[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <aL8kYo1cHHNg1H3N@nvidia.com>
Date: Mon, 8 Sep 2025 11:45:54 -0700
From: Nicolin Chen <nicolinc@...dia.com>
To: Jason Gunthorpe <jgg@...dia.com>
CC: <will@...nel.org>, <robin.murphy@....com>, <joro@...tes.org>,
<jean-philippe@...aro.org>, <miko.lenczewski@....com>, <balbirs@...dia.com>,
<peterz@...radead.org>, <smostafa@...gle.com>, <kevin.tian@...el.com>,
<praan@...gle.com>, <zhangzekun11@...wei.com>,
<linux-arm-kernel@...ts.infradead.org>, <iommu@...ts.linux.dev>,
<linux-kernel@...r.kernel.org>, <patches@...ts.linux.dev>
Subject: Re: [PATCH rfcv1 7/8] iommu/arm-smmu-v3: Add arm_smmu_invs based
arm_smmu_domain_inv_range()
On Mon, Sep 08, 2025 at 03:24:04PM -0300, Jason Gunthorpe wrote:
> On Mon, Sep 08, 2025 at 11:19:40AM -0700, Nicolin Chen wrote:
> > So, would it be better to just always take the read lock, while
> > applying the ATS condition to the writer side:
>
> No, the whole optimization is to avoid read side locking on the fairly
> common no-ATS case.
>
> Always taking the lock destroys that.
OK. I skimmed through the lock_acquire(). It seems to be a bit
heavier than I expected. Perhaps this is the part we wanted to
avoid.
Thanks
Nicolin
Powered by blists - more mailing lists