Messages in this thread | | | From | Jesper Dangaard Brouer <> | Date | Fri, 28 Jul 2023 11:32:01 +0200 | Subject | Re: [PATCH net-next 9/9] net: skbuff: always try to recycle PP pages directly when in softirq |
| |
On 27/07/2023 16.43, Alexander Lobakin wrote: > Commit 8c48eea3adf3 ("page_pool: allow caching from safely localized > NAPI") allowed direct recycling of skb pages to their PP for some cases, > but unfortunately missed a couple of other majors. > For example, %XDP_DROP in skb mode. The netstack just calls kfree_skb(), > which unconditionally passes `false` as @napi_safe. Thus, all pages go > through ptr_ring and locks, although most of time we're actually inside > the NAPI polling this PP is linked with, so that it would be perfectly > safe to recycle pages directly.
The commit messages is hard to read. It would help me as the reader if you used a empty line between paragraphs, like in this location (same goes for other commit descs).
> Let's address such. If @napi_safe is true, we're fine, don't change > anything for this path. But if it's false, check whether we are in the > softirq context. It will most likely be so and then if ->list_owner > is our current CPU, we're good to use direct recycling, even though > @napi_safe is false -- concurrent access is excluded. in_softirq() > protection is needed mostly due to we can hit this place in the > process context (not the hardirq though).
This patch make me a little nervous, as it can create hard-to-debug bugs if this isn't 100% correct. (Thanks for previous patch that exclude hardirq via lockdep).
> For the mentioned xdp-drop-skb-mode case, the improvement I got is > 3-4% in Mpps. As for page_pool stats, recycle_ring is now 0 and > alloc_slow counter doesn't change most of time, which means the > MM layer is not even called to allocate any new pages. > > Suggested-by: Jakub Kicinski <kuba@kernel.org> # in_softirq() > Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com> > --- > net/core/skbuff.c | 4 +++- > 1 file changed, 3 insertions(+), 1 deletion(-) > > diff --git a/net/core/skbuff.c b/net/core/skbuff.c > index e701401092d7..5ba3948cceed 100644 > --- a/net/core/skbuff.c > +++ b/net/core/skbuff.c > @@ -901,8 +901,10 @@ bool page_pool_return_skb_page(struct page *page, bool napi_safe) > /* Allow direct recycle if we have reasons to believe that we are > * in the same context as the consumer would run, so there's > * no possible race. > + * __page_pool_put_page() makes sure we're not in hardirq context > + * and interrupts are enabled prior to accessing the cache. > */ > - if (napi_safe) { > + if (napi_safe || in_softirq()) {
I used to have in_serving_softirq() in PP to exclude process context that just disabled BH to do direct recycling (into a lockless array). This changed in kernel v6.3 commit 542bcea4be86 ("net: page_pool: use in_softirq() instead") to help threaded NAPI. I guess, nothing blew up so I guess this was okay to relax this.
> const struct napi_struct *napi = READ_ONCE(pp->p.napi); > > allow_direct = napi &&
AFAIK this in_softirq() will allow process context with disabled BH to also recycle directly into the PP lockless array. With the additional checks (that are just outside above diff-context) that I assume makes sure CPU (smp_processor_id()) also match. Is this safe?
--Jesper
| |