pci, virtio, vhost: fixes

A bunch of fixes all over the place. Most notably this fixes
 the new MTU feature when using vhost.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJZK2bwAAoJECgfDbjSjVRpNBgIALmNG7VaixhNUlnfX1n1JBnh
 +HBP2zNfvi0q5roBuPFmlziKa3IBHb2Fcte4nb6QxmPg+uoaj39AOzfrrvz210kR
 h2j5Qk2bCdMeWBpxI+xDDScwi/Im23Y6KN1eZyMekFr2CaSGiqOHZPPdbsyEcHPB
 VylM0uHqSTZL5JAAzEuYlH+LLfPu91HoxMsIAdNuQX+qKyM2DZ4eICBQ0zA73USt
 OduZltcRMk7UpvQMqY+2iaEXapXQQEUGrP2Mo8ZyqeIl2ItC33GspqBQIKjuZdrr
 tpr/T1VWsLdZnURZXyELrFqrErDXvKaP9HROwvyLyYPXZF+pJ3LA7TopS5UmfNQ=
 =Z4xG
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'mst/tags/for_upstream' into staging

pci, virtio, vhost: fixes

A bunch of fixes all over the place. Most notably this fixes
the new MTU feature when using vhost.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Mon 29 May 2017 01:10:24 AM BST
# gpg:                using RSA key 0x281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* mst/tags/for_upstream:
  acpi-test: update expected files
  pc: ACPI BIOS: use highest NUMA node for hotplug mem hole SRAT entry
  vhost-user: pass message as a pointer to process_message_reply()
  virtio_net: Bypass backends for MTU feature negotiation
  intel_iommu: turn off pt before 2.9
  intel_iommu: support passthrough (PT)
  intel_iommu: allow dev-iotlb context entry conditionally
  intel_iommu: use IOMMU_ACCESS_FLAG()
  intel_iommu: provide vtd_ce_get_type()
  intel_iommu: renaming context entry helpers
  x86-iommu: use DeviceClass properties
  memory: remove the last param in memory_region_iommu_replay()
  memory: tune last param of iommu_ops.translate()

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

exec.c

@@ -486,7 +486,8 @@ static MemoryRegionSection address_space_do_translate(AddressSpace *as,
             break;
         }
 
-        iotlb = mr->iommu_ops->translate(mr, addr, is_write);
+        iotlb = mr->iommu_ops->translate(mr, addr, is_write ?
+                                         IOMMU_WO : IOMMU_RO);
         addr = ((iotlb.translated_addr & ~iotlb.addr_mask)
                 | (addr & iotlb.addr_mask));
         *plen = MIN(*plen, (addr | iotlb.addr_mask) - addr + 1);

hw/alpha/typhoon.c

@@ -664,7 +664,7 @@ static bool window_translate(TyphoonWindow *win, hwaddr addr,
 /* TODO: A translation failure here ought to set PCI error codes on the
    Pchip and generate a machine check interrupt.  */
 static IOMMUTLBEntry typhoon_translate_iommu(MemoryRegion *iommu, hwaddr addr,
-                                             bool is_write)
+                                             IOMMUAccessFlags flag)
 {
     TyphoonPchip *pchip = container_of(iommu, TyphoonPchip, iommu);
     IOMMUTLBEntry ret;

hw/dma/rc4030.c

@@ -489,7 +489,7 @@ static const MemoryRegionOps jazzio_ops = {
 };
 
 static IOMMUTLBEntry rc4030_dma_translate(MemoryRegion *iommu, hwaddr addr,
-                                          bool is_write)
+                                          IOMMUAccessFlags flag)
 {
     rc4030State *s = container_of(iommu, rc4030State, dma_mr);
     IOMMUTLBEntry ret = {

hw/i386/acpi-build.c

@@ -2404,14 +2404,17 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
     }
 
     /*
-     * Entry is required for Windows to enable memory hotplug in OS.
+     * Entry is required for Windows to enable memory hotplug in OS
+     * and for Linux to enable SWIOTLB when booted with less than
+     * 4G of RAM. Windows works better if the entry sets proximity
+     * to the highest NUMA node in the machine.
      * Memory devices may override proximity set by this entry,
      * providing _PXM method if necessary.
      */
     if (hotplugabble_address_space_size) {
         numamem = acpi_data_push(table_data, sizeof *numamem);
         build_srat_memory(numamem, pcms->hotplug_memory.base,
-                          hotplugabble_address_space_size, 0,
+                          hotplugabble_address_space_size, pcms->numa_nodes - 1,
                           MEM_AFFINITY_HOTPLUGGABLE | MEM_AFFINITY_ENABLED);
     }
 

hw/i386/amd_iommu.c

@@ -988,7 +988,7 @@ static inline bool amdvi_is_interrupt_addr(hwaddr addr)
 }
 
 static IOMMUTLBEntry amdvi_translate(MemoryRegion *iommu, hwaddr addr,
-                                     bool is_write)
+                                     IOMMUAccessFlags flag)
 {
     AMDVIAddressSpace *as = container_of(iommu, AMDVIAddressSpace, iommu);
     AMDVIState *s = as->iommu_state;
@@ -1017,7 +1017,7 @@ static IOMMUTLBEntry amdvi_translate(MemoryRegion *iommu, hwaddr addr,
         return ret;
     }
 
-    amdvi_do_translate(as, addr, is_write, &ret);
+    amdvi_do_translate(as, addr, flag & IOMMU_WO, &ret);
     trace_amdvi_translation_result(as->bus_num, PCI_SLOT(as->devfn),
             PCI_FUNC(as->devfn), addr, ret.translated_addr);
     return ret;

hw/i386/intel_iommu.c

@@ -512,7 +512,7 @@ static int vtd_get_root_entry(IntelIOMMUState *s, uint8_t index,
     return 0;
 }
 
-static inline bool vtd_context_entry_present(VTDContextEntry *context)
+static inline bool vtd_ce_present(VTDContextEntry *context)
 {
     return context->lo & VTD_CONTEXT_ENTRY_P;
 }
@@ -533,7 +533,7 @@ static int vtd_get_context_entry_from_root(VTDRootEntry *root, uint8_t index,
     return 0;
 }
 
-static inline dma_addr_t vtd_get_slpt_base_from_context(VTDContextEntry *ce)
+static inline dma_addr_t vtd_ce_get_slpt_base(VTDContextEntry *ce)
 {
     return ce->lo & VTD_CONTEXT_ENTRY_SLPTPTR;
 }
@@ -585,19 +585,49 @@ static inline bool vtd_is_level_supported(IntelIOMMUState *s, uint32_t level)
 /* Get the page-table level that hardware should use for the second-level
  * page-table walk from the Address Width field of context-entry.
  */
-static inline uint32_t vtd_get_level_from_context_entry(VTDContextEntry *ce)
+static inline uint32_t vtd_ce_get_level(VTDContextEntry *ce)
 {
     return 2 + (ce->hi & VTD_CONTEXT_ENTRY_AW);
 }
 
-static inline uint32_t vtd_get_agaw_from_context_entry(VTDContextEntry *ce)
+static inline uint32_t vtd_ce_get_agaw(VTDContextEntry *ce)
 {
     return 30 + (ce->hi & VTD_CONTEXT_ENTRY_AW) * 9;
 }
 
+static inline uint32_t vtd_ce_get_type(VTDContextEntry *ce)
+{
+    return ce->lo & VTD_CONTEXT_ENTRY_TT;
+}
+
+/* Return true if check passed, otherwise false */
+static inline bool vtd_ce_type_check(X86IOMMUState *x86_iommu,
+                                     VTDContextEntry *ce)
+{
+    switch (vtd_ce_get_type(ce)) {
+    case VTD_CONTEXT_TT_MULTI_LEVEL:
+        /* Always supported */
+        break;
+    case VTD_CONTEXT_TT_DEV_IOTLB:
+        if (!x86_iommu->dt_supported) {
+            return false;
+        }
+        break;
+    case VTD_CONTEXT_TT_PASS_THROUGH:
+        if (!x86_iommu->pt_supported) {
+            return false;
+        }
+        break;
+    default:
+        /* Unknwon type */
+        return false;
+    }
+    return true;
+}
+
 static inline uint64_t vtd_iova_limit(VTDContextEntry *ce)
 {
-    uint32_t ce_agaw = vtd_get_agaw_from_context_entry(ce);
+    uint32_t ce_agaw = vtd_ce_get_agaw(ce);
     return 1ULL << MIN(ce_agaw, VTD_MGAW);
 }
 
@@ -635,6 +665,29 @@ static bool vtd_slpte_nonzero_rsvd(uint64_t slpte, uint32_t level)
     }
 }
 
+/* Find the VTD address space associated with a given bus number */
+static VTDBus *vtd_find_as_from_bus_num(IntelIOMMUState *s, uint8_t bus_num)
+{
+    VTDBus *vtd_bus = s->vtd_as_by_bus_num[bus_num];
+    if (!vtd_bus) {
+        /*
+         * Iterate over the registered buses to find the one which
+         * currently hold this bus number, and update the bus_num
+         * lookup table:
+         */
+        GHashTableIter iter;
+
+        g_hash_table_iter_init(&iter, s->vtd_as_by_busptr);
+        while (g_hash_table_iter_next(&iter, NULL, (void **)&vtd_bus)) {
+            if (pci_bus_num(vtd_bus->bus) == bus_num) {
+                s->vtd_as_by_bus_num[bus_num] = vtd_bus;
+                return vtd_bus;
+            }
+        }
+    }
+    return vtd_bus;
+}
+
 /* Given the @iova, get relevant @slptep. @slpte_level will be the last level
  * of the translation, can be used for deciding the size of large page.
  */
@@ -642,8 +695,8 @@ static int vtd_iova_to_slpte(VTDContextEntry *ce, uint64_t iova, bool is_write,
                              uint64_t *slptep, uint32_t *slpte_level,
                              bool *reads, bool *writes)
 {
-    dma_addr_t addr = vtd_get_slpt_base_from_context(ce);
+    dma_addr_t addr = vtd_ce_get_slpt_base(ce);
-    uint32_t level = vtd_get_level_from_context_entry(ce);
+    uint32_t level = vtd_ce_get_level(ce);
     uint32_t offset;
     uint64_t slpte;
     uint64_t access_right_check;
@@ -664,7 +717,7 @@ static int vtd_iova_to_slpte(VTDContextEntry *ce, uint64_t iova, bool is_write,
             VTD_DPRINTF(GENERAL, "error: fail to access second-level paging "
                         "entry at level %"PRIu32 " for iova 0x%"PRIx64,
                         level, iova);
-            if (level == vtd_get_level_from_context_entry(ce)) {
+            if (level == vtd_ce_get_level(ce)) {
                 /* Invalid programming of context-entry */
                 return -VTD_FR_CONTEXT_ENTRY_INV;
             } else {
@@ -809,8 +862,8 @@ static int vtd_page_walk(VTDContextEntry *ce, uint64_t start, uint64_t end,
                          vtd_page_walk_hook hook_fn, void *private,
                          bool notify_unmap)
 {
-    dma_addr_t addr = vtd_get_slpt_base_from_context(ce);
+    dma_addr_t addr = vtd_ce_get_slpt_base(ce);
-    uint32_t level = vtd_get_level_from_context_entry(ce);
+    uint32_t level = vtd_ce_get_level(ce);
 
     if (!vtd_iova_range_check(start, ce)) {
         return -VTD_FR_ADDR_BEYOND_MGAW;
@@ -831,6 +884,7 @@ static int vtd_dev_to_context_entry(IntelIOMMUState *s, uint8_t bus_num,
 {
     VTDRootEntry re;
     int ret_fr;
+    X86IOMMUState *x86_iommu = X86_IOMMU_DEVICE(s);
 
     ret_fr = vtd_get_root_entry(s, bus_num, &re);
     if (ret_fr) {
@@ -841,7 +895,9 @@ static int vtd_dev_to_context_entry(IntelIOMMUState *s, uint8_t bus_num,
         /* Not error - it's okay we don't have root entry. */
         trace_vtd_re_not_present(bus_num);
         return -VTD_FR_ROOT_ENTRY_P;
-    } else if (re.rsvd || (re.val & VTD_ROOT_ENTRY_RSVD)) {
+    }
+
+    if (re.rsvd || (re.val & VTD_ROOT_ENTRY_RSVD)) {
         trace_vtd_re_invalid(re.rsvd, re.val);
         return -VTD_FR_ROOT_ENTRY_RSVD;
     }
@@ -851,31 +907,116 @@ static int vtd_dev_to_context_entry(IntelIOMMUState *s, uint8_t bus_num,
         return ret_fr;
     }
 
-    if (!vtd_context_entry_present(ce)) {
+    if (!vtd_ce_present(ce)) {
         /* Not error - it's okay we don't have context entry. */
         trace_vtd_ce_not_present(bus_num, devfn);
         return -VTD_FR_CONTEXT_ENTRY_P;
-    } else if ((ce->hi & VTD_CONTEXT_ENTRY_RSVD_HI) ||
+    }
-               (ce->lo & VTD_CONTEXT_ENTRY_RSVD_LO)) {
+
+    if ((ce->hi & VTD_CONTEXT_ENTRY_RSVD_HI) ||
+        (ce->lo & VTD_CONTEXT_ENTRY_RSVD_LO)) {
         trace_vtd_ce_invalid(ce->hi, ce->lo);
         return -VTD_FR_CONTEXT_ENTRY_RSVD;
     }
+
     /* Check if the programming of context-entry is valid */
-    if (!vtd_is_level_supported(s, vtd_get_level_from_context_entry(ce))) {
+    if (!vtd_is_level_supported(s, vtd_ce_get_level(ce))) {
         trace_vtd_ce_invalid(ce->hi, ce->lo);
         return -VTD_FR_CONTEXT_ENTRY_INV;
+    }
+
+    /* Do translation type check */
+    if (!vtd_ce_type_check(x86_iommu, ce)) {
+        trace_vtd_ce_invalid(ce->hi, ce->lo);
+        return -VTD_FR_CONTEXT_ENTRY_INV;
+    }
+
+    return 0;
+}
+
+/*
+ * Fetch translation type for specific device. Returns <0 if error
+ * happens, otherwise return the shifted type to check against
+ * VTD_CONTEXT_TT_*.
+ */
+static int vtd_dev_get_trans_type(VTDAddressSpace *as)
+{
+    IntelIOMMUState *s;
+    VTDContextEntry ce;
+    int ret;
+
+    s = as->iommu_state;
+
+    ret = vtd_dev_to_context_entry(s, pci_bus_num(as->bus),
+                                   as->devfn, &ce);
+    if (ret) {
+        return ret;
+    }
+
+    return vtd_ce_get_type(&ce);
+}
+
+static bool vtd_dev_pt_enabled(VTDAddressSpace *as)
+{
+    int ret;
+
+    assert(as);
+
+    ret = vtd_dev_get_trans_type(as);
+    if (ret < 0) {
+        /*
+         * Possibly failed to parse the context entry for some reason
+         * (e.g., during init, or any guest configuration errors on
+         * context entries). We should assume PT not enabled for
+         * safety.
+         */
+        return false;
+    }
+
+    return ret == VTD_CONTEXT_TT_PASS_THROUGH;
+}
+
+/* Return whether the device is using IOMMU translation. */
+static bool vtd_switch_address_space(VTDAddressSpace *as)
+{
+    bool use_iommu;
+
+    assert(as);
+
+    use_iommu = as->iommu_state->dmar_enabled & !vtd_dev_pt_enabled(as);
+
+    trace_vtd_switch_address_space(pci_bus_num(as->bus),
+                                   VTD_PCI_SLOT(as->devfn),
+                                   VTD_PCI_FUNC(as->devfn),
+                                   use_iommu);
+
+    /* Turn off first then on the other */
+    if (use_iommu) {
+        memory_region_set_enabled(&as->sys_alias, false);
+        memory_region_set_enabled(&as->iommu, true);
     } else {
-        switch (ce->lo & VTD_CONTEXT_ENTRY_TT) {
+        memory_region_set_enabled(&as->iommu, false);
-        case VTD_CONTEXT_TT_MULTI_LEVEL:
+        memory_region_set_enabled(&as->sys_alias, true);
-            /* fall through */
+    }
-        case VTD_CONTEXT_TT_DEV_IOTLB:
+
-            break;
+    return use_iommu;
-        default:
+}
-            trace_vtd_ce_invalid(ce->hi, ce->lo);
+
-            return -VTD_FR_CONTEXT_ENTRY_INV;
+static void vtd_switch_address_space_all(IntelIOMMUState *s)
+{
+    GHashTableIter iter;
+    VTDBus *vtd_bus;
+    int i;
+
+    g_hash_table_iter_init(&iter, s->vtd_as_by_busptr);
+    while (g_hash_table_iter_next(&iter, NULL, (void **)&vtd_bus)) {
+        for (i = 0; i < X86_IOMMU_PCI_DEVFN_MAX; i++) {
+            if (!vtd_bus->dev_as[i]) {
+                continue;
+            }
+            vtd_switch_address_space(vtd_bus->dev_as[i]);
         }
     }
-    return 0;
 }
 
 static inline uint16_t vtd_make_source_id(uint8_t bus_num, uint8_t devfn)
@@ -915,6 +1056,31 @@ static inline bool vtd_is_interrupt_addr(hwaddr addr)
     return VTD_INTERRUPT_ADDR_FIRST <= addr && addr <= VTD_INTERRUPT_ADDR_LAST;
 }
 
+static void vtd_pt_enable_fast_path(IntelIOMMUState *s, uint16_t source_id)
+{
+    VTDBus *vtd_bus;
+    VTDAddressSpace *vtd_as;
+    bool success = false;
+
+    vtd_bus = vtd_find_as_from_bus_num(s, VTD_SID_TO_BUS(source_id));
+    if (!vtd_bus) {
+        goto out;
+    }
+
+    vtd_as = vtd_bus->dev_as[VTD_SID_TO_DEVFN(source_id)];
+    if (!vtd_as) {
+        goto out;
+    }
+
+    if (vtd_switch_address_space(vtd_as) == false) {
+        /* We switched off IOMMU region successfully. */
+        success = true;
+    }
+
+out:
+    trace_vtd_pt_enable_fast_path(source_id, success);
+}
+
 /* Map dev to context-entry then do a paging-structures walk to do a iommu
  * translation.
  *
@@ -986,6 +1152,30 @@ static void vtd_do_iommu_translate(VTDAddressSpace *vtd_as, PCIBus *bus,
         cc_entry->context_cache_gen = s->context_cache_gen;
     }
 
+    /*
+     * We don't need to translate for pass-through context entries.
+     * Also, let's ignore IOTLB caching as well for PT devices.
+     */
+    if (vtd_ce_get_type(&ce) == VTD_CONTEXT_TT_PASS_THROUGH) {
+        entry->translated_addr = entry->iova;
+        entry->addr_mask = VTD_PAGE_SIZE - 1;
+        entry->perm = IOMMU_RW;
+        trace_vtd_translate_pt(source_id, entry->iova);
+
+        /*
+         * When this happens, it means firstly caching-mode is not
+         * enabled, and this is the first passthrough translation for
+         * the device. Let's enable the fast path for passthrough.
+         *
+         * When passthrough is disabled again for the device, we can
+         * capture it via the context entry invalidation, then the
+         * IOMMU region can be swapped back.
+         */
+        vtd_pt_enable_fast_path(s, source_id);
+
+        return;
+    }
+
     ret_fr = vtd_iova_to_slpte(&ce, addr, is_write, &slpte, &level,
                                &reads, &writes);
     if (ret_fr) {
@@ -1005,7 +1195,7 @@ out:
     entry->iova = addr & page_mask;
     entry->translated_addr = vtd_get_slpte_addr(slpte) & page_mask;
     entry->addr_mask = ~page_mask;
-    entry->perm = (writes ? 2 : 0) + (reads ? 1 : 0);
+    entry->perm = IOMMU_ACCESS_FLAG(reads, writes);
 }
 
 static void vtd_root_table_setup(IntelIOMMUState *s)
@@ -1055,6 +1245,7 @@ static void vtd_context_global_invalidate(IntelIOMMUState *s)
     if (s->context_cache_gen == VTD_CONTEXT_CACHE_GEN_MAX) {
         vtd_reset_context_cache(s);
     }
+    vtd_switch_address_space_all(s);
     /*
      * From VT-d spec 6.5.2.1, a global context entry invalidation
      * should be followed by a IOTLB global invalidation, so we should
@@ -1065,29 +1256,6 @@ static void vtd_context_global_invalidate(IntelIOMMUState *s)
     vtd_iommu_replay_all(s);
 }
 
-
-/* Find the VTD address space currently associated with a given bus number,
- */
-static VTDBus *vtd_find_as_from_bus_num(IntelIOMMUState *s, uint8_t bus_num)
-{
-    VTDBus *vtd_bus = s->vtd_as_by_bus_num[bus_num];
-    if (!vtd_bus) {
-        /* Iterate over the registered buses to find the one
-         * which currently hold this bus number, and update the bus_num lookup table:
-         */
-        GHashTableIter iter;
-
-        g_hash_table_iter_init(&iter, s->vtd_as_by_busptr);
-        while (g_hash_table_iter_next (&iter, NULL, (void**)&vtd_bus)) {
-            if (pci_bus_num(vtd_bus->bus) == bus_num) {
-                s->vtd_as_by_bus_num[bus_num] = vtd_bus;
-                return vtd_bus;
-            }
-        }
-    }
-    return vtd_bus;
-}
-
 /* Do a context-cache device-selective invalidation.
  * @func_mask: FM field after shifting
  */
@@ -1129,6 +1297,11 @@ static void vtd_context_device_invalidate(IntelIOMMUState *s,
                 trace_vtd_inv_desc_cc_device(bus_n, VTD_PCI_SLOT(devfn_it),
                                              VTD_PCI_FUNC(devfn_it));
                 vtd_as->context_cache_entry.context_cache_gen = 0;
+                /*
+                 * Do switch address space when needed, in case if the
+                 * device passthrough bit is switched.
+                 */
+                vtd_switch_address_space(vtd_as);
                 /*
                  * So a device is moving out of (or moving into) a
                  * domain, a replay() suites here to notify all the
@@ -1361,42 +1534,6 @@ static void vtd_handle_gcmd_sirtp(IntelIOMMUState *s)
     vtd_set_clear_mask_long(s, DMAR_GSTS_REG, 0, VTD_GSTS_IRTPS);
 }
 
-static void vtd_switch_address_space(VTDAddressSpace *as)
-{
-    assert(as);
-
-    trace_vtd_switch_address_space(pci_bus_num(as->bus),
-                                   VTD_PCI_SLOT(as->devfn),
-                                   VTD_PCI_FUNC(as->devfn),
-                                   as->iommu_state->dmar_enabled);
-
-    /* Turn off first then on the other */
-    if (as->iommu_state->dmar_enabled) {
-        memory_region_set_enabled(&as->sys_alias, false);
-        memory_region_set_enabled(&as->iommu, true);
-    } else {
-        memory_region_set_enabled(&as->iommu, false);
-        memory_region_set_enabled(&as->sys_alias, true);
-    }
-}
-
-static void vtd_switch_address_space_all(IntelIOMMUState *s)
-{
-    GHashTableIter iter;
-    VTDBus *vtd_bus;
-    int i;
-
-    g_hash_table_iter_init(&iter, s->vtd_as_by_busptr);
-    while (g_hash_table_iter_next(&iter, NULL, (void **)&vtd_bus)) {
-        for (i = 0; i < X86_IOMMU_PCI_DEVFN_MAX; i++) {
-            if (!vtd_bus->dev_as[i]) {
-                continue;
-            }
-            vtd_switch_address_space(vtd_bus->dev_as[i]);
-        }
-    }
-}
-
 /* Handle Translation Enable/Disable */
 static void vtd_handle_gcmd_te(IntelIOMMUState *s, bool en)
 {
@@ -2221,7 +2358,7 @@ static void vtd_mem_write(void *opaque, hwaddr addr,
 }
 
 static IOMMUTLBEntry vtd_iommu_translate(MemoryRegion *iommu, hwaddr addr,
-                                         bool is_write)
+                                         IOMMUAccessFlags flag)
 {
     VTDAddressSpace *vtd_as = container_of(iommu, VTDAddressSpace, iommu);
     IntelIOMMUState *s = vtd_as->iommu_state;
@@ -2243,7 +2380,7 @@ static IOMMUTLBEntry vtd_iommu_translate(MemoryRegion *iommu, hwaddr addr,
     }
 
     vtd_do_iommu_translate(vtd_as, vtd_as->bus, vtd_as->devfn, addr,
-                           is_write, &ret);
+                           flag & IOMMU_WO, &ret);
     VTD_DPRINTF(MMU,
                 "bus %"PRIu8 " slot %"PRIu8 " func %"PRIu8 " devfn %"PRIu8
                 " iova 0x%"PRIx64 " hpa 0x%"PRIx64, pci_bus_num(vtd_as->bus),
@@ -2844,6 +2981,10 @@ static void vtd_init(IntelIOMMUState *s)
         s->ecap |= VTD_ECAP_DT;
     }
 
+    if (x86_iommu->pt_supported) {
+        s->ecap |= VTD_ECAP_PT;
+    }
+
     if (s->caching_mode) {
         s->cap |= VTD_CAP_CM;
     }

hw/i386/intel_iommu_internal.h

@@ -187,6 +187,7 @@
 /* Interrupt Remapping support */
 #define VTD_ECAP_IR                 (1ULL << 3)
 #define VTD_ECAP_EIM                (1ULL << 4)
+#define VTD_ECAP_PT                 (1ULL << 6)
 #define VTD_ECAP_MHMV               (15ULL << 20)
 
 /* CAP_REG */

hw/i386/trace-events

@@ -38,6 +38,8 @@ vtd_page_walk_skip_perm(uint64_t iova, uint64_t next) "Page walk skip iova 0x%"P
 vtd_page_walk_skip_reserve(uint64_t iova, uint64_t next) "Page walk skip iova 0x%"PRIx64" - 0x%"PRIx64" due to rsrv set"
 vtd_switch_address_space(uint8_t bus, uint8_t slot, uint8_t fn, bool on) "Device %02x:%02x.%x switching address space (iommu enabled=%d)"
 vtd_as_unmap_whole(uint8_t bus, uint8_t slot, uint8_t fn, uint64_t iova, uint64_t size) "Device %02x:%02x.%x start 0x%"PRIx64" size 0x%"PRIx64
+vtd_translate_pt(uint16_t sid, uint64_t addr) "source id 0x%"PRIu16", iova 0x%"PRIx64
+vtd_pt_enable_fast_path(uint16_t sid, bool success) "sid 0x%"PRIu16" %d"
 
 # hw/i386/amd_iommu.c
 amdvi_evntlog_fail(uint64_t addr, uint32_t head) "error: fail to write at addr 0x%"PRIx64" +  offset 0x%"PRIx32

hw/i386/x86-iommu.c

@@ -88,55 +88,23 @@ static void x86_iommu_realize(DeviceState *dev, Error **errp)
     x86_iommu_set_default(X86_IOMMU_DEVICE(dev));
 }
 
+static Property x86_iommu_properties[] = {
+    DEFINE_PROP_BOOL("intremap", X86IOMMUState, intr_supported, false),
+    DEFINE_PROP_BOOL("device-iotlb", X86IOMMUState, dt_supported, false),
+    DEFINE_PROP_BOOL("pt", X86IOMMUState, pt_supported, true),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
 static void x86_iommu_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     dc->realize = x86_iommu_realize;
-}
+    dc->props = x86_iommu_properties;
-
-static bool x86_iommu_intremap_prop_get(Object *o, Error **errp)
-{
-    X86IOMMUState *s = X86_IOMMU_DEVICE(o);
-    return s->intr_supported;
-}
-
-static void x86_iommu_intremap_prop_set(Object *o, bool value, Error **errp)
-{
-    X86IOMMUState *s = X86_IOMMU_DEVICE(o);
-    s->intr_supported = value;
-}
-
-static bool x86_iommu_device_iotlb_prop_get(Object *o, Error **errp)
-{
-    X86IOMMUState *s = X86_IOMMU_DEVICE(o);
-    return s->dt_supported;
-}
-
-static void x86_iommu_device_iotlb_prop_set(Object *o, bool value, Error **errp)
-{
-    X86IOMMUState *s = X86_IOMMU_DEVICE(o);
-    s->dt_supported = value;
-}
-
-static void x86_iommu_instance_init(Object *o)
-{
-    X86IOMMUState *s = X86_IOMMU_DEVICE(o);
-
-    /* By default, do not support IR */
-    s->intr_supported = false;
-    object_property_add_bool(o, "intremap", x86_iommu_intremap_prop_get,
-                             x86_iommu_intremap_prop_set, NULL);
-    s->dt_supported = false;
-    object_property_add_bool(o, "device-iotlb",
-                             x86_iommu_device_iotlb_prop_get,
-                             x86_iommu_device_iotlb_prop_set,
-                             NULL);
 }
 
 static const TypeInfo x86_iommu_info = {
     .name          = TYPE_X86_IOMMU_DEVICE,
     .parent        = TYPE_SYS_BUS_DEVICE,
-    .instance_init = x86_iommu_instance_init,
     .instance_size = sizeof(X86IOMMUState),
     .class_init    = x86_iommu_class_init,
     .class_size    = sizeof(X86IOMMUClass),

hw/net/virtio-net.c

@@ -589,7 +589,15 @@ static uint64_t virtio_net_get_features(VirtIODevice *vdev, uint64_t features,
     if (!get_vhost_net(nc->peer)) {
         return features;
     }
-    return vhost_net_get_features(get_vhost_net(nc->peer), features);
+    features = vhost_net_get_features(get_vhost_net(nc->peer), features);
+    vdev->backend_features = features;
+
+    if (n->mtu_bypass_backend &&
+            (n->host_features & 1ULL << VIRTIO_NET_F_MTU)) {
+        features |= (1ULL << VIRTIO_NET_F_MTU);
+    }
+
+    return features;
 }
 
 static uint64_t virtio_net_bad_features(VirtIODevice *vdev)
@@ -640,6 +648,11 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features)
     VirtIONet *n = VIRTIO_NET(vdev);
     int i;
 
+    if (n->mtu_bypass_backend &&
+            !virtio_has_feature(vdev->backend_features, VIRTIO_NET_F_MTU)) {
+        features &= ~(1ULL << VIRTIO_NET_F_MTU);
+    }
+
     virtio_net_set_multiqueue(n,
                               virtio_has_feature(features, VIRTIO_NET_F_MQ));
 
@@ -2093,6 +2106,8 @@ static Property virtio_net_properties[] = {
     DEFINE_PROP_UINT16("rx_queue_size", VirtIONet, net_conf.rx_queue_size,
                        VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE),
     DEFINE_PROP_UINT16("host_mtu", VirtIONet, net_conf.mtu, 0),
+    DEFINE_PROP_BOOL("x-mtu-bypass-backend", VirtIONet, mtu_bypass_backend,
+                     true),
     DEFINE_PROP_END_OF_LIST(),
 };
 

hw/pci-host/apb.c

@@ -209,7 +209,7 @@ static AddressSpace *pbm_pci_dma_iommu(PCIBus *bus, void *opaque, int devfn)
 
 /* Called from RCU critical section */
 static IOMMUTLBEntry pbm_translate_iommu(MemoryRegion *iommu, hwaddr addr,
-                                         bool is_write)
+                                         IOMMUAccessFlags flag)
 {
     IOMMUState *is = container_of(iommu, IOMMUState, iommu);
     hwaddr baseaddr, offset;

hw/ppc/spapr_iommu.c

@@ -111,7 +111,7 @@ static void spapr_tce_free_table(uint64_t *table, int fd, uint32_t nb_table)
 
 /* Called from RCU critical section */
 static IOMMUTLBEntry spapr_tce_translate_iommu(MemoryRegion *iommu, hwaddr addr,
-                                               bool is_write)
+                                               IOMMUAccessFlags flag)
 {
     sPAPRTCETable *tcet = container_of(iommu, sPAPRTCETable, iommu);
     uint64_t tce;

hw/s390x/s390-pci-bus.c

@@ -357,7 +357,7 @@ out:
 }
 
 static IOMMUTLBEntry s390_translate_iommu(MemoryRegion *mr, hwaddr addr,
-                                          bool is_write)
+                                          IOMMUAccessFlags flag)
 {
     uint64_t pte;
     uint32_t flags;

hw/s390x/s390-pci-inst.c

@@ -624,7 +624,7 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2)
 
     mr = &iommu->iommu_mr;
     while (start < end) {
-        entry = mr->iommu_ops->translate(mr, start, 0);
+        entry = mr->iommu_ops->translate(mr, start, IOMMU_NONE);
 
         if (!entry.translated_addr) {
             pbdev->state = ZPCI_FS_ERROR;

hw/vfio/common.c

@@ -502,7 +502,7 @@ static void vfio_listener_region_add(MemoryListener *listener,
         QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next);
 
         memory_region_register_iommu_notifier(giommu->iommu, &giommu->n);
-        memory_region_iommu_replay(giommu->iommu, &giommu->n, false);
+        memory_region_iommu_replay(giommu->iommu, &giommu->n);
 
         return;
     }

hw/virtio/vhost-user.c

@@ -162,11 +162,11 @@ fail:
 }
 
 static int process_message_reply(struct vhost_dev *dev,
-                                 VhostUserMsg msg)
+                                 const VhostUserMsg *msg)
 {
     VhostUserMsg msg_reply;
 
-    if ((msg.flags & VHOST_USER_NEED_REPLY_MASK) == 0) {
+    if ((msg->flags & VHOST_USER_NEED_REPLY_MASK) == 0) {
         return 0;
     }
 
@@ -174,10 +174,10 @@ static int process_message_reply(struct vhost_dev *dev,
         return -1;
     }
 
-    if (msg_reply.request != msg.request) {
+    if (msg_reply.request != msg->request) {
         error_report("Received unexpected msg type."
                      "Expected %d received %d",
-                     msg.request, msg_reply.request);
+                     msg->request, msg_reply.request);
         return -1;
     }
 
@@ -324,7 +324,7 @@ static int vhost_user_set_mem_table(struct vhost_dev *dev,
     }
 
     if (reply_supported) {
-        return process_message_reply(dev, msg);
+        return process_message_reply(dev, &msg);
     }
 
     return 0;
@@ -716,7 +716,7 @@ static int vhost_user_net_set_mtu(struct vhost_dev *dev, uint16_t mtu)
 
     /* If reply_ack supported, slave has to ack specified MTU is valid */
     if (reply_supported) {
-        return process_message_reply(dev, msg);
+        return process_message_reply(dev, &msg);
     }
 
     return 0;

include/exec/memory.h

@@ -185,8 +185,14 @@ struct MemoryRegionOps {
 typedef struct MemoryRegionIOMMUOps MemoryRegionIOMMUOps;
 
 struct MemoryRegionIOMMUOps {
-    /* Return a TLB entry that contains a given address. */
+    /*
-    IOMMUTLBEntry (*translate)(MemoryRegion *iommu, hwaddr addr, bool is_write);
+     * Return a TLB entry that contains a given address. Flag should
+     * be the access permission of this translation operation. We can
+     * set flag to IOMMU_NONE to mean that we don't need any
+     * read/write permission checks, like, when for region replay.
+     */
+    IOMMUTLBEntry (*translate)(MemoryRegion *iommu, hwaddr addr,
+                               IOMMUAccessFlags flag);
     /* Returns minimum supported page size */
     uint64_t (*get_min_page_size)(MemoryRegion *iommu);
     /* Called when IOMMU Notifier flag changed */
@@ -725,11 +731,8 @@ void memory_region_register_iommu_notifier(MemoryRegion *mr,
  *
  * @mr: the memory region to observe
  * @n: the notifier to which to replay iommu mappings
- * @is_write: Whether to treat the replay as a translate "write"
- *     through the iommu
  */
-void memory_region_iommu_replay(MemoryRegion *mr, IOMMUNotifier *n,
+void memory_region_iommu_replay(MemoryRegion *mr, IOMMUNotifier *n);
-                                bool is_write);
 
 /**
  * memory_region_iommu_replay_all: replay existing IOMMU translations

include/hw/compat.h

@@ -6,6 +6,14 @@
         .driver   = "pci-bridge",\
         .property = "shpc",\
         .value    = "off",\
+    },{\
+        .driver   = "intel-iommu",\
+        .property = "pt",\
+        .value    = "off",\
+    },{\
+        .driver   = "virtio-net-device",\
+        .property = "x-mtu-bypass-backend",\
+        .value    = "off",\
     },
 
 #define HW_COMPAT_2_8 \

include/hw/i386/x86-iommu.h

@@ -74,6 +74,7 @@ struct X86IOMMUState {
     SysBusDevice busdev;
     bool intr_supported;        /* Whether vIOMMU supports IR */
     bool dt_supported;          /* Whether vIOMMU supports DT */
+    bool pt_supported;          /* Whether vIOMMU supports pass-through */
     IommuType type;             /* IOMMU type - AMD/Intel     */
     QLIST_HEAD(, IEC_Notifier) iec_notifiers; /* IEC notify list */
 };

include/hw/virtio/virtio-net.h

@@ -97,6 +97,7 @@ typedef struct VirtIONet {
     QEMUTimer *announce_timer;
     int announce_counter;
     bool needs_vnet_hdr_swap;
+    bool mtu_bypass_backend;
 } VirtIONet;
 
 void virtio_net_set_netclient_name(VirtIONet *n, const char *name,

include/hw/virtio/virtio.h

@@ -79,6 +79,7 @@ struct VirtIODevice
     uint16_t queue_sel;
     uint64_t guest_features;
     uint64_t host_features;
+    uint64_t backend_features;
     size_t config_len;
     void *config;
     uint16_t config_vector;

memory.c

@@ -1620,8 +1620,7 @@ uint64_t memory_region_iommu_get_min_page_size(MemoryRegion *mr)
     return TARGET_PAGE_SIZE;
 }
 
-void memory_region_iommu_replay(MemoryRegion *mr, IOMMUNotifier *n,
+void memory_region_iommu_replay(MemoryRegion *mr, IOMMUNotifier *n)
-                                bool is_write)
 {
     hwaddr addr, granularity;
     IOMMUTLBEntry iotlb;
@@ -1635,7 +1634,7 @@ void memory_region_iommu_replay(MemoryRegion *mr, IOMMUNotifier *n,
     granularity = memory_region_iommu_get_min_page_size(mr);
 
     for (addr = 0; addr < memory_region_size(mr); addr += granularity) {
-        iotlb = mr->iommu_ops->translate(mr, addr, is_write);
+        iotlb = mr->iommu_ops->translate(mr, addr, IOMMU_NONE);
         if (iotlb.perm != IOMMU_NONE) {
             n->notify(n, &iotlb);
         }
@@ -1653,7 +1652,7 @@ void memory_region_iommu_replay_all(MemoryRegion *mr)
     IOMMUNotifier *notifier;
 
     IOMMU_NOTIFIER_FOREACH(notifier, mr) {
-        memory_region_iommu_replay(mr, notifier, false);
+        memory_region_iommu_replay(mr, notifier);
     }
 }