Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
IronPort-SDR: FEP3bcB4wj0nmzFNT6GlFdXG7JKzQzReCmvwL8+jOQEHHs2Jq1lksxfAFTVSe/pPFW/gnv0rTp
 kPFbDwshMOaQ==
IronPort-SDR: NbLsibavuApzyyE7/vj+NK/ksuZfPLJpxDJt4anVzvYM3jjP4XRNVHzAMFUI085kigQp2+wRdS
 YFEC3k7EWgvg==
From:   "Tian, Kevin" <kevin.tian@intel.com>
To:     Lu Baolu <baolu.lu@linux.intel.com>,
        "iommu@lists.linux-foundation.org" <iommu@lists.linux-foundation.org>
CC:     Joerg Roedel <joro@8bytes.org>,
        Jacob Pan <jacob.jun.pan@linux.intel.com>,
        "Raj, Ashok" <ashok.raj@intel.com>,
        "Liu, Yi L" <yi.l.liu@intel.com>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: RE: [PATCH v2 3/4] iommu/vt-d: Report page request faults for guest
 SVA
Thread-Topic: [PATCH v2 3/4] iommu/vt-d: Report page request faults for guest
 SVA
Thread-Index: AQHWUyyukChEQzBHHE2t9ZcjAFLs+aj5vlKw
Date:   Mon, 6 Jul 2020 01:29:34 +0000
Message-ID: <MWHPR11MB1645466566F629CE524ED9C58C690@MWHPR11MB1645.namprd11.prod.outlook.com>
References: <20200706002535.9381-1-baolu.lu@linux.intel.com>
 <20200706002535.9381-4-baolu.lu@linux.intel.com>
In-Reply-To: <20200706002535.9381-4-baolu.lu@linux.intel.com>
Accept-Language: en-US
Content-Language: en-US
dlp-version: 11.2.0.6
dlp-product: dlpe-windows
dlp-reaction: no-action
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-Network-Message-Id: 5eb9838b-6223-4a96-bf74-08d8214c0a5d
X-MS-Exchange-CrossTenant-originalarrivaltime: 06 Jul 2020 01:29:34.6722
 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: 46c98d88-e344-4ed4-8496-4ed7712e255d
X-MS-Exchange-CrossTenant-mailboxtype: HOSTED
X-MS-Exchange-CrossTenant-userprincipalname: M3VSfBqHjAo8PN6kt7rqbKQ52m2aj6hBRt1s4pxFgup7xEAtOAhadr4icjzk3P9V+B5DUeJfRI7vJYcyFVzxGw==
X-MS-Exchange-Transport-CrossTenantHeadersStamped: MWHPR11MB1293
X-OriginatorOrg: intel.com
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

> From: Lu Baolu <baolu.lu@linux.intel.com>
> Sent: Monday, July 6, 2020 8:26 AM
>=20
> A pasid might be bound to a page table from a VM guest via the iommu
> ops.sva_bind_gpasid. In this case, when a DMA page fault is detected
> on the physical IOMMU, we need to inject the page fault request into
> the guest. After the guest completes handling the page fault, a page
> response need to be sent back via the iommu ops.page_response().
>=20
> This adds support to report a page request fault. Any external module
> which is interested in handling this fault should regiester a notifier
> callback.

be specific on which notifier to be registered...

>=20
> Co-developed-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
> Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
> Co-developed-by: Liu Yi L <yi.l.liu@intel.com>
> Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
> Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
> ---
>  drivers/iommu/intel/svm.c | 99 ++++++++++++++++++++++++++++++++-------
>  1 file changed, 81 insertions(+), 18 deletions(-)
>=20
> diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
> index c23167877b2b..08c58c2b1a06 100644
> --- a/drivers/iommu/intel/svm.c
> +++ b/drivers/iommu/intel/svm.c
> @@ -815,6 +815,57 @@ static void intel_svm_drain_prq(struct device *dev,
> int pasid)
>  	}
>  }
>=20
> +static int prq_to_iommu_prot(struct page_req_dsc *req)
> +{
> +	int prot =3D 0;
> +
> +	if (req->rd_req)
> +		prot |=3D IOMMU_FAULT_PERM_READ;
> +	if (req->wr_req)
> +		prot |=3D IOMMU_FAULT_PERM_WRITE;
> +	if (req->exe_req)
> +		prot |=3D IOMMU_FAULT_PERM_EXEC;
> +	if (req->pm_req)
> +		prot |=3D IOMMU_FAULT_PERM_PRIV;
> +
> +	return prot;
> +}
> +
> +static int
> +intel_svm_prq_report(struct device *dev, struct page_req_dsc *desc)
> +{
> +	struct iommu_fault_event event;
> +	u8 bus, devfn;
> +
> +	memset(&event, 0, sizeof(struct iommu_fault_event));
> +	bus =3D PCI_BUS_NUM(desc->rid);
> +	devfn =3D desc->rid & 0xff;

not required.

> +
> +	/* Fill in event data for device specific processing */
> +	event.fault.type =3D IOMMU_FAULT_PAGE_REQ;
> +	event.fault.prm.addr =3D desc->addr;
> +	event.fault.prm.pasid =3D desc->pasid;
> +	event.fault.prm.grpid =3D desc->prg_index;
> +	event.fault.prm.perm =3D prq_to_iommu_prot(desc);
> +
> +	/*
> +	 * Set last page in group bit if private data is present,
> +	 * page response is required as it does for LPIG.
> +	 */

move to priv_data_present check?

> +	if (desc->lpig)
> +		event.fault.prm.flags |=3D
> IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
> +	if (desc->pasid_present)
> +		event.fault.prm.flags |=3D
> IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
> +	if (desc->priv_data_present) {
> +		event.fault.prm.flags |=3D
> IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
> +		event.fault.prm.flags |=3D
> IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA;
> +		memcpy(event.fault.prm.private_data, desc->priv_data,
> +		       sizeof(desc->priv_data));
> +	}
> +
> +	return iommu_report_device_fault(dev, &event);
> +}
> +
>  static irqreturn_t prq_event_thread(int irq, void *d)
>  {
>  	struct intel_iommu *iommu =3D d;
> @@ -828,7 +879,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
>  	tail =3D dmar_readq(iommu->reg + DMAR_PQT_REG) &
> PRQ_RING_MASK;
>  	head =3D dmar_readq(iommu->reg + DMAR_PQH_REG) &
> PRQ_RING_MASK;
>  	while (head !=3D tail) {
> -		struct intel_svm_dev *sdev;
> +		struct intel_svm_dev *sdev =3D NULL;

move to outside of the loop, otherwise later check always hit "if (!sdev)"

>  		struct vm_area_struct *vma;
>  		struct page_req_dsc *req;
>  		struct qi_desc resp;
> @@ -864,6 +915,20 @@ static irqreturn_t prq_event_thread(int irq, void *d=
)
>  			}
>  		}
>=20
> +		if (!sdev || sdev->sid !=3D req->rid) {
> +			struct intel_svm_dev *t;
> +
> +			sdev =3D NULL;
> +			rcu_read_lock();
> +			list_for_each_entry_rcu(t, &svm->devs, list) {
> +				if (t->sid =3D=3D req->rid) {
> +					sdev =3D t;
> +					break;
> +				}
> +			}
> +			rcu_read_unlock();
> +		}
> +
>  		result =3D QI_RESP_INVALID;
>  		/* Since we're using init_mm.pgd directly, we should never
> take
>  		 * any faults on kernel addresses. */
> @@ -874,6 +939,17 @@ static irqreturn_t prq_event_thread(int irq, void *d=
)
>  		if (!is_canonical_address(address))
>  			goto bad_req;
>=20
> +		/*
> +		 * If prq is to be handled outside iommu driver via receiver of
> +		 * the fault notifiers, we skip the page response here.
> +		 */
> +		if (svm->flags & SVM_FLAG_GUEST_MODE) {
> +			if (sdev && !intel_svm_prq_report(sdev->dev, req))
> +				goto prq_advance;
> +			else
> +				goto bad_req;
> +		}
> +
>  		/* If the mm is already defunct, don't handle faults. */
>  		if (!mmget_not_zero(svm->mm))
>  			goto bad_req;
> @@ -892,24 +968,10 @@ static irqreturn_t prq_event_thread(int irq, void *=
d)
>  			goto invalid;
>=20
>  		result =3D QI_RESP_SUCCESS;
> -	invalid:
> +invalid:
>  		mmap_read_unlock(svm->mm);
>  		mmput(svm->mm);
> -	bad_req:
> -		/* Accounting for major/minor faults? */
> -		rcu_read_lock();
> -		list_for_each_entry_rcu(sdev, &svm->devs, list) {
> -			if (sdev->sid =3D=3D req->rid)
> -				break;
> -		}
> -		/* Other devices can go away, but the drivers are not
> permitted
> -		 * to unbind while any page faults might be in flight. So it's
> -		 * OK to drop the 'lock' here now we have it. */

should we keep and move this comment to earlier sdev lookup? and
regarding to guest unbind, ae we preventing the fault owner (outside
of iommu driver) to unbind against in-flight fault request?

> -		rcu_read_unlock();
> -
> -		if (WARN_ON(&sdev->list =3D=3D &svm->devs))
> -			sdev =3D NULL;

similarly should we keep the WARN_ON check here?

> -
> +bad_req:
>  		if (sdev && sdev->ops && sdev->ops->fault_cb) {
>  			int rwxp =3D (req->rd_req << 3) | (req->wr_req << 2) |
>  				(req->exe_req << 1) | (req->pm_req);
> @@ -920,7 +982,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
>  		   and these can be NULL. Do not use them below this point!
> */
>  		sdev =3D NULL;
>  		svm =3D NULL;
> -	no_pasid:
> +no_pasid:
>  		if (req->lpig || req->priv_data_present) {
>  			/*
>  			 * Per VT-d spec. v3.0 ch7.7, system software must
> @@ -945,6 +1007,7 @@ static irqreturn_t prq_event_thread(int irq, void *d=
)
>  			resp.qw3 =3D 0;
>  			qi_submit_sync(iommu, &resp, 1, 0);
>  		}
> +prq_advance:
>  		head =3D (head + sizeof(*req)) & PRQ_RING_MASK;
>  	}
>=20
> --
> 2.17.1

Thanks
Kevin