From: Logan Gunthorpe <logang@deltatee.com>
To: Dmitry Safonov <0x7f454c46@gmail.com>,
James Sewart <jamessewart@arista.com>,
iommu@lists.linux-foundation.org
Cc: Bjorn Helgaas <bhelgaas@google.com>,
linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org,
Dmitry Safonov <dima@arista.com>
Subject: Re: [PATCH] Ensure pci transactions coming from PLX NTB are handled when IOMMU is turned on
Date: Wed, 20 Nov 2019 12:30:48 -0700 [thread overview]
Message-ID: <c683ec65-40a9-6430-ae85-ce3934ed8af5@deltatee.com> (raw)
In-Reply-To: <5c3b56dd-7088-e544-6628-01506f7b84e8@gmail.com>
On 2019-11-20 10:48 a.m., Dmitry Safonov wrote:
> +Cc: linux-pci@vger.kernel.org
> +Cc: Bjorn Helgaas <bhelgaas@google.com>
> +Cc: Logan Gunthorpe <logang@deltatee.com>
>
> On 11/5/19 12:17 PM, James Sewart wrote:
>> Any comments on this?
>>
>> Cheers,
>> James.
>>
>>> On 24 Oct 2019, at 13:52, James Sewart <jamessewart@arista.com> wrote:
>>>
>>> The PLX PEX NTB forwards DMA transactions using Requester ID's that don't exist as
>>> PCI devices. The devfn for a transaction is used as an index into a lookup table
>>> storing the origin of a transaction on the other side of the bridge.
>>>
>>> This patch aliases all possible devfn's to the NTB device so that any transaction
>>> coming in is governed by the mappings for the NTB.
>>>
>>> Signed-Off-By: James Sewart <jamessewart@arista.com>
>>> ---
>>> drivers/pci/quirks.c | 22 ++++++++++++++++++++++
>>> 1 file changed, 22 insertions(+)
>>>
>>> diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
>>> index 320255e5e8f8..647f546e427f 100644
>>> --- a/drivers/pci/quirks.c
>>> +++ b/drivers/pci/quirks.c
>>> @@ -5315,6 +5315,28 @@ SWITCHTEC_QUIRK(0x8574); /* PFXI 64XG3 */
>>> SWITCHTEC_QUIRK(0x8575); /* PFXI 80XG3 */
>>> SWITCHTEC_QUIRK(0x8576); /* PFXI 96XG3 */
>>>
>>> +/*
>>> + * PLX NTB uses devfn proxy IDs to move TLPs between NT endpoints. These IDs
>>> + * are used to forward responses to the originator on the other side of the
>>> + * NTB. Alias all possible IDs to the NTB to permit access when the IOMMU is
>>> + * turned on.
>>> + */
>>> +static void quirk_PLX_NTB_dma_alias(struct pci_dev *pdev)
>>> +{
>>> + if (!pdev->dma_alias_mask)
>>> + pdev->dma_alias_mask = kcalloc(BITS_TO_LONGS(U8_MAX),
>>> + sizeof(long), GFP_KERNEL);
>>> + if (!pdev->dma_alias_mask) {
>>> + dev_warn(&pdev->dev, "Unable to allocate DMA alias mask\n");
>>> + return;
>>> + }
>>> +
>>> + // PLX NTB may use all 256 devfns
>>> + memset(pdev->dma_alias_mask, U8_MAX, (U8_MAX+1)/BITS_PER_BYTE);
I think it would be better to create a pci_add_dma_alias_range()
function instead of directly accessing dma_alias_mask. We could then use
that function to clean up quirk_switchtec_ntb_dma_alias() which is
essentially doing the same thing.
It's also quite ugly that you're allocating with kcalloc here instead of
bitmap_zalloc() seeing it will be free'd with bitmap_free(). Also, you
should probably use bitmap_set() instead of memset().
Logan
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
next prev parent reply other threads:[~2019-11-20 19:53 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-24 12:52 [PATCH] Ensure pci transactions coming from PLX NTB are handled when IOMMU is turned on James Sewart via iommu
2019-11-05 12:17 ` James Sewart via iommu
2019-11-20 17:48 ` Dmitry Safonov
2019-11-20 19:30 ` Logan Gunthorpe [this message]
2019-11-20 19:49 ` Bjorn Helgaas
2019-11-20 19:32 ` Bjorn Helgaas
2019-11-26 17:03 ` [PATCH v2] PCI: Add DMA alias quirk for PLX PEX NTB James Sewart via iommu
2019-11-26 17:06 ` Logan Gunthorpe
2019-11-26 17:36 ` [PATCH v3 1/2] PCI: Add helper pci_add_dma_alias_range James Sewart via iommu
2019-11-26 17:37 ` [PATCH v3 2/2] PCI: Add DMA alias quirk for PLX PEX NTB James Sewart via iommu
2019-11-26 17:38 ` [PATCH v2] " Christoph Hellwig
2019-11-27 13:27 ` [PATCH v3 1/2] PCI: Add parameter nr_devfns to pci_add_dma_alias James Sewart via iommu
2019-11-27 13:28 ` [PATCH v3 2/2] PCI: Add DMA alias quirk for PLX PEX NTB James Sewart via iommu
2019-11-27 17:38 ` [PATCH v3 1/2] PCI: Add parameter nr_devfns to pci_add_dma_alias Logan Gunthorpe
2019-11-29 12:49 ` [PATCH v4 " James Sewart via iommu
2019-11-29 12:49 ` [PATCH v4 2/2] PCI: Add DMA alias quirk for PLX PEX NTB James Sewart via iommu
2019-11-29 16:50 ` [PATCH v4 1/2] PCI: Add parameter nr_devfns to pci_add_dma_alias Logan Gunthorpe
2019-11-29 17:19 ` James Sewart via iommu
2019-11-29 17:26 ` Logan Gunthorpe
2019-11-29 17:56 ` [PATCH v5 1/3] PCI: Fix off by one in dma_alias_mask allocation size James Sewart via iommu
2019-11-29 17:56 ` [PATCH v5 2/3] PCI: Add parameter nr_devfns to pci_add_dma_alias James Sewart via iommu
2019-11-29 17:57 ` [PATCH v5 3/3] PCI: Add DMA alias quirk for PLX PEX NTB James Sewart via iommu
2019-12-02 17:03 ` [PATCH v5 2/3] PCI: Add parameter nr_devfns to pci_add_dma_alias Christoph Hellwig
2019-11-29 17:58 ` [PATCH v5 1/3] PCI: Fix off by one in dma_alias_mask allocation size Logan Gunthorpe
2019-12-02 17:03 ` Christoph Hellwig
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=c683ec65-40a9-6430-ae85-ce3934ed8af5@deltatee.com \
--to=logang@deltatee.com \
--cc=0x7f454c46@gmail.com \
--cc=bhelgaas@google.com \
--cc=dima@arista.com \
--cc=iommu@lists.linux-foundation.org \
--cc=jamessewart@arista.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).