linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Tian, Kevin" <kevin.tian@intel.com>
To: Jacob Pan <jacob.jun.pan@linux.intel.com>,
	"iommu@lists.linux-foundation.org"
	<iommu@lists.linux-foundation.org>,
	LKML <linux-kernel@vger.kernel.org>,
	Joerg Roedel <joro@8bytes.org>,
	"David Woodhouse" <dwmw2@infradead.org>
Cc: "Liu, Yi L" <yi.l.liu@intel.com>,
	"Lan, Tianyu" <tianyu.lan@intel.com>,
	"Raj, Ashok" <ashok.raj@intel.com>,
	Alex Williamson <alex.williamson@redhat.com>,
	Jean Delvare <khali@linux-fr.org>
Subject: RE: [PATCH 2/9] iommu/vt-d: add bind_pasid_table function
Date: Wed, 5 Jul 2017 07:38:07 +0000	[thread overview]
Message-ID: <AADFC41AFE54684AB9EE6CBC0274A5D190D25C29@SHSMSX101.ccr.corp.intel.com> (raw)
In-Reply-To: <1498592883-56224-3-git-send-email-jacob.jun.pan@linux.intel.com>

> From: Jacob Pan [mailto:jacob.jun.pan@linux.intel.com]
> Sent: Wednesday, June 28, 2017 3:48 AM
> 
> Add Intel VT-d ops to the generic iommu_bind_pasid_table API
> functions.
> 
> The primary use case is for direct assignment of SVM capable
> device. Originated from emulated IOMMU in the guest, the request goes
> through many layers (e.g. VFIO). Upon calling host IOMMU driver, caller
> passes guest PASID table pointer (GPA) and size.
> 
> Device context table entry is modified by Intel IOMMU specific
> bind_pasid_table function. This will turn on nesting mode and matching
> translation type.
> 
> The unbind operation restores default context mapping.
> 
> Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
> Signed-off-by: Liu, Yi L <yi.l.liu@linux.intel.com>
> Signed-off-by: Ashok Raj <ashok.raj@intel.com>
> ---
>  drivers/iommu/intel-iommu.c   | 117
> ++++++++++++++++++++++++++++++++++++++++++
>  include/linux/dma_remapping.h |   1 +
>  2 files changed, 118 insertions(+)
> 
> diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
> index 8274ce3..ef05b59 100644
> --- a/drivers/iommu/intel-iommu.c
> +++ b/drivers/iommu/intel-iommu.c
> @@ -5430,6 +5430,119 @@ struct intel_iommu
> *intel_svm_device_to_iommu(struct device *dev)
> 
>  	return iommu;
>  }
> +
> +static int intel_iommu_bind_pasid_table(struct iommu_domain *domain,
> +		struct device *dev, struct pasid_table_info *pasidt_binfo)
> +{
> +	struct intel_iommu *iommu;
> +	struct context_entry *context;
> +	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
> +	struct device_domain_info *info;
> +	struct pci_dev *pdev;
> +	u8 bus, devfn;
> +	u16 did, *sid;
> +	int ret = 0;
> +	unsigned long flags;
> +	u64 ctx_lo;
> +
> +	if (pasidt_binfo == NULL || pasidt_binfo->model !=
> IOMMU_MODEL_INTEL_VTD) {
> +		pr_warn("%s: Invalid bind request!\n", __func__);
> +		return -EINVAL;
> +	}
> +
> +	iommu = device_to_iommu(dev, &bus, &devfn);
> +	if (!iommu)
> +		return -ENODEV;
> +
> +	sid = (u16 *)&pasidt_binfo->opaque;
> +	/*
> +	 * check SID, if it is not correct, return success to allow looping
> +	 * through all devices within a group
> +	 */

Can you elaborate this comment since it's related to caller behavior?
Also better move to earlier as the comment for whole function...

> +	if (PCI_DEVID(bus, devfn) != *sid)
> +		return 0;
> +
> +	if (!dev || !dev_is_pci(dev))
> +		return -ENODEV;
> +
> +	pdev = to_pci_dev(dev);
> +	if (!pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI))
> +		return -EINVAL;
> +
> +	info = dev->archdata.iommu;
> +	if (!info || !info->pasid_supported ||
> +		!pci_enable_pasid(pdev, info->pasid_supported & ~1)) {
> +		pr_err("PCI %04x:%02x:%02x.%d: has no PASID support\n",
> +			       pci_domain_nr(pdev->bus), bus, PCI_SLOT(devfn),
> +			       PCI_FUNC(devfn));
> +		ret = -EINVAL;
> +		goto out;
> +	}
> +
> +	if (pasidt_binfo->size > intel_iommu_get_pts(iommu)) {
> +		pr_err("Invalid gPASID table size %llu, host size %lu\n",
> +			pasidt_binfo->size,
> +			intel_iommu_get_pts(iommu));
> +		ret = -EINVAL;
> +		goto out;
> +	}
> +	spin_lock_irqsave(&iommu->lock, flags);
> +	context = iommu_context_addr(iommu, bus, devfn, 0);
> +	if (!context || !context_present(context)) {
> +		pr_warn("%s: ctx not present for bus devfn %x:%x\n",
> +			__func__, bus, devfn);
> +		spin_unlock_irqrestore(&iommu->lock, flags);
> +		goto out;
> +	}
> +
> +	/* Anticipate guest to use SVM and owns the first level */
> +	ctx_lo = context[0].lo;
> +	ctx_lo |= CONTEXT_NESTE;
> +	ctx_lo |= CONTEXT_PRS;
> +	ctx_lo |= CONTEXT_PASIDE;
> +	ctx_lo &= ~CONTEXT_TT_MASK;
> +	ctx_lo |= CONTEXT_TT_DEV_IOTLB << 2;
> +	context[0].lo = ctx_lo;
> +
> +	/* Assign guest PASID table pointer and size */
> +	ctx_lo = (pasidt_binfo->ptr & VTD_PAGE_MASK) | pasidt_binfo->size;
> +	context[1].lo = ctx_lo;
> +	/* make sure context entry is updated before flushing */
> +	wmb();
> +	did = dmar_domain->iommu_did[iommu->seq_id];
> +	iommu->flush.flush_context(iommu, did,
> +				(((u16)bus) << 8) | devfn,
> +				DMA_CCMD_MASK_NOBIT,
> +				DMA_CCMD_DEVICE_INVL);
> +	iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
> +	spin_unlock_irqrestore(&iommu->lock, flags);
> +
> +
> +out:
> +	return ret;
> +}
> +
> +static int intel_iommu_unbind_pasid_table(struct iommu_domain *domain,
> +					struct device *dev)
> +{
> +	struct intel_iommu *iommu;
> +	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
> +	u8 bus, devfn;
> +
> +	iommu = device_to_iommu(dev, &bus, &devfn);
> +	if (!iommu)
> +		return -ENODEV;
> +	/*
> +	 * REVISIT: we might want to clear the PASID table pointer
> +	 * as part of context clear operation. Currently, it leaves
> +	 * stale data but should be ignored by hardware since PASIDE
> +	 * is clear.
> +	 */
> +	/* ATS will be reenabled when remapping is restored */
> +	pci_disable_ats(to_pci_dev(dev));
> +	domain_context_clear(iommu, dev);
> +	return domain_context_mapping_one(dmar_domain, iommu, bus,
> devfn);
> +}
>  #endif /* CONFIG_INTEL_IOMMU_SVM */
> 
>  const struct iommu_ops intel_iommu_ops = {
> @@ -5438,6 +5551,10 @@ const struct iommu_ops intel_iommu_ops = {
>  	.domain_free		= intel_iommu_domain_free,
>  	.attach_dev		= intel_iommu_attach_device,
>  	.detach_dev		= intel_iommu_detach_device,
> +#ifdef CONFIG_INTEL_IOMMU_SVM
> +	.bind_pasid_table	= intel_iommu_bind_pasid_table,
> +	.unbind_pasid_table	= intel_iommu_unbind_pasid_table,
> +#endif
>  	.map			= intel_iommu_map,
>  	.unmap			= intel_iommu_unmap,
>  	.map_sg			= default_iommu_map_sg,
> diff --git a/include/linux/dma_remapping.h
> b/include/linux/dma_remapping.h
> index 9088407..85367b7 100644
> --- a/include/linux/dma_remapping.h
> +++ b/include/linux/dma_remapping.h
> @@ -27,6 +27,7 @@
> 
>  #define CONTEXT_DINVE		(1ULL << 8)
>  #define CONTEXT_PRS		(1ULL << 9)
> +#define CONTEXT_NESTE		(1ULL << 10)
>  #define CONTEXT_PASIDE		(1ULL << 11)
> 
>  struct intel_iommu;
> --
> 2.7.4

  parent reply	other threads:[~2017-07-05  7:38 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-06-27 19:47 [RFC 0/9] IOMMU driver support for shared virtual memory virtualization Jacob Pan
2017-06-27 19:47 ` [PATCH 1/9] iommu: Introduce bind_pasid_table API function Jacob Pan
2017-06-28  9:57   ` Joerg Roedel
2017-06-27 19:47 ` [PATCH 2/9] iommu/vt-d: add bind_pasid_table function Jacob Pan
2017-06-28 10:02   ` Joerg Roedel
2017-07-05  7:38   ` Tian, Kevin [this message]
2017-06-27 19:47 ` [PATCH 3/9] iommu: Introduce iommu do invalidate API function Jacob Pan
2017-06-28 10:08   ` Joerg Roedel
2017-06-28 16:09     ` Jacob Pan
2017-06-28 17:07       ` Jean-Philippe Brucker
2017-07-05  7:57         ` Tian, Kevin
2017-07-05 12:42           ` Jean-Philippe Brucker
2017-07-26  9:02           ` Joerg Roedel
2017-06-27 19:47 ` [PATCH 4/9] iommu/vt-d: Add iommu do invalidate function Jacob Pan
2017-06-27 19:47 ` [PATCH 5/9] iommu: Introduce fault notifier API Jacob Pan
2017-06-28 10:16   ` Joerg Roedel
2017-06-28 16:16     ` Jacob Pan
2017-06-27 19:48 ` [PATCH 6/9] iommu/vt-d: track device with pasid table bond to a guest Jacob Pan
2017-06-27 19:48 ` [PATCH 7/9] iommu/dmar: notify unrecoverable faults Jacob Pan
2017-06-27 19:48 ` [PATCH 8/9] iommu/intel-svm: notify page request to guest Jacob Pan
2017-06-27 19:48 ` [PATCH 9/9] iommu/intel-svm: replace dev ops with generic fault notifier Jacob Pan
2017-08-16  9:44 ` [RFC 0/9] IOMMU driver support for shared virtual memory virtualization Joerg Roedel
2017-08-16 15:14   ` Jacob Pan
2017-08-16 16:23     ` Joerg Roedel

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=AADFC41AFE54684AB9EE6CBC0274A5D190D25C29@SHSMSX101.ccr.corp.intel.com \
    --to=kevin.tian@intel.com \
    --cc=alex.williamson@redhat.com \
    --cc=ashok.raj@intel.com \
    --cc=dwmw2@infradead.org \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jacob.jun.pan@linux.intel.com \
    --cc=joro@8bytes.org \
    --cc=khali@linux-fr.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=tianyu.lan@intel.com \
    --cc=yi.l.liu@intel.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).