Re: [PATCH 3/4] iommu/vt-d: Report page request faults for guest SVA
Hi Kevin,
Thanks a lot for reviewing my patches.
On 6/30/20 2:01 PM, Tian, Kevin wrote:
From: Lu Baolu
Sent: Sunday, June 28, 2020 8:34 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.
Co-developed-by: Jacob Pan
Signed-off-by: Jacob Pan
Co-developed-by: Liu Yi L
Signed-off-by: Liu Yi L
Signed-off-by: Lu Baolu
---
drivers/iommu/intel/svm.c | 83
+--
1 file changed, 80 insertions(+), 3 deletions(-)
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index c23167877b2b..4800bb6f8794 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -815,6 +815,69 @@ 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 intel_iommu *iommu, struct page_req_dsc
*desc)
+{
+ struct iommu_fault_event event;
+ struct pci_dev *pdev;
+ u8 bus, devfn;
+ int ret = 0;
+
+ memset(&event, 0, sizeof(struct iommu_fault_event));
+ bus = PCI_BUS_NUM(desc->rid);
+ devfn = desc->rid & 0xff;
+ pdev = pci_get_domain_bus_and_slot(iommu->segment, bus, devfn);
Is this step necessary? dev can be passed in (based on sdev), and more
importantly iommu_report_device_fault already handles the ref counting
e.g. get_device(dev) when fault handler is valid...
Yes, agreed. I will pass device in instead.
+
+ if (!pdev) {
+ pr_err("No PCI device found for PRQ [%02x:%02x.%d]\n",
+ bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
+ return -ENODEV;
+ }
+
+ /* 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.
+*/
+ 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;
why setting lpig under this condition?
/*
* Per VT-d spec. v3.0 ch7.7, system software must
* respond with page group response if private data
* is present (PDP) or last page in group (LPIG) bit
* is set. This is an additional VT-d feature beyond
* PCI ATS spec.
*/
+ event.fault.prm.flags |=
IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA;
+ memcpy(event.fault.prm.private_data, desc->priv_data,
+ sizeof(desc->priv_data));
+ }
+
+ ret = iommu_report_device_fault(&pdev->dev, &event);
+ pci_dev_put(pdev);
+
+ return ret;
+}
+
static irqreturn_t prq_event_thread(int irq, void *d)
{
struct intel_iommu *iommu = d;
@@ -874,6 +937,19 @@ 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) {
+ int res = intel_svm_prq_report(iommu, req);
+
+ if (!res)
+ goto prq_advance;
+ else
+ goto bad_req;
+ }
+
I noted in bad_req there is another reporting logic:
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);
sdev->ops->fault_cb(sdev->dev, req->pasid, req->addr,
req->priv_data, rwxp, result)
RE: [PATCH 3/4] iommu/vt-d: Report page request faults for guest SVA
> From: Lu Baolu
> Sent: Sunday, June 28, 2020 8:34 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.
>
> Co-developed-by: Jacob Pan
> Signed-off-by: Jacob Pan
> Co-developed-by: Liu Yi L
> Signed-off-by: Liu Yi L
> Signed-off-by: Lu Baolu
> ---
> drivers/iommu/intel/svm.c | 83
> +--
> 1 file changed, 80 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
> index c23167877b2b..4800bb6f8794 100644
> --- a/drivers/iommu/intel/svm.c
> +++ b/drivers/iommu/intel/svm.c
> @@ -815,6 +815,69 @@ 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 intel_iommu *iommu, struct page_req_dsc
> *desc)
> +{
> + struct iommu_fault_event event;
> + struct pci_dev *pdev;
> + u8 bus, devfn;
> + int ret = 0;
> +
> + memset(&event, 0, sizeof(struct iommu_fault_event));
> + bus = PCI_BUS_NUM(desc->rid);
> + devfn = desc->rid & 0xff;
> + pdev = pci_get_domain_bus_and_slot(iommu->segment, bus, devfn);
Is this step necessary? dev can be passed in (based on sdev), and more
importantly iommu_report_device_fault already handles the ref counting
e.g. get_device(dev) when fault handler is valid...
> +
> + if (!pdev) {
> + pr_err("No PCI device found for PRQ [%02x:%02x.%d]\n",
> +bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
> + return -ENODEV;
> + }
> +
> + /* 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.
> + */
> + 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;
why setting lpig under this condition?
> + event.fault.prm.flags |=
> IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA;
> + memcpy(event.fault.prm.private_data, desc->priv_data,
> +sizeof(desc->priv_data));
> + }
> +
> + ret = iommu_report_device_fault(&pdev->dev, &event);
> + pci_dev_put(pdev);
> +
> + return ret;
> +}
> +
> static irqreturn_t prq_event_thread(int irq, void *d)
> {
> struct intel_iommu *iommu = d;
> @@ -874,6 +937,19 @@ 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) {
> + int res = intel_svm_prq_report(iommu, req);
> +
> + if (!res)
> + goto prq_advance;
> + else
> + goto bad_req;
> + }
> +
I noted in bad_req there is another reporting logic:
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);
sdev->ops->fault_cb(sdev->dev, req->pasid, req->addr,
req->priv_data, rwxp, result);
}
It was introduced in the 1st version of svm.c. It might be unrelated to
this patch, but I wonder whether that one should be replaced with
iommu_report_device_fault too?
Thanks
Kevin
> /* If the mm is already defunct, don't handle fault
[PATCH 3/4] iommu/vt-d: Report page request faults for guest SVA
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.
Co-developed-by: Jacob Pan
Signed-off-by: Jacob Pan
Co-developed-by: Liu Yi L
Signed-off-by: Liu Yi L
Signed-off-by: Lu Baolu
---
drivers/iommu/intel/svm.c | 83 +--
1 file changed, 80 insertions(+), 3 deletions(-)
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index c23167877b2b..4800bb6f8794 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -815,6 +815,69 @@ 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 intel_iommu *iommu, struct page_req_dsc *desc)
+{
+ struct iommu_fault_event event;
+ struct pci_dev *pdev;
+ u8 bus, devfn;
+ int ret = 0;
+
+ memset(&event, 0, sizeof(struct iommu_fault_event));
+ bus = PCI_BUS_NUM(desc->rid);
+ devfn = desc->rid & 0xff;
+ pdev = pci_get_domain_bus_and_slot(iommu->segment, bus, devfn);
+
+ if (!pdev) {
+ pr_err("No PCI device found for PRQ [%02x:%02x.%d]\n",
+ bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
+ return -ENODEV;
+ }
+
+ /* 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.
+*/
+ 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));
+ }
+
+ ret = iommu_report_device_fault(&pdev->dev, &event);
+ pci_dev_put(pdev);
+
+ return ret;
+}
+
static irqreturn_t prq_event_thread(int irq, void *d)
{
struct intel_iommu *iommu = d;
@@ -874,6 +937,19 @@ 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) {
+ int res = intel_svm_prq_report(iommu, req);
+
+ if (!res)
+ 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;
@@ -892,10 +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:
+bad_req:
/* Accounting for major/minor faults? */
rcu_read_lock();
list_for_each_entry_rcu(sdev, &svm->devs, list) {
@@ -920,7 +996,7 @@ 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 +1021,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
