Re: [PATCH 15/17] gfs2: use bdev_rw_virt in gfs2_read_super
Damien Le Moal <[email protected]>
| Newsgroups | org.kernel.vger.linux-bcache,dev.linux.lists.dm-devel,dev.linux.lists.gfs2,org.kernel.vger.linux-block,org.kernel.vger.linux-btrfs,org.kernel.vger.linux-fsdevel,org.kernel.vger.linux-pm,org.kernel.vger.linux-xfs |
|---|---|
| Organization | Western Digital Research |
| Message-ID | <[email protected]> |
On 4/22/25 23:26, Christoph Hellwig wrote: > Switch gfs2_read_super to allocate the superblock buffer using kmalloc > which falls back to the page allocator for PAGE_SIZE allocation but > gives us a kernel virtual address and then use bdev_rw_virt to perform > the synchronous read into it. > > Signed-off-by: Christoph Hellwig <[email protected]> Reviewed-by: Damien Le Moal <[email protected]> One nit below. > --- > fs/gfs2/ops_fstype.c | 24 +++++++++--------------- > 1 file changed, 9 insertions(+), 15 deletions(-) > > diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c > index e83d293c3614..7c1014ba7ac7 100644 > --- a/fs/gfs2/ops_fstype.c > +++ b/fs/gfs2/ops_fstype.c > @@ -226,28 +226,22 @@ static void gfs2_sb_in(struct gfs2_sbd *sdp, const struct gfs2_sb *str) > > static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector, int silent) > { > - struct super_block *sb = sdp->sd_vfs; > - struct page *page; > - struct bio_vec bvec; > - struct bio bio; > + struct gfs2_sb *sb; > int err; > > - page = alloc_page(GFP_KERNEL); > - if (unlikely(!page)) > + sb = kmalloc(PAGE_SIZE, GFP_KERNEL); > + if (unlikely(!sb)) > return -ENOMEM; > - > - bio_init(&bio, sb->s_bdev, &bvec, 1, REQ_OP_READ | REQ_META); > - bio.bi_iter.bi_sector = sector * (sb->s_blocksize >> 9); > - __bio_add_page(&bio, page, PAGE_SIZE, 0); > - > - err = submit_bio_wait(&bio); > + err = bdev_rw_virt(sdp->sd_vfs->s_bdev, > + sector * (sdp->sd_vfs->s_blocksize >> 9), sb, PAGE_SIZE, While at it, use SECTOR_SHIFT here ? > + REQ_OP_READ | REQ_META); > if (err) { > pr_warn("error %d reading superblock\n", err); > - __free_page(page); > + kfree(sb); > return err; > } > - gfs2_sb_in(sdp, page_address(page)); > - __free_page(page); > + gfs2_sb_in(sdp, sb); > + kfree(sb); > return gfs2_check_sb(sdp, silent); > } > -- Damien Le Moal Western Digital Research