +10,7 @@
 #include "check.h"
 #include "sun.h"
 
-int sun_partition(struct parsed_partitions *state, struct block_device *bdev)
+int sun_partition(struct parsed_partitions *state)
 {
         int i;
         __be16 csum;
@@ -61,7 +61,7 @@ int sun_partition(struct parsed_partitions *state, struct block_device *bdev)
         int use_vtoc;
         int nparts;
 
-        label = (struct sun_disklabel *)read_dev_sector(bdev, 0, &sect);
+        label = read_part_sector(state, 0, &sect);
         if (!label)
                 return -1;
 
@@ -78,7 +78,7 @@ int sun_partition(struct parsed_partitions *state, struct block_device *bdev)
                 csum ^= *ush--;
         if (csum) {
                 printk("Dev %s Sun disklabel: Csum bad, label corrupted\n",
-                       bdevname(bdev, b));
+                       bdevname(state->bdev, b));
                 put_dev_sector(sect);
                 return 0;
         }
diff --git a/fs/partitions/sun.h b/fs/partitions/sun.h
index 7f864d1f86d4..2424baa8319f 100644
--- a/fs/partitions/sun.h
+++ b/fs/partitions/sun.h
@@ -5,4 +5,4 @@
 #define SUN_LABEL_MAGIC          0xDABE
 #define SUN_VTOC_SANITY          0x600DDEEE
 
-int sun_partition(struct parsed_partitions *state, struct block_device *bdev);
+int sun_partition(struct parsed_partitions *state);
diff --git a/fs/partitions/sysv68.c b/fs/partitions/sysv68.c
index 4eba27b78643..9030c864428e 100644
--- a/fs/partitions/sysv68.c
+++ b/fs/partitions/sysv68.c
@@ -46,7 +46,7 @@ struct slice {
 };
 
 
-int sysv68_partition(struct parsed_partitions *state, struct block_device *bdev)
+int sysv68_partition(struct parsed_partitions *state)
 {
         int i, slices;
         int slot = 1;
@@ -55,7 +55,7 @@ int sysv68_partition(struct parsed_partitions *state, struct block_device *bdev)
         struct dkblk0 *b;
         struct slice *slice;
 
-        data = read_dev_sector(bdev, 0, &sect);
+        data = read_part_sector(state, 0, &sect);
         if (!data)
                 return -1;
 
@@ -68,7 +68,7 @@ int sysv68_partition(struct parsed_partitions *state, struct block_device *bdev)
         i = be32_to_cpu(b->dk_ios.ios_slcblk);
         put_dev_sector(sect);
 
-        data = read_dev_sector(bdev, i, &sect);
+        data = read_part_sector(state, i, &sect);
         if (!data)
                 return -1;
 
diff --git a/fs/partitions/sysv68.h b/fs/partitions/sysv68.h
index fa733f68431b..bf2f5ffa97ac 100644
--- a/fs/partitions/sysv68.h
+++ b/fs/partitions/sysv68.h
@@ -1 +1 @@
-extern int sysv68_partition(struct parsed_partitions *state, struct block_device *bdev);
+extern int sysv68_partition(struct parsed_partitions *state);
diff --git a/fs/partitions/ultrix.c b/fs/partitions/ultrix.c
index ec852c11dce4..db9eef260364 100644
--- a/fs/partitions/ultrix.c
+++ b/fs/partitions/ultrix.c
@@ -9,7 +9,7 @@
 #include "check.h"
 #include "ultrix.h"
 
-int ultrix_partition(struct parsed_partitions *state, struct block_device *bdev)
+int ultrix_partition(struct parsed_partitions *state)
 {
         int i;
         Sector sect;
@@ -26,7 +26,7 @@ int ultrix_partition(struct parsed_partitions *state, struct block_device *bdev)
 #define PT_MAGIC        0x032957        /* Partition magic number */
 #define PT_VALID        1               /* Indicates if struct is valid */
 
-        data = read_dev_sector(bdev, (16384 - sizeof(*label))/512, &sect);
+        data = read_part_sector(state, (16384 - sizeof(*label))/512, &sect);
         if (!data)
                 return -1;
         
diff --git a/fs/partitions/ultrix.h b/fs/partitions/ultrix.h
index a74bf8e2d370..a3cc00b2bded 100644
--- a/fs/partitions/ultrix.h
+++ b/fs/partitions/ultrix.h
@@ -2,4 +2,4 @@
  *  fs/partitions/ultrix.h
  */
 
-int ultrix_partition(struct parsed_partitions *state, struct block_device *bdev);
+int ultrix_partition(struct parsed_partitions *state);
diff --git a/fs/pipe.c b/fs/pipe.c
index 37ba29ff3158..d79872eba09a 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/fs.h>
+#include <linux/log2.h>
 #include <linux/mount.h>
 #include <linux/pipe_fs_i.h>
 #include <linux/uio.h>
@@ -18,11 +19,18 @@
 #include <linux/pagemap.h>
 #include <linux/audit.h>
 #include <linux/syscalls.h>
+#include <linux/fcntl.h>
 
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
 
 /*
+ * The max size that a non-root user is allowed to grow the pipe. Can
+ * be set by root in /proc/sys/fs/pipe-max-pages
+ */
+unsigned int pipe_max_pages = PIPE_DEF_BUFFERS * 16;
+
+/*
  * We use a start+len construction, which provides full use of the 
  * allocated memory.
  * -- Florian Coosmann (FGC)
@@ -390,7 +398,7 @@ redo:
                         if (!buf->len) {
                                 buf->ops = NULL;
                                 ops->release(pipe, buf);
-                                curbuf = (curbuf + 1) & (PIPE_BUFFERS-1);
+                                curbuf = (curbuf + 1) & (pipe->buffers - 1);
                                 pipe->curbuf = curbuf;
                                 pipe->nrbufs = --bufs;
                                 do_wakeup = 1;
@@ -472,7 +480,7 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov,
         chars = total_len & (PAGE_SIZE-1); /* size of the last buffer */
         if (pipe->nrbufs && chars != 0) {
                 int lastbuf = (pipe->curbuf + pipe->nrbufs - 1) &
-                                                        (PIPE_BUFFERS-1);
+                                                        (pipe->buffers - 1);
                 struct pipe_buffer *buf = pipe->bufs + lastbuf;
                 const struct pipe_buf_operations *ops = buf->ops;
                 int offset = buf->offset + buf->len;
@@ -518,8 +526,8 @@ redo1:
                         break;
                 }
                 bufs = pipe->nrbufs;
-                if (bufs < PIPE_BUFFERS) {
-                        int newbuf = (pipe->curbuf + bufs) & (PIPE_BUFFERS-1);
+                if (bufs < pipe->buffers) {
+                        int newbuf = (pipe->curbuf + bufs) & (pipe->buffers-1);
                         struct pipe_buffer *buf = pipe->bufs + newbuf;
                         struct page *page = pipe->tmp_page;
                         char *src;
@@ -580,7 +588,7 @@ redo2:
                         if (!total_len)
                                 break;
                 }
-                if (bufs < PIPE_BUFFERS)
+                if (bufs < pipe->buffers)
                         continue;
                 if (filp->f_flags & O_NONBLOCK) {
                         if (!ret)
@@ -640,7 +648,7 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
                         nrbufs = pipe->nrbufs;
                         while (--nrbufs >= 0) {
                                 count += pipe->bufs[buf].len;
-                                buf = (buf+1) & (PIPE_BUFFERS-1);
+                                buf = (buf+1) & (pipe->buffers - 1);
                         }
                         mutex_unlock(&inode->i_mutex);
 
@@ -671,7 +679,7 @@ pipe_poll(struct file *filp, poll_table *wait)
         }
 
         if (filp->f_mode & FMODE_WRITE) {
-                mask |= (nrbufs < PIPE_BUFFERS) ? POLLOUT | POLLWRNORM : 0;
+                mask |= (nrbufs < pipe->buffers) ? POLLOUT | POLLWRNORM : 0;
                 /*
                  * Most Unices do not set POLLERR for FIFOs but on Linux they
                  * behave exactly like pipes for poll().
@@ -877,25 +885,32 @@ struct pipe_inode_info * alloc_pipe_info(struct inode *inode)
 
         pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL);
         if (pipe) {
-                init_waitqueue_head(&pipe->wait);
-                pipe->r_counter = pipe->w_counter = 1;
-                pipe->inode = inode;
+                pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * PIPE_DEF_BUFFERS, GFP_KERNEL);
+                if (pipe->bufs) {
+                        init_waitqueue_head(&pipe->wait);
+                        pipe->r_counter = pipe->w_counter = 1;
+                        pipe->inode = inode;
+                        pipe->buffers = PIPE_DEF_BUFFERS;
+                        return pipe;
+                }
+                kfree(pipe);
         }
 
-        return pipe;
+        return NULL;
 }
 
 void __free_pipe_info(struct pipe_inode_info *pipe)
 {
         int i;
 
-        for (i = 0; i < PIPE_BUFFERS; i++) {
+        for (i = 0; i < pipe->buffers; i++) {
                 struct pipe_buffer *buf = pipe->bufs + i;
                 if (buf->ops)
                         buf->ops->release(pipe, buf);
         }
         if (pipe->tmp_page)
                 __free_page(pipe->tmp_page);
+        kfree(pipe->bufs);
         kfree(pipe);
 }
 
@@ -1094,6 +1109,89 @@ SYSCALL_DEFINE1(pipe, int __user *, fildes)
 }
 
 /*
+ * Allocate a new array of pipe buffers and copy the info over. Returns the
+ * pipe size if successful, or return -ERROR on error.
+ */
+static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
+{
+        struct pipe_buffer *bufs;
+
+        /*
+         * Must be a power-of-2 currently
+         */
+        if (!is_power_of_2(arg))
+                return -EINVAL;
+
+        /*
+         * We can shrink the pipe, if arg >= pipe->nrbufs. Since we don't
+         * expect a lot of shrink+grow operations, just free and allocate
+         * again like we would do for growing. If the pipe currently
+         * contains more buffers than arg, then return busy.
+         */
+        if (arg < pipe->nrbufs)
+                return -EBUSY;
+
+        bufs = kcalloc(arg, sizeof(struct pipe_buffer), GFP_KERNEL);
+        if (unlikely(!bufs))
+                return -ENOMEM;
+
+        /*
+         * The pipe array wraps around, so just start the new one at zero
+         * and adjust the indexes.
+         */
+        if (pipe->nrbufs) {
+                const unsigned int tail = pipe->nrbufs & (pipe->buffers - 1);
+                const unsigned int head = pipe->nrbufs - tail;
+
+                if (head)
+                        memcpy(bufs, pipe->bufs + pipe->curbuf, head * sizeof(struct pipe_buffer));
+                if (tail)
+                        memcpy(bufs + head, pipe->bufs + pipe->curbuf, tail * sizeof(struct pipe_buffer));
+        }
+
+        pipe->curbuf = 0;
+        kfree(pipe->bufs);
+        pipe->bufs = bufs;
+        pipe->buffers = arg;
+        return arg;
+}
+
+long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+        struct pipe_inode_info *pipe;
+        long ret;
+
+        pipe = file->f_path.dentry->d_inode->i_pipe;
+        if (!pipe)
+                return -EBADF;
+
+        mutex_lock(&pipe->inode->i_mutex);
+
+        switch (cmd) {
+        case F_SETPIPE_SZ:
+                if (!capable(CAP_SYS_ADMIN) && arg > pipe_max_pages)
+                        return -EINVAL;
+                /*
+                 * The pipe needs to be at least 2 pages large to
+                 * guarantee POSIX behaviour.
+                 */
+                if (arg < 2)
+                        return -EINVAL;
+                ret = pipe_set_size(pipe, arg);
+                break;
+        case F_GETPIPE_SZ:
+                ret = pipe->buffers;
+                break;
+        default:
+                ret = -EINVAL;
+                break;
+        }
+
+        mutex_unlock(&pipe->inode->i_mutex);
+        return ret;
+}
+
+/*
  * pipefs should _never_ be mounted by userland - too much of security hassle,
  * no real gain from having the whole whorehouse mounted. So we don't need
  * any operations on the root directory. However, we need a non-trivial
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 1d9c12714c5c..9977df9f3a54 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -147,7 +147,8 @@ static int reiserfs_sync_file(struct file *filp,
         barrier_done = reiserfs_commit_for_inode(inode);
         reiserfs_write_unlock(inode->i_sb);
         if (barrier_done != 1 && reiserfs_barrier_flush(inode->i_sb))
-                blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
+                blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL, 
+                        BLKDEV_IFL_WAIT);
         if (barrier_done < 0)
                 return barrier_done;
         return (err < 0) ? -EIO : 0;
diff --git a/fs/splice.c b/fs/splice.c
index 9313b6124a2e..ac22b00d86c3 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -193,8 +193,8 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
                         break;
                 }
 
-                if (pipe->nrbufs < PIPE_BUFFERS) {
-                        int newbuf = (pipe->curbuf + pipe->nrbufs) & (PIPE_BUFFERS - 1);
+                if (pipe->nrbufs < pipe->buffers) {
+                        int newbuf = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1);
                         struct pipe_buffer *buf = pipe->bufs + newbuf;
 
                         buf->page = spd->pages[page_nr];
@@ -214,7 +214,7 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 
                         if (!--spd->nr_pages)
                                 break;
-                        if (pipe->nrbufs < PIPE_BUFFERS)
+                        if (pipe->nrbufs < pipe->buffers)
                                 continue;
 
                         break;
@@ -265,6 +265,36 @@ static void spd_release_page(struct splice_pipe_desc *spd, unsigned int i)
         page_cache_release(spd->pages[i]);
 }
 
+/*
+ * Check if we need to grow the arrays holding pages and partial page
+ * descriptions.
+ */
+int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd)
+{
+        if (pipe->buffers <= PIPE_DEF_BUFFERS)
+                return 0;
+
+        spd->pages = kmalloc(pipe->buffers * sizeof(struct page *), GFP_KERNEL);
+        spd->partial = kmalloc(pipe->buffers * sizeof(struct partial_page), GFP_KERNEL);
+
+        if (spd->pages && spd->partial)
+                return 0;
+
+        kfree(spd->pages);
+        kfree(spd->partial);
+        return -ENOMEM;
+}
+
+void splice_shrink_spd(struct pipe_inode_info *pipe,
+                       struct splice_pipe_desc *spd)
+{
+        if (pipe->buffers <= PIPE_DEF_BUFFERS)
+                return;
+
+        kfree(spd->pages);
+        kfree(spd->partial);
+}
+
 static int
 __generic_file_splice_read(struct file *in, loff_t *ppos,
                            struct pipe_inode_info *pipe, size_t len,
@@ -272,8 +302,8 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
 {
         struct address_space *mapping = in->f_mapping;
         unsigned int loff, nr_pages, req_pages;
-        struct page *pages[PIPE_BUFFERS];
-        struct partial_page partial[PIPE_BUFFERS];
+        struct page *pages[PIPE_DEF_BUFFERS];
+        struct partial_page partial[PIPE_DEF_BUFFERS];
         struct page *page;
         pgoff_t index, end_index;
         loff_t isize;
@@ -286,15 +316,18 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
                 .spd_release = spd_release_page,
         };
 
+        if (splice_grow_spd(pipe, &spd))
+                return -ENOMEM;
+
         index = *ppos >> PAGE_CACHE_SHIFT;
         loff = *ppos & ~PAGE_CACHE_MASK;
         req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-        nr_pages = min(req_pages, (unsigned)PIPE_BUFFERS);
+        nr_pages = min(req_pages, pipe->buffers);
 
         /*
          * Lookup the (hopefully) full range of pages we need.
          */
-        spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, pages);
+        spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, spd.pages);
         index += spd.nr_pages;
 
         /*
@@ -335,7 +368,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
                         unlock_page(page);
                 }
 
-                pages[spd.nr_pages++] = page;
+                spd.pages[spd.nr_pages++] = page;
                 index++;
         }
 
@@ -356,7 +389,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
                  * this_len is the max we'll use from this page
                  */
                 this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff);
-                page = pages[page_nr];
+                page = spd.pages[page_nr];
 
                 if (PageReadahead(page))
                         page_cache_async_readahead(mapping, &in->f_ra, in,
@@ -393,8 +426,8 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
                                         error = -ENOMEM;
                                         break;
                                 }
-                                page_cache_release(pages[page_nr]);
-                                pages[page_nr] = page;
+                                page_cache_release(spd.pages[page_nr]);
+                                spd.pages[page_nr] = page;
                         }
                         /*
                          * page was already under io and is now done, great
@@ -451,8 +484,8 @@ fill_it:
                         len = this_len;
                 }
 
-                partial[page_nr].offset = loff;
-                partial[page_nr].len = this_len;
+                spd.partial[page_nr].offset = loff;
+                spd.partial[page_nr].len = this_len;
                 len -= this_len;
                 loff = 0;
                 spd.nr_pages++;
@@ -464,12 +497,13 @@ fill_it:
          * we got, 'nr_pages' is how many pages are in the map.
          */
         while (page_nr < nr_pages)
-                page_cache_release(pages[page_nr++]);
+                page_cache_release(spd.pages[page_nr++]);
         in->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
 
         if (spd.nr_pages)
-                return splice_to_pipe(pipe, &spd);
+                error = splice_to_pipe(pipe, &spd);
 
+        splice_shrink_spd(pipe, &spd);
         return error;
 }
 
@@ -560,9 +594,9 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
         unsigned int nr_pages;
         unsigned int nr_freed;
         size_t offset;
-        struct page *pages[PIPE_BUFFERS];
-        struct partial_page partial[PIPE_BUFFERS];
-        struct iovec vec[PIPE_BUFFERS];
+        struct page *pages[PIPE_DEF_BUFFERS];
+        struct partial_page partial[PIPE_DEF_BUFFERS];
+        struct iovec *vec, __vec[PIPE_DEF_BUFFERS];
         pgoff_t index;
         ssize_t res;
         size_t this_len;
@@ -576,11 +610,22 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
                 .spd_release = spd_release_page,
         };
 
+        if (splice_grow_spd(pipe, &spd))
+                return -ENOMEM;
+
+        res = -ENOMEM;
+        vec = __vec;
+        if (pipe->buffers > PIPE_DEF_BUFFERS) {
+                vec = kmalloc(pipe->buffers * sizeof(struct iovec), GFP_KERNEL);
+                if (!vec)
+                        goto shrink_ret;
+        }
+
         index = *ppos >> PAGE_CACHE_SHIFT;
         offset = *ppos & ~PAGE_CACHE_MASK;
         nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 
-        for (i = 0; i < nr_pages && i < PIPE_BUFFERS && len; i++) {
+        for (i = 0; i < nr_pages && i < pipe->buffers && len; i++) {
                 struct page *page;
 
                 page = alloc_page(GFP_USER);
@@ -591,7 +636,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
                 this_len = min_t(size_t, len, PAGE_CACHE_SIZE - offset);
                 vec[i].iov_base = (void __user *) page_address(page);
                 vec[i].iov_len = this_len;
-                pages[i] = page;
+                spd.pages[i] = page;
                 spd.nr_pages++;
                 len -= this_len;
                 offset = 0;
@@ -610,11 +655,11 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
         nr_freed = 0;
         for (i = 0; i < spd.nr_pages; i++) {
                 this_len = min_t(size_t, vec[i].iov_len, res);
-                partial[i].offset = 0;
-                partial[i].len = this_len;
+                spd.partial[i].offset = 0;
+                spd.partial[i].len = this_len;
                 if (!this_len) {
-                        __free_page(pages[i]);
-                        pages[i] = NULL;
+                        __free_page(spd.pages[i]);
+                        spd.pages[i] = NULL;
                         nr_freed++;
                 }
                 res -= this_len;
@@ -625,13 +670,18 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
         if (res > 0)
                 *ppos += res;
 
+shrink_ret:
+        if (vec != __vec)
+                kfree(vec);
+        splice_shrink_spd(pipe, &spd);
         return res;
 
 err:
         for (i = 0; i < spd.nr_pages; i++)
-                __free_page(pages[i]);
+                __free_page(spd.pages[i]);
 
-        return error;
+        res = error;
+        goto shrink_ret;
 }
 EXPORT_SYMBOL(default_file_splice_read);
 
@@ -784,7 +834,7 @@ int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd,
                 if (!buf->len) {
                         buf->ops = NULL;
                         ops->release(pipe, buf);
-                        pipe->curbuf = (pipe->curbuf + 1) & (PIPE_BUFFERS - 1);
+                        pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1);
                         pipe->nrbufs--;
                         if (pipe->inode)
                                 sd->need_wakeup = true;
@@ -1211,7 +1261,7 @@ out_release:
          * If we did an incomplete transfer we must release
          * the pipe buffers in question:
          */
-        for (i = 0; i < PIPE_BUFFERS; i++) {
+        for (i = 0; i < pipe->buffers; i++) {
                 struct pipe_buffer *buf = pipe->bufs + i;
 
                 if (buf->ops) {
@@ -1371,7 +1421,8 @@ static long do_splice(struct file *in, loff_t __user *off_in,
  */
 static int get_iovec_page_array(const struct iovec __user *iov,
                                 unsigned int nr_vecs, struct page **pages,
-                                struct partial_page *partial, int aligned)
+                                struct partial_page *partial, int aligned,
+                                unsigned int pipe_buffers)
 {
         int buffers = 0, error = 0;
 
@@ -1414,8 +1465,8 @@ static int get_iovec_page_array(const struct iovec __user *iov,
                         break;
 
                 npages = (off + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
-                if (npages > PIPE_BUFFERS - buffers)
-                        npages = PIPE_BUFFERS - buffers;
+                if (npages > pipe_buffers - buffers)
+                        npages = pipe_buffers - buffers;
 
                 error = get_user_pages_fast((unsigned long)base, npages,
                                         0, &pages[buffers]);
@@ -1450,7 +1501,7 @@ static int get_iovec_page_array(const struct iovec __user *iov,
                  * or if we mapped the max number of pages that we have
                  * room for.
                  */
-                if (error < npages || buffers == PIPE_BUFFERS)
+                if (error < npages || buffers == pipe_buffers)
                         break;
 
                 nr_vecs--;
@@ -1593,8 +1644,8 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov,
                              unsigned long nr_segs, unsigned int flags)
 {
         struct pipe_inode_info *pipe;
-        struct page *pages[PIPE_BUFFERS];
-        struct partial_page partial[PIPE_BUFFERS];
+        struct page *pages[PIPE_DEF_BUFFERS];
+        struct partial_page partial[PIPE_DEF_BUFFERS];
         struct splice_pipe_desc spd = {
                 .pages = pages,
                 .partial = partial,
@@ -1602,17 +1653,25 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov,
                 .ops = &user_page_pipe_buf_ops,
                 .spd_release = spd_release_page,
         };
+        long ret;
 
         pipe = pipe_info(file->f_path.dentry->d_inode);
         if (!pipe)
                 return -EBADF;
 
-        spd.nr_pages = get_iovec_page_array(iov, nr_segs, pages, partial,
-                                            flags & SPLICE_F_GIFT);
+        if (splice_grow_spd(pipe, &spd))
+                return -ENOMEM;
+
+        spd.nr_pages = get_iovec_page_array(iov, nr_segs, spd.pages,
+                                            spd.partial, flags & SPLICE_F_GIFT,
+                                            pipe->buffers);
         if (spd.nr_pages <= 0)
-                return spd.nr_pages;
+                ret = spd.nr_pages;
+        else
+                ret = splice_to_pipe(pipe, &spd);
 
-        return splice_to_pipe(pipe, &spd);
+        splice_shrink_spd(pipe, &spd);
+        return ret;
 }
 
 /*
@@ -1738,13 +1797,13 @@ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
          * Check ->nrbufs without the inode lock first. This function
          * is speculative anyways, so missing one is ok.
          */
-        if (pipe->nrbufs < PIPE_BUFFERS)
+        if (pipe->nrbufs < pipe->buffers)
                 return 0;
 
         ret = 0;
         pipe_lock(pipe);
 
-        while (pipe->nrbufs >= PIPE_BUFFERS) {
+        while (pipe->nrbufs >= pipe->buffers) {
                 if (!pipe->readers) {
                         send_sig(SIGPIPE, current, 0);
                         ret = -EPIPE;
@@ -1810,7 +1869,7 @@ retry:
                  * Cannot make any progress, because either the input
                  * pipe is empty or the output pipe is full.
                  */
-                if (!ipipe->nrbufs || opipe->nrbufs >= PIPE_BUFFERS) {
+                if (!ipipe->nrbufs || opipe->nrbufs >= opipe->buffers) {
                         /* Already processed some buffers, break */
                         if (ret)
                                 break;
@@ -1831,7 +1890,7 @@ retry:
                 }
 
                 ibuf = ipipe->bufs + ipipe->curbuf;
-                nbuf = (opipe->curbuf + opipe->nrbufs) % PIPE_BUFFERS;
+                nbuf = (opipe->curbuf + opipe->nrbufs) & (opipe->buffers - 1);
                 obuf = opipe->bufs + nbuf;
 
                 if (len >= ibuf->len) {
@@ -1841,7 +1900,7 @@ retry:
                         *obuf = *ibuf;
                         ibuf->ops = NULL;
                         opipe->nrbufs++;
-                        ipipe->curbuf = (ipipe->curbuf + 1) % PIPE_BUFFERS;
+                        ipipe->curbuf = (ipipe->curbuf + 1) & (ipipe->buffers - 1);
                         ipipe->nrbufs--;
                         input_wakeup = true;
                 } else {
@@ -1914,11 +1973,11 @@ static int link_pipe(struct pipe_inode_info *ipipe,
                  * If we have iterated all input buffers or ran out of
                  * output room, break.
                  */
-                if (i >= ipipe->nrbufs || opipe->nrbufs >= PIPE_BUFFERS)
+                if (i >= ipipe->nrbufs || opipe->nrbufs >= opipe->buffers)
                         break;
 
-                ibuf = ipipe->bufs + ((ipipe->curbuf + i) & (PIPE_BUFFERS - 1));
-                nbuf = (opipe->curbuf + opipe->nrbufs) & (PIPE_BUFFERS - 1);
+                ibuf = ipipe->bufs + ((ipipe->curbuf + i) & (ipipe->buffers-1));
+                nbuf = (opipe->curbuf + opipe->nrbufs) & (opipe->buffers - 1);
 
                 /*
                  * Get a reference to this pipe buffer,
diff --git a/fs/sync.c b/fs/sync.c
index 5a537ccd2e85..e8cbd415e50a 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -42,7 +42,7 @@ static int __sync_filesystem(struct super_block *sb, int wait)
         if (wait)
                 sync_inodes_sb(sb);
         else
-                writeback_inodes_sb(sb);
+                writeback_inodes_sb_locked(sb);
 
         if (sb->s_op->sync_fs)
                 sb->s_op->sync_fs(sb, wait);
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index e9002513e08f..f24dbe5efde3 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -725,7 +725,8 @@ void
 xfs_blkdev_issue_flush(
         xfs_buftarg_t           *buftarg)
 {
-        blkdev_issue_flush(buftarg->bt_bdev, NULL);
+        blkdev_issue_flush(buftarg->bt_bdev, GFP_KERNEL, NULL,
+                        BLKDEV_IFL_WAIT);
 }
 
 STATIC void