VT-d: size qinval queue dynamically

With the present synchronous model, we need two slots for every
operation (the operation itself and a wait descriptor).  There can be
one such pair of requests pending per CPU. To ensure that under all
normal circumstances a slot is always available when one is requested,
size the queue ring according to the number of present CPUs.

This is part of XSA-373 / CVE-2021-28692.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Paul Durrant <paul@xen.org>
(cherry picked from commit cbfa62bb140c8f10a0ae96db3ce06e22b3b9d302)

diff --git a/xen/drivers/passthrough/vtd/iommu.h b/xen/drivers/passthrough/vtd/iommu.h
index e76b261c81e29d8f9ad515a14d411981b5ebb588..fc52a3249ec3e92edb6802be93ee3f028bba08a1 100644 (file)
--- a/xen/drivers/passthrough/vtd/iommu.h
+++ b/xen/drivers/passthrough/vtd/iommu.h
@@ -447,17 +447,9 @@ struct qinval_entry {
     }q;
 };
 
-/* Order of queue invalidation pages(max is 8) */
-#define QINVAL_PAGE_ORDER   2
-
-#define QINVAL_ARCH_PAGE_ORDER  (QINVAL_PAGE_ORDER + PAGE_SHIFT_4K - PAGE_SHIFT)
-#define QINVAL_ARCH_PAGE_NR     ( QINVAL_ARCH_PAGE_ORDER < 0 ?  \
-                                1 :                             \
-                                1 << QINVAL_ARCH_PAGE_ORDER )
-
 /* Each entry is 16 bytes, so 2^8 entries per page */
 #define QINVAL_ENTRY_ORDER  ( PAGE_SHIFT - 4 )
-#define QINVAL_ENTRY_NR     (1 << (QINVAL_PAGE_ORDER + 8))
+#define QINVAL_MAX_ENTRY_NR (1u << (7 + QINVAL_ENTRY_ORDER))
 
 /* Status data flag */
 #define QINVAL_STAT_INIT  0

diff --git a/xen/drivers/passthrough/vtd/qinval.c b/xen/drivers/passthrough/vtd/qinval.c
index 09cbd36ebb8c9b5df598cb55f7fc9e352841e720..103afc15fe499c2123be3c28c5f9426aa81da1cb 100644 (file)
--- a/xen/drivers/passthrough/vtd/qinval.c
+++ b/xen/drivers/passthrough/vtd/qinval.c
@@ -31,6 +31,9 @@
 
 #define VTD_QI_TIMEOUT 1
 
+static unsigned int __read_mostly qi_pg_order;
+static unsigned int __read_mostly qi_entry_nr;
+
 static int __must_check invalidate_sync(struct iommu *iommu);
 
 static void print_qi_regs(struct iommu *iommu)
@@ -55,7 +58,7 @@ static unsigned int qinval_next_index(struct iommu *iommu)
     tail >>= QINVAL_INDEX_SHIFT;
 
     /* (tail+1 == head) indicates a full queue, wait for HW */
-    while ( ( tail + 1 ) % QINVAL_ENTRY_NR ==
+    while ( ((tail + 1) & (qi_entry_nr - 1)) ==
             ( dmar_readq(iommu->reg, DMAR_IQH_REG) >> QINVAL_INDEX_SHIFT ) )
         cpu_relax();
 
@@ -68,7 +71,7 @@ static void qinval_update_qtail(struct iommu *iommu, unsigned int index)
 
     /* Need hold register lock when update tail */
     ASSERT( spin_is_locked(&iommu->register_lock) );
-    val = (index + 1) % QINVAL_ENTRY_NR;
+    val = (index + 1) & (qi_entry_nr - 1);
     dmar_writeq(iommu->reg, DMAR_IQT_REG, (val << QINVAL_INDEX_SHIFT));
 }
 
@@ -417,7 +420,27 @@ int enable_qinval(struct iommu *iommu)
     if ( qi_ctrl->qinval_maddr == 0 )
     {
         drhd = iommu_to_drhd(iommu);
-        qi_ctrl->qinval_maddr = alloc_pgtable_maddr(drhd, QINVAL_ARCH_PAGE_NR);
+        if ( !qi_entry_nr )
+        {
+            /*
+             * With the present synchronous model, we need two slots for every
+             * operation (the operation itself and a wait descriptor).  There
+             * can be one such pair of requests pending per CPU.  One extra
+             * entry is needed as the ring is considered full when there's
+             * only one entry left.
+             */
+            BUILD_BUG_ON(CONFIG_NR_CPUS * 2 >= QINVAL_MAX_ENTRY_NR);
+            qi_pg_order = get_order_from_bytes((num_present_cpus() * 2 + 1) <<
+                                               (PAGE_SHIFT -
+                                                QINVAL_ENTRY_ORDER));
+            qi_entry_nr = 1u << (qi_pg_order + QINVAL_ENTRY_ORDER);
+
+            dprintk(XENLOG_INFO VTDPREFIX,
+                    "QI: using %u-entry ring(s)\n", qi_entry_nr);
+        }
+
+        qi_ctrl->qinval_maddr =
+            alloc_pgtable_maddr(drhd, qi_entry_nr >> QINVAL_ENTRY_ORDER);
         if ( qi_ctrl->qinval_maddr == 0 )
         {
             dprintk(XENLOG_WARNING VTDPREFIX,
@@ -431,15 +454,16 @@ int enable_qinval(struct iommu *iommu)
 
     spin_lock_irqsave(&iommu->register_lock, flags);
 
-    /* Setup Invalidation Queue Address(IQA) register with the
-     * address of the page we just allocated.  QS field at
-     * bits[2:0] to indicate size of queue is one 4KB page.
-     * That's 256 entries.  Queued Head (IQH) and Queue Tail (IQT)
-     * registers are automatically reset to 0 with write
-     * to IQA register.
+    /*
+     * Setup Invalidation Queue Address (IQA) register with the address of the
+     * pages we just allocated.  The QS field at bits[2:0] indicates the size
+     * (page order) of the queue.
+     *
+     * Queued Head (IQH) and Queue Tail (IQT) registers are automatically
+     * reset to 0 with write to IQA register.
      */
     dmar_writeq(iommu->reg, DMAR_IQA_REG,
-                qi_ctrl->qinval_maddr | QINVAL_PAGE_ORDER);
+                qi_ctrl->qinval_maddr | qi_pg_order);
 
     dmar_writeq(iommu->reg, DMAR_IQT_REG, 0);