intel-iommu: optimize nodmar memory regions

Previously we have per-device system memory aliases when DMAR is
disabled by the system.  It will slow the system down if there are
lots of devices especially when DMAR is disabled, because each of the
aliased system address space will contain O(N) slots, and rendering
such N address spaces will be O(N^2) complexity.

This patch introduces a shared nodmar memory region and for each
device we only create an alias to the shared memory region.  With the
aliasing, QEMU memory core API will be able to detect when devices are
sharing the same address space (which is the nodmar address space)
when rendering the FlatViews and the total number of FlatViews can be
dramatically reduced when there are a lot of devices.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20190313094323.18263-1-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index b90de6c6646152726d85b3a57b16bdc3ad361b52..055a1e865d2f7ec030ab103df1aae7943ce48e66 100644 (file)
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -1485,11 +1485,11 @@ static bool vtd_switch_address_space(VTDAddressSpace *as)
 
     /* Turn off first then on the other */
     if (use_iommu) {
-        memory_region_set_enabled(&as->sys_alias, false);
+        memory_region_set_enabled(&as->nodmar, false);
         memory_region_set_enabled(MEMORY_REGION(&as->iommu), true);
     } else {
         memory_region_set_enabled(MEMORY_REGION(&as->iommu), false);
-        memory_region_set_enabled(&as->sys_alias, true);
+        memory_region_set_enabled(&as->nodmar, true);
     }
 
     if (take_bql) {
@@ -3286,7 +3286,8 @@ VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus, int devfn)
     vtd_dev_as = vtd_bus->dev_as[devfn];
 
     if (!vtd_dev_as) {
-        snprintf(name, sizeof(name), "intel_iommu_devfn_%d", devfn);
+        snprintf(name, sizeof(name), "vtd-%02x.%x", PCI_SLOT(devfn),
+                 PCI_FUNC(devfn));
         vtd_bus->dev_as[devfn] = vtd_dev_as = g_malloc0(sizeof(VTDAddressSpace));
 
         vtd_dev_as->bus = bus;
@@ -3295,44 +3296,53 @@ VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus, int devfn)
         vtd_dev_as->context_cache_entry.context_cache_gen = 0;
         vtd_dev_as->iova_tree = iova_tree_new();
 
+        memory_region_init(&vtd_dev_as->root, OBJECT(s), name, UINT64_MAX);
+        address_space_init(&vtd_dev_as->as, &vtd_dev_as->root, "vtd-root");
+
         /*
-         * Memory region relationships looks like (Address range shows
-         * only lower 32 bits to make it short in length...):
-         *
-         * |-----------------+-------------------+----------|
-         * | Name            | Address range     | Priority |
-         * |-----------------+-------------------+----------+
-         * | vtd_root        | 00000000-ffffffff |        0 |
-         * |  intel_iommu    | 00000000-ffffffff |        1 |
-         * |  vtd_sys_alias  | 00000000-ffffffff |        1 |
-         * |  intel_iommu_ir | fee00000-feefffff |       64 |
-         * |-----------------+-------------------+----------|
+         * Build the DMAR-disabled container with aliases to the
+         * shared MRs.  Note that aliasing to a shared memory region
+         * could help the memory API to detect same FlatViews so we
+         * can have devices to share the same FlatView when DMAR is
+         * disabled (either by not providing "intel_iommu=on" or with
+         * "iommu=pt").  It will greatly reduce the total number of
+         * FlatViews of the system hence VM runs faster.
+         */
+        memory_region_init_alias(&vtd_dev_as->nodmar, OBJECT(s),
+                                 "vtd-nodmar", &s->mr_nodmar, 0,
+                                 memory_region_size(&s->mr_nodmar));
+
+        /*
+         * Build the per-device DMAR-enabled container.
          *
-         * We enable/disable DMAR by switching enablement for
-         * vtd_sys_alias and intel_iommu regions. IR region is always
-         * enabled.
+         * TODO: currently we have per-device IOMMU memory region only
+         * because we have per-device IOMMU notifiers for devices.  If
+         * one day we can abstract the IOMMU notifiers out of the
+         * memory regions then we can also share the same memory
+         * region here just like what we've done above with the nodmar
+         * region.
          */
+        strcat(name, "-dmar");
         memory_region_init_iommu(&vtd_dev_as->iommu, sizeof(vtd_dev_as->iommu),
                                  TYPE_INTEL_IOMMU_MEMORY_REGION, OBJECT(s),
-                                 "intel_iommu_dmar",
-                                 UINT64_MAX);
-        memory_region_init_alias(&vtd_dev_as->sys_alias, OBJECT(s),
-                                 "vtd_sys_alias", get_system_memory(),
-                                 0, memory_region_size(get_system_memory()));
-        memory_region_init_io(&vtd_dev_as->iommu_ir, OBJECT(s),
-                              &vtd_mem_ir_ops, s, "intel_iommu_ir",
-                              VTD_INTERRUPT_ADDR_SIZE);
-        memory_region_init(&vtd_dev_as->root, OBJECT(s),
-                           "vtd_root", UINT64_MAX);
-        memory_region_add_subregion_overlap(&vtd_dev_as->root,
+                                 name, UINT64_MAX);
+        memory_region_init_alias(&vtd_dev_as->iommu_ir, OBJECT(s), "vtd-ir",
+                                 &s->mr_ir, 0, memory_region_size(&s->mr_ir));
+        memory_region_add_subregion_overlap(MEMORY_REGION(&vtd_dev_as->iommu),
                                             VTD_INTERRUPT_ADDR_FIRST,
-                                            &vtd_dev_as->iommu_ir, 64);
-        address_space_init(&vtd_dev_as->as, &vtd_dev_as->root, name);
-        memory_region_add_subregion_overlap(&vtd_dev_as->root, 0,
-                                            &vtd_dev_as->sys_alias, 1);
+                                            &vtd_dev_as->iommu_ir, 1);
+
+        /*
+         * Hook both the containers under the root container, we
+         * switch between DMAR & noDMAR by enable/disable
+         * corresponding sub-containers
+         */
         memory_region_add_subregion_overlap(&vtd_dev_as->root, 0,
                                             MEMORY_REGION(&vtd_dev_as->iommu),
-                                            1);
+                                            0);
+        memory_region_add_subregion_overlap(&vtd_dev_as->root, 0,
+                                            &vtd_dev_as->nodmar, 0);
+
         vtd_switch_address_space(vtd_dev_as);
     }
     return vtd_dev_as;
@@ -3676,6 +3686,21 @@ static void vtd_realize(DeviceState *dev, Error **errp)
     memset(s->vtd_as_by_bus_num, 0, sizeof(s->vtd_as_by_bus_num));
     memory_region_init_io(&s->csrmem, OBJECT(s), &vtd_mem_ops, s,
                           "intel_iommu", DMAR_REG_SIZE);
+
+    /* Create the shared memory regions by all devices */
+    memory_region_init(&s->mr_nodmar, OBJECT(s), "vtd-nodmar",
+                       UINT64_MAX);
+    memory_region_init_io(&s->mr_ir, OBJECT(s), &vtd_mem_ir_ops,
+                          s, "vtd-ir", VTD_INTERRUPT_ADDR_SIZE);
+    memory_region_init_alias(&s->mr_sys_alias, OBJECT(s),
+                             "vtd-sys-alias", get_system_memory(), 0,
+                             memory_region_size(get_system_memory()));
+    memory_region_add_subregion_overlap(&s->mr_nodmar, 0,
+                                        &s->mr_sys_alias, 0);
+    memory_region_add_subregion_overlap(&s->mr_nodmar,
+                                        VTD_INTERRUPT_ADDR_FIRST,
+                                        &s->mr_ir, 1);
+
     sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->csrmem);
     /* No corresponding destroy */
     s->iotlb = g_hash_table_new_full(vtd_uint64_hash, vtd_uint64_equal,

diff --git a/include/hw/i386/intel_iommu.h b/include/hw/i386/intel_iommu.h
index c11e3d5b34b8fda0c01d3347abca688895df50ae..536f62667b29f927cd756fc5fcb84918186c6662 100644 (file)
--- a/include/hw/i386/intel_iommu.h
+++ b/include/hw/i386/intel_iommu.h
@@ -105,8 +105,8 @@ struct VTDAddressSpace {
     uint8_t devfn;
     AddressSpace as;
     IOMMUMemoryRegion iommu;
-    MemoryRegion root;
-    MemoryRegion sys_alias;
+    MemoryRegion root;          /* The root container of the device */
+    MemoryRegion nodmar;        /* The alias of shared nodmar MR */
     MemoryRegion iommu_ir;      /* Interrupt region: 0xfeeXXXXX */
     IntelIOMMUState *iommu_state;
     VTDContextCacheEntry context_cache_entry;
@@ -221,6 +221,9 @@ union VTD_IR_MSIAddress {
 struct IntelIOMMUState {
     X86IOMMUState x86_iommu;
     MemoryRegion csrmem;
+    MemoryRegion mr_nodmar;
+    MemoryRegion mr_ir;
+    MemoryRegion mr_sys_alias;
     uint8_t csr[DMAR_REG_SIZE];     /* register values */
     uint8_t wmask[DMAR_REG_SIZE];   /* R/W bytes */
     uint8_t w1cmask[DMAR_REG_SIZE]; /* RW1C(Write 1 to Clear) bytes */