linux-kernel - Re: [RFT PATCH] hwmon: (spd5118) Add support for Renesas/ITD SPD5118 hub controllers

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: Mon, 17 Jun 2024 00:50:41 +0200
From: Armin Wolf <W_Armin@....de>
To: Guenter Roeck <linux@...ck-us.net>, linux-hwmon@...r.kernel.org
Cc: linux-i2c@...r.kernel.org, linux-kernel@...r.kernel.org,
 devicetree@...r.kernel.org, Krzysztof Kozlowski <krzk+dt@...nel.org>,
 Wolfram Sang <wsa+renesas@...g-engineering.com>,
 René Rebe <rene@...ctcode.de>,
 Thomas Weißschuh <linux@...ssschuh.net>,
 Stephen Horvath <s.horvath@...look.com.au>,
 Paul Menzel <pmenzel@...gen.mpg.de>, Sasha Kozachuk <skozachuk@...gle.com>,
 John Hamrick <johnham@...gle.com>
Subject: Re: [RFT PATCH] hwmon: (spd5118) Add support for Renesas/ITD SPD5118
 hub controllers

Am 16.06.24 um 22:26 schrieb Guenter Roeck:

> Hi Armin,
>
> On 6/16/24 11:09, Armin Wolf wrote:
>> Am 14.06.24 um 20:59 schrieb Guenter Roeck:
>>
>>> The SPD5118 specification says, in its documentation of the page bits
>>> in the MR11 register:
>>>
>>> "
>>> This register only applies to non-volatile memory (1024) Bytes)
>>> access of
>>> SPD5 Hub device.
>>> For volatile memory access, this register must be programmed to '000'.
>>> ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
>>> "
>>>
>>> Renesas/ITD SPD5118 hub controllers take this literally and disable
>>> access
>>> to volatile memory if the page selected in MR11 is != 0. Since the
>>> BIOS or
>>> ROMMON will access the non-volatile memory and likely select a page
>>> != 0,
>>> this means that the driver will not instantiate since it can not
>>> identify
>>> the chip. Even if the driver instantiates, access to volatile registers
>>> is blocked after a nvram read operation which selects a page other
>>> than 0.
>>>
>>> To solve the problem, add initialization code to select page 0 during
>>> probe. Before doing that, use basic validation to ensure that this is
>>> really a SPD5118 device and not some random EEPROM. Explicitly select
>>> page 0 when accessing the volatile register space, and protect volatile
>>> register access against nvmem access using the device mutex.
>>
>> Hi,
>>
>> maybe we can use struct regmap_range_cfg so the paged register
>> accesses are being
>> done by the regmap code itself?
>>
>
> In theory that might work, but regmap does not permit a selector
> register to
> be part of another range. The first range would be the non-volatile
> registers,
> and the selector register is part of that for all ranges.
>
> I tried the following ranges configuration.
>
> static const struct regmap_range_cfg spd5118_regmap_range_cfg[] = {
>         {
>         .selector_reg     = SPD5118_REG_I2C_LEGACY_MODE,
>         .selector_mask    = SPD5118_LEGACY_PAGE_MASK,
>         .selector_shift   = 0,
>         .window_start     = 0,
>         .window_len       = SPD5118_PAGE_SIZE,
>         .range_min        = 0,
>         .range_max        = SPD5118_PAGE_SIZE - 1,
>         },
>         {
>         .selector_reg     = SPD5118_REG_I2C_LEGACY_MODE,
>         .selector_mask    = SPD5118_LEGACY_PAGE_MASK,
>         .selector_shift   = 0,
>         .window_start     = SPD5118_PAGE_SIZE,
>         .window_len       = SPD5118_PAGE_SIZE,
>         .range_min        = SPD5118_PAGE_SIZE,
>         .range_max        = 9 * SPD5118_PAGE_SIZE - 1,
>         },
> };
>
> This results in
>
> spd5118 0-0050: Range 0: selector for 1 in window
> spd5118 0-0050: error -EINVAL: regmap init failed
>
> If you have an idea how to configure the ranges differently,
> please let me know.
>
> Thanks,
> Guenter
>
Oh, i did not think of this. In this case we indeed cannot use regmap here. I will test the patch tomorrow.

Thanks,
Armin Wolf