On Mon, Jul 12, 2021 at 5:17 AM Yunsheng Lin <linyunsheng@xxxxxxxxxx> wrote:
>
> As suggested by Alexander, "A DMA mapping should be page
> aligned anyway so the lower 12 bits would be reserved 0",
> so it might make more sense to repurpose the lower 12 bits
> of the dma address to store the pagecnt_bias for frag page
> support in page pool.
>
> As newly added page_pool_get_pagecnt_bias() may be called
> outside of the softirq context, so annotate the access to
> page->dma_addr[0] with READ_ONCE() and WRITE_ONCE().
>
> And page_pool_get_pagecnt_bias_ptr() is added to implement
> the pagecnt_bias atomic updating when a page is passsed to
> the user.
>
> Other three interfaces using page->dma_addr[0] is only called
> in the softirq context during normal rx processing, hopefully
> the barrier in the rx processing will ensure the correct order
> between getting and setting pagecnt_bias.
>
> Signed-off-by: Yunsheng Lin <linyunsheng@xxxxxxxxxx>
> ---
> include/net/page_pool.h | 29 +++++++++++++++++++++++++++--
> net/core/page_pool.c | 8 +++++++-
> 2 files changed, 34 insertions(+), 3 deletions(-)
>
> diff --git a/include/net/page_pool.h b/include/net/page_pool.h
> index 8d7744d..84cd972 100644
> --- a/include/net/page_pool.h
> +++ b/include/net/page_pool.h
> @@ -200,17 +200,42 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
>
> static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
> {
> - dma_addr_t ret = page->dma_addr[0];
> + dma_addr_t ret = READ_ONCE(page->dma_addr[0]) & PAGE_MASK;
> if (sizeof(dma_addr_t) > sizeof(unsigned long))
> ret |= (dma_addr_t)page->dma_addr[1] << 16 << 16;
> return ret;
> }
>
> -static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
> +static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
> {
> + if (WARN_ON(addr & ~PAGE_MASK))
> + return false;
> +
> page->dma_addr[0] = addr;
> if (sizeof(dma_addr_t) > sizeof(unsigned long))
> page->dma_addr[1] = upper_32_bits(addr);
> +
> + return true;
> +}
> +
Rather than making this a part of the check here it might make more
sense to pull this out and perform the WARN_ON after the check for
dma_mapping_error.
Also it occurs to me that we only really have to do this in the case
where dma_addr_t is larger than the size of a long. Otherwise we could
just have the code split things so that dma_addr[0] is the dma_addr
and dma_addr[1] is our pagecnt_bias value in which case we could
probably just skip the check.
> +static inline int page_pool_get_pagecnt_bias(struct page *page)
> +{
> + return READ_ONCE(page->dma_addr[0]) & ~PAGE_MASK;
> +}
> +
> +static inline unsigned long *page_pool_pagecnt_bias_ptr(struct page *page)
> +{
> + return page->dma_addr;
> +}
> +
> +static inline void page_pool_set_pagecnt_bias(struct page *page, int bias)
> +{
> + unsigned long dma_addr_0 = READ_ONCE(page->dma_addr[0]);
> +
> + dma_addr_0 &= PAGE_MASK;
> + dma_addr_0 |= bias;
> +
> + WRITE_ONCE(page->dma_addr[0], dma_addr_0);
> }
>
> static inline bool is_page_pool_compiled_in(void)
> diff --git a/net/core/page_pool.c b/net/core/page_pool.c
> index 78838c6..1abefc6 100644
> --- a/net/core/page_pool.c
> +++ b/net/core/page_pool.c
> @@ -198,7 +198,13 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
> if (dma_mapping_error(pool->p.dev, dma))
> return false;
>
So instead of adding to the function below you could just add your
WARN_ON check here with the unmapping call.
> - page_pool_set_dma_addr(page, dma);
> + if (unlikely(!page_pool_set_dma_addr(page, dma))) {
> + dma_unmap_page_attrs(pool->p.dev, dma,
> + PAGE_SIZE << pool->p.order,
> + pool->p.dma_dir,
> + DMA_ATTR_SKIP_CPU_SYNC);
> + return false;
> + }
>
> if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
> page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
> --
> 2.7.4
>
