VT-d: Don't assume register-based invalidation is always supported

According to Intel VT-d SPEC rev3.3 Section 6.5, Register-based Invalidation
isn't supported by Intel VT-d version 6 and beyond.

This hardware change impacts following two scenarios: admin can disable
queued invalidation via 'qinval' cmdline and use register-based interface;
VT-d switches to register-based invalidation when queued invalidation needs
to be disabled, for example, during disabling x2apic or during system
suspension or after enabling queued invalidation fails.

To deal with this hardware change, if register-based invalidation isn't
supported, queued invalidation cannot be disabled through Xen cmdline; and
if queued invalidation has to be disabled temporarily in some scenarios,
VT-d won't switch to register-based interface but use some dummy functions
to catch errors in case there is any invalidation request issued when queued
invalidation is disabled.

Signed-off-by: Chao Gao <chao.gao@intel.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>

diff --git a/docs/misc/xen-command-line.pandoc b/docs/misc/xen-command-line.pandoc
index a4bd3f12c53b4d8860c4a08e59b687d98b92f198..c32a397a12b86e14457aee2c7f5e5f594a33931a 100644 (file)
--- a/docs/misc/xen-command-line.pandoc
+++ b/docs/misc/xen-command-line.pandoc
@@ -1458,7 +1458,9 @@ The following options are specific to Intel VT-d hardware:
 *   The `qinval` boolean controls the Queued Invalidation sub-feature, and is
     active by default on compatible hardware.  Queued Invalidation is a
     feature in second-generation IOMMUs and is a functional prerequisite for
-    Interrupt Remapping.
+    Interrupt Remapping. Note that Xen disregards this setting for Intel VT-d
+    version 6 and greater as Registered-Based Invalidation isn't supported
+    by them.
 
 *   The `igfx` boolean is active by default, and controls whether the IOMMU in
     front of an Intel Graphics Device is enabled or not.

diff --git a/xen/drivers/passthrough/vtd/iommu.c b/xen/drivers/passthrough/vtd/iommu.c
index b2ca152e1f21fc0bab5653f3d6f4c0c1645da08b..82ae2f5e97ad0ccb2428dab30389611922ebdebf 100644 (file)
--- a/xen/drivers/passthrough/vtd/iommu.c
+++ b/xen/drivers/passthrough/vtd/iommu.c
@@ -1185,6 +1185,14 @@ int __init iommu_alloc(struct acpi_drhd_unit *drhd)
 
     iommu->cap = dmar_readq(iommu->reg, DMAR_CAP_REG);
     iommu->ecap = dmar_readq(iommu->reg, DMAR_ECAP_REG);
+    iommu->version = dmar_readl(iommu->reg, DMAR_VER_REG);
+
+    if ( !iommu_qinval && !has_register_based_invalidation(iommu) )
+    {
+        printk(XENLOG_WARNING VTDPREFIX "IOMMU %d: cannot disable Queued Invalidation\n",
+               iommu->index);
+        iommu_qinval = true;
+    }
 
     if ( iommu_verbose )
     {
@@ -2133,6 +2141,10 @@ static int __must_check init_vtd_hw(bool resume)
          */
         if ( enable_qinval(iommu) != 0 )
         {
+            /* Ensure register-based invalidation is available */
+            if ( !has_register_based_invalidation(iommu) )
+                return -EIO;
+
             iommu->flush.context = vtd_flush_context_reg;
             iommu->flush.iotlb   = vtd_flush_iotlb_reg;
         }
@@ -2227,6 +2239,7 @@ static int __init vtd_setup(void)
     struct acpi_drhd_unit *drhd;
     struct vtd_iommu *iommu;
     int ret;
+    bool reg_inval_supported = true;
 
     if ( list_empty(&acpi_drhd_units) )
     {
@@ -2255,8 +2268,8 @@ static int __init vtd_setup(void)
     }
 
     /* We enable the following features only if they are supported by all VT-d
-     * engines: Snoop Control, DMA passthrough, Queued Invalidation, Interrupt
-     * Remapping, and Posted Interrupt
+     * engines: Snoop Control, DMA passthrough, Register-based Invalidation,
+     * Queued Invalidation, Interrupt Remapping, and Posted Interrupt.
      */
     for_each_drhd_unit ( drhd )
     {
@@ -2278,6 +2291,9 @@ static int __init vtd_setup(void)
         if ( iommu_qinval && !ecap_queued_inval(iommu->ecap) )
             iommu_qinval = 0;
 
+        if ( !has_register_based_invalidation(iommu) )
+            reg_inval_supported = false;
+
         if ( iommu_intremap && !ecap_intr_remap(iommu->ecap) )
             iommu_intremap = iommu_intremap_off;
 
@@ -2304,6 +2320,13 @@ static int __init vtd_setup(void)
 
     softirq_tasklet_init(&vtd_fault_tasklet, do_iommu_page_fault, NULL);
 
+    if ( !iommu_qinval && !reg_inval_supported )
+    {
+        dprintk(XENLOG_ERR VTDPREFIX, "No available invalidation interface\n");
+        ret = -ENODEV;
+        goto error;
+    }
+
     if ( !iommu_qinval && iommu_intremap )
     {
         iommu_intremap = iommu_intremap_off;

diff --git a/xen/drivers/passthrough/vtd/iommu.h b/xen/drivers/passthrough/vtd/iommu.h
index aaf9e864ffdfaa253c05662a6dd750646bed94bd..68b3c76ea9d49bdd035a3bb45e1a173c76f70558 100644 (file)
--- a/xen/drivers/passthrough/vtd/iommu.h
+++ b/xen/drivers/passthrough/vtd/iommu.h
@@ -526,6 +526,7 @@ struct vtd_iommu {
     struct list_head ats_devices;
     unsigned long *domid_bitmap;  /* domain id bitmap */
     u16 *domid_map;               /* domain id mapping array */
+    uint32_t version;
 };
 
 #define INTEL_IOMMU_DEBUG(fmt, args...) \
@@ -535,4 +536,10 @@ struct vtd_iommu {
             dprintk(XENLOG_WARNING VTDPREFIX, fmt, ## args);    \
     } while(0)
 
+/* Register-based invalidation isn't supported by VT-d version 6 and beyond. */
+static inline bool has_register_based_invalidation(const struct vtd_iommu *vtd)
+{
+    return VER_MAJOR(vtd->version) < 6;
+}
+
 #endif

diff --git a/xen/drivers/passthrough/vtd/qinval.c b/xen/drivers/passthrough/vtd/qinval.c
index c0ea19d4bd8e2851d7e3adb6b0ecfdb6acefa64b..0976def43d494eae433595dd31a8bf7293ed06e0 100644 (file)
--- a/xen/drivers/passthrough/vtd/qinval.c
+++ b/xen/drivers/passthrough/vtd/qinval.c
@@ -434,6 +434,23 @@ int enable_qinval(struct vtd_iommu *iommu)
     return 0;
 }
 
+static int vtd_flush_context_noop(struct vtd_iommu *iommu, uint16_t did,
+                                  uint16_t source_id, uint8_t function_mask,
+                                  uint64_t type, bool flush_non_present_entry)
+{
+    WARN();
+    return -EIO;
+}
+
+static int vtd_flush_iotlb_noop(struct vtd_iommu *iommu, uint16_t did,
+                                uint64_t addr, unsigned int size_order,
+                                uint64_t type, bool flush_non_present_entry,
+                                bool flush_dev_iotlb)
+{
+    WARN();
+    return -EIO;
+}
+
 void disable_qinval(struct vtd_iommu *iommu)
 {
     u32 sts;
@@ -455,6 +472,18 @@ void disable_qinval(struct vtd_iommu *iommu)
 out:
     spin_unlock_irqrestore(&iommu->register_lock, flags);
 
-    iommu->flush.context = vtd_flush_context_reg;
-    iommu->flush.iotlb   = vtd_flush_iotlb_reg;
+    /*
+     * Assign callbacks to noop to catch errors if register-based invalidation
+     * isn't supported.
+     */
+    if ( has_register_based_invalidation(iommu) )
+    {
+        iommu->flush.context = vtd_flush_context_reg;
+        iommu->flush.iotlb   = vtd_flush_iotlb_reg;
+    }
+    else
+    {
+        iommu->flush.context = vtd_flush_context_noop;
+        iommu->flush.iotlb   = vtd_flush_iotlb_noop;
+    }
 }