pci, pc, virtio: fixes, features

AMD IOMMU VAPIC support + fixes all over the place.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJb4IrKAAoJECgfDbjSjVRp9xEIAIT25r0SeThU32cl8955dBu3
 L2q2e+4du4KcwrC1a65mhBeATFtRthL/cWFHf1rvmwsp1t6ib+uVBH/3ezH1b48o
 rhrPjysYGbX+M/gxHv8uBM01JnMnmsaZVJv2iAifkO1fjJ5VCWXqJt89y7VryeUz
 LRzN1Zzq84umDXUuqptBKI8MF8ySwqnRHCE6YrbpTAppaJRY8zIyWkQzMd+Ls9m/
 Rwuo6QiySD4z5WrnL2hpvUCQw2qDTct9xDNrlGpxL1JVvOgo5Y5VFkF2X9IP7qap
 TIC7Y9cfUjGNf8ferYsydgzpyTjFrBMUqqcu65HjUlpACXwwwrLHPScfpT37VJI=
 =WPCi
 -----END PGP SIGNATURE-----

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

pci, pc, virtio: fixes, features

AMD IOMMU VAPIC support + fixes all over the place.

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

# gpg: Signature made Mon 05 Nov 2018 18:24:10 GMT
# gpg:                using RSA key 281F0DB8D28D5469
# 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

* remotes/mst/tags/for_upstream: (33 commits)
  vhost-scsi: prevent using uninitialized vqs
  piix_pci: fix i440fx data sheet link
  piix: use TYPE_FOO constants than string constats
  i440fx: use ARRAY_SIZE for pam_regions
  pci_bridge: fix typo in comment
  hw/pci: Add missing include
  hw/pci-bridge/ioh3420: Remove unuseful header
  hw/pci-bridge/xio3130: Remove unused functions
  tests/bios-tables-test: add 64-bit PCI MMIO aperture round-up test on Q35
  bios-tables-test: prepare expected files for mmio64
  hw/pci-host/x86: extend the 64-bit PCI hole relative to the fw-assigned base
  hw/pci-host/x86: extract get_pci_hole64_start_value() helpers
  pci-testdev: add optional memory bar
  MAINTAINERS: list "tests/acpi-test-data" files in ACPI/SMBIOS section
  x86_iommu/amd: Enable Guest virtual APIC support
  x86_iommu/amd: Add interrupt remap support when VAPIC is enabled
  i386: acpi: add IVHD device entry for IOAPIC
  x86_iommu/amd: Add interrupt remap support when VAPIC is not enabled
  x86_iommu/amd: Prepare for interrupt remap support
  x86_iommu/amd: make the address space naming consistent with intel-iommu
  ...

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

MAINTAINERS

@@ -1120,6 +1120,8 @@ F: hw/i386/acpi-build.[hc]
 F: hw/arm/virt-acpi-build.c
 F: tests/bios-tables-test.c
 F: tests/acpi-utils.[hc]
+F: tests/acpi-test-data/*
+F: tests/acpi-test-data/*/*
 
 ppc4xx
 M: Alexander Graf <agraf@suse.de>
@@ -1376,7 +1378,7 @@ Intel Hexadecimal Object File Loader
 M: Su Hang <suhang16@mails.ucas.ac.cn>
 S: Maintained
 F: tests/hexloader-test.c
-F: tests/hex-loader-check-data/test.hex
+F: tests/data/hex-loader/test.hex
 
 CHRP NVRAM
 M: Thomas Huth <thuth@redhat.com>

configure

@@ -7392,22 +7392,33 @@ if test "$ccache_cpp2" = "yes"; then
   echo "export CCACHE_CPP2=y" >> $config_host_mak
 fi
 
-# build tree in object directory in case the source is not in the current directory
+# If we're using a separate build tree, set it up now.
+# DIRS are directories which we simply mkdir in the build tree;
+# LINKS are things to symlink back into the source tree
+# (these can be both files and directories).
+# Caution: do not add files or directories here using wildcards. This
+# will result in problems later if a new file matching the wildcard is
+# added to the source tree -- nothing will cause configure to be rerun
+# so the build tree will be missing the link back to the new file, and
+# tests might fail. Prefer to keep the relevant files in their own
+# directory and symlink the directory instead.
 DIRS="tests tests/tcg tests/tcg/cris tests/tcg/lm32 tests/libqos tests/qapi-schema tests/tcg/xtensa tests/qemu-iotests tests/vm"
 DIRS="$DIRS tests/fp"
 DIRS="$DIRS docs docs/interop fsdev scsi"
 DIRS="$DIRS pc-bios/optionrom pc-bios/spapr-rtas pc-bios/s390-ccw"
 DIRS="$DIRS roms/seabios roms/vgabios"
-FILES="Makefile tests/tcg/Makefile qdict-test-data.txt"
+LINKS="Makefile tests/tcg/Makefile qdict-test-data.txt"
-FILES="$FILES tests/tcg/cris/Makefile tests/tcg/cris/.gdbinit"
+LINKS="$LINKS tests/tcg/cris/Makefile tests/tcg/cris/.gdbinit"
-FILES="$FILES tests/tcg/lm32/Makefile tests/tcg/xtensa/Makefile po/Makefile"
+LINKS="$LINKS tests/tcg/lm32/Makefile tests/tcg/xtensa/Makefile po/Makefile"
-FILES="$FILES tests/fp/Makefile"
+LINKS="$LINKS tests/fp/Makefile"
-FILES="$FILES pc-bios/optionrom/Makefile pc-bios/keymaps"
+LINKS="$LINKS pc-bios/optionrom/Makefile pc-bios/keymaps"
-FILES="$FILES pc-bios/spapr-rtas/Makefile"
+LINKS="$LINKS pc-bios/spapr-rtas/Makefile"
-FILES="$FILES pc-bios/s390-ccw/Makefile"
+LINKS="$LINKS pc-bios/s390-ccw/Makefile"
-FILES="$FILES roms/seabios/Makefile roms/vgabios/Makefile"
+LINKS="$LINKS roms/seabios/Makefile roms/vgabios/Makefile"
-FILES="$FILES pc-bios/qemu-icon.bmp"
+LINKS="$LINKS pc-bios/qemu-icon.bmp"
-FILES="$FILES .gdbinit scripts" # scripts needed by relative path in .gdbinit
+LINKS="$LINKS .gdbinit scripts" # scripts needed by relative path in .gdbinit
+LINKS="$LINKS tests/acceptance tests/data"
+LINKS="$LINKS tests/qemu-iotests/check"
 for bios_file in \
     $source_path/pc-bios/*.bin \
     $source_path/pc-bios/*.lid \
@@ -7419,18 +7430,10 @@ for bios_file in \
     $source_path/pc-bios/u-boot.* \
     $source_path/pc-bios/palcode-*
 do
-    FILES="$FILES pc-bios/$(basename $bios_file)"
+    LINKS="$LINKS pc-bios/$(basename $bios_file)"
-done
-for test_file in $(find $source_path/tests/acpi-test-data -type f)
-do
-    FILES="$FILES tests/acpi-test-data$(echo $test_file | sed -e 's/.*acpi-test-data//')"
-done
-for test_file in $(find $source_path/tests/hex-loader-check-data -type f)
-do
-    FILES="$FILES tests/hex-loader-check-data$(echo $test_file | sed -e 's/.*hex-loader-check-data//')"
 done
 mkdir -p $DIRS
-for f in $FILES ; do
+for f in $LINKS ; do
     if [ -e "$source_path/$f" ] && [ "$pwd_is_source_path" != "y" ]; then
         symlink "$source_path/$f" "$f"
     fi
@@ -7452,25 +7455,13 @@ for rom in seabios vgabios ; do
     echo "RANLIB=$ranlib" >> $config_mak
 done
 
-# set up tests data directory
-for tests_subdir in acceptance data; do
-    if [ ! -e tests/$tests_subdir ]; then
-        symlink "$source_path/tests/$tests_subdir" tests/$tests_subdir
-    fi
-done
-
 # set up qemu-iotests in this build directory
 iotests_common_env="tests/qemu-iotests/common.env"
-iotests_check="tests/qemu-iotests/check"
 
 echo "# Automatically generated by configure - do not modify" > "$iotests_common_env"
 echo >> "$iotests_common_env"
 echo "export PYTHON='$python'" >> "$iotests_common_env"
 
-if [ ! -e "$iotests_check" ]; then
-    symlink "$source_path/$iotests_check" "$iotests_check"
-fi
-
 # Save the configure command line for later reuse.
 cat <<EOD >config.status
 #!/bin/sh

docs/specs/pci-testdev.txt

@@ -1,11 +1,11 @@
 pci-test is a device used for testing low level IO
 
-device implements up to two BARs: BAR0 and BAR1.
+device implements up to three BARs: BAR0, BAR1 and BAR2.
-Each BAR can be memory or IO. Guests must detect
+Each of BAR 0+1 can be memory or IO. Guests must detect
-BAR type and act accordingly.
+BAR types and act accordingly.
 
-Each BAR size is up to 4K bytes.
+BAR 0+1 size is up to 4K bytes each.
-Each BAR starts with the following header:
+BAR 0+1 starts with the following header:
 
 typedef struct PCITestDevHdr {
     uint8_t test;  <- write-only, starts a given test number
@@ -24,3 +24,8 @@ All registers are little endian.
 device is expected to always implement tests 0 to N on each BAR, and to add new
 tests with higher numbers.  In this way a guest can scan test numbers until it
 detects an access type that it does not support on this BAR, then stop.
+
+BAR2 is a 64bit memory bar, without backing storage.  It is disabled
+by default and can be enabled using the membar=<size> property.  This
+can be used to test whether guests handle pci bars of a specific
+(possibly quite large) size correctly.

hw/block/vhost-user-blk.c

@@ -217,7 +217,32 @@ static uint64_t vhost_user_blk_get_features(VirtIODevice *vdev,
 
 static void vhost_user_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
 {
+    VHostUserBlk *s = VHOST_USER_BLK(vdev);
+    int i;
 
+    if (!(virtio_host_has_feature(vdev, VIRTIO_F_VERSION_1) &&
+        !virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1))) {
+        return;
+    }
+
+    if (s->dev.started) {
+        return;
+    }
+
+    /* Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start
+     * vhost here instead of waiting for .set_status().
+     */
+    vhost_user_blk_start(vdev);
+
+    /* Kick right away to begin processing requests already in vring */
+    for (i = 0; i < s->dev.nvqs; i++) {
+        VirtQueue *kick_vq = virtio_get_queue(vdev, i);
+
+        if (!virtio_queue_get_desc_addr(vdev, i)) {
+            continue;
+        }
+        event_notifier_set(virtio_queue_get_host_notifier(kick_vq));
+    }
 }
 
 static void vhost_user_blk_device_realize(DeviceState *dev, Error **errp)

hw/block/virtio-blk.c

@@ -97,8 +97,8 @@ static void virtio_blk_rw_complete(void *opaque, int ret)
 
         if (req->qiov.nalloc != -1) {
             /* If nalloc is != 1 req->qiov is a local copy of the original
-             * external iovec. It was allocated in submit_merged_requests
+             * external iovec. It was allocated in submit_requests to be
-             * to be able to merge requests. */
+             * able to merge requests. */
             qemu_iovec_destroy(&req->qiov);
         }
 

hw/i386/acpi-build.c

@@ -2467,9 +2467,12 @@ build_dmar_q35(GArray *table_data, BIOSLinker *linker)
  *   IVRS table as specified in AMD IOMMU Specification v2.62, Section 5.2
  *   accessible here http://support.amd.com/TechDocs/48882_IOMMU.pdf
  */
+#define IOAPIC_SB_DEVID   (uint64_t)PCI_BUILD_BDF(0, PCI_DEVFN(0x14, 0))
+
 static void
 build_amd_iommu(GArray *table_data, BIOSLinker *linker)
 {
+    int ivhd_table_len = 28;
     int iommu_start = table_data->len;
     AMDVIState *s = AMD_IOMMU_DEVICE(x86_iommu_get_default());
 
@@ -2491,8 +2494,16 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker)
                              (1UL << 6) | /* PrefSup      */
                              (1UL << 7),  /* PPRSup       */
                              1);
+
+    /*
+     * When interrupt remapping is supported, we add a special IVHD device
+     * for type IO-APIC.
+     */
+    if (x86_iommu_get_default()->intr_supported) {
+        ivhd_table_len += 8;
+    }
     /* IVHD length */
-    build_append_int_noprefix(table_data, 28, 2);
+    build_append_int_noprefix(table_data, ivhd_table_len, 2);
     /* DeviceID */
     build_append_int_noprefix(table_data, s->devid, 2);
     /* Capability offset */
@@ -2507,7 +2518,8 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker)
     build_append_int_noprefix(table_data,
                              (48UL << 30) | /* HATS   */
                              (48UL << 28) | /* GATS   */
-                             (1UL << 2),    /* GTSup  */
+                             (1UL << 2)   | /* GTSup  */
+                             (1UL << 6),    /* GASup  */
                              4);
     /*
      *   Type 1 device entry reporting all devices
@@ -2516,6 +2528,21 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker)
      */
     build_append_int_noprefix(table_data, 0x0000001, 4);
 
+    /*
+     * Add a special IVHD device type.
+     * Refer to spec - Table 95: IVHD device entry type codes
+     *
+     * Linux IOMMU driver checks for the special IVHD device (type IO-APIC).
+     * See Linux kernel commit 'c2ff5cf5294bcbd7fa50f7d860e90a66db7e5059'
+     */
+    if (x86_iommu_get_default()->intr_supported) {
+        build_append_int_noprefix(table_data,
+                                 (0x1ull << 56) |           /* type IOAPIC */
+                                 (IOAPIC_SB_DEVID << 40) |  /* IOAPIC devid */
+                                 0x48,                      /* special device */
+                                 8);
+    }
+
     build_header(linker, table_data, (void *)(table_data->data + iommu_start),
                  "IVRS", table_data->len - iommu_start, 1, NULL, NULL);
 }

hw/i386/amd_iommu.c

@@ -26,7 +26,9 @@
 #include "amd_iommu.h"
 #include "qapi/error.h"
 #include "qemu/error-report.h"
+#include "hw/i386/apic_internal.h"
 #include "trace.h"
+#include "hw/i386/apic-msidef.h"
 
 /* used AMD-Vi MMIO registers */
 const char *amdvi_mmio_low[] = {
@@ -55,6 +57,7 @@ struct AMDVIAddressSpace {
     uint8_t bus_num;            /* bus number                           */
     uint8_t devfn;              /* device function                      */
     AMDVIState *iommu_state;    /* AMDVI - one per machine              */
+    MemoryRegion root;          /* AMDVI Root memory map region */
     IOMMUMemoryRegion iommu;    /* Device's address translation region  */
     MemoryRegion iommu_ir;      /* Device's interrupt remapping region  */
     AddressSpace as;            /* device's corresponding address space */
@@ -605,6 +608,7 @@ static void amdvi_handle_control_write(AMDVIState *s)
     s->completion_wait_intr = !!(control & AMDVI_MMIO_CONTROL_COMWAITINTEN);
     s->cmdbuf_enabled = s->enabled && !!(control &
                         AMDVI_MMIO_CONTROL_CMDBUFLEN);
+    s->ga_enabled = !!(control & AMDVI_MMIO_CONTROL_GAEN);
 
     /* update the flags depending on the control register */
     if (s->cmdbuf_enabled) {
@@ -807,7 +811,7 @@ static inline uint64_t amdvi_get_perms(uint64_t entry)
            AMDVI_DEV_PERM_SHIFT;
 }
 
-/* a valid entry should have V = 1 and reserved bits honoured */
+/* validate that reserved bits are honoured */
 static bool amdvi_validate_dte(AMDVIState *s, uint16_t devid,
                                uint64_t *dte)
 {
@@ -820,7 +824,7 @@ static bool amdvi_validate_dte(AMDVIState *s, uint16_t devid,
         return false;
     }
 
-    return dte[0] & AMDVI_DEV_VALID;
+    return true;
 }
 
 /* get a device table entry given the devid */
@@ -966,8 +970,12 @@ static void amdvi_do_translate(AMDVIAddressSpace *as, hwaddr addr,
         return;
     }
 
-    /* devices with V = 0 are not translated */
     if (!amdvi_get_dte(s, devid, entry)) {
+        return;
+    }
+
+    /* devices with V = 0 are not translated */
+    if (!(entry[0] & AMDVI_DEV_VALID)) {
         goto out;
     }
 
@@ -1026,10 +1034,366 @@ static IOMMUTLBEntry amdvi_translate(IOMMUMemoryRegion *iommu, hwaddr addr,
     return ret;
 }
 
+static int amdvi_get_irte(AMDVIState *s, MSIMessage *origin, uint64_t *dte,
+                          union irte *irte, uint16_t devid)
+{
+    uint64_t irte_root, offset;
+
+    irte_root = dte[2] & AMDVI_IR_PHYS_ADDR_MASK;
+    offset = (origin->data & AMDVI_IRTE_OFFSET) << 2;
+
+    trace_amdvi_ir_irte(irte_root, offset);
+
+    if (dma_memory_read(&address_space_memory, irte_root + offset,
+                        irte, sizeof(*irte))) {
+        trace_amdvi_ir_err("failed to get irte");
+        return -AMDVI_IR_GET_IRTE;
+    }
+
+    trace_amdvi_ir_irte_val(irte->val);
+
+    return 0;
+}
+
+static int amdvi_int_remap_legacy(AMDVIState *iommu,
+                                  MSIMessage *origin,
+                                  MSIMessage *translated,
+                                  uint64_t *dte,
+                                  X86IOMMUIrq *irq,
+                                  uint16_t sid)
+{
+    int ret;
+    union irte irte;
+
+    /* get interrupt remapping table */
+    ret = amdvi_get_irte(iommu, origin, dte, &irte, sid);
+    if (ret < 0) {
+        return ret;
+    }
+
+    if (!irte.fields.valid) {
+        trace_amdvi_ir_target_abort("RemapEn is disabled");
+        return -AMDVI_IR_TARGET_ABORT;
+    }
+
+    if (irte.fields.guest_mode) {
+        error_report_once("guest mode is not zero");
+        return -AMDVI_IR_ERR;
+    }
+
+    if (irte.fields.int_type > AMDVI_IOAPIC_INT_TYPE_ARBITRATED) {
+        error_report_once("reserved int_type");
+        return -AMDVI_IR_ERR;
+    }
+
+    irq->delivery_mode = irte.fields.int_type;
+    irq->vector = irte.fields.vector;
+    irq->dest_mode = irte.fields.dm;
+    irq->redir_hint = irte.fields.rq_eoi;
+    irq->dest = irte.fields.destination;
+
+    return 0;
+}
+
+static int amdvi_get_irte_ga(AMDVIState *s, MSIMessage *origin, uint64_t *dte,
+                             struct irte_ga *irte, uint16_t devid)
+{
+    uint64_t irte_root, offset;
+
+    irte_root = dte[2] & AMDVI_IR_PHYS_ADDR_MASK;
+    offset = (origin->data & AMDVI_IRTE_OFFSET) << 4;
+    trace_amdvi_ir_irte(irte_root, offset);
+
+    if (dma_memory_read(&address_space_memory, irte_root + offset,
+                        irte, sizeof(*irte))) {
+        trace_amdvi_ir_err("failed to get irte_ga");
+        return -AMDVI_IR_GET_IRTE;
+    }
+
+    trace_amdvi_ir_irte_ga_val(irte->hi.val, irte->lo.val);
+    return 0;
+}
+
+static int amdvi_int_remap_ga(AMDVIState *iommu,
+                              MSIMessage *origin,
+                              MSIMessage *translated,
+                              uint64_t *dte,
+                              X86IOMMUIrq *irq,
+                              uint16_t sid)
+{
+    int ret;
+    struct irte_ga irte;
+
+    /* get interrupt remapping table */
+    ret = amdvi_get_irte_ga(iommu, origin, dte, &irte, sid);
+    if (ret < 0) {
+        return ret;
+    }
+
+    if (!irte.lo.fields_remap.valid) {
+        trace_amdvi_ir_target_abort("RemapEn is disabled");
+        return -AMDVI_IR_TARGET_ABORT;
+    }
+
+    if (irte.lo.fields_remap.guest_mode) {
+        error_report_once("guest mode is not zero");
+        return -AMDVI_IR_ERR;
+    }
+
+    if (irte.lo.fields_remap.int_type > AMDVI_IOAPIC_INT_TYPE_ARBITRATED) {
+        error_report_once("reserved int_type is set");
+        return -AMDVI_IR_ERR;
+    }
+
+    irq->delivery_mode = irte.lo.fields_remap.int_type;
+    irq->vector = irte.hi.fields.vector;
+    irq->dest_mode = irte.lo.fields_remap.dm;
+    irq->redir_hint = irte.lo.fields_remap.rq_eoi;
+    irq->dest = irte.lo.fields_remap.destination;
+
+    return 0;
+}
+
+static int __amdvi_int_remap_msi(AMDVIState *iommu,
+                                 MSIMessage *origin,
+                                 MSIMessage *translated,
+                                 uint64_t *dte,
+                                 X86IOMMUIrq *irq,
+                                 uint16_t sid)
+{
+    int ret;
+    uint8_t int_ctl;
+
+    int_ctl = (dte[2] >> AMDVI_IR_INTCTL_SHIFT) & 3;
+    trace_amdvi_ir_intctl(int_ctl);
+
+    switch (int_ctl) {
+    case AMDVI_IR_INTCTL_PASS:
+        memcpy(translated, origin, sizeof(*origin));
+        return 0;
+    case AMDVI_IR_INTCTL_REMAP:
+        break;
+    case AMDVI_IR_INTCTL_ABORT:
+        trace_amdvi_ir_target_abort("int_ctl abort");
+        return -AMDVI_IR_TARGET_ABORT;
+    default:
+        trace_amdvi_ir_err("int_ctl reserved");
+        return -AMDVI_IR_ERR;
+    }
+
+    if (iommu->ga_enabled) {
+        ret = amdvi_int_remap_ga(iommu, origin, translated, dte, irq, sid);
+    } else {
+        ret = amdvi_int_remap_legacy(iommu, origin, translated, dte, irq, sid);
+    }
+
+    return ret;
+}
+
+/* Interrupt remapping for MSI/MSI-X entry */
+static int amdvi_int_remap_msi(AMDVIState *iommu,
+                               MSIMessage *origin,
+                               MSIMessage *translated,
+                               uint16_t sid)
+{
+    int ret = 0;
+    uint64_t pass = 0;
+    uint64_t dte[4] = { 0 };
+    X86IOMMUIrq irq = { 0 };
+    uint8_t dest_mode, delivery_mode;
+
+    assert(origin && translated);
+
+    /*
+     * When IOMMU is enabled, interrupt remap request will come either from
+     * IO-APIC or PCI device. If interrupt is from PCI device then it will
+     * have a valid requester id but if the interrupt is from IO-APIC
+     * then requester id will be invalid.
+     */
+    if (sid == X86_IOMMU_SID_INVALID) {
+        sid = AMDVI_IOAPIC_SB_DEVID;
+    }
+
+    trace_amdvi_ir_remap_msi_req(origin->address, origin->data, sid);
+
+    /* check if device table entry is set before we go further. */
+    if (!iommu || !iommu->devtab_len) {
+        memcpy(translated, origin, sizeof(*origin));
+        goto out;
+    }
+
+    if (!amdvi_get_dte(iommu, sid, dte)) {
+        return -AMDVI_IR_ERR;
+    }
+
+    /* Check if IR is enabled in DTE */
+    if (!(dte[2] & AMDVI_IR_REMAP_ENABLE)) {
+        memcpy(translated, origin, sizeof(*origin));
+        goto out;
+    }
+
+    /* validate that we are configure with intremap=on */
+    if (!X86_IOMMU_DEVICE(iommu)->intr_supported) {
+        trace_amdvi_err("Interrupt remapping is enabled in the guest but "
+                        "not in the host. Use intremap=on to enable interrupt "
+                        "remapping in amd-iommu.");
+        return -AMDVI_IR_ERR;
+    }
+
+    if (origin->address & AMDVI_MSI_ADDR_HI_MASK) {
+        trace_amdvi_err("MSI address high 32 bits non-zero when "
+                        "Interrupt Remapping enabled.");
+        return -AMDVI_IR_ERR;
+    }
+
+    if ((origin->address & AMDVI_MSI_ADDR_LO_MASK) != APIC_DEFAULT_ADDRESS) {
+        trace_amdvi_err("MSI is not from IOAPIC.");
+        return -AMDVI_IR_ERR;
+    }
+
+    /*
+     * The MSI data register [10:8] are used to get the upstream interrupt type.
+     *
+     * See MSI/MSI-X format:
+     * https://pdfs.semanticscholar.org/presentation/9420/c279e942eca568157711ef5c92b800c40a79.pdf
+     * (page 5)
+     */
+    delivery_mode = (origin->data >> MSI_DATA_DELIVERY_MODE_SHIFT) & 7;
+
+    switch (delivery_mode) {
+    case AMDVI_IOAPIC_INT_TYPE_FIXED:
+    case AMDVI_IOAPIC_INT_TYPE_ARBITRATED:
+        trace_amdvi_ir_delivery_mode("fixed/arbitrated");
+        ret = __amdvi_int_remap_msi(iommu, origin, translated, dte, &irq, sid);
+        if (ret < 0) {
+            goto remap_fail;
+        } else {
+            /* Translate IRQ to MSI messages */
+            x86_iommu_irq_to_msi_message(&irq, translated);
+            goto out;
+        }
+        break;
+    case AMDVI_IOAPIC_INT_TYPE_SMI:
+        error_report("SMI is not supported!");
+        ret = -AMDVI_IR_ERR;
+        break;
+    case AMDVI_IOAPIC_INT_TYPE_NMI:
+        pass = dte[3] & AMDVI_DEV_NMI_PASS_MASK;
+        trace_amdvi_ir_delivery_mode("nmi");
+        break;
+    case AMDVI_IOAPIC_INT_TYPE_INIT:
+        pass = dte[3] & AMDVI_DEV_INT_PASS_MASK;
+        trace_amdvi_ir_delivery_mode("init");
+        break;
+    case AMDVI_IOAPIC_INT_TYPE_EINT:
+        pass = dte[3] & AMDVI_DEV_EINT_PASS_MASK;
+        trace_amdvi_ir_delivery_mode("eint");
+        break;
+    default:
+        trace_amdvi_ir_delivery_mode("unsupported delivery_mode");
+        ret = -AMDVI_IR_ERR;
+        break;
+    }
+
+    if (ret < 0) {
+        goto remap_fail;
+    }
+
+    /*
+     * The MSI address register bit[2] is used to get the destination
+     * mode. The dest_mode 1 is valid for fixed and arbitrated interrupts
+     * only.
+     */
+    dest_mode = (origin->address >> MSI_ADDR_DEST_MODE_SHIFT) & 1;
+    if (dest_mode) {
+        trace_amdvi_ir_err("invalid dest_mode");
+        ret = -AMDVI_IR_ERR;
+        goto remap_fail;
+    }
+
+    if (pass) {
+        memcpy(translated, origin, sizeof(*origin));
+    } else {
+        trace_amdvi_ir_err("passthrough is not enabled");
+        ret = -AMDVI_IR_ERR;
+        goto remap_fail;
+    }
+
+out:
+    trace_amdvi_ir_remap_msi(origin->address, origin->data,
+                             translated->address, translated->data);
+    return 0;
+
+remap_fail:
+    return ret;
+}
+
+static int amdvi_int_remap(X86IOMMUState *iommu,
+                           MSIMessage *origin,
+                           MSIMessage *translated,
+                           uint16_t sid)
+{
+    return amdvi_int_remap_msi(AMD_IOMMU_DEVICE(iommu), origin,
+                               translated, sid);
+}
+
+static MemTxResult amdvi_mem_ir_write(void *opaque, hwaddr addr,
+                                      uint64_t value, unsigned size,
+                                      MemTxAttrs attrs)
+{
+    int ret;
+    MSIMessage from = { 0, 0 }, to = { 0, 0 };
+    uint16_t sid = AMDVI_IOAPIC_SB_DEVID;
+
+    from.address = (uint64_t) addr + AMDVI_INT_ADDR_FIRST;
+    from.data = (uint32_t) value;
+
+    trace_amdvi_mem_ir_write_req(addr, value, size);
+
+    if (!attrs.unspecified) {
+        /* We have explicit Source ID */
+        sid = attrs.requester_id;
+    }
+
+    ret = amdvi_int_remap_msi(opaque, &from, &to, sid);
+    if (ret < 0) {
+        /* TODO: log the event using IOMMU log event interface */
+        error_report_once("failed to remap interrupt from devid 0x%x", sid);
+        return MEMTX_ERROR;
+    }
+
+    apic_get_class()->send_msi(&to);
+
+    trace_amdvi_mem_ir_write(to.address, to.data);
+    return MEMTX_OK;
+}
+
+static MemTxResult amdvi_mem_ir_read(void *opaque, hwaddr addr,
+                                     uint64_t *data, unsigned size,
+                                     MemTxAttrs attrs)
+{
+    return MEMTX_OK;
+}
+
+static const MemoryRegionOps amdvi_ir_ops = {
+    .read_with_attrs = amdvi_mem_ir_read,
+    .write_with_attrs = amdvi_mem_ir_write,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+    .impl = {
+        .min_access_size = 4,
+        .max_access_size = 4,
+    },
+    .valid = {
+        .min_access_size = 4,
+        .max_access_size = 4,
+    }
+};
+
 static AddressSpace *amdvi_host_dma_iommu(PCIBus *bus, void *opaque, int devfn)
 {
+    char name[128];
     AMDVIState *s = opaque;
-    AMDVIAddressSpace **iommu_as;
+    AMDVIAddressSpace **iommu_as, *amdvi_dev_as;
     int bus_num = pci_bus_num(bus);
 
     iommu_as = s->address_spaces[bus_num];
@@ -1042,19 +1406,45 @@ static AddressSpace *amdvi_host_dma_iommu(PCIBus *bus, void *opaque, int devfn)
 
     /* set up AMD-Vi region */
     if (!iommu_as[devfn]) {
+        snprintf(name, sizeof(name), "amd_iommu_devfn_%d", devfn);
+
         iommu_as[devfn] = g_malloc0(sizeof(AMDVIAddressSpace));
         iommu_as[devfn]->bus_num = (uint8_t)bus_num;
         iommu_as[devfn]->devfn = (uint8_t)devfn;
         iommu_as[devfn]->iommu_state = s;
 
-        memory_region_init_iommu(&iommu_as[devfn]->iommu,
+        amdvi_dev_as = iommu_as[devfn];
-                                 sizeof(iommu_as[devfn]->iommu),
+
+        /*
+         * Memory region relationships looks like (Address range shows
+         * only lower 32 bits to make it short in length...):
+         *
+         * |-----------------+-------------------+----------|
+         * | Name            | Address range     | Priority |
+         * |-----------------+-------------------+----------+
+         * | amdvi_root      | 00000000-ffffffff |        0 |
+         * |  amdvi_iommu    | 00000000-ffffffff |        1 |
+         * |  amdvi_iommu_ir | fee00000-feefffff |       64 |
+         * |-----------------+-------------------+----------|
+         */
+        memory_region_init_iommu(&amdvi_dev_as->iommu,
+                                 sizeof(amdvi_dev_as->iommu),
                                  TYPE_AMD_IOMMU_MEMORY_REGION,
                                  OBJECT(s),
-                                 "amd-iommu", UINT64_MAX);
+                                 "amd_iommu", UINT64_MAX);
-        address_space_init(&iommu_as[devfn]->as,
+        memory_region_init(&amdvi_dev_as->root, OBJECT(s),
-                           MEMORY_REGION(&iommu_as[devfn]->iommu),
+                           "amdvi_root", UINT64_MAX);
-                           "amd-iommu");
+        address_space_init(&amdvi_dev_as->as, &amdvi_dev_as->root, name);
+        memory_region_init_io(&amdvi_dev_as->iommu_ir, OBJECT(s),
+                              &amdvi_ir_ops, s, "amd_iommu_ir",
+                              AMDVI_INT_ADDR_SIZE);
+        memory_region_add_subregion_overlap(&amdvi_dev_as->root,
+                                            AMDVI_INT_ADDR_FIRST,
+                                            &amdvi_dev_as->iommu_ir,
+                                            64);
+        memory_region_add_subregion_overlap(&amdvi_dev_as->root, 0,
+                                            MEMORY_REGION(&amdvi_dev_as->iommu),
+                                            1);
     }
     return &iommu_as[devfn]->as;
 }
@@ -1172,6 +1562,9 @@ static void amdvi_realize(DeviceState *dev, Error **err)
         return;
     }
 
+    /* Pseudo address space under root PCI bus. */
+    pcms->ioapic_as = amdvi_host_dma_iommu(bus, s, AMDVI_IOAPIC_SB_DEVID);
+
     /* set up MMIO */
     memory_region_init_io(&s->mmio, OBJECT(s), &mmio_mem_ops, s, "amdvi-mmio",
                           AMDVI_MMIO_SIZE);
@@ -1205,6 +1598,7 @@ static void amdvi_class_init(ObjectClass *klass, void* data)
     dc->vmsd = &vmstate_amdvi;
     dc->hotpluggable = false;
     dc_class->realize = amdvi_realize;
+    dc_class->int_remap = amdvi_int_remap;
     /* Supported by the pc-q35-* machine types */
     dc->user_creatable = true;
 }

hw/i386/amd_iommu.h

@@ -103,6 +103,7 @@
 #define AMDVI_MMIO_CONTROL_EVENTINTEN     (1ULL << 3)
 #define AMDVI_MMIO_CONTROL_COMWAITINTEN   (1ULL << 4)
 #define AMDVI_MMIO_CONTROL_CMDBUFLEN      (1ULL << 12)
+#define AMDVI_MMIO_CONTROL_GAEN           (1ULL << 17)
 
 /* MMIO status register bits */
 #define AMDVI_MMIO_STATUS_CMDBUF_RUN  (1 << 4)
@@ -175,7 +176,7 @@
 /* extended feature support */
 #define AMDVI_EXT_FEATURES (AMDVI_FEATURE_PREFETCH | AMDVI_FEATURE_PPR | \
         AMDVI_FEATURE_IA | AMDVI_FEATURE_GT | AMDVI_FEATURE_HE | \
-        AMDVI_GATS_MODE | AMDVI_HATS_MODE)
+        AMDVI_GATS_MODE | AMDVI_HATS_MODE | AMDVI_FEATURE_GA)
 
 /* capabilities header */
 #define AMDVI_CAPAB_FEATURES (AMDVI_CAPAB_FLAT_EXT | \
@@ -206,8 +207,94 @@
 
 #define AMDVI_COMMAND_SIZE   16
 
-#define AMDVI_INT_ADDR_FIRST 0xfee00000
+#define AMDVI_INT_ADDR_FIRST    0xfee00000
-#define AMDVI_INT_ADDR_LAST  0xfeefffff
+#define AMDVI_INT_ADDR_LAST     0xfeefffff
+#define AMDVI_INT_ADDR_SIZE     (AMDVI_INT_ADDR_LAST - AMDVI_INT_ADDR_FIRST + 1)
+#define AMDVI_MSI_ADDR_HI_MASK  (0xffffffff00000000ULL)
+#define AMDVI_MSI_ADDR_LO_MASK  (0x00000000ffffffffULL)
+
+/* SB IOAPIC is always on this device in AMD systems */
+#define AMDVI_IOAPIC_SB_DEVID   PCI_BUILD_BDF(0, PCI_DEVFN(0x14, 0))
+
+/* Interrupt remapping errors */
+#define AMDVI_IR_ERR            0x1
+#define AMDVI_IR_GET_IRTE       0x2
+#define AMDVI_IR_TARGET_ABORT   0x3
+
+/* Interrupt remapping */
+#define AMDVI_IR_REMAP_ENABLE           1ULL
+#define AMDVI_IR_INTCTL_SHIFT           60
+#define AMDVI_IR_INTCTL_ABORT           0
+#define AMDVI_IR_INTCTL_PASS            1
+#define AMDVI_IR_INTCTL_REMAP           2
+
+#define AMDVI_IR_PHYS_ADDR_MASK         (((1ULL << 45) - 1) << 6)
+
+/* MSI data 10:0 bits (section 2.2.5.1 Fig 14) */
+#define AMDVI_IRTE_OFFSET               0x7ff
+
+/* Delivery mode of MSI data (same as IOAPIC deilver mode encoding) */
+#define AMDVI_IOAPIC_INT_TYPE_FIXED          0x0
+#define AMDVI_IOAPIC_INT_TYPE_ARBITRATED     0x1
+#define AMDVI_IOAPIC_INT_TYPE_SMI            0x2
+#define AMDVI_IOAPIC_INT_TYPE_NMI            0x4
+#define AMDVI_IOAPIC_INT_TYPE_INIT           0x5
+#define AMDVI_IOAPIC_INT_TYPE_EINT           0x7
+
+/* Pass through interrupt */
+#define AMDVI_DEV_INT_PASS_MASK         (1ULL << 56)
+#define AMDVI_DEV_EINT_PASS_MASK        (1ULL << 57)
+#define AMDVI_DEV_NMI_PASS_MASK         (1ULL << 58)
+#define AMDVI_DEV_LINT0_PASS_MASK       (1ULL << 62)
+#define AMDVI_DEV_LINT1_PASS_MASK       (1ULL << 63)
+
+/* Interrupt remapping table fields (Guest VAPIC not enabled) */
+union irte {
+    uint32_t val;
+    struct {
+        uint32_t valid:1,
+                 no_fault:1,
+                 int_type:3,
+                 rq_eoi:1,
+                 dm:1,
+                 guest_mode:1,
+                 destination:8,
+                 vector:8,
+                 rsvd:8;
+    } fields;
+};
+
+/* Interrupt remapping table fields (Guest VAPIC is enabled) */
+union irte_ga_lo {
+  uint64_t val;
+
+  /* For int remapping */
+  struct {
+      uint64_t  valid:1,
+                no_fault:1,
+                /* ------ */
+                int_type:3,
+                rq_eoi:1,
+                dm:1,
+                /* ------ */
+                guest_mode:1,
+                destination:8,
+                rsvd_1:48;
+  } fields_remap;
+};
+
+union irte_ga_hi {
+  uint64_t val;
+  struct {
+      uint64_t  vector:8,
+                rsvd_2:56;
+  } fields;
+};
+
+struct irte_ga {
+  union irte_ga_lo lo;
+  union irte_ga_hi hi;
+};
 
 #define TYPE_AMD_IOMMU_DEVICE "amd-iommu"
 #define AMD_IOMMU_DEVICE(obj)\
@@ -278,6 +365,9 @@ typedef struct AMDVIState {
 
     /* IOTLB */
     GHashTable *iotlb;
+
+    /* Interrupt remapping */
+    bool ga_enabled;
 } AMDVIState;
 
 #endif

hw/i386/intel_iommu.c

@@ -37,6 +37,9 @@
 #include "kvm_i386.h"
 #include "trace.h"
 
+static void vtd_address_space_refresh_all(IntelIOMMUState *s);
+static void vtd_address_space_unmap(VTDAddressSpace *as, IOMMUNotifier *n);
+
 static void vtd_define_quad(IntelIOMMUState *s, hwaddr addr, uint64_t val,
                             uint64_t wmask, uint64_t w1cmask)
 {
@@ -227,6 +230,14 @@ static void vtd_reset_iotlb(IntelIOMMUState *s)
     vtd_iommu_unlock(s);
 }
 
+static void vtd_reset_caches(IntelIOMMUState *s)
+{
+    vtd_iommu_lock(s);
+    vtd_reset_iotlb_locked(s);
+    vtd_reset_context_cache_locked(s);
+    vtd_iommu_unlock(s);
+}
+
 static uint64_t vtd_get_iotlb_key(uint64_t gfn, uint16_t source_id,
                                   uint32_t level)
 {
@@ -1035,7 +1046,6 @@ static int vtd_sync_shadow_page_hook(IOMMUTLBEntry *entry,
     return 0;
 }
 
-/* If context entry is NULL, we'll try to fetch it on our own. */
 static int vtd_sync_shadow_page_table_range(VTDAddressSpace *vtd_as,
                                             VTDContextEntry *ce,
                                             hwaddr addr, hwaddr size)
@@ -1047,39 +1057,41 @@ static int vtd_sync_shadow_page_table_range(VTDAddressSpace *vtd_as,
         .notify_unmap = true,
         .aw = s->aw_bits,
         .as = vtd_as,
+        .domain_id = VTD_CONTEXT_ENTRY_DID(ce->hi),
     };
-    VTDContextEntry ce_cache;
-    int ret;
 
-    if (ce) {
+    return vtd_page_walk(ce, addr, addr + size, &info);
-        /* If the caller provided context entry, use it */
-        ce_cache = *ce;
-    } else {
-        /* If the caller didn't provide ce, try to fetch */
-        ret = vtd_dev_to_context_entry(s, pci_bus_num(vtd_as->bus),
-                                       vtd_as->devfn, &ce_cache);
-        if (ret) {
-            /*
-             * This should not really happen, but in case it happens,
-             * we just skip the sync for this time.  After all we even
-             * don't have the root table pointer!
-             */
-            error_report_once("%s: invalid context entry for bus 0x%x"
-                              " devfn 0x%x",
-                              __func__, pci_bus_num(vtd_as->bus),
-                              vtd_as->devfn);
-            return 0;
-        }
-    }
-
-    info.domain_id = VTD_CONTEXT_ENTRY_DID(ce_cache.hi);
-
-    return vtd_page_walk(&ce_cache, addr, addr + size, &info);
 }
 
 static int vtd_sync_shadow_page_table(VTDAddressSpace *vtd_as)
 {
-    return vtd_sync_shadow_page_table_range(vtd_as, NULL, 0, UINT64_MAX);
+    int ret;
+    VTDContextEntry ce;
+    IOMMUNotifier *n;
+
+    ret = vtd_dev_to_context_entry(vtd_as->iommu_state,
+                                   pci_bus_num(vtd_as->bus),
+                                   vtd_as->devfn, &ce);
+    if (ret) {
+        if (ret == -VTD_FR_CONTEXT_ENTRY_P) {
+            /*
+             * It's a valid scenario to have a context entry that is
+             * not present.  For example, when a device is removed
+             * from an existing domain then the context entry will be
+             * zeroed by the guest before it was put into another
+             * domain.  When this happens, instead of synchronizing
+             * the shadow pages we should invalidate all existing
+             * mappings and notify the backends.
+             */
+            IOMMU_NOTIFIER_FOREACH(n, &vtd_as->iommu) {
+                vtd_address_space_unmap(vtd_as, n);
+            }
+            ret = 0;
+        }
+        return ret;
+    }
+
+    return vtd_sync_shadow_page_table_range(vtd_as, &ce, 0, UINT64_MAX);
 }
 
 /*
@@ -1428,7 +1440,7 @@ static void vtd_context_global_invalidate(IntelIOMMUState *s)
         vtd_reset_context_cache_locked(s);
     }
     vtd_iommu_unlock(s);
-    vtd_switch_address_space_all(s);
+    vtd_address_space_refresh_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
@@ -1719,6 +1731,8 @@ static void vtd_handle_gcmd_srtp(IntelIOMMUState *s)
     vtd_root_table_setup(s);
     /* Ok - report back to driver */
     vtd_set_clear_mask_long(s, DMAR_GSTS_REG, 0, VTD_GSTS_RTPS);
+    vtd_reset_caches(s);
+    vtd_address_space_refresh_all(s);
 }
 
 /* Set Interrupt Remap Table Pointer */
@@ -1751,7 +1765,8 @@ static void vtd_handle_gcmd_te(IntelIOMMUState *s, bool en)
         vtd_set_clear_mask_long(s, DMAR_GSTS_REG, VTD_GSTS_TES, 0);
     }
 
-    vtd_switch_address_space_all(s);
+    vtd_reset_caches(s);
+    vtd_address_space_refresh_all(s);
 }
 
 /* Handle Interrupt Remap Enable/Disable */
@@ -2701,7 +2716,7 @@ static int vtd_irte_get(IntelIOMMUState *iommu, uint16_t index,
 
 /* Fetch IRQ information of specific IR index */
 static int vtd_remap_irq_get(IntelIOMMUState *iommu, uint16_t index,
-                             VTDIrq *irq, uint16_t sid)
+                             X86IOMMUIrq *irq, uint16_t sid)
 {
     VTD_IR_TableEntry irte = {};
     int ret = 0;
@@ -2730,30 +2745,6 @@ static int vtd_remap_irq_get(IntelIOMMUState *iommu, uint16_t index,
     return 0;
 }
 
-/* Generate one MSI message from VTDIrq info */
-static void vtd_generate_msi_message(VTDIrq *irq, MSIMessage *msg_out)
-{
-    VTD_MSIMessage msg = {};
-
-    /* Generate address bits */
-    msg.dest_mode = irq->dest_mode;
-    msg.redir_hint = irq->redir_hint;
-    msg.dest = irq->dest;
-    msg.__addr_hi = irq->dest & 0xffffff00;
-    msg.__addr_head = cpu_to_le32(0xfee);
-    /* Keep this from original MSI address bits */
-    msg.__not_used = irq->msi_addr_last_bits;
-
-    /* Generate data bits */
-    msg.vector = irq->vector;
-    msg.delivery_mode = irq->delivery_mode;
-    msg.level = 1;
-    msg.trigger_mode = irq->trigger_mode;
-
-    msg_out->address = msg.msi_addr;
-    msg_out->data = msg.msi_data;
-}
-
 /* Interrupt remapping for MSI/MSI-X entry */
 static int vtd_interrupt_remap_msi(IntelIOMMUState *iommu,
                                    MSIMessage *origin,
@@ -2763,7 +2754,7 @@ static int vtd_interrupt_remap_msi(IntelIOMMUState *iommu,
     int ret = 0;
     VTD_IR_MSIAddress addr;
     uint16_t index;
-    VTDIrq irq = {};
+    X86IOMMUIrq irq = {};
 
     assert(origin && translated);
 
@@ -2842,8 +2833,8 @@ static int vtd_interrupt_remap_msi(IntelIOMMUState *iommu,
      */
     irq.msi_addr_last_bits = addr.addr.__not_care;
 
-    /* Translate VTDIrq to MSI message */
+    /* Translate X86IOMMUIrq to MSI message */
-    vtd_generate_msi_message(&irq, translated);
+    x86_iommu_irq_to_msi_message(&irq, translated);
 
 out:
     trace_vtd_ir_remap_msi(origin->address, origin->data,
@@ -3051,6 +3042,12 @@ static void vtd_address_space_unmap_all(IntelIOMMUState *s)
     }
 }
 
+static void vtd_address_space_refresh_all(IntelIOMMUState *s)
+{
+    vtd_address_space_unmap_all(s);
+    vtd_switch_address_space_all(s);
+}
+
 static int vtd_replay_hook(IOMMUTLBEntry *entry, void *private)
 {
     memory_region_notify_one((IOMMUNotifier *)private, entry);
@@ -3160,10 +3157,7 @@ static void vtd_init(IntelIOMMUState *s)
         s->cap |= VTD_CAP_CM;
     }
 
-    vtd_iommu_lock(s);
+    vtd_reset_caches(s);
-    vtd_reset_context_cache_locked(s);
-    vtd_reset_iotlb_locked(s);
-    vtd_iommu_unlock(s);
 
     /* Define registers with default values and bit semantics */
     vtd_define_long(s, DMAR_VER_REG, 0x10UL, 0, 0);
@@ -3226,11 +3220,7 @@ static void vtd_reset(DeviceState *dev)
     IntelIOMMUState *s = INTEL_IOMMU_DEVICE(dev);
 
     vtd_init(s);
-
+    vtd_address_space_refresh_all(s);
-    /*
-     * When device reset, throw away all mappings and external caches
-     */
-    vtd_address_space_unmap_all(s);
 }
 
 static AddressSpace *vtd_host_dma_iommu(PCIBus *bus, void *opaque, int devfn)
@@ -3248,13 +3238,6 @@ static bool vtd_decide_config(IntelIOMMUState *s, Error **errp)
 {
     X86IOMMUState *x86_iommu = X86_IOMMU_DEVICE(s);
 
-    /* Currently Intel IOMMU IR only support "kernel-irqchip={off|split}" */
-    if (x86_iommu->intr_supported && kvm_irqchip_in_kernel() &&
-        !kvm_irqchip_is_split()) {
-        error_setg(errp, "Intel Interrupt Remapping cannot work with "
-                         "kernel-irqchip=on, please use 'split|off'.");
-        return false;
-    }
     if (s->intr_eim == ON_OFF_AUTO_ON && !x86_iommu->intr_supported) {
         error_setg(errp, "eim=on cannot be selected without intremap=on");
         return false;

hw/i386/trace-events

@@ -101,6 +101,20 @@ amdvi_mode_invalid(uint8_t level, uint64_t addr)"error: translation level 0x%"PR
 amdvi_page_fault(uint64_t addr) "error: page fault accessing guest physical address 0x%"PRIx64
 amdvi_iotlb_hit(uint8_t bus, uint8_t slot, uint8_t func, uint64_t addr, uint64_t txaddr) "hit iotlb devid %02x:%02x.%x gpa 0x%"PRIx64" hpa 0x%"PRIx64
 amdvi_translation_result(uint8_t bus, uint8_t slot, uint8_t func, uint64_t addr, uint64_t txaddr) "devid: %02x:%02x.%x gpa 0x%"PRIx64" hpa 0x%"PRIx64
+amdvi_mem_ir_write_req(uint64_t addr, uint64_t val, uint32_t size) "addr 0x%"PRIx64" data 0x%"PRIx64" size 0x%"PRIx32
+amdvi_mem_ir_write(uint64_t addr, uint64_t val) "addr 0x%"PRIx64" data 0x%"PRIx64
+amdvi_ir_remap_msi_req(uint64_t addr, uint64_t data, uint8_t devid) "addr 0x%"PRIx64" data 0x%"PRIx64" devid 0x%"PRIx8
+amdvi_ir_remap_msi(uint64_t addr, uint64_t data, uint64_t addr2, uint64_t data2) "(addr 0x%"PRIx64", data 0x%"PRIx64") -> (addr 0x%"PRIx64", data 0x%"PRIx64")"
+amdvi_err(const char *str) "%s"
+amdvi_ir_irte(uint64_t addr, uint64_t data) "addr 0x%"PRIx64" offset 0x%"PRIx64
+amdvi_ir_irte_val(uint32_t data) "data 0x%"PRIx32
+amdvi_ir_err(const char *str) "%s"
+amdvi_ir_intctl(uint8_t val) "int_ctl 0x%"PRIx8
+amdvi_ir_target_abort(const char *str) "%s"
+amdvi_ir_delivery_mode(const char *str) "%s"
+amdvi_ir_generate_msi_message(uint8_t vector, uint8_t delivery_mode, uint8_t dest_mode, uint8_t dest, uint8_t rh) "vector %d delivery-mode %d dest-mode %d dest-id %d rh %d"
+amdvi_ir_irte_ga(uint64_t addr, uint64_t data) "addr 0x%"PRIx64" offset 0x%"PRIx64
+amdvi_ir_irte_ga_val(uint64_t hi, uint64_t lo) "hi 0x%"PRIx64" lo 0x%"PRIx64
 
 # hw/i386/vmport.c
 vmport_register(unsigned char command, void *func, void *opaque) "command: 0x%02x func: %p opaque: %p"

hw/i386/x86-iommu.c

@@ -25,6 +25,7 @@
 #include "qapi/error.h"
 #include "qemu/error-report.h"
 #include "trace.h"
+#include "sysemu/kvm.h"
 
 void x86_iommu_iec_register_notifier(X86IOMMUState *iommu,
                                      iec_notify_fn fn, void *data)
@@ -52,6 +53,30 @@ void x86_iommu_iec_notify_all(X86IOMMUState *iommu, bool global,
     }
 }
 
+/* Generate one MSI message from VTDIrq info */
+void x86_iommu_irq_to_msi_message(X86IOMMUIrq *irq, MSIMessage *msg_out)
+{
+    X86IOMMU_MSIMessage msg = {};
+
+    /* Generate address bits */
+    msg.dest_mode = irq->dest_mode;
+    msg.redir_hint = irq->redir_hint;
+    msg.dest = irq->dest;
+    msg.__addr_hi = irq->dest & 0xffffff00;
+    msg.__addr_head = cpu_to_le32(0xfee);
+    /* Keep this from original MSI address bits */
+    msg.__not_used = irq->msi_addr_last_bits;
+
+    /* Generate data bits */
+    msg.vector = irq->vector;
+    msg.delivery_mode = irq->delivery_mode;
+    msg.level = 1;
+    msg.trigger_mode = irq->trigger_mode;
+
+    msg_out->address = msg.msi_addr;
+    msg_out->data = msg.msi_data;
+}
+
 /* Default X86 IOMMU device */
 static X86IOMMUState *x86_iommu_default = NULL;
 
@@ -94,6 +119,14 @@ static void x86_iommu_realize(DeviceState *dev, Error **errp)
         return;
     }
 
+    /* Both Intel and AMD IOMMU IR only support "kernel-irqchip={off|split}" */
+    if (x86_iommu->intr_supported && kvm_irqchip_in_kernel() &&
+        !kvm_irqchip_is_split()) {
+        error_setg(errp, "Interrupt Remapping cannot work with "
+                         "kernel-irqchip=on, please use 'split|off'.");
+        return;
+    }
+
     if (x86_class->realize) {
         x86_class->realize(dev, errp);
     }

hw/misc/pci-testdev.c

@@ -85,6 +85,9 @@ typedef struct PCITestDevState {
     MemoryRegion portio;
     IOTest *tests;
     int current;
+
+    uint64_t membar_size;
+    MemoryRegion membar;
 } PCITestDevState;
 
 #define TYPE_PCI_TEST_DEV "pci-testdev"
@@ -253,6 +256,16 @@ static void pci_testdev_realize(PCIDevice *pci_dev, Error **errp)
     pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY, &d->mmio);
     pci_register_bar(pci_dev, 1, PCI_BASE_ADDRESS_SPACE_IO, &d->portio);
 
+    if (d->membar_size) {
+        memory_region_init(&d->membar, OBJECT(d), "pci-testdev-membar",
+                           d->membar_size);
+        pci_register_bar(pci_dev, 2,
+                         PCI_BASE_ADDRESS_SPACE_MEMORY |
+                         PCI_BASE_ADDRESS_MEM_PREFETCH |
+                         PCI_BASE_ADDRESS_MEM_TYPE_64,
+                         &d->membar);
+    }
+
     d->current = -1;
     d->tests = g_malloc0(IOTEST_MAX * sizeof *d->tests);
     for (i = 0; i < IOTEST_MAX; ++i) {
@@ -305,6 +318,11 @@ static void qdev_pci_testdev_reset(DeviceState *dev)
     pci_testdev_reset(d);
 }
 
+static Property pci_testdev_properties[] = {
+    DEFINE_PROP_SIZE("membar", PCITestDevState, membar_size, 0),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
 static void pci_testdev_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
@@ -319,6 +337,7 @@ static void pci_testdev_class_init(ObjectClass *klass, void *data)
     dc->desc = "PCI Test Device";
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     dc->reset = qdev_pci_testdev_reset;
+    dc->props = pci_testdev_properties;
 }
 
 static const TypeInfo pci_testdev_info = {

hw/pci-bridge/ioh3420.c

@@ -24,7 +24,7 @@
 #include "hw/pci/pci_ids.h"
 #include "hw/pci/msi.h"
 #include "hw/pci/pcie.h"
-#include "ioh3420.h"
+#include "hw/pci/pcie_port.h"
 
 #define PCI_DEVICE_ID_IOH_EPORT         0x3420  /* D0:F0 express mode */
 #define PCI_DEVICE_ID_IOH_REV           0x2

hw/pci-bridge/ioh3420.h

@@ -1,6 +0,0 @@
-#ifndef QEMU_IOH3420_H
-#define QEMU_IOH3420_H
-
-#include "hw/pci/pcie_port.h"
-
-#endif /* QEMU_IOH3420_H */

hw/pci-bridge/xio3130_downstream.c

@@ -23,7 +23,7 @@
 #include "hw/pci/pci_ids.h"
 #include "hw/pci/msi.h"
 #include "hw/pci/pcie.h"
-#include "xio3130_downstream.h"
+#include "hw/pci/pcie_port.h"
 #include "qapi/error.h"
 
 #define PCI_DEVICE_ID_TI_XIO3130D       0x8233  /* downstream port */
@@ -127,32 +127,6 @@ static void xio3130_downstream_exitfn(PCIDevice *d)
     pci_bridge_exitfn(d);
 }
 
-PCIESlot *xio3130_downstream_init(PCIBus *bus, int devfn, bool multifunction,
-                                  const char *bus_name, pci_map_irq_fn map_irq,
-                                  uint8_t port, uint8_t chassis,
-                                  uint16_t slot)
-{
-    PCIDevice *d;
-    PCIBridge *br;
-    DeviceState *qdev;
-
-    d = pci_create_multifunction(bus, devfn, multifunction,
-                                 "xio3130-downstream");
-    if (!d) {
-        return NULL;
-    }
-    br = PCI_BRIDGE(d);
-
-    qdev = DEVICE(d);
-    pci_bridge_map_irq(br, bus_name, map_irq);
-    qdev_prop_set_uint8(qdev, "port", port);
-    qdev_prop_set_uint8(qdev, "chassis", chassis);
-    qdev_prop_set_uint16(qdev, "slot", slot);
-    qdev_init_nofail(qdev);
-
-    return PCIE_SLOT(d);
-}
-
 static Property xio3130_downstream_props[] = {
     DEFINE_PROP_BIT(COMPAT_PROP_PCP, PCIDevice, cap_present,
                     QEMU_PCIE_SLTCAP_PCP_BITNR, true),

hw/pci-bridge/xio3130_downstream.h

@@ -1,11 +0,0 @@
-#ifndef QEMU_XIO3130_DOWNSTREAM_H
-#define QEMU_XIO3130_DOWNSTREAM_H
-
-#include "hw/pci/pcie_port.h"
-
-PCIESlot *xio3130_downstream_init(PCIBus *bus, int devfn, bool multifunction,
-                                  const char *bus_name, pci_map_irq_fn map_irq,
-                                  uint8_t port, uint8_t chassis,
-                                  uint16_t slot);
-
-#endif /* QEMU_XIO3130_DOWNSTREAM_H */

hw/pci-bridge/xio3130_upstream.c

@@ -23,7 +23,7 @@
 #include "hw/pci/pci_ids.h"
 #include "hw/pci/msi.h"
 #include "hw/pci/pcie.h"
-#include "xio3130_upstream.h"
+#include "hw/pci/pcie_port.h"
 
 #define PCI_DEVICE_ID_TI_XIO3130U       0x8232  /* upstream port */
 #define XIO3130_REVISION                0x2
@@ -108,28 +108,6 @@ static void xio3130_upstream_exitfn(PCIDevice *d)
     pci_bridge_exitfn(d);
 }
 
-PCIEPort *xio3130_upstream_init(PCIBus *bus, int devfn, bool multifunction,
-                             const char *bus_name, pci_map_irq_fn map_irq,
-                             uint8_t port)
-{
-    PCIDevice *d;
-    PCIBridge *br;
-    DeviceState *qdev;
-
-    d = pci_create_multifunction(bus, devfn, multifunction, "x3130-upstream");
-    if (!d) {
-        return NULL;
-    }
-    br = PCI_BRIDGE(d);
-
-    qdev = DEVICE(d);
-    pci_bridge_map_irq(br, bus_name, map_irq);
-    qdev_prop_set_uint8(qdev, "port", port);
-    qdev_init_nofail(qdev);
-
-    return PCIE_PORT(d);
-}
-
 static const VMStateDescription vmstate_xio3130_upstream = {
     .name = "xio3130-express-upstream-port",
     .priority = MIG_PRI_PCI_BUS,

hw/pci-bridge/xio3130_upstream.h

@@ -1,10 +0,0 @@
-#ifndef QEMU_XIO3130_UPSTREAM_H
-#define QEMU_XIO3130_UPSTREAM_H
-
-#include "hw/pci/pcie_port.h"
-
-PCIEPort *xio3130_upstream_init(PCIBus *bus, int devfn, bool multifunction,
-                                const char *bus_name, pci_map_irq_fn map_irq,
-                                uint8_t port);
-
-#endif /* QEMU_XIO3130_UPSTREAM_H */

hw/pci-host/piix.c

@@ -40,7 +40,7 @@
 
 /*
  * I440FX chipset data sheet.
- * http://download.intel.com/design/chipsets/datashts/29054901.pdf
+ * https://wiki.qemu.org/File:29054901.pdf
  */
 
 #define I440FX_PCI_HOST_BRIDGE(obj) \
@@ -95,6 +95,9 @@ typedef struct PIIX3State {
 #define I440FX_PCI_DEVICE(obj) \
     OBJECT_CHECK(PCII440FXState, (obj), TYPE_I440FX_PCI_DEVICE)
 
+#define TYPE_PIIX3_DEVICE "PIIX3"
+#define TYPE_PIIX3_XEN_DEVICE "PIIX3-xen"
+
 struct PCII440FXState {
     /*< private >*/
     PCIDevice parent_obj;
@@ -142,7 +145,7 @@ static void i440fx_update_memory_mappings(PCII440FXState *d)
     PCIDevice *pd = PCI_DEVICE(d);
 
     memory_region_transaction_begin();
-    for (i = 0; i < 13; i++) {
+    for (i = 0; i < ARRAY_SIZE(d->pam_regions); i++) {
         pam_update(&d->pam_regions[i], i,
                    pd->config[I440FX_PAM + DIV_ROUND_UP(i, 2)]);
     }
@@ -249,9 +252,7 @@ static void i440fx_pcihost_get_pci_hole_end(Object *obj, Visitor *v,
  * the 64bit PCI hole will start after "over 4G RAM" and the
  * reserved space for memory hotplug if any.
  */
-static void i440fx_pcihost_get_pci_hole64_start(Object *obj, Visitor *v,
+static uint64_t i440fx_pcihost_get_pci_hole64_start_value(Object *obj)
-                                                const char *name,
-                                                void *opaque, Error **errp)
 {
     PCIHostState *h = PCI_HOST_BRIDGE(obj);
     I440FXState *s = I440FX_PCI_HOST_BRIDGE(obj);
@@ -263,7 +264,16 @@ static void i440fx_pcihost_get_pci_hole64_start(Object *obj, Visitor *v,
     if (!value && s->pci_hole64_fix) {
         value = pc_pci_hole64_start();
     }
-    visit_type_uint64(v, name, &value, errp);
+    return value;
+}
+
+static void i440fx_pcihost_get_pci_hole64_start(Object *obj, Visitor *v,
+                                                const char *name,
+                                                void *opaque, Error **errp)
+{
+    uint64_t hole64_start = i440fx_pcihost_get_pci_hole64_start_value(obj);
+
+    visit_type_uint64(v, name, &hole64_start, errp);
 }
 
 /*
@@ -278,7 +288,7 @@ static void i440fx_pcihost_get_pci_hole64_end(Object *obj, Visitor *v,
 {
     PCIHostState *h = PCI_HOST_BRIDGE(obj);
     I440FXState *s = I440FX_PCI_HOST_BRIDGE(obj);
-    uint64_t hole64_start = pc_pci_hole64_start();
+    uint64_t hole64_start = i440fx_pcihost_get_pci_hole64_start_value(obj);
     Range w64;
     uint64_t value, hole64_end;
 
@@ -405,7 +415,7 @@ PCIBus *i440fx_init(const char *host_type, const char *pci_type,
 
     init_pam(dev, f->ram_memory, f->system_memory, f->pci_address_space,
              &f->pam_regions[0], PAM_BIOS_BASE, PAM_BIOS_SIZE);
-    for (i = 0; i < 12; ++i) {
+    for (i = 0; i < ARRAY_SIZE(f->pam_regions) - 1; ++i) {
         init_pam(dev, f->ram_memory, f->system_memory, f->pci_address_space,
                  &f->pam_regions[i+1], PAM_EXPAN_BASE + i * PAM_EXPAN_SIZE,
                  PAM_EXPAN_SIZE);
@@ -417,13 +427,13 @@ PCIBus *i440fx_init(const char *host_type, const char *pci_type,
      * These additional routes can be discovered through ACPI. */
     if (xen_enabled()) {
         PCIDevice *pci_dev = pci_create_simple_multifunction(b,
-                             -1, true, "PIIX3-xen");
+                             -1, true, TYPE_PIIX3_XEN_DEVICE);
         piix3 = PIIX3_PCI_DEVICE(pci_dev);
         pci_bus_irqs(b, xen_piix3_set_irq, xen_pci_slot_get_pirq,
                 piix3, XEN_PIIX_NUM_PIRQS);
     } else {
         PCIDevice *pci_dev = pci_create_simple_multifunction(b,
-                             -1, true, "PIIX3");
+                             -1, true, TYPE_PIIX3_DEVICE);
         piix3 = PIIX3_PCI_DEVICE(pci_dev);
         pci_bus_irqs(b, piix3_set_irq, pci_slot_get_pirq, piix3,
                 PIIX_NUM_PIRQS);
@@ -741,7 +751,7 @@ static void piix3_class_init(ObjectClass *klass, void *data)
 }
 
 static const TypeInfo piix3_info = {
-    .name          = "PIIX3",
+    .name          = TYPE_PIIX3_DEVICE,
     .parent        = TYPE_PIIX3_PCI_DEVICE,
     .class_init    = piix3_class_init,
 };
@@ -754,7 +764,7 @@ static void piix3_xen_class_init(ObjectClass *klass, void *data)
 };
 
 static const TypeInfo piix3_xen_info = {
-    .name          = "PIIX3-xen",
+    .name          = TYPE_PIIX3_XEN_DEVICE,
     .parent        = TYPE_PIIX3_PCI_DEVICE,
     .class_init    = piix3_xen_class_init,
 };

hw/pci-host/q35.c

@@ -113,9 +113,7 @@ static void q35_host_get_pci_hole_end(Object *obj, Visitor *v,
  * the 64bit PCI hole will start after "over 4G RAM" and the
  * reserved space for memory hotplug if any.
  */
-static void q35_host_get_pci_hole64_start(Object *obj, Visitor *v,
+static uint64_t q35_host_get_pci_hole64_start_value(Object *obj)
-                                          const char *name, void *opaque,
-                                          Error **errp)
 {
     PCIHostState *h = PCI_HOST_BRIDGE(obj);
     Q35PCIHost *s = Q35_HOST_DEVICE(obj);
@@ -127,7 +125,16 @@ static void q35_host_get_pci_hole64_start(Object *obj, Visitor *v,
     if (!value && s->pci_hole64_fix) {
         value = pc_pci_hole64_start();
     }
-    visit_type_uint64(v, name, &value, errp);
+    return value;
+}
+
+static void q35_host_get_pci_hole64_start(Object *obj, Visitor *v,
+                                          const char *name, void *opaque,
+                                          Error **errp)
+{
+    uint64_t hole64_start = q35_host_get_pci_hole64_start_value(obj);
+
+    visit_type_uint64(v, name, &hole64_start, errp);
 }
 
 /*
@@ -142,7 +149,7 @@ static void q35_host_get_pci_hole64_end(Object *obj, Visitor *v,
 {
     PCIHostState *h = PCI_HOST_BRIDGE(obj);
     Q35PCIHost *s = Q35_HOST_DEVICE(obj);
-    uint64_t hole64_start = pc_pci_hole64_start();
+    uint64_t hole64_start = q35_host_get_pci_hole64_start_value(obj);
     Range w64;
     uint64_t value, hole64_end;
 

hw/pci/pci_bridge.c

@@ -399,7 +399,7 @@ void pci_bridge_exitfn(PCIDevice *pci_dev)
 
 /*
  * before qdev initialization(qdev_init()), this function sets bus_name and
- * map_irq callback which are necessry for pci_bridge_initfn() to
+ * map_irq callback which are necessary for pci_bridge_initfn() to
  * initialize bus.
  */
 void pci_bridge_map_irq(PCIBridge *br, const char* bus_name,

hw/scsi/vhost-scsi.c

@@ -183,7 +183,7 @@ static void vhost_scsi_realize(DeviceState *dev, Error **errp)
     }
 
     vsc->dev.nvqs = VHOST_SCSI_VQ_NUM_FIXED + vs->conf.num_queues;
-    vsc->dev.vqs = g_new(struct vhost_virtqueue, vsc->dev.nvqs);
+    vsc->dev.vqs = g_new0(struct vhost_virtqueue, vsc->dev.nvqs);
     vsc->dev.vq_index = 0;
     vsc->dev.backend_features = 0;
 

include/hw/i386/intel_iommu.h

@@ -66,8 +66,6 @@ typedef struct VTDIOTLBEntry VTDIOTLBEntry;
 typedef struct VTDBus VTDBus;
 typedef union VTD_IR_TableEntry VTD_IR_TableEntry;
 typedef union VTD_IR_MSIAddress VTD_IR_MSIAddress;
-typedef struct VTDIrq VTDIrq;
-typedef struct VTD_MSIMessage VTD_MSIMessage;
 
 /* Context-Entry */
 struct VTDContextEntry {
@@ -197,63 +195,6 @@ union VTD_IR_MSIAddress {
     uint32_t data;
 };
 
-/* Generic IRQ entry information */
-struct VTDIrq {
-    /* Used by both IOAPIC/MSI interrupt remapping */
-    uint8_t trigger_mode;
-    uint8_t vector;
-    uint8_t delivery_mode;
-    uint32_t dest;
-    uint8_t dest_mode;
-
-    /* only used by MSI interrupt remapping */
-    uint8_t redir_hint;
-    uint8_t msi_addr_last_bits;
-};
-
-struct VTD_MSIMessage {
-    union {
-        struct {
-#ifdef HOST_WORDS_BIGENDIAN
-            uint32_t __addr_head:12; /* 0xfee */
-            uint32_t dest:8;
-            uint32_t __reserved:8;
-            uint32_t redir_hint:1;
-            uint32_t dest_mode:1;
-            uint32_t __not_used:2;
-#else
-            uint32_t __not_used:2;
-            uint32_t dest_mode:1;
-            uint32_t redir_hint:1;
-            uint32_t __reserved:8;
-            uint32_t dest:8;
-            uint32_t __addr_head:12; /* 0xfee */
-#endif
-            uint32_t __addr_hi;
-        } QEMU_PACKED;
-        uint64_t msi_addr;
-    };
-    union {
-        struct {
-#ifdef HOST_WORDS_BIGENDIAN
-            uint16_t trigger_mode:1;
-            uint16_t level:1;
-            uint16_t __resved:3;
-            uint16_t delivery_mode:3;
-            uint16_t vector:8;
-#else
-            uint16_t vector:8;
-            uint16_t delivery_mode:3;
-            uint16_t __resved:3;
-            uint16_t level:1;
-            uint16_t trigger_mode:1;
-#endif
-            uint16_t __resved1;
-        } QEMU_PACKED;
-        uint32_t msi_data;
-    };
-};
-
 /* When IR is enabled, all MSI/MSI-X data bits should be zero */
 #define VTD_IR_MSI_DATA          (0)
 

include/hw/i386/x86-iommu.h

@@ -22,6 +22,7 @@
 
 #include "hw/sysbus.h"
 #include "hw/pci/pci.h"
+#include "hw/pci/msi.h"
 
 #define  TYPE_X86_IOMMU_DEVICE  ("x86-iommu")
 #define  X86_IOMMU_DEVICE(obj) \
@@ -35,6 +36,8 @@
 
 typedef struct X86IOMMUState X86IOMMUState;
 typedef struct X86IOMMUClass X86IOMMUClass;
+typedef struct X86IOMMUIrq X86IOMMUIrq;
+typedef struct X86IOMMU_MSIMessage X86IOMMU_MSIMessage;
 
 typedef enum IommuType {
     TYPE_INTEL,
@@ -78,6 +81,63 @@ struct X86IOMMUState {
     QLIST_HEAD(, IEC_Notifier) iec_notifiers; /* IEC notify list */
 };
 
+/* Generic IRQ entry information when interrupt remapping is enabled */
+struct X86IOMMUIrq {
+    /* Used by both IOAPIC/MSI interrupt remapping */
+    uint8_t trigger_mode;
+    uint8_t vector;
+    uint8_t delivery_mode;
+    uint32_t dest;
+    uint8_t dest_mode;
+
+    /* only used by MSI interrupt remapping */
+    uint8_t redir_hint;
+    uint8_t msi_addr_last_bits;
+};
+
+struct X86IOMMU_MSIMessage {
+    union {
+        struct {
+#ifdef HOST_WORDS_BIGENDIAN
+            uint32_t __addr_head:12; /* 0xfee */
+            uint32_t dest:8;
+            uint32_t __reserved:8;
+            uint32_t redir_hint:1;
+            uint32_t dest_mode:1;
+            uint32_t __not_used:2;
+#else
+            uint32_t __not_used:2;
+            uint32_t dest_mode:1;
+            uint32_t redir_hint:1;
+            uint32_t __reserved:8;
+            uint32_t dest:8;
+            uint32_t __addr_head:12; /* 0xfee */
+#endif
+            uint32_t __addr_hi;
+        } QEMU_PACKED;
+        uint64_t msi_addr;
+    };
+    union {
+        struct {
+#ifdef HOST_WORDS_BIGENDIAN
+            uint16_t trigger_mode:1;
+            uint16_t level:1;
+            uint16_t __resved:3;
+            uint16_t delivery_mode:3;
+            uint16_t vector:8;
+#else
+            uint16_t vector:8;
+            uint16_t delivery_mode:3;
+            uint16_t __resved:3;
+            uint16_t level:1;
+            uint16_t trigger_mode:1;
+#endif
+            uint16_t __resved1;
+        } QEMU_PACKED;
+        uint32_t msi_data;
+    };
+};
+
 /**
  * x86_iommu_get_default - get default IOMMU device
  * @return: pointer to default IOMMU device
@@ -110,4 +170,10 @@ void x86_iommu_iec_register_notifier(X86IOMMUState *iommu,
 void x86_iommu_iec_notify_all(X86IOMMUState *iommu, bool global,
                               uint32_t index, uint32_t mask);
 
+/**
+ * x86_iommu_irq_to_msi_message - Populate one MSIMessage from X86IOMMUIrq
+ * @X86IOMMUIrq: The IRQ information
+ * @out: Output MSI message
+ */
+void x86_iommu_irq_to_msi_message(X86IOMMUIrq *irq, MSIMessage *out);
 #endif

include/hw/pci/pci_bus.h

@@ -1,6 +1,8 @@
 #ifndef QEMU_PCI_BUS_H
 #define QEMU_PCI_BUS_H
 
+#include "hw/pci/pci.h"
+
 /*
  * PCI Bus datastructures.
  *

tests/bios-tables-test.c

@@ -42,7 +42,7 @@ typedef struct {
 } test_data;
 
 static char disk[] = "tests/acpi-test-disk-XXXXXX";
-static const char *data_dir = "tests/acpi-test-data";
+static const char *data_dir = "tests/data/acpi";
 #ifdef CONFIG_IASL
 static const char *iasl = stringify(CONFIG_IASL);
 #else
@@ -708,6 +708,21 @@ static void test_acpi_q35_tcg_bridge(void)
     free_test_data(&data);
 }
 
+static void test_acpi_q35_tcg_mmio64(void)
+{
+    test_data data = {
+        .machine = MACHINE_Q35,
+        .variant = ".mmio64",
+        .required_struct_types = base_required_struct_types,
+        .required_struct_types_len = ARRAY_SIZE(base_required_struct_types)
+    };
+
+    test_acpi_one("-m 128M,slots=1,maxmem=2G "
+                  "-device pci-testdev,membar=2G",
+                  &data);
+    free_test_data(&data);
+}
+
 static void test_acpi_piix4_tcg_cphp(void)
 {
     test_data data;
@@ -875,6 +890,7 @@ int main(int argc, char *argv[])
         qtest_add_func("acpi/piix4/bridge", test_acpi_piix4_tcg_bridge);
         qtest_add_func("acpi/q35", test_acpi_q35_tcg);
         qtest_add_func("acpi/q35/bridge", test_acpi_q35_tcg_bridge);
+        qtest_add_func("acpi/q35/mmio64", test_acpi_q35_tcg_mmio64);
         qtest_add_func("acpi/piix4/ipmi", test_acpi_piix4_tcg_ipmi);
         qtest_add_func("acpi/q35/ipmi", test_acpi_q35_tcg_ipmi);
         qtest_add_func("acpi/piix4/cpuhp", test_acpi_piix4_tcg_cphp);

tests/data/acpi/rebuild-expected-aml.sh

@@ -32,5 +32,3 @@ fi
 TEST_ACPI_REBUILD_AML=y QTEST_QEMU_BINARY=$qemu tests/bios-tables-test
 
 echo "The files were rebuilt and can be added to git."
-echo "However, if new files were created, please copy them manually" \
-     "to tests/acpi-test-data/pc/ or tests/acpi-test-data/q35/ ."

tests/hexloader-test.c

@@ -23,7 +23,7 @@ static void hex_loader_test(void)
     const unsigned int base_addr = 0x00010000;
 
     QTestState *s = qtest_initf(
-        "-M vexpress-a9 -nographic -device loader,file=tests/hex-loader-check-data/test.hex");
+        "-M vexpress-a9 -nographic -device loader,file=tests/data/hex-loader/test.hex");
 
     for (i = 0; i < 256; ++i) {
         uint8_t val = qtest_readb(s, base_addr + i);