From mboxrd@z Thu Jan 1 00:00:00 1970 From: Lu Baolu Subject: Re: [PATCH v5 02/12] iommu/vt-d: Manage scalalble mode PASID tables Date: Thu, 6 Dec 2018 09:13:50 +0800 Message-ID: References: <20181128035449.10226-1-baolu.lu@linux.intel.com> <20181128035449.10226-3-baolu.lu@linux.intel.com> <20181203134411.lejlkbnagxml54ro@8bytes.org> <5c81008b-30e8-177d-0182-db366608562f@linux.intel.com> <20181205155012.GC16835@8bytes.org> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20181205155012.GC16835@8bytes.org> Content-Language: en-US Sender: linux-kernel-owner@vger.kernel.org To: Joerg Roedel Cc: baolu.lu@linux.intel.com, "Liu, Yi L" , David Woodhouse , "Raj, Ashok" , "Kumar, Sanjay K" , "Pan, Jacob jun" , "Tian, Kevin" , "Sun, Yi Y" , "peterx@redhat.com" , Jean-Philippe Brucker , "iommu@lists.linux-foundation.org" , "linux-kernel@vger.kernel.org" , Jacob Pan List-Id: iommu@lists.linux-foundation.org Hi Joerg, On 12/5/18 11:50 PM, Joerg Roedel wrote: > On Tue, Dec 04, 2018 at 01:58:06PM +0800, Lu Baolu wrote: >> This function is called in an unsleepable context. >> >> spin_lock(&lock) >> [...] >> if (pasid_table_is_necessary) >> allocate_pasid_table(dev) >> [...] >> spin_unlock(&lock) >> >> We can move it out of the lock range. >> >> How about >> >> if (pasid_table_is_necessary) >> pasid_table = allocate_pasid_table(dev) >> >> spin_lock(&lock) >> [...] >> if (pasid_table_is_necessary) >> set_up_pasid_table(pasid_table) >> [...] >> spin_unlock(&lock) > > Hmm, so when the IOMMU is configured in scalable mode we can just > allocate a pasid-table for the device when we set it up, right? > > Scalable mode is a boot-time decision, so we know for sure whether we > need a pasid-table on device-setup time. And the device-setup code it > preemptable, so I think it this allocation should be outside of any > spin-locked section. Fair enough. I will fix this up in the next version. Thank you for pointing this out. Best regards, Lu Baolu