Received-SPF: pass (google.com: domain of linux-kernel+bounces-19338-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
From: David Laight <David.Laight@ACULAB.COM>
To: 'Andrew Lunn' <andrew@lunn.ch>, =?iso-8859-2?Q?Petr_Tesa=F8=EDk?=
	<petr@tesarici.cz>
CC: Eric Dumazet <edumazet@google.com>, Alexandre Torgue
	<alexandre.torgue@foss.st.com>, Jose Abreu <joabreu@synopsys.com>, "David S.
 Miller" <davem@davemloft.net>, Jakub Kicinski <kuba@kernel.org>, Paolo Abeni
	<pabeni@redhat.com>, Maxime Coquelin <mcoquelin.stm32@gmail.com>, "Chen-Yu
 Tsai" <wens@csie.org>, Jernej Skrabec <jernej.skrabec@gmail.com>, "Samuel
 Holland" <samuel@sholland.org>, "open list:STMMAC ETHERNET DRIVER"
	<netdev@vger.kernel.org>, "moderated list:ARM/STM32 ARCHITECTURE"
	<linux-stm32@st-md-mailman.stormreply.com>, "moderated list:ARM/STM32
 ARCHITECTURE" <linux-arm-kernel@lists.infradead.org>, open list
	<linux-kernel@vger.kernel.org>, "open list:ARM/Allwinner sunXi SoC support"
	<linux-sunxi@lists.linux.dev>, Jiri Pirko <jiri@resnulli.us>
Subject: RE: [PATCH] net: stmmac: protect statistics updates with a spinlock
Thread-Topic: [PATCH] net: stmmac: protect statistics updates with a spinlock
Thread-Index: AQHaP/3Ni9qIc9t6xUGHU0aBdMePobDPuW8A
Date: Mon, 8 Jan 2024 10:34:35 +0000
Message-ID: <d05ca29283eb47df9c58838cb87a887c@AcuMS.aculab.com>
References: <20240105091556.15516-1-petr@tesarici.cz>
 <CANn89iLuYZBersxq4aH-9Fg_ojD0fh=0xtdLbRdbMrup=nvrkA@mail.gmail.com>
 <20240105113402.0f5f1232@meshulam.tesarici.cz>
 <CANn89iLEvW9ZS=+WPETPC=mKRyu9AKmueGCWZZOrz9oX3Xef=g@mail.gmail.com>
 <20240105121447.11ae80d1@meshulam.tesarici.cz>
 <20240105142732.1903bc70@meshulam.tesarici.cz>
 <CANn89iLHLvGFX_JEYU-en0ZoCUpTvjXPBzFECxLFfa_Jhpcjmg@mail.gmail.com>
 <CANn89iKWSemsKmfsLjupwWBnyeKjtHH+mZjTzYiJT4G=xyUrNQ@mail.gmail.com>
 <20240105154558.2ca38aca@meshulam.tesarici.cz>
 <a8bb0eb0-8398-4e7e-8dc5-6ebf2f981ca8@lunn.ch>
In-Reply-To: <a8bb0eb0-8398-4e7e-8dc5-6ebf2f981ca8@lunn.ch>
Accept-Language: en-GB, en-US
Precedence: bulk
MIME-Version: 1.0
Content-Language: en-US
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

From: Andrew Lunn
> Sent: 05 January 2024 17:37
>=20
> > This only leaves an atomic_t in hard irq context. I have tried to find
> > something that could relax the requirement, but AFAICS at least some
> > setups use several interrupts that can be delivered to different CPUs
> > simultaneously, and all of them will walk over all channels. So we're
> > left with an atomic_t here.
>=20
> You might want to consider per CPU statistics. Since each CPU has its
> own structure of statistics, you don't need atomic.
>=20
> The code actually using the statistics then needs to sum up the per
> CPU statistics, and using syncp should be sufficient for that.

Doesn't that consume rather a lot of memory on systems with
'silly numbers' of cpu?

Updating an atomic_t is (pretty much) the same as taking a lock.
unlock() is also likely to also contain an atomic operation.
So if you update more than two atomic_t it is likely that a lock
will be faster.

=09David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1=
PT, UK
Registration No: 1397386 (Wales)