[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20200908110757.477bacb8@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com>
Date: Tue, 8 Sep 2020 11:07:57 -0700
From: Jakub Kicinski <kuba@...nel.org>
To: Maxim Mikityanskiy <maximmi@...dia.com>
Cc: Saeed Mahameed <saeedm@...dia.com>, <netdev@...r.kernel.org>,
"Maxim Mikityanskiy" <maximmi@...lanox.com>,
Tariq Toukan <tariqt@...lanox.com>
Subject: Re: [net-next 06/10] net/mlx5e: Support multiple SKBs in a TX WQE
On Tue, 8 Sep 2020 11:59:54 +0300 Maxim Mikityanskiy wrote:
> On 2020-09-04 01:46, Jakub Kicinski wrote:
> > On Thu, 3 Sep 2020 14:00:18 -0700 Saeed Mahameed wrote:
> >> +static inline void mlx5e_tx_wi_consume_fifo_skbs(struct mlx5e_txqsq *sq,
> >> + struct mlx5e_tx_wqe_info *wi,
> >> + struct mlx5_cqe64 *cqe,
> >> + int napi_budget)
> >> +{
> >> + int i;
> >> +
> >> + for (i = 0; i < wi->num_fifo_pkts; i++) {
> >> + struct sk_buff *skb = mlx5e_skb_fifo_pop(sq);
> >> +
> >> + mlx5e_consume_skb(sq, skb, cqe, napi_budget);
> >> + }
> >> +}
> >
> > The compiler was not inlining this one either?
>
> Regarding this one, gcc inlines it automatically, but I went on the safe
> side and inlined it explicitly - it's small and called for every WQE, so
> we never want it to be non-inline.
Everyone always wants to be on the safe side :/ That's not an argument
we accept in this context.
Powered by blists - more mailing lists