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
| ||
|
Date: Tue, 10 Mar 2020 09:52:31 -0700 From: "Jonathan Lemon" <jonathan.lemon@...il.com> To: "David Miller" <davem@...emloft.net> Cc: netdev@...r.kernel.org, brouer@...hat.com, ilias.apalodimas@...aro.org, kernel-team@...com Subject: Re: [PATCH] page_pool: use irqsave/irqrestore to protect ring access. On 9 Mar 2020, at 17:55, David Miller wrote: > From: Jonathan Lemon <jonathan.lemon@...il.com> > Date: Mon, 9 Mar 2020 12:49:29 -0700 > >> netpoll may be called from IRQ context, which may access the >> page pool ring. The current _bh variants do not provide sufficient >> protection, so use irqsave/restore instead. >> >> Error observed on a modified mlx4 driver, but the code path exists >> for any driver which calls page_pool_recycle from napi poll. >> >> WARNING: CPU: 34 PID: 550248 at /ro/source/kernel/softirq.c:161 >> __local_bh_enable_ip+0x35/0x50 > ... >> Signed-off-by: Jonathan Lemon <jonathan.lemon@...il.com> > > The netpoll stuff always makes the locking more complicated than it > needs > to be. I wonder if there is another way around this issue? > > Because IRQ save/restore is a high cost to pay in this critical path. I agree with this - the proposed patch is more of a bandaid than anything else. Why is the entire network poll path being called with IRQs off? That seems wrong - while netcons is expected to work in all cases, it does seem like it should be smarter and for the normal case, just queue and raise NET_TX_SOFTIRQ would be a more logical path. -- Jonathan
Powered by blists - more mailing lists