Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <20190701083604.24528-1-ttayar@habana.ai>
In-Reply-To: <20190701083604.24528-1-ttayar@habana.ai>
From:   Oded Gabbay <oded.gabbay@gmail.com>
Date:   Mon, 1 Jul 2019 12:00:32 +0300
Message-ID: <CAFCwf12F+LWE4brhJ9rj35yJfdnv=EqRtXfo4MVUpKYGCc6JKA@mail.gmail.com>
Subject: Re: [PATCH 1/2] habanalabs: Add debugfs node for engines status
To:     Tomer Tayar <ttayar@habana.ai>
Cc:     "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, Jul 1, 2019 at 11:36 AM Tomer Tayar <ttayar@habana.ai> wrote:
>
> Command submissions sent to the device are composed of command buffers
> which are targeted to different device engines, like DMA and compute
> entities. When a command submission gets stuck, knowing in which engine
> the stuck is, is crucial for debugging.
> This patch adds a debugfs node that exports this information, by
> displaying the engines' various registers that assemble their idle/busy
> status.
If this is a new node, then you are missing the update to
Documentation/debugfs-driver-habanalabs

>
> The information retrieval is based on the is_device_idle ASIC function.
> The printout in this function, of the first detected busy engine, is
> removed because it becomes redundant in the presence of the more
> elaborated info of the new debugfs node.
>
> The patch also updates the device idle check:
> - Add reading the DMA core status register, because it is possible that
>   QMAN has finished its work but the DMA itself is still running.
> - Remove the MME shadow status check, as the MME ARCH status register
>   includes the status of all MME shadows.
This seems better to separate into a different patch.
So I suggest first a patch that fixes the device idle check and then
this patch (that adds the debugfs node and uses the idle check
function).

Thanks,
Oded