block: add partition resize function to blkpg ioctl

Add a new operation code (BLKPG_RESIZE_PARTITION) to the BLKPG ioctl that
allows altering the size of an existing partition, even if it is currently
in use.

This patch converts hd_struct->nr_sects into sequence counter because
One might extend a partition while IO is happening to it and update of
nr_sects can be non-atomic on 32bit machines with 64bit sector_t. This
can lead to issues like reading inconsistent size of a partition. Sequence
counter have been used so that readers don't have to take bdev mutex lock
as we call sector_in_part() very frequently.

Now all the access to hd_struct->nr_sects should happen using sequence
counter read/update helper functions part_nr_sects_read/part_nr_sects_write.
There is one exception though, set_capacity()/get_capacity(). I think
theoritically race should exist there too but this patch does not
modify set_capacity()/get_capacity() due to sheer number of call sites
and I am afraid that change might break something. I have left that as a
TODO item. We can handle it later if need be. This patch does not introduce
any new races as such w.r.t set_capacity()/get_capacity().

v2: Add CONFIG_LBDAF test to UP preempt case as suggested by Phillip.

Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Phillip Susi <psusi@ubuntu.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 15 insertions, 5 deletions

diff --git a/block/genhd.c b/block/genhd.c
index 9cf5583c90ff..cac7366957c3 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -154,7 +154,7 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
                 part = rcu_dereference(ptbl->part[piter->idx]);
                 if (!part)
                         continue;
-                if (!part->nr_sects &&
+                if (!part_nr_sects_read(part) &&
                     !(piter->flags & DISK_PITER_INCL_EMPTY) &&
                     !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
                       piter->idx == 0))
@@ -191,7 +191,7 @@ EXPORT_SYMBOL_GPL(disk_part_iter_exit);
 static inline int sector_in_part(struct hd_struct *part, sector_t sector)
 {
         return part->start_sect <= sector &&
-                sector < part->start_sect + part->nr_sects;
+                sector < part->start_sect + part_nr_sects_read(part);
 }
 
 /**
@@ -769,8 +769,8 @@ void __init printk_all_partitions(void)
 
                         printk("%s%s %10llu %s %s", is_part0 ? "" : "  ",
                                bdevt_str(part_devt(part), devt_buf),
-                               (unsigned long long)part->nr_sects >> 1,
-                               disk_name(disk, part->partno, name_buf),
+                               (unsigned long long)part_nr_sects_read(part) >> 1
+                               , disk_name(disk, part->partno, name_buf),
                                uuid_buf);
                         if (is_part0) {
                                 if (disk->driverfs_dev != NULL &&
@@ -862,7 +862,7 @@ static int show_partition(struct seq_file *seqf, void *v)
         while ((part = disk_part_iter_next(&piter)))
                 seq_printf(seqf, "%4d  %7d %10llu %s\n",
                            MAJOR(part_devt(part)), MINOR(part_devt(part)),
-                           (unsigned long long)part->nr_sects >> 1,
+                           (unsigned long long)part_nr_sects_read(part) >> 1,
                            disk_name(sgp, part->partno, buf));
         disk_part_iter_exit(&piter);
 
@@ -1268,6 +1268,16 @@ struct gendisk *alloc_disk_node(int minors, int node_id)
                 }
                 disk->part_tbl->part[0] = &disk->part0;
 
+                /*
+                 * set_capacity() and get_capacity() currently don't use
+                 * seqcounter to read/update the part0->nr_sects. Still init
+                 * the counter as we can read the sectors in IO submission
+                 * patch using seqence counters.
+                 *
+                 * TODO: Ideally set_capacity() and get_capacity() should be
+                 * converted to make use of bd_mutex and sequence counters.
+                 */
+                seqcount_init(&disk->part0.nr_sects_seq);
                 hd_ref_init(&disk->part0);
 
                 disk->minors = minors;