[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-changelog] [xen master] VT-d: fix Device-TLB flush timeout issue



commit 1b39e1085c83929826eda4db6c7a10dce6971619
Author:     Quan Xu <quan.xu@xxxxxxxxx>
AuthorDate: Fri Jul 8 00:46:15 2016 -0600
Commit:     Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
CommitDate: Fri Jul 15 10:50:42 2016 +0100

    VT-d: fix Device-TLB flush timeout issue
    
    If Device-TLB flush timed out, we hide the target ATS device
    immediately. By hiding the device, we make sure it can't be
    assigned to any domain any longer (see device_assigned).
    
    Signed-off-by: Quan Xu <quan.xu@xxxxxxxxx>
    Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
    Acked-by: Kevin Tian <kevin.tian@xxxxxxxxx>
    Tested-by: Quan Xu <quan.xu@xxxxxxxxx>
---
 xen/drivers/passthrough/pci.c         | 29 ++++++++++++++++++
 xen/drivers/passthrough/vtd/extern.h  |  5 ++--
 xen/drivers/passthrough/vtd/qinval.c  | 56 ++++++++++++++++++++++++++---------
 xen/drivers/passthrough/vtd/x86/ats.c | 11 +++----
 xen/include/xen/iommu.h               |  2 ++
 5 files changed, 80 insertions(+), 23 deletions(-)

diff --git a/xen/drivers/passthrough/pci.c b/xen/drivers/passthrough/pci.c
index bb5f344..8bce213 100644
--- a/xen/drivers/passthrough/pci.c
+++ b/xen/drivers/passthrough/pci.c
@@ -32,6 +32,7 @@
 #include <xen/tasklet.h>
 #include <xsm/xsm.h>
 #include <asm/msi.h>
+#include "ats.h"
 
 struct pci_seg {
     struct list_head alldevs_list;
@@ -1504,6 +1505,34 @@ static int iommu_get_device_group(
     return i;
 }
 
+void iommu_dev_iotlb_flush_timeout(struct domain *d, struct pci_dev *pdev)
+{
+    pcidevs_lock();
+
+    disable_ats_device(pdev);
+
+    ASSERT(pdev->domain);
+    if ( d != pdev->domain )
+    {
+        pcidevs_unlock();
+        return;
+    }
+
+    list_del(&pdev->domain_list);
+    pdev->domain = NULL;
+    _pci_hide_device(pdev);
+
+    if ( !d->is_shutting_down && printk_ratelimit() )
+        printk(XENLOG_ERR
+               "dom%d: ATS device %04x:%02x:%02x.%u flush failed\n",
+               d->domain_id, pdev->seg, pdev->bus, PCI_SLOT(pdev->devfn),
+               PCI_FUNC(pdev->devfn));
+    if ( !is_hardware_domain(d) )
+        domain_crash(d);
+
+    pcidevs_unlock();
+}
+
 int iommu_do_pci_domctl(
     struct xen_domctl *domctl, struct domain *d,
     XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)
diff --git a/xen/drivers/passthrough/vtd/extern.h 
b/xen/drivers/passthrough/vtd/extern.h
index 45357f2..fb7edfa 100644
--- a/xen/drivers/passthrough/vtd/extern.h
+++ b/xen/drivers/passthrough/vtd/extern.h
@@ -25,6 +25,7 @@
 
 #define VTDPREFIX "[VT-D]"
 
+struct pci_ats_dev;
 extern bool_t rwbf_quirk;
 
 void print_iommu_regs(struct acpi_drhd_unit *drhd);
@@ -60,8 +61,8 @@ int dev_invalidate_iotlb(struct iommu *iommu, u16 did,
                          u64 addr, unsigned int size_order, u64 type);
 
 int __must_check qinval_device_iotlb_sync(struct iommu *iommu,
-                                          u32 max_invs_pend,
-                                          u16 sid, u16 size, u64 addr);
+                                          struct pci_dev *pdev,
+                                          u16 did, u16 size, u64 addr);
 
 unsigned int get_cache_line_size(void);
 void cacheline_flush(char *);
diff --git a/xen/drivers/passthrough/vtd/qinval.c 
b/xen/drivers/passthrough/vtd/qinval.c
index 4492b29..e95dc54 100644
--- a/xen/drivers/passthrough/vtd/qinval.c
+++ b/xen/drivers/passthrough/vtd/qinval.c
@@ -27,11 +27,11 @@
 #include "dmar.h"
 #include "vtd.h"
 #include "extern.h"
+#include "../ats.h"
 
 #define VTD_QI_TIMEOUT 1
 
-static int __must_check invalidate_sync(struct iommu *iommu,
-                                        bool_t flush_dev_iotlb);
+static int __must_check invalidate_sync(struct iommu *iommu);
 
 static void print_qi_regs(struct iommu *iommu)
 {
@@ -103,7 +103,7 @@ static int __must_check 
queue_invalidate_context_sync(struct iommu *iommu,
 
     unmap_vtd_domain_page(qinval_entries);
 
-    return invalidate_sync(iommu, 0);
+    return invalidate_sync(iommu);
 }
 
 static int __must_check queue_invalidate_iotlb_sync(struct iommu *iommu,
@@ -140,7 +140,7 @@ static int __must_check queue_invalidate_iotlb_sync(struct 
iommu *iommu,
     qinval_update_qtail(iommu, index);
     spin_unlock_irqrestore(&iommu->register_lock, flags);
 
-    return invalidate_sync(iommu, 0);
+    return invalidate_sync(iommu);
 }
 
 static int __must_check queue_invalidate_wait(struct iommu *iommu,
@@ -199,25 +199,53 @@ static int __must_check queue_invalidate_wait(struct 
iommu *iommu,
     return -EOPNOTSUPP;
 }
 
-static int __must_check invalidate_sync(struct iommu *iommu,
-                                        bool_t flush_dev_iotlb)
+static int __must_check invalidate_sync(struct iommu *iommu)
 {
     struct qi_ctrl *qi_ctrl = iommu_qi_ctrl(iommu);
 
     ASSERT(qi_ctrl->qinval_maddr);
 
-    return queue_invalidate_wait(iommu, 0, 1, 1, flush_dev_iotlb);
+    return queue_invalidate_wait(iommu, 0, 1, 1, 0);
 }
 
-int qinval_device_iotlb_sync(struct iommu *iommu,
-                             u32 max_invs_pend,
-                             u16 sid, u16 size, u64 addr)
+static int __must_check dev_invalidate_sync(struct iommu *iommu,
+                                            struct pci_dev *pdev, u16 did)
+{
+    struct qi_ctrl *qi_ctrl = iommu_qi_ctrl(iommu);
+    int rc;
+
+    ASSERT(qi_ctrl->qinval_maddr);
+    rc = queue_invalidate_wait(iommu, 0, 1, 1, 1);
+    if ( rc == -ETIMEDOUT )
+    {
+        struct domain *d = NULL;
+
+        if ( test_bit(did, iommu->domid_bitmap) )
+            d = rcu_lock_domain_by_id(iommu->domid_map[did]);
+
+        /*
+         * In case the domain has been freed or the IOMMU domid bitmap is
+         * not valid, the device no longer belongs to this domain.
+         */
+        if ( d == NULL )
+            return rc;
+
+        iommu_dev_iotlb_flush_timeout(d, pdev);
+        rcu_unlock_domain(d);
+    }
+
+    return rc;
+}
+
+int qinval_device_iotlb_sync(struct iommu *iommu, struct pci_dev *pdev,
+                             u16 did, u16 size, u64 addr)
 {
     unsigned long flags;
     unsigned int index;
     u64 entry_base;
     struct qinval_entry *qinval_entry, *qinval_entries;
 
+    ASSERT(pdev);
     spin_lock_irqsave(&iommu->register_lock, flags);
     index = qinval_next_index(iommu);
     entry_base = iommu_qi_ctrl(iommu)->qinval_maddr +
@@ -227,9 +255,9 @@ int qinval_device_iotlb_sync(struct iommu *iommu,
 
     qinval_entry->q.dev_iotlb_inv_dsc.lo.type = TYPE_INVAL_DEVICE_IOTLB;
     qinval_entry->q.dev_iotlb_inv_dsc.lo.res_1 = 0;
-    qinval_entry->q.dev_iotlb_inv_dsc.lo.max_invs_pend = max_invs_pend;
+    qinval_entry->q.dev_iotlb_inv_dsc.lo.max_invs_pend = pdev->ats.queue_depth;
     qinval_entry->q.dev_iotlb_inv_dsc.lo.res_2 = 0;
-    qinval_entry->q.dev_iotlb_inv_dsc.lo.sid = sid;
+    qinval_entry->q.dev_iotlb_inv_dsc.lo.sid = PCI_BDF2(pdev->bus, 
pdev->devfn);
     qinval_entry->q.dev_iotlb_inv_dsc.lo.res_3 = 0;
 
     qinval_entry->q.dev_iotlb_inv_dsc.hi.size = size;
@@ -240,7 +268,7 @@ int qinval_device_iotlb_sync(struct iommu *iommu,
     qinval_update_qtail(iommu, index);
     spin_unlock_irqrestore(&iommu->register_lock, flags);
 
-    return invalidate_sync(iommu, 1);
+    return dev_invalidate_sync(iommu, pdev, did);
 }
 
 static int __must_check queue_invalidate_iec_sync(struct iommu *iommu,
@@ -271,7 +299,7 @@ static int __must_check queue_invalidate_iec_sync(struct 
iommu *iommu,
     qinval_update_qtail(iommu, index);
     spin_unlock_irqrestore(&iommu->register_lock, flags);
 
-    ret = invalidate_sync(iommu, 0);
+    ret = invalidate_sync(iommu);
 
     /*
      * reading vt-d architecture register will ensure
diff --git a/xen/drivers/passthrough/vtd/x86/ats.c 
b/xen/drivers/passthrough/vtd/x86/ats.c
index 5c54f3a..1a3adb4 100644
--- a/xen/drivers/passthrough/vtd/x86/ats.c
+++ b/xen/drivers/passthrough/vtd/x86/ats.c
@@ -109,15 +109,14 @@ out:
 int dev_invalidate_iotlb(struct iommu *iommu, u16 did,
     u64 addr, unsigned int size_order, u64 type)
 {
-    const struct pci_dev *pdev;
+    struct pci_dev *pdev, *temp;
     int ret = 0;
 
     if ( !ecap_dev_iotlb(iommu->ecap) )
         return ret;
 
-    list_for_each_entry( pdev, &iommu->ats_devices, ats.list )
+    list_for_each_entry_safe( pdev, temp, &iommu->ats_devices, ats.list )
     {
-        u16 sid = PCI_BDF2(pdev->bus, pdev->devfn);
         bool_t sbit;
         int rc = 0;
 
@@ -131,8 +130,7 @@ int dev_invalidate_iotlb(struct iommu *iommu, u16 did,
             /* invalidate all translations: sbit=1,bit_63=0,bit[62:12]=1 */
             sbit = 1;
             addr = (~0UL << PAGE_SHIFT_4K) & 0x7FFFFFFFFFFFFFFF;
-            rc = qinval_device_iotlb_sync(iommu, pdev->ats.queue_depth,
-                                          sid, sbit, addr);
+            rc = qinval_device_iotlb_sync(iommu, pdev, did, sbit, addr);
             break;
         case DMA_TLB_PSI_FLUSH:
             if ( !device_in_domain(iommu, pdev, did) )
@@ -151,8 +149,7 @@ int dev_invalidate_iotlb(struct iommu *iommu, u16 did,
                 addr |= (((u64)1 << (size_order - 1)) - 1) << PAGE_SHIFT_4K;
             }
 
-            rc = qinval_device_iotlb_sync(iommu, pdev->ats.queue_depth,
-                                          sid, sbit, addr);
+            rc = qinval_device_iotlb_sync(iommu, pdev, did, sbit, addr);
             break;
         default:
             dprintk(XENLOG_WARNING VTDPREFIX, "invalid vt-d flush type\n");
diff --git a/xen/include/xen/iommu.h b/xen/include/xen/iommu.h
index a759f2b..5803e3f 100644
--- a/xen/include/xen/iommu.h
+++ b/xen/include/xen/iommu.h
@@ -207,6 +207,8 @@ int __must_check iommu_iotlb_flush(struct domain *d, 
unsigned long gfn,
                                    unsigned int page_count);
 int __must_check iommu_iotlb_flush_all(struct domain *d);
 
+void iommu_dev_iotlb_flush_timeout(struct domain *d, struct pci_dev *pdev);
+
 /*
  * The purpose of the iommu_dont_flush_iotlb optional cpu flag is to
  * avoid unecessary iotlb_flush in the low level IOMMU code.
--
generated by git-patchbot for /home/xen/git/xen.git#master

_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxx
https://lists.xenproject.org/xen-changelog

 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.