LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Lu Baolu <baolu.lu@linux.intel.com>
To: Jacob Pan <jacob.jun.pan@linux.intel.com>,
	iommu@lists.linux-foundation.org,
	LKML <linux-kernel@vger.kernel.org>,
	Joerg Roedel <joro@8bytes.org>,
	David Woodhouse <dwmw2@infradead.org>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Alex Williamson <alex.williamson@redhat.com>,
	Jean-Philippe Brucker <jean-philippe.brucker@arm.com>
Cc: Rafael Wysocki <rafael.j.wysocki@intel.com>,
	"Liu, Yi L" <yi.l.liu@intel.com>,
	"Tian, Kevin" <kevin.tian@intel.com>,
	Raj Ashok <ashok.raj@intel.com>,
	Jean Delvare <khali@linux-fr.org>,
	Christoph Hellwig <hch@infradead.org>,
	"Liu, Yi L" <yi.l.liu@intel.com>
Subject: Re: [PATCH v5 04/23] iommu/vt-d: add bind_pasid_table function
Date: Sun, 13 May 2018 17:29:47 +0800	[thread overview]
Message-ID: <5AF8058B.4090703@linux.intel.com> (raw)
In-Reply-To: <1526072055-86990-5-git-send-email-jacob.jun.pan@linux.intel.com>

Hi,

On 05/12/2018 04:53 AM, Jacob Pan wrote:
> 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   | 122 ++++++++++++++++++++++++++++++++++++++++++
>  include/linux/dma_remapping.h |   1 +
>  2 files changed, 123 insertions(+)
>
> diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
> index a0f81a4..4623294 100644
> --- a/drivers/iommu/intel-iommu.c
> +++ b/drivers/iommu/intel-iommu.c
> @@ -2409,6 +2409,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
>  	info->ats_supported = info->pasid_supported = info->pri_supported = 0;
>  	info->ats_enabled = info->pasid_enabled = info->pri_enabled = 0;
>  	info->ats_qdep = 0;
> +	info->pasid_table_bound = 0;
>  	info->dev = dev;
>  	info->domain = domain;
>  	info->iommu = iommu;
> @@ -5132,6 +5133,7 @@ static void intel_iommu_put_resv_regions(struct device *dev,
>  
>  #ifdef CONFIG_INTEL_IOMMU_SVM
>  #define MAX_NR_PASID_BITS (20)
> +#define MIN_NR_PASID_BITS (5)
>  static inline unsigned long intel_iommu_get_pts(struct intel_iommu *iommu)
>  {
>  	/*
> @@ -5258,6 +5260,122 @@ 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_config *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, host_table_pasid_bits;
> +	u16 did, sid;
> +	int ret = 0;
> +	unsigned long flags;
> +	u64 ctx_lo;

I personally prefer to have this in order.

        struct dmar_domain *dmar_domain = to_dmar_domain(domain);
        u8 bus, devfn, host_table_pasid_bits;
        struct device_domain_info *info;
        struct context_entry *context;
        struct intel_iommu *iommu;
        struct pci_dev *pdev;
        unsigned long flags;
        u16 did, sid;
        int ret = 0;
        u64 ctx_lo;

> +
> +	if ((pasidt_binfo->version != PASID_TABLE_CFG_VERSION_1) ||

Unnecessary parentheses.

> +		pasidt_binfo->bytes != sizeof(*pasidt_binfo))

Alignment should match open parenthesis.

> +		return -EINVAL;
> +	iommu = device_to_iommu(dev, &bus, &devfn);
> +	if (!iommu)
> +		return -ENODEV;
> +	/* VT-d spec section 9.4 says pasid table size is encoded as 2^(x+5) */
> +	host_table_pasid_bits = intel_iommu_get_pts(iommu) + MIN_NR_PASID_BITS;
> +	if (!pasidt_binfo || pasidt_binfo->pasid_bits > host_table_pasid_bits ||

"!pasidt_binfo" checking should be moved up to the version checking.

> +		pasidt_binfo->pasid_bits < MIN_NR_PASID_BITS) {
> +		pr_err("Invalid gPASID bits %d, host range %d - %d\n",

How about dev_err()? 

> +			pasidt_binfo->pasid_bits,
> +			MIN_NR_PASID_BITS, host_table_pasid_bits);
> +		return -ERANGE;
> +	}
> +	if (!ecap_nest(iommu->ecap)) {
> +		dev_err(dev, "Cannot bind PASID table, no nested translation\n");
> +		ret = -ENODEV;
> +		goto out;

How about
+        return -ENODEV;
?

> +	}
> +	pdev = to_pci_dev(dev);

We can't always assume that it is a PCI device, right?

> +	sid = PCI_DEVID(bus, devfn);
> +	info = dev->archdata.iommu;
> +
> +	if (!info) {
> +		dev_err(dev, "Invalid device domain info\n");
> +		ret = -EINVAL;
> +		goto out;
> +	}
> +	if (info->pasid_table_bound) {

We should do this checking with lock hold.

Otherwise,

Thread A on CPUx                Thread B on CPUy
===========                ============
check pasid_table_bound    check pasid_table_bound

mutex_lock()
Setup context
pasid_table_bound = 1
mutex_unlock()

                                               mutex_lock()
                                               Setup context
                                               pasid_table_bound = 1
                                               mutex_unlock()


> +		dev_err(dev, "Device PASID table already bound\n");
> +		ret = -EBUSY;
> +		goto out;
> +	}
> +	if (!info->pasid_enabled) {
> +		ret = pci_enable_pasid(pdev, info->pasid_supported & ~1);
> +		if (ret) {
> +			dev_err(dev, "Failed to enable PASID\n");
> +			goto out;
> +		}
> +	}

I prefer a blank line here.

> +	spin_lock_irqsave(&iommu->lock, flags);
> +	context = iommu_context_addr(iommu, bus, devfn, 0);
> +	if (!context_present(context)) {
> +		dev_err(dev, "Context not present\n");
> +		ret = -EINVAL;
> +		goto out_unlock;
> +	}
> +
> +	/* Anticipate guest to use SVM and owns the first level, so we turn
> +	 * nested mode on
> +	 */
> +	ctx_lo = context[0].lo;
> +	ctx_lo |= CONTEXT_NESTE | CONTEXT_PRS | 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 order */
> +	ctx_lo = (pasidt_binfo->base_ptr & VTD_PAGE_MASK) |
> +		(pasidt_binfo->pasid_bits - MIN_NR_PASID_BITS);
> +	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);
> +	info->pasid_table_bound = 1;
> +out_unlock:
> +	spin_unlock_irqrestore(&iommu->lock, flags);
> +out:
> +	return ret;
> +}
> +
> +static void 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);
> +	struct device_domain_info *info;
> +	u8 bus, devfn;
> +
> +	info = dev->archdata.iommu;
> +	if (!info) {
> +		dev_err(dev, "Invalid device domain info\n");
> +		return;
> +	}
> +	iommu = device_to_iommu(dev, &bus, &devfn);
> +	if (!iommu) {
> +		dev_err(dev, "No IOMMU for device to unbind PASID table\n");
> +		return;
> +	}
> +
> +	domain_context_clear(iommu, dev);
> +
> +	domain_context_mapping_one(dmar_domain, iommu, bus, devfn);
> +	info->pasid_table_bound = 0;
> +}
>  #endif /* CONFIG_INTEL_IOMMU_SVM */
>  
>  const struct iommu_ops intel_iommu_ops = {
> @@ -5266,6 +5384,10 @@ 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 21b3e7d..db290b2 100644
> --- a/include/linux/dma_remapping.h
> +++ b/include/linux/dma_remapping.h
> @@ -28,6 +28,7 @@
>  
>  #define CONTEXT_DINVE		(1ULL << 8)
>  #define CONTEXT_PRS		(1ULL << 9)
> +#define CONTEXT_NESTE		(1ULL << 10)
>  #define CONTEXT_PASIDE		(1ULL << 11)
>  
>  struct intel_iommu;

Best regards,
Lu Baolu

  reply	other threads:[~2018-05-13  9:29 UTC|newest]

Thread overview: 81+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-11 20:53 [PATCH v5 00/23] IOMMU and VT-d driver support for Shared Virtual Address (SVA) Jacob Pan
2018-05-11 20:53 ` [PATCH v5 01/23] iommu: introduce bind_pasid_table API function Jacob Pan
2018-08-23 16:34   ` Auger Eric
2018-08-24 12:47     ` Liu, Yi L
2018-08-24 13:20       ` Auger Eric
2018-08-28 17:04         ` Jacob Pan
2018-08-24 15:00   ` Auger Eric
2018-08-28  5:14     ` Jacob Pan
2018-08-28  8:34       ` Auger Eric
2018-08-28 16:36         ` Jacob Pan
2018-05-11 20:53 ` [PATCH v5 02/23] iommu/vt-d: move device_domain_info to header Jacob Pan
2018-05-11 20:53 ` [PATCH v5 03/23] iommu/vt-d: add a flag for pasid table bound status Jacob Pan
2018-05-13  7:33   ` Lu Baolu
2018-05-14 18:51     ` Jacob Pan
2018-05-13  8:01   ` Lu Baolu
2018-05-14 18:52     ` Jacob Pan
2018-05-11 20:53 ` [PATCH v5 04/23] iommu/vt-d: add bind_pasid_table function Jacob Pan
2018-05-13  9:29   ` Lu Baolu [this message]
2018-05-14 20:22     ` Jacob Pan
2018-05-11 20:53 ` [PATCH v5 05/23] iommu: introduce iommu invalidate API function Jacob Pan
2018-05-11 20:53 ` [PATCH v5 06/23] iommu/vt-d: add definitions for PFSID Jacob Pan
2018-05-14  1:36   ` Lu Baolu
2018-05-14 20:30     ` Jacob Pan
2018-05-11 20:53 ` [PATCH v5 07/23] iommu/vt-d: fix dev iotlb pfsid use Jacob Pan
2018-05-14  1:52   ` Lu Baolu
2018-05-14 20:38     ` Jacob Pan
2018-05-11 20:54 ` [PATCH v5 08/23] iommu/vt-d: support flushing more translation cache types Jacob Pan
2018-05-14  2:18   ` Lu Baolu
2018-05-14 20:46     ` Jacob Pan
2018-05-17  8:44   ` kbuild test robot
2018-05-11 20:54 ` [PATCH v5 09/23] iommu/vt-d: add svm/sva invalidate function Jacob Pan
2018-05-14  3:35   ` Lu Baolu
2018-05-14 20:49     ` Jacob Pan
2018-05-11 20:54 ` [PATCH v5 10/23] iommu: introduce device fault data Jacob Pan
2018-09-21 10:07   ` Auger Eric
2018-09-21 17:05     ` Jacob Pan
2018-09-26 10:20       ` Auger Eric
2018-05-11 20:54 ` [PATCH v5 11/23] driver core: add per device iommu param Jacob Pan
2018-05-14  5:27   ` Lu Baolu
2018-05-14 20:52     ` Jacob Pan
2018-05-11 20:54 ` [PATCH v5 12/23] iommu: add a timeout parameter for prq response Jacob Pan
2018-05-11 20:54 ` [PATCH v5 13/23] iommu: introduce device fault report API Jacob Pan
2018-05-14  6:01   ` Lu Baolu
2018-05-14 20:55     ` Jacob Pan
2018-05-15  6:52       ` Lu Baolu
2018-05-17 11:41   ` Liu, Yi L
2018-05-17 15:59     ` Jacob Pan
2018-05-17 23:22       ` Liu, Yi L
2018-05-21 23:03         ` Jacob Pan
2018-09-06  9:25   ` Auger Eric
2018-09-06 12:42     ` Jean-Philippe Brucker
2018-09-06 13:14       ` Auger Eric
2018-09-06 17:06         ` Jean-Philippe Brucker
2018-09-07  7:11           ` Auger Eric
2018-09-07 11:23             ` Jean-Philippe Brucker
2018-09-14 13:24   ` Auger Eric
2018-09-17 16:57     ` Jacob Pan
2018-09-25 14:58   ` Jean-Philippe Brucker
2018-09-25 22:17     ` Jacob Pan
2018-09-26 10:14       ` Jean-Philippe Brucker
2018-05-11 20:54 ` [PATCH v5 14/23] iommu: introduce page response function Jacob Pan
2018-05-14  6:39   ` Lu Baolu
2018-05-29 16:13     ` Jacob Pan
2018-09-10 14:52   ` Auger Eric
2018-09-10 17:50     ` Jacob Pan
2018-09-10 19:06       ` Auger Eric
2018-05-11 20:54 ` [PATCH v5 15/23] iommu: handle page response timeout Jacob Pan
2018-05-14  7:43   ` Lu Baolu
2018-05-29 16:20     ` Jacob Pan
2018-05-30  7:46       ` Lu Baolu
2018-05-11 20:54 ` [PATCH v5 16/23] iommu/config: add build dependency for dmar Jacob Pan
2018-05-11 20:54 ` [PATCH v5 17/23] iommu/vt-d: report non-recoverable faults to device Jacob Pan
2018-05-14  8:17   ` Lu Baolu
2018-05-29 17:33     ` Jacob Pan
2018-05-11 20:54 ` [PATCH v5 18/23] iommu/intel-svm: report device page request Jacob Pan
2018-05-11 20:54 ` [PATCH v5 19/23] iommu/intel-svm: replace dev ops with fault report API Jacob Pan
2018-05-11 20:54 ` [PATCH v5 20/23] iommu/intel-svm: do not flush iotlb for viommu Jacob Pan
2018-05-11 20:54 ` [PATCH v5 21/23] iommu/vt-d: add intel iommu page response function Jacob Pan
2018-05-11 20:54 ` [PATCH v5 22/23] trace/iommu: add sva trace events Jacob Pan
2018-05-11 20:54 ` [PATCH v5 23/23] iommu: use sva invalidate and device fault trace event Jacob Pan
2018-05-29 15:54 ` [PATCH v5 00/23] IOMMU and VT-d driver support for Shared Virtual Address (SVA) Jacob Pan

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=5AF8058B.4090703@linux.intel.com \
    --to=baolu.lu@linux.intel.com \
    --cc=alex.williamson@redhat.com \
    --cc=ashok.raj@intel.com \
    --cc=dwmw2@infradead.org \
    --cc=gregkh@linuxfoundation.org \
    --cc=hch@infradead.org \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jacob.jun.pan@linux.intel.com \
    --cc=jean-philippe.brucker@arm.com \
    --cc=joro@8bytes.org \
    --cc=kevin.tian@intel.com \
    --cc=khali@linux-fr.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=rafael.j.wysocki@intel.com \
    --cc=yi.l.liu@intel.com \
    --subject='Re: [PATCH v5 04/23] iommu/vt-d: add bind_pasid_table function' \
    /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

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).