iommu/vt-d: Add callback to device driver on page faults

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

3 files changed, 46 insertions, 4 deletions

diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index 0e8654282484..006e95dd64ae 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -264,7 +264,7 @@ static const struct mmu_notifier_ops intel_mmuops = {
 
 static DEFINE_MUTEX(pasid_mutex);
 
-int intel_svm_bind_mm(struct device *dev, int *pasid)
+int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ops *ops)
 {
         struct intel_iommu *iommu = intel_svm_device_to_iommu(dev);
         struct intel_svm_dev *sdev;
@@ -302,6 +302,10 @@ int intel_svm_bind_mm(struct device *dev, int *pasid)
 
                         list_for_each_entry(sdev, &svm->devs, list) {
                                 if (dev == sdev->dev) {
+                                        if (sdev->ops != ops) {
+                                                ret = -EBUSY;
+                                                goto out;
+                                        }
                                         sdev->users++;
                                         goto success;
                                 }
@@ -327,6 +331,7 @@ int intel_svm_bind_mm(struct device *dev, int *pasid)
         }
         /* Finish the setup now we know we're keeping it */
         sdev->users = 1;
+        sdev->ops = ops;
         init_rcu_head(&sdev->rcu);
 
         if (!svm) {
@@ -456,6 +461,7 @@ 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 vm_area_struct *vma;
                 struct page_req_dsc *req;
                 struct qi_desc resp;
@@ -507,6 +513,24 @@ static irqreturn_t prq_event_thread(int irq, void *d)
                 up_read(&svm->mm->mmap_sem);
         bad_req:
                 /* Accounting for major/minor faults? */
+                rcu_read_lock();
+                list_for_each_entry_rcu(sdev, &svm->devs, list) {
+                        if (sdev->sid == PCI_DEVID(req->bus, req->devfn));
+                                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. */
+                rcu_read_unlock();
+
+                if (WARN_ON(&sdev->list == &svm->devs))
+                        sdev = NULL;
+
+                if (sdev && sdev->ops && sdev->ops->fault_cb) {
+                        int rwxp = (req->rd_req << 3) | (req->wr_req << 2) |
+                                (req->wr_req << 1) | (req->exe_req);
+                        sdev->ops->fault_cb(sdev->dev, req->pasid, req->addr, req->private, rwxp, result);
+                }
 
                 if (req->lpig) {
                         /* Page Group Response */
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index e5b80d31eb1b..57be14fce640 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -472,10 +472,13 @@ extern int intel_svm_free_pasid_tables(struct intel_iommu *iommu);
 extern int intel_svm_enable_prq(struct intel_iommu *iommu);
 extern int intel_svm_finish_prq(struct intel_iommu *iommu);
 
+struct svm_dev_ops;
+
 struct intel_svm_dev {
         struct list_head list;
         struct rcu_head rcu;
         struct device *dev;
+        struct svm_dev_ops *ops;
         int users;
         u16 did;
         u16 dev_iotlb:1;
diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h
index 42f80ad7a7a0..239f8a13a332 100644
--- a/include/linux/intel-svm.h
+++ b/include/linux/intel-svm.h
@@ -20,10 +20,23 @@
 
 struct device;
 
+struct svm_dev_ops {
+        void (*fault_cb)(struct device *dev, int pasid, u64 address,
+                         u32 private, int rwxp, int response);
+};
+
+/* Values for rxwp in fault_cb callback */
+#define SVM_REQ_READ    (1<<3)
+#define SVM_REQ_WRITE   (1<<2)
+#define SVM_REQ_EXEC    (1<<1)
+#define SVM_REQ_PRIV    (1<<0)
+
 /**
  * intel_svm_bind_mm() - Bind the current process to a PASID
  * @dev:        Device to be granted acccess
  * @pasid:      Address for allocated PASID
+ * @flags:      Flags. Later for requesting supervisor mode, etc.
+ * @ops:        Callbacks to device driver
  *
  * This function attempts to enable PASID support for the given device.
  * If the @pasid argument is non-%NULL, a PASID is allocated for access
@@ -45,7 +58,8 @@ struct device;
  * Multiple calls from the same process may result in the same PASID
  * being re-used. A reference count is kept.
  */
-extern int intel_svm_bind_mm(struct device *dev, int *pasid);
+extern int intel_svm_bind_mm(struct device *dev, int *pasid, int flags,
+                             struct svm_dev_ops *ops);
 
 /**
  * intel_svm_unbind_mm() - Unbind a specified PASID
@@ -66,7 +80,8 @@ extern int intel_svm_unbind_mm(struct device *dev, int pasid);
 
 #else /* CONFIG_INTEL_IOMMU_SVM */
 
-static inline int intel_svm_bind_mm(struct device *dev, int *pasid)
+static inline int intel_svm_bind_mm(struct device *dev, int *pasid,
+                                    int flags, struct svm_dev_ops *ops)
 {
         return -ENOSYS;
 }
@@ -77,6 +92,6 @@ static inline int intel_svm_unbind_mm(struct device *dev, int pasid)
 }
 #endif /* CONFIG_INTEL_IOMMU_SVM */
 
-#define intel_svm_available(dev) (!intel_svm_bind_mm((dev), NULL))
+#define intel_svm_available(dev) (!intel_svm_bind_mm((dev), NULL, 0, NULL))
 
 #endif /* __INTEL_SVM_H__ */