On 12/20/24 22:38, Jakub Kicinski wrote:
On Tue, 17 Dec 2024 16:37:40 -0800 David Wei wrote:
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index e4be227d3ad6..13d810a28ed6 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
The top of this file says:
/* Do not edit directly, auto-generated from: */
/* Documentation/netlink/specs/netdev.yaml */
Ok
+static void io_zcrx_refill_slow(struct page_pool *pp, struct io_zcrx_ifq *ifq)
+{
+ struct io_zcrx_area *area = ifq->area;
+
+ spin_lock_bh(&area->freelist_lock);
+ while (area->free_count && pp->alloc.count < PP_ALLOC_CACHE_REFILL) {
+ struct net_iov *niov = __io_zcrx_get_free_niov(area);
+ netmem_ref netmem = net_iov_to_netmem(niov);
+
+ page_pool_set_pp_info(pp, netmem);
+ page_pool_mp_return_in_cache(pp, netmem);
+ pp->pages_state_hold_cnt++;
But the kdoc on page_pool_mp_return_in_cache() says:
+ * Return already allocated and accounted netmem to the page pool's allocation
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Ok, I'll reword it
+ trace_page_pool_state_hold(pp, netmem, pp->pages_state_hold_cnt);
+ }
+ spin_unlock_bh(&area->freelist_lock);
+}
+ if (page_pool_unref_netmem(netmem, 1) == 0)
page_pool_unref_and_test()
That would make the series to depend on net-next, which would make
merging with io_uring trickier. I actually used page_pool_is_last_ref()
for a brief moment until it got renamed.
--
Pavel Begunkov