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>
master commit: 6773b1a7584a75a486e9774541ad5bd84c9aa5ee
master date: 2021-04-26 10:16:50 +0200

diff --git a/docs/misc/xen-command-line.pandoc b/docs/misc/xen-command-line.pandoc
index f63fe9680ad1310d9a20ed50ee4f708383e7e647..b9824d443faa67fde032bd24d839e9eecca823c5 100644 (file)
--- a/docs/misc/xen-command-line.pandoc
+++ b/docs/misc/xen-command-line.pandoc
@@ -1405,7 +1405,9 @@ 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 74c7aca24b7a157b4423e1455e125324c08bc24d..32ff60bfe39c9b98a0c0e1c9ab42a7ec5fe86dad 100644 (file)
--- a/xen/drivers/passthrough/vtd/iommu.c
+++ b/xen/drivers/passthrough/vtd/iommu.c
@@ -1188,6 +1188,14 @@ 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 )
     {
@@ -2161,6 +2169,10 @@ 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;
         }
@@ -2251,6 +2263,7 @@ 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) )
     {
@@ -2272,8 +2285,8 @@ 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 )
     {
@@ -2295,6 +2308,9 @@ 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;
 
@@ -2321,6 +2337,13 @@ 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 216791b3d63498137b56c3231478007ddef9746a..57737b1a4a1c54f1a574008831929f2be94cec31 100644 (file)
--- a/xen/drivers/passthrough/vtd/iommu.h
+++ b/xen/drivers/passthrough/vtd/iommu.h
@@ -540,6 +540,7 @@ 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...) \
@@ -549,4 +550,10 @@ 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 764ef9f0fc61725648f2e53962a2898f154349bb..dfcbb66c8a82f27929b3697800ea4b015a06f141 100644 (file)
--- a/xen/drivers/passthrough/vtd/qinval.c
+++ b/xen/drivers/passthrough/vtd/qinval.c
@@ -442,6 +442,23 @@ 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;
@@ -463,6 +480,18 @@ 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;
+    }
 }