[PATCH net-next v11 1/6] page_pool: fragment API support for 32-bit arch with 64-bit DMA

[PATCH net-next v11 1/6] page_pool: fragment API support for 32-bit arch with 64-bit DMA

[Yunsheng Lin]

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 fragment 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 aligned
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@huawei.com/
2. https://lore.kernel.org/all/20230818145145.4b357c89@kernel.org/

Tested-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
CC: Lorenzo Bianconi <lorenzo@kernel.org>
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: Liang Chen <liangchen.linux@gmail.com>
CC: Alexander Lobakin <aleksander.lobakin@intel.com>
CC: Guillaume Tucker <guillaume.tucker@collabora.com>
CC: Matthew Wilcox <willy@infradead.org>
CC: Linux-MM <linux-mm@kvack.org>
---
 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 8e7751464ff5..8f64adf86f5b 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,
-- 
2.33.0

Re: [PATCH net-next v11 1/6] page_pool: fragment API support for 32-bit arch with 64-bit DMA

[Jakub Kicinski]

On Fri, 13 Oct 2023 14:48:21 +0800 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 fragment 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 aligned
> 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.

Let me apply this one already, I think it should be uncontroversial
from review perspective. And the more time it gets in linux-next
the better..

Re: [PATCH net-next v11 1/6] page_pool: fragment API support for 32-bit arch with 64-bit DMA

[Ilias Apalodimas]

[-- Attachment #1: Type: text/plain, Size: 6374 bytes --]

Hi Yunsheng,

Apologies for the late reply.


On Fri, 13 Oct 2023 at 09:47, Yunsheng Lin <linyunsheng@huawei.com> 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 fragment 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 aligned
> 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@huawei.com/
> 2. https://lore.kernel.org/all/20230818145145.4b357c89@kernel.org/
>
> Tested-by: Alexander Lobakin <aleksander.lobakin@intel.com>
> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> CC: Lorenzo Bianconi <lorenzo@kernel.org>
> CC: Alexander Duyck <alexander.duyck@gmail.com>
> CC: Liang Chen <liangchen.linux@gmail.com>
> CC: Alexander Lobakin <aleksander.lobakin@intel.com>
> CC: Guillaume Tucker <guillaume.tucker@collabora.com>
> CC: Matthew Wilcox <willy@infradead.org>
> CC: Linux-MM <linux-mm@kvack.org>
> ---
>  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 8e7751464ff5..8f64adf86f5b 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,
> --
> 2.33.0
>

That looks fine wrt what we discussed with Jakub,

Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>

[-- Attachment #2: Type: text/html, Size: 9376 bytes --]

Re: [PATCH net-next v11 1/6] page_pool: fragment API support for 32-bit arch with 64-bit DMA

[Ilias Apalodimas]

Hi Yunsheng

re-sending, HTML was somehow enabled and the ML dropped the public part.

Apologies for the late reply (and the noise)


On Fri, 13 Oct 2023 at 09:47, Yunsheng Lin <linyunsheng@huawei.com> 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 fragment 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 aligned
> 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@huawei.com/
> 2. https://lore.kernel.org/all/20230818145145.4b357c89@kernel.org/
>
> Tested-by: Alexander Lobakin <aleksander.lobakin@intel.com>
> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> CC: Lorenzo Bianconi <lorenzo@kernel.org>
> CC: Alexander Duyck <alexander.duyck@gmail.com>
> CC: Liang Chen <liangchen.linux@gmail.com>
> CC: Alexander Lobakin <aleksander.lobakin@intel.com>
> CC: Guillaume Tucker <guillaume.tucker@collabora.com>
> CC: Matthew Wilcox <willy@infradead.org>
> CC: Linux-MM <linux-mm@kvack.org>
> ---
>  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 8e7751464ff5..8f64adf86f5b 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,
> --
> 2.33.0
>

That looks fine wrt what we discussed with Jakub,

Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>

Re: [PATCH net-next v11 1/6] page_pool: fragment API support for 32-bit arch with 64-bit DMA

[Yunsheng Lin]

On 2023/10/17 20:17, Ilias Apalodimas wrote:
>>
> 
> That looks fine wrt what we discussed with Jakub,
> 
> Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>

Thanks. What about other patches in this series? Could you take
some time to review them too?

> 
> .
> 

Re: [PATCH net-next v11 1/6] page_pool: fragment API support for 32-bit arch with 64-bit DMA

[Ilias Apalodimas]

Hi Yunsheng

On Tue, 17 Oct 2023 at 15:53, Yunsheng Lin <linyunsheng@huawei.com> wrote:
>
> On 2023/10/17 20:17, Ilias Apalodimas wrote:
> >>
> >
> > That looks fine wrt what we discussed with Jakub,
> >
> > Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
>
> Thanks. What about other patches in this series? Could you take
> some time to review them too?

Yes I will, I was on nonstop trips, and was a bit cumbersome to
review/test.  Also, there Plumbers is in a month, and I have an idea I
need to discuss with Jakub about adding page pool patches to a CI.
That should make the whole process a bit faster

Thanks
/Ilias
>
> >
> > .
> >