Re: [PATCH net-next v8 1/6] page_pool: frag API support for 32-bit arch with 64-bit DMA

[Ilias Apalodimas]

Hi

On Wed, 20 Sept 2023 at 11:59, Yunsheng Lin <linyunsheng@xxxxxxxxxx> wrote:
>
> On 2023/9/15 16:28, Jesper Dangaard Brouer wrote:
> > Hi Lin,
> >
> > This looks reasonable, but given you are changing struct-page
> > (include/linux/mm_types.h) we need to MM-list <linux-mm@xxxxxxxxx>.
> > Also Cc Wilcox.
> >
> > I think it was Ilias and Duyck that validated the assumptions, last time
> > this patch was discussed. Thus I want to see their review before this is
> > applied.
>
> FWIW, PAGE_SIZE aligned buffer being PAGE_SIZE aligned in DMA is
> validated by Duyck:
> https://lore.kernel.org/all/CAKgT0UfeUAUQpEffxnkc+gzXsjOrHkuMgxU_Aw0VXSJYKzaovQ@xxxxxxxxxxxxxx/
>
> And I had done researching to find out there seems to be no combination of
> the above arch with an address space >16TB:
> https://lore.kernel.org/all/2b570282-24f8-f23b-1ff7-ad836794baa9@xxxxxxxxxx/

Apologies for the late reply.  I just saw you sent a v9, I'll review
that instead, but I am traveling right now, will take a while

Thanks
/Ilias
>
> >
> > -Jesper
> >
> > On 12/09/2023 10.31, Yunsheng Lin wrote:
> >> Currently page_pool_alloc_frag() is not supported in 32-bit
> >> arch with 64-bit DMA because of the overlap issue between
> >> pp_frag_count and dma_addr_upper in 'struct page' for those
> >> arches, which seems to be quite common, see [1], which means
> >> driver may need to handle it when using frag API.
> >>
> >> It is assumed that the combination of the above arch with an
> >> address space >16TB does not exist, as all those arches have
> >> 64b equivalent, it seems logical to use the 64b version for a
> >> system with a large address space. It is also assumed that dma
> >> address is page aligned when we are dma mapping a page aliged
> >> buffer, see [2].
> >>
> >> That means we're storing 12 bits of 0 at the lower end for a
> >> dma address, we can reuse those bits for the above arches to
> >> support 32b+12b, which is 16TB of memory.
> >>
> >> If we make a wrong assumption, a warning is emitted so that
> >> user can report to us.
> >>
> >> 1. https://lore.kernel.org/all/20211117075652.58299-1-linyunsheng@xxxxxxxxxx/
> >> 2. https://lore.kernel.org/all/20230818145145.4b357c89@xxxxxxxxxx/
> >>
> >> Signed-off-by: Jakub Kicinski <kuba@xxxxxxxxxx>
> >> Signed-off-by: Yunsheng Lin <linyunsheng@xxxxxxxxxx>
> >> CC: Lorenzo Bianconi <lorenzo@xxxxxxxxxx>
> >> CC: Alexander Duyck <alexander.duyck@xxxxxxxxx>
> >> CC: Liang Chen <liangchen.linux@xxxxxxxxx>
> >> CC: Alexander Lobakin <aleksander.lobakin@xxxxxxxxx>
> >> CC: Guillaume Tucker <guillaume.tucker@xxxxxxxxxxxxx>
> >> ---
> >>   include/linux/mm_types.h        | 13 +------------
> >>   include/net/page_pool/helpers.h | 20 ++++++++++++++------
> >>   net/core/page_pool.c            | 14 +++++++++-----
> >>   3 files changed, 24 insertions(+), 23 deletions(-)
> >>
> >> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> >> index 36c5b43999e6..74b49c4c7a52 100644
> >> --- a/include/linux/mm_types.h
> >> +++ b/include/linux/mm_types.h
> >> @@ -125,18 +125,7 @@ struct page {
> >>               struct page_pool *pp;
> >>               unsigned long _pp_mapping_pad;
> >>               unsigned long dma_addr;
> >> -            union {
> >> -                /**
> >> -                 * dma_addr_upper: might require a 64-bit
> >> -                 * value on 32-bit architectures.
> >> -                 */
> >> -                unsigned long dma_addr_upper;
> >> -                /**
> >> -                 * For frag page support, not supported in
> >> -                 * 32-bit architectures with 64-bit DMA.
> >> -                 */
> >> -                atomic_long_t pp_frag_count;
> >> -            };
> >> +            atomic_long_t pp_frag_count;
> >>           };
> >>           struct {    /* Tail pages of compound page */
> >>               unsigned long compound_head;    /* Bit zero is set */
> >> diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
> >> index 94231533a369..8e1c85de4995 100644
> >> --- a/include/net/page_pool/helpers.h
> >> +++ b/include/net/page_pool/helpers.h
> >> @@ -197,7 +197,7 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
> >>       page_pool_put_full_page(pool, page, true);
> >>   }
> >>   -#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT    \
> >> +#define PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA    \
> >>           (sizeof(dma_addr_t) > sizeof(unsigned long))
> >>     /**
> >> @@ -211,17 +211,25 @@ static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
> >>   {
> >>       dma_addr_t ret = page->dma_addr;
> >>   -    if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
> >> -        ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16;
> >> +    if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA)
> >> +        ret <<= PAGE_SHIFT;
> >>         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 (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) {
> >> +        page->dma_addr = addr >> PAGE_SHIFT;
> >> +
> >> +        /* We assume page alignment to shave off bottom bits,
> >> +         * if this "compression" doesn't work we need to drop.
> >> +         */
> >> +        return addr != (dma_addr_t)page->dma_addr << PAGE_SHIFT;
> >> +    }
> >> +
> >>       page->dma_addr = addr;
> >> -    if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
> >> -        page->dma_addr_upper = upper_32_bits(addr);
> >> +    return false;
> >>   }
> >>     static inline bool page_pool_put(struct page_pool *pool)
> >> diff --git a/net/core/page_pool.c b/net/core/page_pool.c
> >> index 77cb75e63aca..8a9868ea5067 100644
> >> --- a/net/core/page_pool.c
> >> +++ b/net/core/page_pool.c
> >> @@ -211,10 +211,6 @@ static int page_pool_init(struct page_pool *pool,
> >>            */
> >>       }
> >>   -    if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT &&
> >> -        pool->p.flags & PP_FLAG_PAGE_FRAG)
> >> -        return -EINVAL;
> >> -
> >>   #ifdef CONFIG_PAGE_POOL_STATS
> >>       pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats);
> >>       if (!pool->recycle_stats)
> >> @@ -359,12 +355,20 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
> >>       if (dma_mapping_error(pool->p.dev, dma))
> >>           return false;
> >>   -    page_pool_set_dma_addr(page, dma);
> >> +    if (page_pool_set_dma_addr(page, dma))
> >> +        goto unmap_failed;
> >>         if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
> >>           page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
> >>         return true;
> >> +
> >> +unmap_failed:
> >> +    WARN_ON_ONCE("unexpected DMA address, please report to netdev@");
> >> +    dma_unmap_page_attrs(pool->p.dev, dma,
> >> +                 PAGE_SIZE << pool->p.order, pool->p.dma_dir,
> >> +                 DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
> >> +    return false;
> >>   }
> >>     static void page_pool_set_pp_info(struct page_pool *pool,
> >
> > .
> >