Linux IOMMU Development
 help / color / mirror / Atom feed
From: Robin Murphy <robin.murphy@arm.com>
To: Oded Gabbay <ogabbay@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	iommu@lists.linux-foundation.org,
	"Linux-Kernel@Vger. Kernel. Org" <linux-kernel@vger.kernel.org>,
	Arnd Bergmann <arnd@arndb.de>
Subject: Re: [PATCH] habanalabs: Stop using iommu_present()
Date: Mon, 11 Apr 2022 11:43:24 +0100	[thread overview]
Message-ID: <97c6b2e1-3d9f-bf03-a14e-df3249d166dd@arm.com> (raw)
In-Reply-To: <CAFCwf10bwtpC=syFgcz8Ym5S797x3wmkGx3RFnUNkSsjdeyGgw@mail.gmail.com>

On 2022-04-10 11:59, Oded Gabbay wrote:
> On Tue, Apr 5, 2022 at 4:46 PM Robin Murphy <robin.murphy@arm.com> wrote:
>>
>> Even if an IOMMU might be present for some PCI segment in the system,
>> that doesn't necessarily mean it provides translation for the device
>> we care about. Replace iommu_present() with a more appropriate check.
>>
>> Signed-off-by: Robin Murphy <robin.murphy@arm.com>
>> ---
>>   drivers/misc/habanalabs/gaudi/gaudi.c | 8 ++++----
>>   drivers/misc/habanalabs/goya/goya.c   | 8 ++++----
>>   2 files changed, 8 insertions(+), 8 deletions(-)
>>
>> diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
>> index 21c2b678ff72..5dc66dc7618e 100644
>> --- a/drivers/misc/habanalabs/gaudi/gaudi.c
>> +++ b/drivers/misc/habanalabs/gaudi/gaudi.c
>> @@ -6133,7 +6133,7 @@ static int gaudi_debugfs_read32(struct hl_device *hdev, u64 addr,
>>                          rc = -EIO;
>>
>>          } else if (addr >= HOST_PHYS_BASE && addr < host_phys_end &&
>> -                       user_address && !iommu_present(&pci_bus_type)) {
>> +                       user_address && !device_iommu_mapped(&hdev->pdev->dev)) {
>>
>>                  *val = *(u32 *) phys_to_virt(addr - HOST_PHYS_BASE);
>>
>> @@ -6176,7 +6176,7 @@ static int gaudi_debugfs_write32(struct hl_device *hdev, u64 addr,
>>                          rc = -EIO;
>>
>>          } else if (addr >= HOST_PHYS_BASE && addr < host_phys_end &&
>> -                       user_address && !iommu_present(&pci_bus_type)) {
>> +                       user_address && !device_iommu_mapped(&hdev->pdev->dev)) {
>>
>>                  *(u32 *) phys_to_virt(addr - HOST_PHYS_BASE) = val;
>>
>> @@ -6223,7 +6223,7 @@ static int gaudi_debugfs_read64(struct hl_device *hdev, u64 addr,
>>                          rc = -EIO;
>>
>>          } else if (addr >= HOST_PHYS_BASE && addr < host_phys_end &&
>> -                       user_address && !iommu_present(&pci_bus_type)) {
>> +                       user_address && !device_iommu_mapped(&hdev->pdev->dev)) {
>>
>>                  *val = *(u64 *) phys_to_virt(addr - HOST_PHYS_BASE);
>>
>> @@ -6268,7 +6268,7 @@ static int gaudi_debugfs_write64(struct hl_device *hdev, u64 addr,
>>                          rc = -EIO;
>>
>>          } else if (addr >= HOST_PHYS_BASE && addr < host_phys_end &&
>> -                       user_address && !iommu_present(&pci_bus_type)) {
>> +                       user_address && !device_iommu_mapped(&hdev->pdev->dev)) {
>>
>>                  *(u64 *) phys_to_virt(addr - HOST_PHYS_BASE) = val;
>>
>> diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
>> index ec9358bcbf0b..0c455bf460f4 100644
>> --- a/drivers/misc/habanalabs/goya/goya.c
>> +++ b/drivers/misc/habanalabs/goya/goya.c
>> @@ -4309,7 +4309,7 @@ static int goya_debugfs_read32(struct hl_device *hdev, u64 addr,
>>                          rc = -EIO;
>>
>>          } else if (addr >= HOST_PHYS_BASE && addr < host_phys_end &&
>> -                       user_address && !iommu_present(&pci_bus_type)) {
>> +                       user_address && !device_iommu_mapped(&hdev->pdev->dev)) {
>>                  *val = *(u32 *) phys_to_virt(addr - HOST_PHYS_BASE);
>>
>>          } else {
>> @@ -4369,7 +4369,7 @@ static int goya_debugfs_write32(struct hl_device *hdev, u64 addr,
>>                          rc = -EIO;
>>
>>          } else if (addr >= HOST_PHYS_BASE && addr < host_phys_end &&
>> -                       user_address && !iommu_present(&pci_bus_type)) {
>> +                       user_address && !device_iommu_mapped(&hdev->pdev->dev)) {
>>                  *(u32 *) phys_to_virt(addr - HOST_PHYS_BASE) = val;
>>
>>          } else {
>> @@ -4418,7 +4418,7 @@ static int goya_debugfs_read64(struct hl_device *hdev, u64 addr,
>>                          rc = -EIO;
>>
>>          } else if (addr >= HOST_PHYS_BASE && addr < host_phys_end &&
>> -                       user_address && !iommu_present(&pci_bus_type)) {
>> +                       user_address && !device_iommu_mapped(&hdev->pdev->dev)) {
>>                  *val = *(u64 *) phys_to_virt(addr - HOST_PHYS_BASE);
>>
>>          } else {
>> @@ -4465,7 +4465,7 @@ static int goya_debugfs_write64(struct hl_device *hdev, u64 addr,
>>                          rc = -EIO;
>>
>>          } else if (addr >= HOST_PHYS_BASE && addr < host_phys_end &&
>> -                       user_address && !iommu_present(&pci_bus_type)) {
>> +                       user_address && !device_iommu_mapped(&hdev->pdev->dev)) {
>>                  *(u64 *) phys_to_virt(addr - HOST_PHYS_BASE) = val;
>>
>>          } else {
>> --
>> 2.28.0.dirty
>>
> 
> Hi Robin,
> Can you please rebase this over the latest habanalabs-next ?
> The code was totally changed, but I think your core change is
> definitely relevant.

Oh, lovely, that makes for a much nicer patch indeed! I'll spin a v2 
shortly.

Thanks,
Robin.
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

      reply	other threads:[~2022-04-11 10:43 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-05 13:46 [PATCH] habanalabs: Stop using iommu_present() Robin Murphy
2022-04-10 10:59 ` Oded Gabbay
2022-04-11 10:43   ` Robin Murphy [this message]

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=97c6b2e1-3d9f-bf03-a14e-df3249d166dd@arm.com \
    --to=robin.murphy@arm.com \
    --cc=arnd@arndb.de \
    --cc=gregkh@linuxfoundation.org \
    --cc=iommu@lists.linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ogabbay@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