[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20120302185457.GD26315@redhat.com>
Date: Fri, 2 Mar 2012 13:54:57 -0500
From: Vivek Goyal <vgoyal@...hat.com>
To: axboe@...nel.dk
Cc: psusi@...ntu.com, psusi@....rr.com, maxim.patlasov@...il.com,
dm-devel@...hat.com, kzak@...hat.com, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 1/2] block: add partition resize function to blkpg ioctl
On Mon, Feb 20, 2012 at 10:28:49AM -0500, Vivek Goyal wrote:
> On Tue, Feb 14, 2012 at 03:39:50PM -0500, Vivek Goyal wrote:
> > 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.
> >
> > Signed-off-by: Vivek Goyal <vgoyal@...hat.com>
>
> Hi Jens,
>
> Can you please consider this patch for inclusion. One of our customer
> does want to be able to grow partitions without having to reboot
> the system.
Hi Jens,
Do you have concerns about this patch? If no, can you please consider
merging it.
Thanks
Vivek
>
> > ---
> > block/genhd.c | 20 ++++++++++++----
> > block/ioctl.c | 57 ++++++++++++++++++++++++++++++++++++++++++--
> > block/partition-generic.c | 4 ++-
> > include/linux/blkpg.h | 1 +
> > include/linux/genhd.h | 57 +++++++++++++++++++++++++++++++++++++++++++++
> > 5 files changed, 130 insertions(+), 9 deletions(-)
> >
> > diff --git a/block/genhd.c b/block/genhd.c
> > index 23b4f70..935e09b 100644
> > --- a/block/genhd.c
> > +++ b/block/genhd.c
> > @@ -153,7 +153,7 @@ 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))
> > @@ -190,7 +190,7 @@ 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);
> > }
> >
> > /**
> > @@ -765,8 +765,8 @@ 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), uuid);
> > + (unsigned long long)part_nr_sects_read(part) >> 1
> > + , disk_name(disk, part->partno, name_buf), uuid);
> > if (is_part0) {
> > if (disk->driverfs_dev != NULL &&
> > disk->driverfs_dev->driver != NULL)
> > @@ -857,7 +857,7 @@ 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);
> >
> > @@ -1263,6 +1263,16 @@ 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;
> > diff --git a/block/ioctl.c b/block/ioctl.c
> > index ba15b2d..ddbc649 100644
> > --- a/block/ioctl.c
> > +++ b/block/ioctl.c
> > @@ -13,7 +13,7 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
> > {
> > struct block_device *bdevp;
> > struct gendisk *disk;
> > - struct hd_struct *part;
> > + struct hd_struct *part, *lpart;
> > struct blkpg_ioctl_arg a;
> > struct blkpg_partition p;
> > struct disk_part_iter piter;
> > @@ -36,8 +36,8 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
> > case BLKPG_ADD_PARTITION:
> > start = p.start >> 9;
> > length = p.length >> 9;
> > - /* check for fit in a hd_struct */
> > - if (sizeof(sector_t) == sizeof(long) &&
> > + /* check for fit in a hd_struct */
> > + if (sizeof(sector_t) == sizeof(long) &&
> > sizeof(long long) > sizeof(long)) {
> > long pstart = start, plength = length;
> > if (pstart != start || plength != length
> > @@ -92,6 +92,57 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
> > bdput(bdevp);
> >
> > return 0;
> > + case BLKPG_RESIZE_PARTITION:
> > + start = p.start >> 9;
> > + /* new length of partition in bytes */
> > + length = p.length >> 9;
> > + /* check for fit in a hd_struct */
> > + if (sizeof(sector_t) == sizeof(long) &&
> > + sizeof(long long) > sizeof(long)) {
> > + long pstart = start, plength = length;
> > + if (pstart != start || plength != length
> > + || pstart < 0 || plength < 0)
> > + return -EINVAL;
> > + }
> > + part = disk_get_part(disk, partno);
> > + if (!part)
> > + return -ENXIO;
> > + bdevp = bdget(part_devt(part));
> > + if (!bdevp) {
> > + disk_put_part(part);
> > + return -ENOMEM;
> > + }
> > + mutex_lock(&bdevp->bd_mutex);
> > + mutex_lock_nested(&bdev->bd_mutex, 1);
> > + if (start != part->start_sect) {
> > + mutex_unlock(&bdevp->bd_mutex);
> > + mutex_unlock(&bdev->bd_mutex);
> > + disk_put_part(part);
> > + return -EINVAL;
> > + }
> > + /* overlap? */
> > + disk_part_iter_init(&piter, disk,
> > + DISK_PITER_INCL_EMPTY);
> > + while ((lpart = disk_part_iter_next(&piter))) {
> > + if (lpart->partno != partno &&
> > + !(start + length <= lpart->start_sect ||
> > + start >= lpart->start_sect + lpart->nr_sects)
> > + ) {
> > + disk_part_iter_exit(&piter);
> > + mutex_unlock(&bdevp->bd_mutex);
> > + mutex_unlock(&bdev->bd_mutex);
> > + disk_put_part(part);
> > + return -EBUSY;
> > + }
> > + }
> > + disk_part_iter_exit(&piter);
> > + part_nr_sects_write(part, (sector_t)length);
> > + i_size_write(bdevp->bd_inode, p.length);
> > + mutex_unlock(&bdevp->bd_mutex);
> > + mutex_unlock(&bdev->bd_mutex);
> > + bdput(bdevp);
> > + disk_put_part(part);
> > + return 0;
> > default:
> > return -EINVAL;
> > }
> > diff --git a/block/partition-generic.c b/block/partition-generic.c
> > index d06ec1c..363a6f6 100644
> > --- a/block/partition-generic.c
> > +++ b/block/partition-generic.c
> > @@ -84,7 +84,7 @@ ssize_t part_size_show(struct device *dev,
> > struct device_attribute *attr, char *buf)
> > {
> > struct hd_struct *p = dev_to_part(dev);
> > - return sprintf(buf, "%llu\n",(unsigned long long)p->nr_sects);
> > + return sprintf(buf, "%llu\n",(unsigned long long)part_nr_sects_read(p));
> > }
> >
> > static ssize_t part_ro_show(struct device *dev,
> > @@ -294,6 +294,8 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
> > err = -ENOMEM;
> > goto out_free;
> > }
> > +
> > + seqcount_init(&p->nr_sects_seq);
> > pdev = part_to_dev(p);
> >
> > p->start_sect = start;
> > diff --git a/include/linux/blkpg.h b/include/linux/blkpg.h
> > index faf8a45..a851944 100644
> > --- a/include/linux/blkpg.h
> > +++ b/include/linux/blkpg.h
> > @@ -40,6 +40,7 @@ struct blkpg_ioctl_arg {
> > /* The subfunctions (for the op field) */
> > #define BLKPG_ADD_PARTITION 1
> > #define BLKPG_DEL_PARTITION 2
> > +#define BLKPG_RESIZE_PARTITION 3
> >
> > /* Sizes of name fields. Unused at present. */
> > #define BLKPG_DEVNAMELTH 64
> > diff --git a/include/linux/genhd.h b/include/linux/genhd.h
> > index fe23ee7..0def3ef 100644
> > --- a/include/linux/genhd.h
> > +++ b/include/linux/genhd.h
> > @@ -98,7 +98,13 @@ struct partition_meta_info {
> >
> > struct hd_struct {
> > sector_t start_sect;
> > + /*
> > + * nr_sects is protected by sequence counter. 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.
> > + */
> > sector_t nr_sects;
> > + seqcount_t nr_sects_seq;
> > sector_t alignment_offset;
> > unsigned int discard_alignment;
> > struct device __dev;
> > @@ -653,6 +659,57 @@ static inline void hd_struct_put(struct hd_struct *part)
> > __delete_partition(part);
> > }
> >
> > +/*
> > + * Any access of part->nr_sects which is not protected by partition
> > + * bd_mutex or gendisk bdev bd_mutex, should be done using this
> > + * accessor function.
> > + *
> > + * Code written along the lines of i_size_read() and i_size_write().
> > + * CONFIG_PREEMPT case optimizes the case of UP kernel with preemption
> > + * on.
> > + */
> > +static inline sector_t part_nr_sects_read(struct hd_struct *part)
> > +{
> > +#if BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_SMP)
> > + sector_t nr_sects;
> > + unsigned seq;
> > + do {
> > + seq = read_seqcount_begin(&part->nr_sects_seq);
> > + nr_sects = part->nr_sects;
> > + } while (read_seqcount_retry(&part->nr_sects_seq, seq));
> > + return nr_sects;
> > +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
> > + sector_t nr_sects;
> > +
> > + preempt_disable();
> > + nr_sects = part->nr_sects;
> > + preempt_enable();
> > + return nr_sects;
> > +#else
> > + return part->nr_sects;
> > +#endif
> > +}
> > +
> > +/*
> > + * Should be called with mutex lock held (typically bd_mutex) of partition
> > + * to provide mutual exlusion among writers otherwise seqcount might be
> > + * left in wrong state leaving the readers spinning infinitely.
> > + */
> > +static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
> > +{
> > +#if BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_SMP)
> > + write_seqcount_begin(&part->nr_sects_seq);
> > + part->nr_sects = size;
> > + write_seqcount_end(&part->nr_sects_seq);
> > +#elif BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_PREEMPT)
> > + preempt_disable();
> > + part->nr_sects = size;
> > + preempt_enable();
> > +#else
> > + part->nr_sects = size;
> > +#endif
> > +}
> > +
> > #else /* CONFIG_BLOCK */
> >
> > static inline void printk_all_partitions(void) { }
> > --
> > 1.7.6.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists