lkml.org 
[lkml]   [2020]   [Jul]   [6]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    SubjectRe: [PATCH v2 3/4] iommu/vt-d: Report page request faults for guest SVA
    From
    Date
    Hi Kevin,

    On 2020/7/6 9:29, Tian, Kevin wrote:
    >> From: Lu Baolu <baolu.lu@linux.intel.com>
    >> Sent: Monday, July 6, 2020 8:26 AM
    >>
    >> 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().
    >>
    >> 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...

    Sure.

    >
    >>
    >> 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(-)
    >>
    >> 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)
    >> }
    >> }
    >>
    >> +static int prq_to_iommu_prot(struct page_req_dsc *req)
    >> +{
    >> + int prot = 0;
    >> +
    >> + if (req->rd_req)
    >> + prot |= IOMMU_FAULT_PERM_READ;
    >> + if (req->wr_req)
    >> + prot |= IOMMU_FAULT_PERM_WRITE;
    >> + if (req->exe_req)
    >> + prot |= IOMMU_FAULT_PERM_EXEC;
    >> + if (req->pm_req)
    >> + prot |= 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 = PCI_BUS_NUM(desc->rid);
    >> + devfn = desc->rid & 0xff;
    >
    > not required.

    Yes. Will remove them.

    >
    >> +
    >> + /* Fill in event data for device specific processing */
    >> + event.fault.type = IOMMU_FAULT_PAGE_REQ;
    >> + event.fault.prm.addr = desc->addr;
    >> + event.fault.prm.pasid = desc->pasid;
    >> + event.fault.prm.grpid = desc->prg_index;
    >> + event.fault.prm.perm = 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?

    Yes.

    >
    >> + if (desc->lpig)
    >> + event.fault.prm.flags |=
    >> IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
    >> + if (desc->pasid_present)
    >> + event.fault.prm.flags |=
    >> IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
    >> + if (desc->priv_data_present) {
    >> + event.fault.prm.flags |=
    >> IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
    >> + event.fault.prm.flags |=
    >> 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 = d;
    >> @@ -828,7 +879,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
    >> tail = dmar_readq(iommu->reg + DMAR_PQT_REG) &
    >> PRQ_RING_MASK;
    >> head = dmar_readq(iommu->reg + DMAR_PQH_REG) &
    >> PRQ_RING_MASK;
    >> while (head != tail) {
    >> - struct intel_svm_dev *sdev;
    >> + struct intel_svm_dev *sdev = NULL;
    >
    > move to outside of the loop, otherwise later check always hit "if (!sdev)"

    Yes, good catch!

    >
    >> 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)
    >> }
    >> }
    >>
    >> + if (!sdev || sdev->sid != req->rid) {
    >> + struct intel_svm_dev *t;
    >> +
    >> + sdev = NULL;
    >> + rcu_read_lock();
    >> + list_for_each_entry_rcu(t, &svm->devs, list) {
    >> + if (t->sid == req->rid) {
    >> + sdev = t;
    >> + break;
    >> + }
    >> + }
    >> + rcu_read_unlock();
    >> + }
    >> +
    >> result = 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;
    >>
    >> + /*
    >> + * 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;
    >>
    >> result = 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 == 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

    I thought this comment explained why rcu_read_unlock() before the next
    checking. In the new lookup code, we don't need to check, hence I
    removed the comments.

    > regarding to guest unbind, ae we preventing the fault owner (outside
    > of iommu driver) to unbind against in-flight fault request?

    Yes. We always wait until all prq with the same pasid completes in
    gpasid_unbind().

    >
    >> - rcu_read_unlock();
    >> -
    >> - if (WARN_ON(&sdev->list == &svm->devs))
    >> - sdev = NULL;
    >
    > similarly should we keep the WARN_ON check here?

    Yes, agreed. We can keep a WARN_ON() here.

    >
    >> -
    >> +bad_req:
    >> if (sdev && sdev->ops && sdev->ops->fault_cb) {
    >> int rwxp = (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 = NULL;
    >> svm = 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 = 0;
    >> qi_submit_sync(iommu, &resp, 1, 0);
    >> }
    >> +prq_advance:
    >> head = (head + sizeof(*req)) & PRQ_RING_MASK;
    >> }
    >>
    >> --
    >> 2.17.1
    >
    > Thanks
    > Kevin
    >

    Best regards,
    baolu

    \
     
     \ /
      Last update: 2020-07-06 09:38    [W:4.232 / U:0.676 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site