[Xen-devel] [PATCH v7 2/2] VT-d: Fix vt-d Device-TLB flush timeout issue

[Quan Xu <quan.xu@xxxxxxxxx>]

If Device-TLB flush timed out, we would hide the target ATS
device and crash the domain owning this ATS device. If impacted
domain is hardware domain, just throw out a warning.

The hidden device should be disallowed to be further assigned
to any domain.

Signed-off-by: Quan Xu <quan.xu@xxxxxxxxx>
---
 xen/drivers/passthrough/pci.c         |  6 ++--
 xen/drivers/passthrough/vtd/extern.h  |  2 ++
 xen/drivers/passthrough/vtd/qinval.c  | 65 ++++++++++++++++++++++++++++++++---
 xen/drivers/passthrough/vtd/x86/ats.c | 12 +++++++
 xen/include/xen/pci.h                 |  1 +
 5 files changed, 78 insertions(+), 8 deletions(-)

diff --git a/xen/drivers/passthrough/pci.c b/xen/drivers/passthrough/pci.c
index 9f1716a..9a214c6 100644
--- a/xen/drivers/passthrough/pci.c
+++ b/xen/drivers/passthrough/pci.c
@@ -420,7 +420,7 @@ static void free_pdev(struct pci_seg *pseg, struct pci_dev 
*pdev)
     xfree(pdev);
 }
 
-static void _pci_hide_device(struct pci_dev *pdev)
+void pci_hide_existing_device(struct pci_dev *pdev)
 {
     if ( pdev->domain )
         return;
@@ -437,7 +437,7 @@ int __init pci_hide_device(int bus, int devfn)
     pdev = alloc_pdev(get_pseg(0), bus, devfn);
     if ( pdev )
     {
-        _pci_hide_device(pdev);
+        pci_hide_existing_device(pdev);
         rc = 0;
     }
     pcidevs_unlock();
@@ -467,7 +467,7 @@ int __init pci_ro_device(int seg, int bus, int devfn)
     }
 
     __set_bit(PCI_BDF2(bus, devfn), pseg->ro_map);
-    _pci_hide_device(pdev);
+    pci_hide_existing_device(pdev);
 
     return 0;
 }
diff --git a/xen/drivers/passthrough/vtd/extern.h 
b/xen/drivers/passthrough/vtd/extern.h
index d4d37c3..5b8673e 100644
--- a/xen/drivers/passthrough/vtd/extern.h
+++ b/xen/drivers/passthrough/vtd/extern.h
@@ -58,6 +58,8 @@ int ats_device(const struct pci_dev *, const struct 
acpi_drhd_unit *);
 
 int dev_invalidate_iotlb(struct iommu *iommu, u16 did,
                          u64 addr, unsigned int size_order, u64 type);
+int dev_invalidate_iotlb_sync(struct iommu *iommu, u16 did,
+                              u16 seg, u8 bus, u8 devfn);
 
 int qinval_device_iotlb(struct iommu *iommu,
                         u32 max_invs_pend, u16 sid, u16 size, u64 addr);
diff --git a/xen/drivers/passthrough/vtd/qinval.c 
b/xen/drivers/passthrough/vtd/qinval.c
index 37a15fb..2a5c638 100644
--- a/xen/drivers/passthrough/vtd/qinval.c
+++ b/xen/drivers/passthrough/vtd/qinval.c
@@ -233,6 +233,57 @@ int qinval_device_iotlb(struct iommu *iommu,
     return 0;
 }
 
+static void dev_invalidate_iotlb_timeout(struct iommu *iommu, u16 did,
+                                         u16 seg, u8 bus, u8 devfn)
+{
+    struct domain *d = NULL;
+    struct pci_dev *pdev;
+
+    if ( test_bit(did, iommu->domid_bitmap) )
+        d = rcu_lock_domain_by_id(iommu->domid_map[did]);
+
+    if ( d == NULL )
+        return;
+
+    pcidevs_lock();
+    for_each_pdev(d, pdev)
+    {
+        if ( ( pdev->seg == seg ) &&
+             ( pdev->bus == bus ) &&
+             ( pdev->devfn == devfn ) )
+        {
+            ASSERT ( pdev->domain );
+            list_del(&pdev->domain_list);
+            pdev->domain = NULL;
+            pci_hide_existing_device(pdev);
+            break;
+        }
+    }
+
+    pcidevs_unlock();
+
+    if ( !is_hardware_domain(d) )
+        domain_crash(d);
+
+    rcu_unlock_domain(d);
+}
+
+int dev_invalidate_iotlb_sync(struct iommu *iommu, u16 did,
+                              u16 seg, u8 bus, u8 devfn)
+{
+    struct qi_ctrl *qi_ctrl = iommu_qi_ctrl(iommu);
+    int rc = 0;
+
+    if ( qi_ctrl->qinval_maddr )
+    {
+        rc = queue_invalidate_wait(iommu, 0, 1, 1);
+        if ( rc == -ETIMEDOUT )
+            dev_invalidate_iotlb_timeout(iommu, did, seg, bus, devfn);
+    }
+
+    return rc;
+}
+
 static void queue_invalidate_iec(struct iommu *iommu, u8 granu, u8 im, u16 
iidx)
 {
     unsigned long flags;
@@ -342,8 +393,6 @@ static int flush_iotlb_qi(
 
     if ( qi_ctrl->qinval_maddr != 0 )
     {
-        int rc;
-
         /* use queued invalidation */
         if (cap_write_drain(iommu->cap))
             dw = 1;
@@ -353,11 +402,17 @@ static int flush_iotlb_qi(
         queue_invalidate_iotlb(iommu,
                                type >> DMA_TLB_FLUSH_GRANU_OFFSET, dr,
                                dw, did, size_order, 0, addr);
+
+        /*
+         * Before Device-TLB invalidation we need to synchronize
+         * invalidation completions with hardware.
+         */
+        ret = invalidate_sync(iommu);
+        if ( ret )
+             return ret;
+
         if ( flush_dev_iotlb )
             ret = dev_invalidate_iotlb(iommu, did, addr, size_order, type);
-        rc = invalidate_sync(iommu);
-        if ( !ret )
-            ret = rc;
     }
     return ret;
 }
diff --git a/xen/drivers/passthrough/vtd/x86/ats.c 
b/xen/drivers/passthrough/vtd/x86/ats.c
index 334b9c1..c87ffe3 100644
--- a/xen/drivers/passthrough/vtd/x86/ats.c
+++ b/xen/drivers/passthrough/vtd/x86/ats.c
@@ -162,6 +162,18 @@ int dev_invalidate_iotlb(struct iommu *iommu, u16 did,
             return -EOPNOTSUPP;
         }
 
+        /*
+         * Synchronize with hardware for Device-TLB invalidate
+         * descriptor.
+         */
+        rc = dev_invalidate_iotlb_sync(iommu, did, pdev->seg,
+                                       pdev->bus, pdev->devfn);
+        if ( rc )
+            printk(XENLOG_ERR
+                   "Flush error %d on device %04x:%02x:%02x.%u.\n",
+                   ret, pdev->seg, pdev->bus, PCI_SLOT(pdev->devfn),
+                   PCI_FUNC(pdev->devfn));
+
         if ( !ret )
             ret = rc;
     }
diff --git a/xen/include/xen/pci.h b/xen/include/xen/pci.h
index 6ed29dd..bb9f791 100644
--- a/xen/include/xen/pci.h
+++ b/xen/include/xen/pci.h
@@ -116,6 +116,7 @@ const unsigned long *pci_get_ro_map(u16 seg);
 int pci_add_device(u16 seg, u8 bus, u8 devfn,
                    const struct pci_dev_info *, nodeid_t node);
 int pci_remove_device(u16 seg, u8 bus, u8 devfn);
+void pci_hide_existing_device(struct pci_dev *pdev);
 int pci_ro_device(int seg, int bus, int devfn);
 int pci_hide_device(int bus, int devfn);
 struct pci_dev *pci_get_pdev(int seg, int bus, int devfn);
-- 
1.9.1


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel