netdev - Re: [PATCH v3 net-next 1/6] net: dsa: introduce a dsa_port_from

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20200506115550.GB1265908@t480s.localdomain>
Date:   Wed, 6 May 2020 11:55:50 -0400
From:   Vivien Didelot <vivien.didelot@...il.com>
To:     Vladimir Oltean <olteanv@...il.com>
Cc:     netdev@...r.kernel.org, andrew@...n.ch, f.fainelli@...il.com,
        vinicius.gomes@...el.com, po.liu@....com
Subject: Re: [PATCH v3 net-next 1/6] net: dsa: introduce a
 dsa_port_from_netdev public helper

On Tue,  5 May 2020 22:20:52 +0300, Vladimir Oltean <olteanv@...il.com> wrote:
> From: Vladimir Oltean <vladimir.oltean@....com>
> 
> As its implementation shows, this is synonimous with calling
> dsa_slave_dev_check followed by dsa_slave_to_port, so it is quite simple
> already and provides functionality which is already there.
> 
> However there is now a need for these functions outside dsa_priv.h, for
> example in drivers that perform mirroring and redirection through
> tc-flower offloads (they are given raw access to the flow_cls_offload
> structure), where they need to call this function on act->dev.
> 
> But simply exporting dsa_slave_to_port would make it non-inline and
> would result in an extra function call in the hotpath, as can be seen
> for example in sja1105:
> 
> Before:
> 
> 000006dc <sja1105_xmit>:
> {
>  6dc:	e92d4ff0 	push	{r4, r5, r6, r7, r8, r9, sl, fp, lr}
>  6e0:	e1a04000 	mov	r4, r0
>  6e4:	e591958c 	ldr	r9, [r1, #1420]	; 0x58c <- Inline dsa_slave_to_port
>  6e8:	e1a05001 	mov	r5, r1
>  6ec:	e24dd004 	sub	sp, sp, #4
> 	u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index);
>  6f0:	e1c901d8 	ldrd	r0, [r9, #24]
>  6f4:	ebfffffe 	bl	0 <dsa_8021q_tx_vid>
> 			6f4: R_ARM_CALL	dsa_8021q_tx_vid
> 	u8 pcp = netdev_txq_to_tc(netdev, queue_mapping);
>  6f8:	e1d416b0 	ldrh	r1, [r4, #96]	; 0x60
> 	u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index);
>  6fc:	e1a08000 	mov	r8, r0
> 
> After:
> 
> 000006e4 <sja1105_xmit>:
> {
>  6e4:	e92d4ff0 	push	{r4, r5, r6, r7, r8, r9, sl, fp, lr}
>  6e8:	e1a04000 	mov	r4, r0
>  6ec:	e24dd004 	sub	sp, sp, #4
> 	struct dsa_port *dp = dsa_slave_to_port(netdev);
>  6f0:	e1a00001 	mov	r0, r1
> {
>  6f4:	e1a05001 	mov	r5, r1
> 	struct dsa_port *dp = dsa_slave_to_port(netdev);
>  6f8:	ebfffffe 	bl	0 <dsa_slave_to_port>
> 			6f8: R_ARM_CALL	dsa_slave_to_port
>  6fc:	e1a09000 	mov	r9, r0
> 	u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index);
>  700:	e1c001d8 	ldrd	r0, [r0, #24]
>  704:	ebfffffe 	bl	0 <dsa_8021q_tx_vid>
> 			704: R_ARM_CALL	dsa_8021q_tx_vid
> 
> Because we want to avoid possible performance regressions, introduce
> this new function which is designed to be public.
> 
> Suggested-by: Vivien Didelot <vivien.didelot@...il.com>
> Signed-off-by: Vladimir Oltean <vladimir.oltean@....com>

Reviewed-by: Vivien Didelot <vivien.didelot@...il.com>