On ke, 2017-05-31 at 19:51 +0100, Matthew Auld wrote:
> Enable transparent-huge-pages through gemfs by mounting with
> huge=within_size.
>
> Signed-off-by: Matthew Auld <matthew.auld@xxxxxxxxx>
> Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx>
> Cc: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
<SNIP>
> @@ -41,6 +42,28 @@ struct vfsmount *i915_gemfs_create(void)
>
> gemfs_mnt = kern_mount(type);
>
> +#if defined(CONFIG_TRANSPARENT_HUGE_PAGECACHE)
> + if (!IS_ERR(gemfs_mnt) && has_transparent_hugepage()) {
> + struct super_block *sb = gemfs_mnt->mnt_sb;
> + char options[] = "huge=within_size";
> + int flags = 0;
> + int ret;
> +
> + /* Idealy we would just pass the mount options when mounting,
> + * but for some reason shmem chooses not to parse the options
> + * for MS_KERNMOUNT, probably because shm_mnt is the only tmpfs
> + * kernel mount other than this, where the mount options aren't
> + * used. To workaround this we do a remount, which is fairly
> + * inexpensive, where we know the options are never igonored.
> + */
> + ret = sb->s_op->remount_fs(sb, &flags, options);
This sounds like a bugfix to be sent.
Regards, Joonas
--
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
