On Fri, Oct 17, 2025 at 01:11:52PM -0700, Ackerley Tng wrote:
> For shared to private conversions, if refcounts on any of the folios
> within the range are elevated, fail the conversion with -EAGAIN.
>
> At the point of shared to private conversion, all folios in range are
> also unmapped. The filemap_invalidate_lock() is held, so no faulting
> can occur. Hence, from that point on, only transient refcounts can be
> taken on the folios associated with that guest_memfd.
>
> Hence, it is safe to do the conversion from shared to private.
>
> After conversion is complete, refcounts may become elevated, but that
> is fine since users of transient refcounts don't actually access
> memory.
>
> For private to shared conversions, there are no refcount checks. any
> transient refcounts are expected to drop their refcounts soon. The
> conversion process will spin waiting for these transient refcounts to
> go away.
Where's the code to spin?
> +/*
> + * Preallocate memory for attributes to be stored on a maple tree, pointed to
> + * by mas. Adjacent ranges with attributes identical to the new attributes
> + * will be merged. Also sets mas's bounds up for storing attributes.
> + *
> + * This maintains the invariant that ranges with the same attributes will
> + * always be merged.
> + */
> +static int kvm_gmem_mas_preallocate(struct ma_state *mas, u64 attributes,
> + pgoff_t start, size_t nr_pages)
> +{
> + pgoff_t end = start + nr_pages;
> + pgoff_t last = end - 1;
> + void *entry;
> +
> + /* Try extending range. entry is NULL on overflow/wrap-around. */
> + mas_set_range(mas, end, end);
> + entry = mas_find(mas, end);
> + if (entry && xa_to_value(entry) == attributes)
> + last = mas->last;
> +
> + mas_set_range(mas, start - 1, start - 1);
Check start == 0 ?
> + entry = mas_find(mas, start - 1);
> + if (entry && xa_to_value(entry) == attributes)
> + start = mas->index;
> +
> + mas_set_range(mas, start, last);
> + return mas_preallocate(mas, xa_mk_value(attributes), GFP_KERNEL);
> +}
...
> +static long kvm_gmem_set_attributes(struct file *file, void __user *argp)
> +{
> + struct gmem_file *f = file->private_data;
> + struct inode *inode = file_inode(file);
> + struct kvm_memory_attributes2 attrs;
> + pgoff_t err_index;
> + size_t nr_pages;
> + pgoff_t index;
> + int r;
> +
> + if (copy_from_user(&attrs, argp, sizeof(attrs)))
> + return -EFAULT;
> +
> + if (attrs.flags)
> + return -EINVAL;
> + if (attrs.attributes & ~kvm_supported_mem_attributes(f->kvm))
> + return -EINVAL;
> + if (attrs.size == 0 || attrs.offset + attrs.size < attrs.offset)
> + return -EINVAL;
> + if (!PAGE_ALIGNED(attrs.offset) || !PAGE_ALIGNED(attrs.offset))
Should be
if (!PAGE_ALIGNED(attrs.offset) || !PAGE_ALIGNED(attrs.size))
?
> + return -EINVAL;
> +
> + if (attrs.offset > inode->i_size ||
Should be
if (attrs.offset >= inode->i_size ||
?
> + attrs.offset + attrs.size > inode->i_size)
> + return -EINVAL;
> +
> + nr_pages = attrs.size >> PAGE_SHIFT;
> + index = attrs.offset >> PAGE_SHIFT;
> + r = __kvm_gmem_set_attributes(inode, index, nr_pages, attrs.attributes,
> + &err_index);
> + if (r) {
> + attrs.error_offset = err_index << PAGE_SHIFT;
> +
> + if (copy_to_user(argp, &attrs, sizeof(attrs)))
> + return -EFAULT;
> + }
> +
> + return r;
> +}
