netdev - Re: [PATCH V5 1/5] PCI: Add TLP Processing Hints (TPH) support

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]

Message-ID: <26c176a9-aa68-95de-7157-b3669d5bb404@amd.com>
Date: Tue, 24 Sep 2024 15:33:54 +0100
From: Alejandro Lucero Palau <alucerop@....com>
To: Wei Huang <wei.huang2@....com>, linux-pci@...r.kernel.org,
 linux-kernel@...r.kernel.org, linux-doc@...r.kernel.org,
 netdev@...r.kernel.org
Cc: Jonathan.Cameron@...wei.com, helgaas@...nel.org, corbet@....net,
 davem@...emloft.net, edumazet@...gle.com, kuba@...nel.org,
 pabeni@...hat.com, alex.williamson@...hat.com, gospo@...adcom.com,
 michael.chan@...adcom.com, ajit.khaparde@...adcom.com,
 somnath.kotur@...adcom.com, andrew.gospodarek@...adcom.com,
 manoj.panicker2@....com, Eric.VanTassell@....com, vadim.fedorenko@...ux.dev,
 horms@...nel.org, bagasdotme@...il.com, bhelgaas@...gle.com,
 lukas@...ner.de, paul.e.luse@...el.com, jing2.liu@...el.com
Subject: Re: [PATCH V5 1/5] PCI: Add TLP Processing Hints (TPH) support


On 9/23/24 21:27, Wei Huang wrote:
>
>
> On 9/23/24 7:07 AM, Alejandro Lucero Palau wrote:
>>
>
> ...
>
>>> +/**
>>> + * pcie_enable_tph - Enable TPH support for device using a specific 
>>> ST mode
>>> + * @pdev: PCI device
>>> + * @mode: ST mode to enable. Current supported modes include:
>>> + *
>>> + *   - PCI_TPH_ST_NS_MODE: NO ST Mode
>>> + *   - PCI_TPH_ST_IV_MODE: Interrupt Vector Mode
>>> + *   - PCI_TPH_ST_DS_MODE: Device Specific Mode
>>> + *
>>> + * Checks whether the mode is actually supported by the device 
>>> before enabling
>>> + * and returns an error if not. Additionally determines what types 
>>> of requests,
>>> + * TPH or extended TPH, can be issued by the device based on its 
>>> TPH requester
>>> + * capability and the Root Port's completer capability.
>>> + *
>>> + * Return: 0 on success, otherwise negative value (-errno)
>>> + */
>>> +int pcie_enable_tph(struct pci_dev *pdev, int mode)
>>> +{
>>> +    u32 reg;
>>> +    u8 dev_modes;
>>> +    u8 rp_req_type;
>>> +
>>> +    /* Honor "notph" kernel parameter */
>>> +    if (pci_tph_disabled)
>>> +        return -EINVAL;
>>> +
>>> +    if (!pdev->tph_cap)
>>> +        return -EINVAL;
>>> +
>>> +    if (pdev->tph_enabled)
>>> +        return -EBUSY;
>>> +
>>> +    /* Sanitize and check ST mode comptability */
>>> +    mode &= PCI_TPH_CTRL_MODE_SEL_MASK;
>>> +    dev_modes = get_st_modes(pdev);
>>> +    if (!((1 << mode) & dev_modes))
>>
>>
>> This is wrong. The mode definition is about the bit on and not about bit
>> position. You got this right in v4 ...
>
> This code is correct. In V5, I changed the "mode" parameter to the 
> following values, as defined in TPH Ctrl register. These values are 
> defined as bit positions:
>
> PCI_TPH_ST_NS_MODE: NO ST Mode
> PCI_TPH_ST_IV_MODE: Interrupt Vector Mode
> PCI_TPH_ST_DS_MODE: Device Specific Mode
>

OK. I found the issue. I was using PCI_TPH_CAP_ST_DS for the mode 
instead of PCI_TPH_ST_DS_MODE.

That change confused me.

Apologies.


> In V4, "mode" is defined as masks of TPH Cap register. I felt that V5 
> looks more straightforward:
>
> V4: pcie_enable_tph(dev, PCI_TPH_CAP_ST_IV)
> vs.
> V5: pcie_enable_tph(dev, PCI_TPH_ST_IV_MODE)
>
>>
>>
>>> +        return -EINVAL;
>