linux-kernel - Re: [PATCH] PCI: apple: Fix REFCLK1 enable/poll logic

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Wed, 1 Dec 2021 02:26:39 +0900
From:   Hector Martin <marcan@...can.st>
To:     Lorenzo Pieralisi <lorenzo.pieralisi@....com>,
        Marc Zyngier <maz@...nel.org>, bhelgaas@...gle.com
Cc:     Alyssa Rosenzweig <alyssa@...enzweig.io>,
        Rob Herring <robh@...nel.org>,
        Krzysztof Wilczyński <kw@...ux.com>,
        linux-pci@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH] PCI: apple: Fix REFCLK1 enable/poll logic

On 01/12/2021 01.49, Lorenzo Pieralisi wrote:
> On Wed, Nov 17, 2021 at 05:56:12PM +0000, Marc Zyngier wrote:
>> On Wed, 17 Nov 2021 14:00:44 +0000,
>> Hector Martin <marcan@...can.st> wrote:
>>>
>>> REFCLK1 has req/ack bits just like REFCLK0
>>>
>>> Signed-off-by: Hector Martin <marcan@...can.st>
>>> ---
>>>   drivers/pci/controller/pcie-apple.c | 7 ++++---
>>>   1 file changed, 4 insertions(+), 3 deletions(-)
>>>
>>> diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c
>>> index b665d29af77a..420c291a5c68 100644
>>> --- a/drivers/pci/controller/pcie-apple.c
>>> +++ b/drivers/pci/controller/pcie-apple.c
>>> @@ -42,8 +42,9 @@
>>>   #define   CORE_FABRIC_STAT_MASK		0x001F001F
>>>   #define CORE_LANE_CFG(port)		(0x84000 + 0x4000 * (port))
>>>   #define   CORE_LANE_CFG_REFCLK0REQ	BIT(0)
>>> -#define   CORE_LANE_CFG_REFCLK1		BIT(1)
>>> +#define   CORE_LANE_CFG_REFCLK1REQ	BIT(1)
>>>   #define   CORE_LANE_CFG_REFCLK0ACK	BIT(2)
>>> +#define   CORE_LANE_CFG_REFCLK1ACK	BIT(3)
>>>   #define   CORE_LANE_CFG_REFCLKEN	(BIT(9) | BIT(10))
>>>   #define CORE_LANE_CTL(port)		(0x84004 + 0x4000 * (port))
>>>   #define   CORE_LANE_CTL_CFGACC		BIT(15)
>>> @@ -481,9 +482,9 @@ static int apple_pcie_setup_refclk(struct apple_pcie *pcie,
>>>   	if (res < 0)
>>>   		return res;
>>>   
>>> -	rmw_set(CORE_LANE_CFG_REFCLK1, pcie->base + CORE_LANE_CFG(port->idx));
>>> +	rmw_set(CORE_LANE_CFG_REFCLK1REQ, pcie->base + CORE_LANE_CFG(port->idx));
>>>   	res = readl_relaxed_poll_timeout(pcie->base + CORE_LANE_CFG(port->idx),
>>> -					 stat, stat & CORE_LANE_CFG_REFCLK1,
>>> +					 stat, stat & CORE_LANE_CFG_REFCLK1ACK,
>>>   					 100, 50000);
>>>   
>>>   	if (res < 0)
>>> -- 
>>> 2.33.0
>>>
>>>
>>
>> Fixes: 1e33888fbe44 ("PCI: apple: Add initial hardware bring-up")
>> Acked-by: Marc Zyngier <maz@...nel.org>
> 
> Hi Hector, Bjorn,
> 
> if this is a fix we can aim at one of the upcoming -rcX.
> 
> It would be nicer though to explain a bit better what it is
> fixing in the commit log (and what's broken if we don't merge it),
> as it stands it is a bit terse.

I don't think anything is broken per se, it still works without this 
patch (probably because the refclk gets enabled fast enough that we 
don't have to wait for it); it's just that I think this is the correct 
logic. This is all reverse engineered anyway, so ultimately there is no 
hardware documentation to point to to say what's right and what's wrong...

-- 
Hector Martin (marcan@...can.st)
Public Key: https://mrcn.st/pub