Re: [PATCH] mm: extend zero pages to same element pages for zram

From: Matthew Wilcox
Date: Fri Feb 03 2017 - 10:49:30 EST


On Fri, Feb 03, 2017 at 04:42:27PM +0800, zhouxianrong@xxxxxxxxxx wrote:
> +static inline void zram_fill_page_partial(char *ptr, unsigned int size,
> + unsigned long value)
> +{
> + int i;
> + unsigned long *page;
> +
> + if (likely(value == 0)) {
> + memset(ptr, 0, size);
> + return;
> + }
> +
> + i = ((unsigned long)ptr) % sizeof(*page);
> + if (i) {
> + while (i < sizeof(*page)) {
> + *ptr++ = (value >> (i * 8)) & 0xff;
> + --size;
> + ++i;
> + }
> + }
> +
> + for (i = size / sizeof(*page); i > 0; --i) {
> + page = (unsigned long *)ptr;
> + *page = value;
> + ptr += sizeof(*page);
> + size -= sizeof(*page);
> + }
> +
> + for (i = 0; i < size; ++i)
> + *ptr++ = (value >> (i * 8)) & 0xff;
> +}

You're assuming little-endian here. I think you need to do a
cpu_to_le() here, but I don't think we have a cpu_to_leul, only
cpu_to_le64/cpu_to_le32. So you may have some work to do ...