pc, acpi, virtio: fixes, test speedup for rc1

Some fixes all over the place. Notably vhost-user gained a new message
 to set endian-ness. Borderline for 2.10 but seems to be the only way to
 fix legacy guests.  Also pc tests are run on kvm now. Not a fix at all
 but doesn't touch qemu itself, so I merged it since I had to run these a
 lot and I just got tired of waiting for these to finish.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJZgPRvAAoJECgfDbjSjVRpUKAH/RE1PohaH/klzEVFLPZUdISN
 /1zOdFN0BgVOUxS2udLVdZBUrWBiJWt11fbzASeGtOu3ruTpVfp69C7HUH8z4MOB
 cyBWgtcf7qQc9cqE0VGO1kLU+ujSyPlkZonjWVfeCrf298SElIXUNVXcihqVsglA
 VAL+tIUFT2Bbc3SH5xGsqHCMAy1hNRkEuF5t7enphOoxm7CdqghDLMfUEW65igYg
 XNt3DELfFDQVnwGP8DWSWjgLVAvGAGWGNHQ9QD/FO5mdVrXh1lukV8ZtXf6K2VJc
 svR670n3ZbMOkEIOGJYcYUFEKMgJXLNEpQX8WRM+vjnuEpDML6bBROtA8hckRv8=
 =9TSs
 -----END PGP SIGNATURE-----

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

pc, acpi, virtio: fixes, test speedup for rc1

Some fixes all over the place. Notably vhost-user gained a new message
to set endian-ness. Borderline for 2.10 but seems to be the only way to
fix legacy guests.  Also pc tests are run on kvm now. Not a fix at all
but doesn't touch qemu itself, so I merged it since I had to run these a
lot and I just got tired of waiting for these to finish.

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

# gpg: Signature made Tue 01 Aug 2017 22:36:47 BST
# gpg:                using RSA key 0x281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# 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

* remotes/mst/tags/for_upstream:
  pc: acpi: force FADT rev1 for 440fx based machine types
  pc: make 'pc.rom' readonly when machine has PCI enabled
  vhost-user: fix watcher need be removed when vhost-user hotplug
  tests/bios-tables-test: Compiler warning fix
  accel: cleanup error output
  intel_iommu: use access_flags for iotlb
  intel_iommu: fix iova for pt
  vhost-user: fix legacy cross-endian configurations
  vhost: fix a memory leak
  tests: switch pxe and vm gen id tests to use kvm

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

docs/interop/vhost-user.txt

@@ -326,6 +326,7 @@ Protocol features
 #define VHOST_USER_PROTOCOL_F_REPLY_ACK      3
 #define VHOST_USER_PROTOCOL_F_MTU            4
 #define VHOST_USER_PROTOCOL_F_SLAVE_REQ      5
+#define VHOST_USER_PROTOCOL_F_CROSS_ENDIAN   6
 
 Master message types
 --------------------
@@ -580,6 +581,21 @@ Master message types
       This request should be send only when VIRTIO_F_IOMMU_PLATFORM feature
       has been successfully negotiated.
 
+ * VHOST_USER_SET_VRING_ENDIAN
+
+      Id: 23
+      Equivalent ioctl: VHOST_SET_VRING_ENDIAN
+      Master payload: vring state description
+
+      Set the endianess of a VQ for legacy devices. Little-endian is indicated
+      with state.num set to 0 and big-endian is indicated with state.num set
+      to 1. Other values are invalid.
+      This request should be sent only when VHOST_USER_PROTOCOL_F_CROSS_ENDIAN
+      has been negotiated.
+      Backends that negotiated this feature should handle both endianesses
+      and expect this message once (per VQ) during device configuration
+      (ie. before the master starts the VQ).
+
 Slave message types
 -------------------
 

hw/i386/acpi-build.c

@@ -90,6 +90,7 @@ typedef struct AcpiMcfgInfo {
 } AcpiMcfgInfo;
 
 typedef struct AcpiPmInfo {
+    bool force_rev1_fadt;
     bool s3_disabled;
     bool s4_disabled;
     bool pcihp_bridge_en;
@@ -129,10 +130,13 @@ static void acpi_get_pm_info(AcpiPmInfo *pm)
     Object *obj = NULL;
     QObject *o;
 
+    pm->force_rev1_fadt = false;
     pm->cpu_hp_io_base = 0;
     pm->pcihp_io_base = 0;
     pm->pcihp_io_len = 0;
     if (piix) {
+        /* w2k requires FADT(rev1) or it won't boot, keep PC compatible */
+        pm->force_rev1_fadt = true;
         obj = piix;
         pm->cpu_hp_io_base = PIIX4_CPU_HOTPLUG_IO_BASE;
         pm->pcihp_io_base =
@@ -304,6 +308,9 @@ static void fadt_setup(AcpiFadtDescriptorRev3 *fadt, AcpiPmInfo *pm)
         fadt->flags |= cpu_to_le32(1 << ACPI_FADT_F_FORCE_APIC_CLUSTER_MODEL);
     }
     fadt->century = RTC_CENTURY;
+    if (pm->force_rev1_fadt) {
+        return;
+    }
 
     fadt->flags |= cpu_to_le32(1 << ACPI_FADT_F_RESET_REG_SUP);
     fadt->reset_value = 0xf;
@@ -342,6 +349,8 @@ build_fadt(GArray *table_data, BIOSLinker *linker, AcpiPmInfo *pm,
     unsigned fw_ctrl_offset = (char *)&fadt->firmware_ctrl - table_data->data;
     unsigned dsdt_entry_offset = (char *)&fadt->dsdt - table_data->data;
     unsigned xdsdt_entry_offset = (char *)&fadt->x_dsdt - table_data->data;
+    int fadt_size = sizeof(*fadt);
+    int rev = 3;
 
     /* FACS address to be filled by Guest linker */
     bios_linker_loader_add_pointer(linker,
@@ -353,12 +362,17 @@ build_fadt(GArray *table_data, BIOSLinker *linker, AcpiPmInfo *pm,
     bios_linker_loader_add_pointer(linker,
         ACPI_BUILD_TABLE_FILE, dsdt_entry_offset, sizeof(fadt->dsdt),
         ACPI_BUILD_TABLE_FILE, dsdt_tbl_offset);
-    bios_linker_loader_add_pointer(linker,
+    if (pm->force_rev1_fadt) {
-        ACPI_BUILD_TABLE_FILE, xdsdt_entry_offset, sizeof(fadt->x_dsdt),
+        rev = 1;
-        ACPI_BUILD_TABLE_FILE, dsdt_tbl_offset);
+        fadt_size = offsetof(typeof(*fadt), reset_register);
+    } else {
+        bios_linker_loader_add_pointer(linker,
+            ACPI_BUILD_TABLE_FILE, xdsdt_entry_offset, sizeof(fadt->x_dsdt),
+            ACPI_BUILD_TABLE_FILE, dsdt_tbl_offset);
+    }
 
     build_header(linker, table_data,
-                 (void *)fadt, "FACP", sizeof(*fadt), 3, oem_id, oem_table_id);
+                 (void *)fadt, "FACP", fadt_size, rev, oem_id, oem_table_id);
 }
 
 void pc_madt_cpu_entry(AcpiDeviceIf *adev, int uid,

hw/i386/intel_iommu.c

@@ -237,8 +237,7 @@ out:
 
 static void vtd_update_iotlb(IntelIOMMUState *s, uint16_t source_id,
                              uint16_t domain_id, hwaddr addr, uint64_t slpte,
-                             bool read_flags, bool write_flags,
+                             uint8_t access_flags, uint32_t level)
-                             uint32_t level)
 {
     VTDIOTLBEntry *entry = g_malloc(sizeof(*entry));
     uint64_t *key = g_malloc(sizeof(*key));
@@ -253,8 +252,7 @@ static void vtd_update_iotlb(IntelIOMMUState *s, uint16_t source_id,
     entry->gfn = gfn;
     entry->domain_id = domain_id;
     entry->slpte = slpte;
-    entry->read_flags = read_flags;
+    entry->access_flags = access_flags;
-    entry->write_flags = write_flags;
     entry->mask = vtd_slpt_level_page_mask(level);
     *key = vtd_get_iotlb_key(gfn, source_id, level);
     g_hash_table_replace(s->iotlb, key, entry);
@@ -1087,6 +1085,7 @@ static bool vtd_do_iommu_translate(VTDAddressSpace *vtd_as, PCIBus *bus,
     bool is_fpd_set = false;
     bool reads = true;
     bool writes = true;
+    uint8_t access_flags;
     VTDIOTLBEntry *iotlb_entry;
 
     /*
@@ -1101,8 +1100,7 @@ static bool vtd_do_iommu_translate(VTDAddressSpace *vtd_as, PCIBus *bus,
         trace_vtd_iotlb_page_hit(source_id, addr, iotlb_entry->slpte,
                                  iotlb_entry->domain_id);
         slpte = iotlb_entry->slpte;
-        reads = iotlb_entry->read_flags;
+        access_flags = iotlb_entry->access_flags;
-        writes = iotlb_entry->write_flags;
         page_mask = iotlb_entry->mask;
         goto out;
     }
@@ -1139,9 +1137,9 @@ static bool vtd_do_iommu_translate(VTDAddressSpace *vtd_as, PCIBus *bus,
      * Also, let's ignore IOTLB caching as well for PT devices.
      */
     if (vtd_ce_get_type(&ce) == VTD_CONTEXT_TT_PASS_THROUGH) {
-        entry->iova = addr & VTD_PAGE_MASK;
+        entry->iova = addr & VTD_PAGE_MASK_4K;
         entry->translated_addr = entry->iova;
-        entry->addr_mask = VTD_PAGE_MASK;
+        entry->addr_mask = ~VTD_PAGE_MASK_4K;
         entry->perm = IOMMU_RW;
         trace_vtd_translate_pt(source_id, entry->iova);
 
@@ -1172,13 +1170,14 @@ static bool vtd_do_iommu_translate(VTDAddressSpace *vtd_as, PCIBus *bus,
     }
 
     page_mask = vtd_slpt_level_page_mask(level);
+    access_flags = IOMMU_ACCESS_FLAG(reads, writes);
     vtd_update_iotlb(s, source_id, VTD_CONTEXT_ENTRY_DID(ce.hi), addr, slpte,
-                     reads, writes, level);
+                     access_flags, level);
 out:
     entry->iova = addr & page_mask;
     entry->translated_addr = vtd_get_slpte_addr(slpte) & page_mask;
     entry->addr_mask = ~page_mask;
-    entry->perm = IOMMU_ACCESS_FLAG(reads, writes);
+    entry->perm = access_flags;
     return true;
 
 error:

hw/i386/intel_iommu_internal.h

@@ -384,7 +384,6 @@ typedef struct VTDIOTLBPageInvInfo VTDIOTLBPageInvInfo;
 /* Pagesize of VTD paging structures, including root and context tables */
 #define VTD_PAGE_SHIFT              12
 #define VTD_PAGE_SIZE               (1ULL << VTD_PAGE_SHIFT)
-#define VTD_PAGE_MASK               (VTD_PAGE_SIZE - 1)
 
 #define VTD_PAGE_SHIFT_4K           12
 #define VTD_PAGE_MASK_4K            (~((1ULL << VTD_PAGE_SHIFT_4K) - 1))

hw/i386/pc.c

@@ -1443,6 +1443,9 @@ void pc_memory_init(PCMachineState *pcms,
     option_rom_mr = g_malloc(sizeof(*option_rom_mr));
     memory_region_init_ram(option_rom_mr, NULL, "pc.rom", PC_ROM_SIZE,
                            &error_fatal);
+    if (pcmc->pci_enabled) {
+        memory_region_set_readonly(option_rom_mr, true);
+    }
     memory_region_add_subregion_overlap(rom_memory,
                                         PC_ROM_MIN_VGA,
                                         option_rom_mr,

hw/virtio/vhost-backend.c

@@ -52,11 +52,13 @@ static int vhost_kernel_memslots_limit(struct vhost_dev *dev)
                             &s, NULL, NULL)) {
         uint64_t val = g_ascii_strtoull(s, NULL, 10);
         if (!((val == G_MAXUINT64 || !val) && errno)) {
+            g_free(s);
             return val;
         }
         error_report("ignoring invalid max_mem_regions value in vhost module:"
                      " %s", s);
     }
+    g_free(s);
     return limit;
 }
 

hw/virtio/vhost-user.c

@@ -33,6 +33,7 @@ enum VhostUserProtocolFeature {
     VHOST_USER_PROTOCOL_F_REPLY_ACK = 3,
     VHOST_USER_PROTOCOL_F_NET_MTU = 4,
     VHOST_USER_PROTOCOL_F_SLAVE_REQ = 5,
+    VHOST_USER_PROTOCOL_F_CROSS_ENDIAN = 6,
 
     VHOST_USER_PROTOCOL_F_MAX
 };
@@ -63,6 +64,7 @@ typedef enum VhostUserRequest {
     VHOST_USER_NET_SET_MTU = 20,
     VHOST_USER_SET_SLAVE_REQ_FD = 21,
     VHOST_USER_IOTLB_MSG = 22,
+    VHOST_USER_SET_VRING_ENDIAN = 23,
     VHOST_USER_MAX
 } VhostUserRequest;
 
@@ -367,8 +369,25 @@ static int vhost_user_set_vring_addr(struct vhost_dev *dev,
 static int vhost_user_set_vring_endian(struct vhost_dev *dev,
                                        struct vhost_vring_state *ring)
 {
-    error_report("vhost-user trying to send unhandled ioctl");
+    bool cross_endian = virtio_has_feature(dev->protocol_features,
-    return -1;
+                                           VHOST_USER_PROTOCOL_F_CROSS_ENDIAN);
+    VhostUserMsg msg = {
+        .request = VHOST_USER_SET_VRING_ENDIAN,
+        .flags = VHOST_USER_VERSION,
+        .payload.state = *ring,
+        .size = sizeof(msg.payload.state),
+    };
+
+    if (!cross_endian) {
+        error_report("vhost-user trying to send unhandled ioctl");
+        return -1;
+    }
+
+    if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
+        return -1;
+    }
+
+    return 0;
 }
 
 static int vhost_set_vring(struct vhost_dev *dev,

include/hw/i386/intel_iommu.h

@@ -103,8 +103,7 @@ struct VTDIOTLBEntry {
     uint16_t domain_id;
     uint64_t slpte;
     uint64_t mask;
-    bool read_flags;
+    uint8_t access_flags;
-    bool write_flags;
 };
 
 /* VT-d Source-ID Qualifier types */

net/vhost-user.c

@@ -151,6 +151,10 @@ static void vhost_user_cleanup(NetClientState *nc)
         s->vhost_net = NULL;
     }
     if (nc->queue_index == 0) {
+        if (s->watch) {
+            g_source_remove(s->watch);
+            s->watch = 0;
+        }
         qemu_chr_fe_deinit(&s->chr, true);
     }
 

tests/bios-tables-test.c

@@ -108,7 +108,7 @@ static void test_acpi_rsdt_table(test_data *data)
     /* compute the table entries in rsdt */
     tables_nr = (rsdt_table->length - sizeof(AcpiRsdtDescriptorRev1)) /
                 sizeof(uint32_t);
-    g_assert_cmpint(tables_nr, >, 0);
+    g_assert(tables_nr > 0);
 
     /* get the addresses of the tables pointed by rsdt */
     tables = g_new0(uint32_t, tables_nr);

tests/pxe-test.c

@@ -25,7 +25,7 @@ static void test_pxe_one(const char *params, bool ipv6)
 {
     char *args;
 
-    args = g_strdup_printf("-machine accel=tcg -nodefaults -boot order=n "
+    args = g_strdup_printf("-machine accel=kvm:tcg -nodefaults -boot order=n "
                            "-netdev user,id=" NETNAME ",tftp=./,bootfile=%s,"
                            "ipv4=%s,ipv6=%s %s", disk, ipv6 ? "off" : "on",
                            ipv6 ? "on" : "off", params);

tests/vmgenid-test.c

@@ -132,7 +132,7 @@ static char disk[] = "tests/vmgenid-test-disk-XXXXXX";
 
 static char *guid_cmd_strdup(const char *guid)
 {
-    return g_strdup_printf("-machine accel=tcg "
+    return g_strdup_printf("-machine accel=kvm:tcg "
                            "-device vmgenid,id=testvgid,guid=%s "
                            "-drive id=hd0,if=none,file=%s,format=raw "
                            "-device ide-hd,drive=hd0 ",