[PATCH net-next 6/7] page_pool: check for DMA sync shortcut earlier

From: Alexander Lobakin
Date: Fri Jan 26 2024 - 08:58:15 EST


We can save a couple more function calls in the Page Pool code if we
check for dma_skip_sync() earlier, just when we test pp->p.dma_sync.
Move both these checks into an inline wrapper and call the PP wrapper
over the generic DMA sync function only when both are true.
You can't cache the result of dma_skip_sync() in &page_pool, as it may
change anytime if an SWIOTLB buffer is allocated or mapped.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@xxxxxxxxx>
---
net/core/page_pool.c | 30 +++++++++++++++++-------------
1 file changed, 17 insertions(+), 13 deletions(-)

diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 2c353906407c..cefdd9822fb7 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -369,16 +369,24 @@ static struct page *__page_pool_get_cached(struct page_pool *pool)
return page;
}

-static void page_pool_dma_sync_for_device(struct page_pool *pool,
- struct page *page,
- unsigned int dma_sync_size)
+static void __page_pool_dma_sync_for_device(struct page_pool *pool,
+ struct page *page,
+ unsigned int dma_sync_size)
{
dma_addr_t dma_addr = page_pool_get_dma_addr(page);

dma_sync_size = min(dma_sync_size, pool->p.max_len);
- dma_sync_single_range_for_device(pool->p.dev, dma_addr,
- pool->p.offset, dma_sync_size,
- pool->p.dma_dir);
+ __dma_sync_single_range_for_device(pool->p.dev, dma_addr,
+ pool->p.offset, dma_sync_size,
+ pool->p.dma_dir);
+}
+
+static __always_inline void
+page_pool_dma_sync_for_device(struct page_pool *pool, struct page *page,
+ unsigned int dma_sync_size)
+{
+ if (pool->dma_sync && !dma_skip_sync(pool->p.dev))
+ __page_pool_dma_sync_for_device(pool, page, dma_sync_size);
}

static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
@@ -400,8 +408,7 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
if (page_pool_set_dma_addr(page, dma))
goto unmap_failed;

- if (pool->dma_sync)
- page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
+ page_pool_dma_sync_for_device(pool, page, pool->p.max_len);

return true;

@@ -665,9 +672,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
if (likely(page_ref_count(page) == 1 && !page_is_pfmemalloc(page))) {
/* Read barrier done in page_ref_count / READ_ONCE */

- if (pool->dma_sync)
- page_pool_dma_sync_for_device(pool, page,
- dma_sync_size);
+ page_pool_dma_sync_for_device(pool, page, dma_sync_size);

if (allow_direct && in_softirq() &&
page_pool_recycle_in_cache(page, pool))
@@ -778,8 +783,7 @@ static struct page *page_pool_drain_frag(struct page_pool *pool,
return NULL;

if (page_ref_count(page) == 1 && !page_is_pfmemalloc(page)) {
- if (pool->dma_sync)
- page_pool_dma_sync_for_device(pool, page, -1);
+ page_pool_dma_sync_for_device(pool, page, -1);

return page;
}
--
2.43.0