Messages in this thread | | | Date | Thu, 18 May 2023 15:34:44 +0200 | Subject | Re: [PATCH net-next 06/11] net: page_pool: avoid calling no-op externals when possible | From | Alexander Lobakin <> |
| |
From: Jakub Kicinski <kuba@kernel.org> Date: Wed, 17 May 2023 21:08:04 -0700
> On Tue, 16 May 2023 18:18:36 +0200 Alexander Lobakin wrote: >> + /* Try to avoid calling no-op syncs */ >> + pool->p.flags |= PP_FLAG_DMA_MAYBE_SYNC; >> + pool->p.flags &= ~PP_FLAG_DMA_SYNC_DEV; >> } >> >> if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT && >> @@ -323,6 +327,12 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page) >> >> page_pool_set_dma_addr(page, dma); >> >> + if ((pool->p.flags & PP_FLAG_DMA_MAYBE_SYNC) && >> + dma_need_sync(pool->p.dev, dma)) { >> + pool->p.flags |= PP_FLAG_DMA_SYNC_DEV; >> + pool->p.flags &= ~PP_FLAG_DMA_MAYBE_SYNC; >> + } > > is it just me or does it feel cleaner to allocate a page at init, > and throw it into the cache, rather than adding a condition to a > fast(ish) path?
When recycling is on, not that fast -- new allocations occur relatively rarely and it's allocations anyway, one `if` doesn't change anything there.
And seems like I didn't get the sentence regarding "allocate and throw" :s This condition just disables the shortcut if any new page suddenly requires real DMA syncs (and if it does, then the sync a line below will take way more time than 1 more `if` anyway).
Thanks, Olek
| |