page_pool: check for DMA sync shortcut earlier

JIRA: https://issues.redhat.com/browse/RHEL-57765
Conflicts:
- net/core/page_pool.c: upstream ef9226cd56b7 ("page_pool: constify some
  read-only function arguments") and this commit happened in parallel
  leading to conflicts in which args of
  {,__}page_pool_dma_sync_for_device() were const; this was resolved in
  daa121128a2d ("Merge tag 'dma-mapping-6.10-2024-05-20' of
  git://git.infradead.org/users/hch/dma-mapping"). Fixing accordingly in
  the backport: page and page_pool args should be const.

commit 4321de4497b24fbf22389331f4ecd4039a451aa9
Author: Alexander Lobakin <aleksander.lobakin@intel.com>
Date:   Tue May 7 13:20:25 2024 +0200

    page_pool: check for DMA sync shortcut earlier

    We can save a couple more function calls in the Page Pool code if we
    check for dma_need_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_need_sync() in &page_pool, as it may
    change anytime if an SWIOTLB buffer is allocated or mapped.

    Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
    Signed-off-by: Christoph Hellwig <hch@lst.de>

Signed-off-by: Felix Maurer <fmaurer@redhat.com>
This commit is contained in:
Felix Maurer 2024-10-11 17:06:38 +02:00
parent ea81551570
commit d4192ad886
1 changed files with 19 additions and 14 deletions

View File

@ -398,16 +398,26 @@ static struct page *__page_pool_get_cached(struct page_pool *pool)
return page;
}
static void page_pool_dma_sync_for_device(const struct page_pool *pool,
const struct page *page,
unsigned int dma_sync_size)
static void __page_pool_dma_sync_for_device(const struct page_pool *pool,
const struct page *page,
u32 dma_sync_size)
{
#if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC)
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_for_device(pool->p.dev, dma_addr + pool->p.offset,
dma_sync_size, pool->p.dma_dir);
#endif
}
static __always_inline void
page_pool_dma_sync_for_device(const struct page_pool *pool,
const struct page *page,
u32 dma_sync_size)
{
if (pool->dma_sync && dma_dev_need_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)
@ -429,8 +439,7 @@ 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;
@ -699,9 +708,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
if (likely(__page_pool_page_can_be_recycled(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 && page_pool_recycle_in_cache(page, pool))
return NULL;
@ -840,9 +847,7 @@ static struct page *page_pool_drain_frag(struct page_pool *pool,
return NULL;
if (__page_pool_page_can_be_recycled(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;
}