[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Mon, 1 Feb 2021 23:59:52 +0000
From: Chaitanya Kulkarni <Chaitanya.Kulkarni@....com>
To: Jianxiong Gao <jxgao@...gle.com>, Keith Busch <kbusch@...nel.org>
CC: "heikki.krogerus@...ux.intel.com" <heikki.krogerus@...ux.intel.com>,
"sagi@...mberg.me" <sagi@...mberg.me>,
Saravana Kannan <saravanak@...gle.com>,
Konrad Rzeszutek Wilk <konrad.wilk@...cle.com>,
Marc Orr <marcorr@...gle.com>,
"gregkh@...uxfoundation.org" <gregkh@...uxfoundation.org>,
"rafael.j.wysocki@...el.com" <rafael.j.wysocki@...el.com>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"linux-nvme@...ts.infradead.org" <linux-nvme@...ts.infradead.org>,
"axboe@...com" <axboe@...com>,
"bgolaszewski@...libre.com" <bgolaszewski@...libre.com>,
"iommu@...ts.linux-foundation.org" <iommu@...ts.linux-foundation.org>,
"jroedel@...e.de" <jroedel@...e.de>,
Erdem Aktas <erdemaktas@...gle.com>,
"dan.j.williams@...el.com" <dan.j.williams@...el.com>,
Andy Shevchenko <andriy.shevchenko@...ux.intel.com>,
Robin Murphy <robin.murphy@....com>,
Christoph Hellwig <hch@....de>,
"m.szyprowski@...sung.com" <m.szyprowski@...sung.com>
Subject: Re: [PATCH V2 3/3] Adding device_dma_parameters->offset_preserve_mask
to NVMe driver.
On 2/1/21 13:27, Jianxiong Gao wrote:
>> Why is this setting being done and undone on each IO? Wouldn't it be
>> more efficient to set it once during device initialization?
>>
>> And more importantly, this isn't thread safe: one CPU may be setting the
>> device's dma alignment mask to 0 while another CPU is expecting it to be
>> NVME_CTRL_PAGE_SIZE - 1.
> I was having trouble getting the OS booted when setting it once during
> initialization. However when I rebased to the latest rc6 this morning it
> seems to be working with setting the mask on probe. I am still testing out
> and will appreciate any idea what may cause the nvme driver to fail
> with a single mask.
Based on the Keith's comment it needs to be completely avoided in hot path.
Did you get a chance to bisect the problem in the rc6 ? We need to know the
root cause otherwise it might happen again after we add this patch.
Powered by blists - more mailing lists