Re: [PATCH rfc v2 2/5] page_pool: add interface for getting and setting pagecnt_bias
From: Alexander Duyck <hidden>
Date: 2021-07-10 16:55:27
Also in:
bpf, lkml
On Sat, Jul 10, 2021 at 12:44 AM Yunsheng Lin [off-list ref] wrote:
quoted hunk ↗ jump to hunk
As suggested by Alexander, "A DMA mapping should be page aligned anyway so the lower 12 bits would be reserved 0", so it might make more sense to repurpose the lower 12 bits of the dma address to store the pagecnt_bias for elevated refcnt case in page pool. As newly added page_pool_get_pagecnt_bias() may be called outside of the softirq context, so annotate the access to page->dma_addr[0] with READ_ONCE() and WRITE_ONCE(). Other three interfaces using page->dma_addr[0] is only called in the softirq context during normal rx processing, hopefully the barrier in the rx processing will ensure the correct order between getting and setting pagecnt_bias. Signed-off-by: Yunsheng Lin <redacted> --- include/net/page_pool.h | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-)diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 8d7744d..5746f17 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h@@ -200,7 +200,7 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - dma_addr_t ret = page->dma_addr[0]; + dma_addr_t ret = READ_ONCE(page->dma_addr[0]) & PAGE_MASK; if (sizeof(dma_addr_t) > sizeof(unsigned long)) ret |= (dma_addr_t)page->dma_addr[1] << 16 << 16; return ret;@@ -208,11 +208,31 @@ static inline dma_addr_t page_pool_get_dma_addr(struct page *page) static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) { - page->dma_addr[0] = addr; + unsigned long dma_addr_0 = READ_ONCE(page->dma_addr[0]); + + dma_addr_0 &= ~PAGE_MASK; + dma_addr_0 |= (addr & PAGE_MASK);
So rather than doing all this testing and clearing it would probably
be better to add a return value to the function and do something like:
if (WARN_ON(dma_addr_0 & ~PAGE_MASK))
return -1;
That way you could have page_pool_dma_map unmap, free the page, and
return false indicating that the DMA mapping failed with a visible
error in the event that our expectionat that the dma_addr is page
aligned is ever violated.
+ WRITE_ONCE(page->dma_addr[0], dma_addr_0);
+
if (sizeof(dma_addr_t) > sizeof(unsigned long))
page->dma_addr[1] = upper_32_bits(addr);
}
+static inline int page_pool_get_pagecnt_bias(struct page *page)
+{
+ return (READ_ONCE(page->dma_addr[0]) & ~PAGE_MASK);You don't need the parenthesis around the READ_ONCE and PAGE_MASK.
+}
+
+static inline void page_pool_set_pagecnt_bias(struct page *page, int bias)
+{
+ unsigned long dma_addr_0 = READ_ONCE(page->dma_addr[0]);
+
+ dma_addr_0 &= PAGE_MASK;
+ dma_addr_0 |= (bias & ~PAGE_MASK);
+
+ WRITE_ONCE(page->dma_addr[0], dma_addr_0);
+}
+
static inline bool is_page_pool_compiled_in(void)
{
#ifdef CONFIG_PAGE_POOL
--
2.7.4