Currently when PP_FLAG_PAGE_FRAG is set, the caller is not
expected to call page_pool_alloc_pages() directly because of
the PP_FLAG_PAGE_FRAG checking in __page_pool_put_page().
The patch removes the above checking to enable non-split page
support when PP_FLAG_PAGE_FRAG is set.
Signed-off-by: Yunsheng Lin <[email protected]>
---
include/net/page_pool.h | 6 ++++++
net/core/page_pool.c | 12 +++++++-----
2 files changed, 13 insertions(+), 5 deletions(-)
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index a408240..2ad0706 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -238,6 +238,9 @@ static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
static inline void page_pool_set_frag_count(struct page *page, long nr)
{
+ if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
+ return;
+
atomic_long_set(&page->pp_frag_count, nr);
}
@@ -246,6 +249,9 @@ static inline long page_pool_atomic_sub_frag_count_return(struct page *page,
{
long ret;
+ if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
+ return 0;
+
/* As suggested by Alexander, atomic_long_read() may cover up the
* reference count errors, so avoid calling atomic_long_read() in
* the cases of freeing or draining the page_frags, where we would
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 1a69784..ba9f14d 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -313,11 +313,14 @@ struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp)
/* Fast-path: Get a page from cache */
page = __page_pool_get_cached(pool);
- if (page)
- return page;
/* Slow-path: cache empty, do real allocation */
- page = __page_pool_alloc_pages_slow(pool, gfp);
+ if (!page)
+ page = __page_pool_alloc_pages_slow(pool, gfp);
+
+ if (likely(page))
+ page_pool_set_frag_count(page, 1);
+
return page;
}
EXPORT_SYMBOL(page_pool_alloc_pages);
@@ -426,8 +429,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
unsigned int dma_sync_size, bool allow_direct)
{
/* It is not the last user for the page frag case */
- if (pool->p.flags & PP_FLAG_PAGE_FRAG &&
- page_pool_atomic_sub_frag_count_return(page, 1))
+ if (page_pool_atomic_sub_frag_count_return(page, 1))
return NULL;
/* This allocator is optimized for the XDP mode that uses
--
2.7.4
On Sun, Aug 29, 2021 at 6:19 PM Yunsheng Lin <[email protected]> wrote:
>
> Currently when PP_FLAG_PAGE_FRAG is set, the caller is not
> expected to call page_pool_alloc_pages() directly because of
> the PP_FLAG_PAGE_FRAG checking in __page_pool_put_page().
>
> The patch removes the above checking to enable non-split page
> support when PP_FLAG_PAGE_FRAG is set.
>
> Signed-off-by: Yunsheng Lin <[email protected]>
> ---
> include/net/page_pool.h | 6 ++++++
> net/core/page_pool.c | 12 +++++++-----
> 2 files changed, 13 insertions(+), 5 deletions(-)
>
> diff --git a/include/net/page_pool.h b/include/net/page_pool.h
> index a408240..2ad0706 100644
> --- a/include/net/page_pool.h
> +++ b/include/net/page_pool.h
> @@ -238,6 +238,9 @@ static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
>
> static inline void page_pool_set_frag_count(struct page *page, long nr)
> {
> + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
> + return;
> +
> atomic_long_set(&page->pp_frag_count, nr);
> }
>
> @@ -246,6 +249,9 @@ static inline long page_pool_atomic_sub_frag_count_return(struct page *page,
> {
> long ret;
>
> + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
> + return 0;
> +
> /* As suggested by Alexander, atomic_long_read() may cover up the
> * reference count errors, so avoid calling atomic_long_read() in
> * the cases of freeing or draining the page_frags, where we would
> diff --git a/net/core/page_pool.c b/net/core/page_pool.c
> index 1a69784..ba9f14d 100644
> --- a/net/core/page_pool.c
> +++ b/net/core/page_pool.c
> @@ -313,11 +313,14 @@ struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp)
>
> /* Fast-path: Get a page from cache */
> page = __page_pool_get_cached(pool);
> - if (page)
> - return page;
>
> /* Slow-path: cache empty, do real allocation */
> - page = __page_pool_alloc_pages_slow(pool, gfp);
> + if (!page)
> + page = __page_pool_alloc_pages_slow(pool, gfp);
> +
> + if (likely(page))
> + page_pool_set_frag_count(page, 1);
> +
> return page;
> }
> EXPORT_SYMBOL(page_pool_alloc_pages);
> @@ -426,8 +429,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
> unsigned int dma_sync_size, bool allow_direct)
> {
> /* It is not the last user for the page frag case */
> - if (pool->p.flags & PP_FLAG_PAGE_FRAG &&
> - page_pool_atomic_sub_frag_count_return(page, 1))
> + if (page_pool_atomic_sub_frag_count_return(page, 1))
> return NULL;
Isn't this going to have a negative performance impact on page pool
pages in general? Essentially you are adding an extra atomic operation
for all the non-frag pages.
It would work better if this was doing a check against 1 to determine
if it is okay for this page to be freed here and only if the check
fails then you perform the atomic sub_return.
On 2021/8/30 23:05, Alexander Duyck wrote:
> On Sun, Aug 29, 2021 at 6:19 PM Yunsheng Lin <[email protected]> wrote:
>>
>> Currently when PP_FLAG_PAGE_FRAG is set, the caller is not
>> expected to call page_pool_alloc_pages() directly because of
>> the PP_FLAG_PAGE_FRAG checking in __page_pool_put_page().
>>
>> The patch removes the above checking to enable non-split page
>> support when PP_FLAG_PAGE_FRAG is set.
>>
>> Signed-off-by: Yunsheng Lin <[email protected]>
>> ---
>> include/net/page_pool.h | 6 ++++++
>> net/core/page_pool.c | 12 +++++++-----
>> 2 files changed, 13 insertions(+), 5 deletions(-)
>>
>> diff --git a/include/net/page_pool.h b/include/net/page_pool.h
>> index a408240..2ad0706 100644
>> --- a/include/net/page_pool.h
>> +++ b/include/net/page_pool.h
>> @@ -238,6 +238,9 @@ static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
>>
>> static inline void page_pool_set_frag_count(struct page *page, long nr)
>> {
>> + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
>> + return;
>> +
>> atomic_long_set(&page->pp_frag_count, nr);
>> }
>>
>> @@ -246,6 +249,9 @@ static inline long page_pool_atomic_sub_frag_count_return(struct page *page,
>> {
>> long ret;
>>
>> + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
>> + return 0;
>> +
>> /* As suggested by Alexander, atomic_long_read() may cover up the
>> * reference count errors, so avoid calling atomic_long_read() in
>> * the cases of freeing or draining the page_frags, where we would
>> diff --git a/net/core/page_pool.c b/net/core/page_pool.c
>> index 1a69784..ba9f14d 100644
>> --- a/net/core/page_pool.c
>> +++ b/net/core/page_pool.c
>> @@ -313,11 +313,14 @@ struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp)
>>
>> /* Fast-path: Get a page from cache */
>> page = __page_pool_get_cached(pool);
>> - if (page)
>> - return page;
>>
>> /* Slow-path: cache empty, do real allocation */
>> - page = __page_pool_alloc_pages_slow(pool, gfp);
>> + if (!page)
>> + page = __page_pool_alloc_pages_slow(pool, gfp);
>> +
>> + if (likely(page))
>> + page_pool_set_frag_count(page, 1);
>> +
>> return page;
>> }
>> EXPORT_SYMBOL(page_pool_alloc_pages);
>> @@ -426,8 +429,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
>> unsigned int dma_sync_size, bool allow_direct)
>> {
>> /* It is not the last user for the page frag case */
>> - if (pool->p.flags & PP_FLAG_PAGE_FRAG &&
>> - page_pool_atomic_sub_frag_count_return(page, 1))
>> + if (page_pool_atomic_sub_frag_count_return(page, 1))
>> return NULL;
>
> Isn't this going to have a negative performance impact on page pool
> pages in general? Essentially you are adding an extra atomic operation
> for all the non-frag pages.
>
> It would work better if this was doing a check against 1 to determine
> if it is okay for this page to be freed here and only if the check
> fails then you perform the atomic sub_return.
The page_pool_atomic_sub_frag_count_return() has added the optimization
to not do the atomic sub_return when the caller is the last user of the
page, see page_pool_atomic_sub_frag_count_return():
/* As suggested by Alexander, atomic_long_read() may cover up the
* reference count errors, so avoid calling atomic_long_read() in
* the cases of freeing or draining the page_frags, where we would
* not expect it to match or that are slowpath anyway.
*/
if (__builtin_constant_p(nr) &&
atomic_long_read(&page->pp_frag_count) == nr)
return 0;
So the check against 1 is not needed here?
> .
>
On Mon, Aug 30, 2021 at 11:14 PM Yunsheng Lin <[email protected]> wrote:
>
> On 2021/8/30 23:05, Alexander Duyck wrote:
> > On Sun, Aug 29, 2021 at 6:19 PM Yunsheng Lin <[email protected]> wrote:
> >>
> >> Currently when PP_FLAG_PAGE_FRAG is set, the caller is not
> >> expected to call page_pool_alloc_pages() directly because of
> >> the PP_FLAG_PAGE_FRAG checking in __page_pool_put_page().
> >>
> >> The patch removes the above checking to enable non-split page
> >> support when PP_FLAG_PAGE_FRAG is set.
> >>
> >> Signed-off-by: Yunsheng Lin <[email protected]>
> >> ---
> >> include/net/page_pool.h | 6 ++++++
> >> net/core/page_pool.c | 12 +++++++-----
> >> 2 files changed, 13 insertions(+), 5 deletions(-)
> >>
> >> diff --git a/include/net/page_pool.h b/include/net/page_pool.h
> >> index a408240..2ad0706 100644
> >> --- a/include/net/page_pool.h
> >> +++ b/include/net/page_pool.h
> >> @@ -238,6 +238,9 @@ static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
> >>
> >> static inline void page_pool_set_frag_count(struct page *page, long nr)
> >> {
> >> + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
> >> + return;
> >> +
> >> atomic_long_set(&page->pp_frag_count, nr);
> >> }
> >>
> >> @@ -246,6 +249,9 @@ static inline long page_pool_atomic_sub_frag_count_return(struct page *page,
> >> {
> >> long ret;
> >>
> >> + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
> >> + return 0;
> >> +
> >> /* As suggested by Alexander, atomic_long_read() may cover up the
> >> * reference count errors, so avoid calling atomic_long_read() in
> >> * the cases of freeing or draining the page_frags, where we would
> >> diff --git a/net/core/page_pool.c b/net/core/page_pool.c
> >> index 1a69784..ba9f14d 100644
> >> --- a/net/core/page_pool.c
> >> +++ b/net/core/page_pool.c
> >> @@ -313,11 +313,14 @@ struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp)
> >>
> >> /* Fast-path: Get a page from cache */
> >> page = __page_pool_get_cached(pool);
> >> - if (page)
> >> - return page;
> >>
> >> /* Slow-path: cache empty, do real allocation */
> >> - page = __page_pool_alloc_pages_slow(pool, gfp);
> >> + if (!page)
> >> + page = __page_pool_alloc_pages_slow(pool, gfp);
> >> +
> >> + if (likely(page))
> >> + page_pool_set_frag_count(page, 1);
> >> +
> >> return page;
> >> }
> >> EXPORT_SYMBOL(page_pool_alloc_pages);
> >> @@ -426,8 +429,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
> >> unsigned int dma_sync_size, bool allow_direct)
> >> {
> >> /* It is not the last user for the page frag case */
> >> - if (pool->p.flags & PP_FLAG_PAGE_FRAG &&
> >> - page_pool_atomic_sub_frag_count_return(page, 1))
> >> + if (page_pool_atomic_sub_frag_count_return(page, 1))
> >> return NULL;
> >
> > Isn't this going to have a negative performance impact on page pool
> > pages in general? Essentially you are adding an extra atomic operation
> > for all the non-frag pages.
> >
> > It would work better if this was doing a check against 1 to determine
> > if it is okay for this page to be freed here and only if the check
> > fails then you perform the atomic sub_return.
>
> The page_pool_atomic_sub_frag_count_return() has added the optimization
> to not do the atomic sub_return when the caller is the last user of the
> page, see page_pool_atomic_sub_frag_count_return():
>
> /* As suggested by Alexander, atomic_long_read() may cover up the
> * reference count errors, so avoid calling atomic_long_read() in
> * the cases of freeing or draining the page_frags, where we would
> * not expect it to match or that are slowpath anyway.
> */
> if (__builtin_constant_p(nr) &&
> atomic_long_read(&page->pp_frag_count) == nr)
> return 0;
>
> So the check against 1 is not needed here?
Ah, okay. I hadn't seen that part. So yeah, then this should be mostly
harmless since 1 falls into the category of a builtin constant and
would result in the standard case being the frag count being set to 1
and then being read which should be minimal overhead.
Reviewed-by: Alexander Duyck <[email protected]>