From: Daniel Drake <drake@endlessm.com>
To: dwmw2@infradead.org, baolu.lu@linux.intel.com, joro@8bytes.org
Cc: bhelgaas@google.com, iommu@lists.linux-foundation.org,
linux@endlessm.com, jonathan.derrick@intel.com
Subject: [PATCH v2] iommu/vt-d: consider real PCI device when checking if mapping is needed
Date: Fri, 14 Feb 2020 17:02:34 +0800 [thread overview]
Message-ID: <20200214090234.5746-1-drake@endlessm.com> (raw)
From: Jon Derrick <jonathan.derrick@intel.com>
The PCI devices handled by intel-iommu may have a DMA requester on
another bus, such as VMD subdevices needing to use the VMD endpoint.
The real DMA device is now used for the DMA mapping, but one case was
missed earlier: if the VMD device (and hence subdevices too) are under
IOMMU_DOMAIN_IDENTITY, mappings do not work.
Codepaths like intel_map_page() handle the IOMMU_DOMAIN_DMA case by
creating an iommu DMA mapping, and fall back on dma_direct_map_page()
for the IOMMU_DOMAIN_IDENTITY case. However, handling of the IDENTITY
case is broken when intel_page_page() handles a subdevice.
We observe that at iommu attach time, dmar_insert_one_dev_info() for
the subdevices will never set dev->archdata.iommu. This is because
that function uses find_domain() to check if there is already an IOMMU
for the device, and find_domain() then defers to the real DMA device
which does have one. Thus dmar_insert_one_dev_info() returns without
assigning dev->archdata.iommu.
Then, later:
1. intel_map_page() checks if an IOMMU mapping is needed by calling
iommu_need_mapping() on the subdevice. identity_mapping() returns
false because dev->archdata.iommu is NULL, so this function
returns false indicating that mapping is needed.
2. __intel_map_single() is called to create the mapping.
3. __intel_map_single() calls find_domain(). This function now returns
the IDENTITY domain corresponding to the real DMA device.
4. __intel_map_single() calls domain_get_iommu() on this "real" domain.
A failure is hit and the entire operation is aborted, because this
codepath is not intended to handle IDENTITY mappings:
if (WARN_ON(domain->domain.type != IOMMU_DOMAIN_DMA))
return NULL;
Fix this by using the real DMA device when checking if a mapping is
needed, while also considering the subdevice DMA mask.
The IDENTITY case will then directly fall back on dma_direct_map_page().
Reported-by: Daniel Drake <drake@endlessm.com>
Fixes: b0140c69637e ("iommu/vt-d: Use pci_real_dma_dev() for mapping")
Signed-off-by: Daniel Drake <drake@endlessm.com>
---
Notes:
v2: switch to Jon's approach instead.
This problem was detected with a non-upstream patch
"PCI: Add Intel remapped NVMe device support"
(https://marc.info/?l=linux-ide&m=156015271021615&w=2)
This patch creates PCI devices a bit like VMD, and hence
I believe VMD would hit this class of problem for any cases where
the VMD device is in the IDENTITY domain. (I presume the reason this
bug was not seen already there is that it is in a DMA iommu domain).
However this hasn't actually been tested on VMD (don't have the hardware)
so if I've missed anything and/or it's not a real issue then feel free to
drop this patch.
drivers/iommu/intel-iommu.c | 16 ++++++++++------
1 file changed, 10 insertions(+), 6 deletions(-)
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 9dc37672bf89..edbe2866b515 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3582,19 +3582,23 @@ static struct dmar_domain *get_private_domain_for_dev(struct device *dev)
/* Check if the dev needs to go through non-identity map and unmap process.*/
static bool iommu_need_mapping(struct device *dev)
{
+ u64 dma_mask, required_dma_mask;
int ret;
if (iommu_dummy(dev))
return false;
- ret = identity_mapping(dev);
- if (ret) {
- u64 dma_mask = *dev->dma_mask;
+ dma_mask = *dev->dma_mask;
+ if (dev->coherent_dma_mask && dev->coherent_dma_mask < dma_mask)
+ dma_mask = dev->coherent_dma_mask;
+ required_dma_mask = dma_direct_get_required_mask(dev);
- if (dev->coherent_dma_mask && dev->coherent_dma_mask < dma_mask)
- dma_mask = dev->coherent_dma_mask;
+ if (dev_is_pci(dev))
+ dev = &pci_real_dma_dev(to_pci_dev(dev))->dev;
- if (dma_mask >= dma_direct_get_required_mask(dev))
+ ret = identity_mapping(dev);
+ if (ret) {
+ if (dma_mask >= required_dma_mask)
return false;
/*
--
2.20.1
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
next reply other threads:[~2020-02-14 9:02 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-14 9:02 Daniel Drake [this message]
2020-02-14 12:16 ` [PATCH v2] iommu/vt-d: consider real PCI device when checking if mapping is needed Lu Baolu
2020-02-14 16:43 ` Derrick, Jonathan
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=20200214090234.5746-1-drake@endlessm.com \
--to=drake@endlessm.com \
--cc=baolu.lu@linux.intel.com \
--cc=bhelgaas@google.com \
--cc=dwmw2@infradead.org \
--cc=iommu@lists.linux-foundation.org \
--cc=jonathan.derrick@intel.com \
--cc=joro@8bytes.org \
--cc=linux@endlessm.com \
/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).