On Thu, Mar 29, 2018 at 4:18 PM, Amir Goldstein <amir73il@xxxxxxxxx> wrote:
> With mount option "xino", mounter declares that there are enough
> free high bits in underlying fs to hold the layer fsid.
> If overlayfs does encounter underlying inodes using the high xino
> bits reserved for layer fsid, a warning will be emitted and the original
> inode number will be used.
>
> The mount option name "xino" goes after a similar meaning mount option
> of aufs, but in overlayfs case, the mapping is stateless.
>
> An example for a use case of "xino" is when upper/lower is on an xfs
> filesystem. xfs uses 64bit inode numbers, but it currently never uses the
> upper 8bit for inode numbers exposed via stat(2) and that is not likely to
> change in the future without user opting-in for a new xfs feature. The
> actual number of unused upper bit is much larger and determined by the xfs
> filesystem geometry (64 - agno_log - agblklog - inopblog). That means
> that for all practical purpose, there are enough unused bits in xfs
> inode numbers for more than OVL_MAX_STACK unique fsid's.
>
> Another example for a use case of "xino" is when upper/lower is on tmpfs.
> tmpfs inode numbers are allocated sequentially since boot, so they will
> practially never use the high inode number bits.
>
> Signed-off-by: Amir Goldstein <amir73il@xxxxxxxxx>
> ---
> fs/overlayfs/ovl_entry.h | 1 +
> fs/overlayfs/super.c | 34 ++++++++++++++++++++++++++++++++--
> 2 files changed, 33 insertions(+), 2 deletions(-)
>
> diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
> index 6a077fb2a75f..e830470c77bd 100644
> --- a/fs/overlayfs/ovl_entry.h
> +++ b/fs/overlayfs/ovl_entry.h
> @@ -18,6 +18,7 @@ struct ovl_config {
> const char *redirect_mode;
> bool index;
> bool nfs_export;
> + bool xino;
> };
>
> struct ovl_sb {
> diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
> index d7284444f404..26a5db244081 100644
> --- a/fs/overlayfs/super.c
> +++ b/fs/overlayfs/super.c
> @@ -352,6 +352,8 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
> if (ofs->config.nfs_export != ovl_nfs_export_def)
> seq_printf(m, ",nfs_export=%s", ofs->config.nfs_export ?
> "on" : "off");
> + if (ofs->config.xino)
> + seq_puts(m, ",xino");
> return 0;
> }
>
> @@ -386,6 +388,7 @@ enum {
> OPT_INDEX_OFF,
> OPT_NFS_EXPORT_ON,
> OPT_NFS_EXPORT_OFF,
> + OPT_XINO,
> OPT_ERR,
> };
>
> @@ -399,6 +402,7 @@ static const match_table_t ovl_tokens = {
> {OPT_INDEX_OFF, "index=off"},
> {OPT_NFS_EXPORT_ON, "nfs_export=on"},
> {OPT_NFS_EXPORT_OFF, "nfs_export=off"},
> + {OPT_XINO, "xino"},
> {OPT_ERR, NULL}
> };
>
> @@ -513,6 +517,10 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
> config->nfs_export = false;
> break;
>
> + case OPT_XINO:
> + config->xino = true;
> + break;
> +
> default:
> pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p);
> return -EINVAL;
> @@ -1197,9 +1205,31 @@ static int ovl_get_lower_layers(struct ovl_fs *ofs, struct path *stack,
> ofs->numlower++;
> }
>
> - /* When all layers on same fs, overlay can use real inode numbers */
> - if (!ofs->numlowerfs || (ofs->numlowerfs == 1 && !ofs->upper_mnt))
> + /*
> + * When all layers on same fs, overlay can use real inode numbers.
> + * With mount option "xino", mounter declares that there are enough
> + * free high bits in underlying fs to hold the unique fsid.
> + * If overlayfs does encounter underlying inodes using the high xino
> + * bits reserved for fsid, it emits a warning and uses the original
> + * inode number.
> + */
> + if (!ofs->numlowerfs || (ofs->numlowerfs == 1 && !ofs->upper_mnt)) {
> ofs->xino_bits = 0;
> + ofs->config.xino = false;
> + } else if (ofs->config.xino && !ofs->xino_bits) {
> + /*
> + * This is a roundup of number of bits needed for numlowerfs+1
> + * (i.e. ilog2(numlowerfs+1 - 1) + 1). fsid 0 is reserved for
> + * upper fs even with non upper overlay.
> + */
> + BUILD_BUG_ON(ilog2(OVL_MAX_STACK) > 31);
> + ofs->xino_bits = ilog2(ofs->numlowerfs) + 1;
Shouldn't this be
ilog2(ofs->numlowerfs + (ofs->upper_mnt ? 1 : 0))
?
Upper layer doesn't require a separate bit, just a separate fsid slot.
Thanks,
Miklos
> + }
> +
> + if (ofs->xino_bits) {
> + pr_info("overlayfs: \"xino\" feature enabled using %d upper inode bits.\n",
> + ofs->xino_bits);
> + }
>
> err = 0;
> out:
> --
> 2.7.4
>
--
To unsubscribe from this list: send the line "unsubscribe linux-unionfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
