Merge tag 'pull-vfio-20231106' of https://github.com/legoater/qemu into staging

vfio queue:

* Support for non 64b IOVA space
* Introduction of a PCIIOMMUOps callback structure to ease future
  extensions
* Fix for a buffer overrun when writing the VF token
* PPC cleanups preparing ground for IOMMUFD support

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEoPZlSPBIlev+awtgUaNDx8/77KEFAmVI+bIACgkQUaNDx8/7
# 7KHW4g/9FmgX0k2Elm1BAul3slJtuBT8/iHKfK19rhXICxhxS5xBWJA8FmosTWAT
# 91YqQJhOHARxLd9VROfv8Fq8sAo+Ys8bP3PTXh5satjY5gR9YtmMSVqvsAVLn7lv
# a/0xp7wPJt2UeKzvRNUqFXNr7yHPwxFxbJbmmAJbNte8p+TfE2qvojbJnu7BjJbg
# sTtS/vFWNJwtuNYTkMRoiZaUKEoEZ8LnslOqKUjgeO59g4i3Dq8e2JCmHANPFWUK
# cWmr7AqcXgXEnLSDWTtfN53bjcSCYkFVb4WV4Wv1/7hUF5jQ4UR0l3B64xWe0M3/
# Prak3bWOM/o7JwLBsgaWPngXA9V0WFBTXVF4x5qTwhuR1sSV8MxUvTKxI+qqiEzA
# FjU89oSZ+zXId/hEUuTL6vn1Th8/6mwD0L9ORchNOQUKzCjBzI4MVPB09nM3AdPC
# LGThlufsZktdoU2KjMHpc+gMIXQYsxkgvm07K5iZTZ5eJ4tV5KB0aPvTZppGUxe1
# YY9og9F3hxjDHQtEuSY2rzBQI7nrUpd1ZI5ut/3ZgDWkqD6aGRtMme4n4GsGsYb2
# Ht9+d2RL9S8uPUh+7rV8K/N3+vXgXRaEYTuAScKtflEbA7YnZA5nUdMng8x0kMTQ
# Y73XCd4UGWDfSSZsgaIHGkM/MRIHgmlrfcwPkWqWW9vF+92O6Hw=
# =/Du0
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 06 Nov 2023 22:35:30 HKT
# gpg:                using RSA key A0F66548F04895EBFE6B0B6051A343C7CFFBECA1
# gpg: Good signature from "Cédric Le Goater <clg@redhat.com>" [unknown]
# gpg:                 aka "Cédric Le Goater <clg@kaod.org>" [unknown]
# 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: A0F6 6548 F048 95EB FE6B  0B60 51A3 43C7 CFFB ECA1

* tag 'pull-vfio-20231106' of https://github.com/legoater/qemu: (22 commits)
  vfio/common: Move vfio_host_win_add/del into spapr.c
  vfio/spapr: Make vfio_spapr_create/remove_window static
  vfio/container: Move spapr specific init/deinit into spapr.c
  vfio/container: Move vfio_container_add/del_section_window into spapr.c
  vfio/container: Move IBM EEH related functions into spapr_pci_vfio.c
  util/uuid: Define UUID_STR_LEN from UUID_NONE string
  util/uuid: Remove UUID_FMT_LEN
  vfio/pci: Fix buffer overrun when writing the VF token
  util/uuid: Add UUID_STR_LEN definition
  hw/pci: modify pci_setup_iommu() to set PCIIOMMUOps
  test: Add some tests for range and resv-mem helpers
  virtio-iommu: Consolidate host reserved regions and property set ones
  virtio-iommu: Implement set_iova_ranges() callback
  virtio-iommu: Record whether a probe request has been issued
  range: Introduce range_inverse_array()
  virtio-iommu: Introduce per IOMMUDevice reserved regions
  util/reserved-region: Add new ReservedRegion helpers
  range: Make range_compare() public
  virtio-iommu: Rename reserved_regions into prop_resv_regions
  vfio: Collect container iova range info
  ...

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

3 files changed, 151 insertions, 19 deletions

diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events
index 0af7a2886c..637cac4edf 100644
--- a/hw/virtio/trace-events
+++ b/hw/virtio/trace-events
@@ -135,6 +135,7 @@ virtio_iommu_notify_flag_add(const char *name) "add notifier to mr %s"
 virtio_iommu_notify_flag_del(const char *name) "del notifier from mr %s"
 virtio_iommu_switch_address_space(uint8_t bus, uint8_t slot, uint8_t fn, bool on) "Device %02x:%02x.%x switching address space (iommu enabled=%d)"
 virtio_iommu_freeze_granule(uint64_t page_size_mask) "granule set to 0x%"PRIx64
+virtio_iommu_host_resv_regions(const char *name, uint32_t index, uint64_t lob, uint64_t upb) "mr=%s host-resv-reg[%d] = [0x%"PRIx64",0x%"PRIx64"]"
 
 # virtio-mem.c
 virtio_mem_send_response(uint16_t type) "type=%" PRIu16
diff --git a/hw/virtio/virtio-iommu-pci.c b/hw/virtio/virtio-iommu-pci.c
index 7ef2f9dcdb..9459fbf6ed 100644
--- a/hw/virtio/virtio-iommu-pci.c
+++ b/hw/virtio/virtio-iommu-pci.c
@@ -37,7 +37,7 @@ struct VirtIOIOMMUPCI {
 static Property virtio_iommu_pci_properties[] = {
     DEFINE_PROP_UINT32("class", VirtIOPCIProxy, class_code, 0),
     DEFINE_PROP_ARRAY("reserved-regions", VirtIOIOMMUPCI,
-                      vdev.nb_reserved_regions, vdev.reserved_regions,
+                      vdev.nr_prop_resv_regions, vdev.prop_resv_regions,
                       qdev_prop_reserved_region, ReservedRegion),
     DEFINE_PROP_END_OF_LIST(),
 };
@@ -54,9 +54,9 @@ static void virtio_iommu_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
                          "for the virtio-iommu-pci device");
         return;
     }
-    for (int i = 0; i < s->nb_reserved_regions; i++) {
-        if (s->reserved_regions[i].type != VIRTIO_IOMMU_RESV_MEM_T_RESERVED &&
-            s->reserved_regions[i].type != VIRTIO_IOMMU_RESV_MEM_T_MSI) {
+    for (int i = 0; i < s->nr_prop_resv_regions; i++) {
+        if (s->prop_resv_regions[i].type != VIRTIO_IOMMU_RESV_MEM_T_RESERVED &&
+            s->prop_resv_regions[i].type != VIRTIO_IOMMU_RESV_MEM_T_MSI) {
             error_setg(errp, "reserved region %d has an invalid type", i);
             error_append_hint(errp, "Valid values are 0 and 1\n");
             return;
diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c
index be51635895..89fb5767d1 100644
--- a/hw/virtio/virtio-iommu.c
+++ b/hw/virtio/virtio-iommu.c
@@ -20,12 +20,15 @@
 #include "qemu/osdep.h"
 #include "qemu/log.h"
 #include "qemu/iov.h"
+#include "qemu/range.h"
+#include "qemu/reserved-region.h"
 #include "exec/target_page.h"
 #include "hw/qdev-properties.h"
 #include "hw/virtio/virtio.h"
 #include "sysemu/kvm.h"
 #include "sysemu/reset.h"
 #include "sysemu/sysemu.h"
+#include "qemu/reserved-region.h"
 #include "qapi/error.h"
 #include "qemu/error-report.h"
 #include "trace.h"
@@ -378,6 +381,19 @@ static void virtio_iommu_put_domain(gpointer data)
     g_free(domain);
 }
 
+static void add_prop_resv_regions(IOMMUDevice *sdev)
+{
+    VirtIOIOMMU *s = sdev->viommu;
+    int i;
+
+    for (i = 0; i < s->nr_prop_resv_regions; i++) {
+        ReservedRegion *reg = g_new0(ReservedRegion, 1);
+
+        *reg = s->prop_resv_regions[i];
+        sdev->resv_regions = resv_region_list_insert(sdev->resv_regions, reg);
+    }
+}
+
 static AddressSpace *virtio_iommu_find_add_as(PCIBus *bus, void *opaque,
                                               int devfn)
 {
@@ -408,6 +424,7 @@ static AddressSpace *virtio_iommu_find_add_as(PCIBus *bus, void *opaque,
 
         memory_region_init(&sdev->root, OBJECT(s), name, UINT64_MAX);
         address_space_init(&sdev->as, &sdev->root, TYPE_VIRTIO_IOMMU);
+        add_prop_resv_regions(sdev);
 
         /*
          * Build the IOMMU disabled container with aliases to the
@@ -444,6 +461,10 @@ static AddressSpace *virtio_iommu_find_add_as(PCIBus *bus, void *opaque,
     return &sdev->as;
 }
 
+static const PCIIOMMUOps virtio_iommu_ops = {
+    .get_address_space = virtio_iommu_find_add_as,
+};
+
 static int virtio_iommu_attach(VirtIOIOMMU *s,
                                struct virtio_iommu_req_attach *req)
 {
@@ -624,29 +645,30 @@ static int virtio_iommu_unmap(VirtIOIOMMU *s,
     return ret;
 }
 
-static ssize_t virtio_iommu_fill_resv_mem_prop(VirtIOIOMMU *s, uint32_t ep,
+static ssize_t virtio_iommu_fill_resv_mem_prop(IOMMUDevice *sdev, uint32_t ep,
                                                uint8_t *buf, size_t free)
 {
     struct virtio_iommu_probe_resv_mem prop = {};
     size_t size = sizeof(prop), length = size - sizeof(prop.head), total;
-    int i;
-
-    total = size * s->nb_reserved_regions;
+    GList *l;
 
+    total = size * g_list_length(sdev->resv_regions);
     if (total > free) {
         return -ENOSPC;
     }
 
-    for (i = 0; i < s->nb_reserved_regions; i++) {
-        unsigned subtype = s->reserved_regions[i].type;
+    for (l = sdev->resv_regions; l; l = l->next) {
+        ReservedRegion *reg = l->data;
+        unsigned subtype = reg->type;
+        Range *range = &reg->range;
 
         assert(subtype == VIRTIO_IOMMU_RESV_MEM_T_RESERVED ||
                subtype == VIRTIO_IOMMU_RESV_MEM_T_MSI);
         prop.head.type = cpu_to_le16(VIRTIO_IOMMU_PROBE_T_RESV_MEM);
         prop.head.length = cpu_to_le16(length);
         prop.subtype = subtype;
-        prop.start = cpu_to_le64(s->reserved_regions[i].low);
-        prop.end = cpu_to_le64(s->reserved_regions[i].high);
+        prop.start = cpu_to_le64(range_lob(range));
+        prop.end = cpu_to_le64(range_upb(range));
 
         memcpy(buf, &prop, size);
 
@@ -666,19 +688,27 @@ static int virtio_iommu_probe(VirtIOIOMMU *s,
                               uint8_t *buf)
 {
     uint32_t ep_id = le32_to_cpu(req->endpoint);
+    IOMMUMemoryRegion *iommu_mr = virtio_iommu_mr(s, ep_id);
     size_t free = VIOMMU_PROBE_SIZE;
+    IOMMUDevice *sdev;
     ssize_t count;
 
-    if (!virtio_iommu_mr(s, ep_id)) {
+    if (!iommu_mr) {
         return VIRTIO_IOMMU_S_NOENT;
     }
 
-    count = virtio_iommu_fill_resv_mem_prop(s, ep_id, buf, free);
+    sdev = container_of(iommu_mr, IOMMUDevice, iommu_mr);
+    if (!sdev) {
+        return -EINVAL;
+    }
+
+    count = virtio_iommu_fill_resv_mem_prop(sdev, ep_id, buf, free);
     if (count < 0) {
         return VIRTIO_IOMMU_S_INVAL;
     }
     buf += count;
     free -= count;
+    sdev->probe_done = true;
 
     return VIRTIO_IOMMU_S_OK;
 }
@@ -856,7 +886,7 @@ static IOMMUTLBEntry virtio_iommu_translate(IOMMUMemoryRegion *mr, hwaddr addr,
     bool bypass_allowed;
     int granule;
     bool found;
-    int i;
+    GList *l;
 
     interval.low = addr;
     interval.high = addr + 1;
@@ -894,10 +924,10 @@ static IOMMUTLBEntry virtio_iommu_translate(IOMMUMemoryRegion *mr, hwaddr addr,
         goto unlock;
     }
 
-    for (i = 0; i < s->nb_reserved_regions; i++) {
-        ReservedRegion *reg = &s->reserved_regions[i];
+    for (l = sdev->resv_regions; l; l = l->next) {
+        ReservedRegion *reg = l->data;
 
-        if (addr >= reg->low && addr <= reg->high) {
+        if (range_contains(&reg->range, addr)) {
             switch (reg->type) {
             case VIRTIO_IOMMU_RESV_MEM_T_MSI:
                 entry.perm = flag;
@@ -1131,6 +1161,106 @@ static int virtio_iommu_set_page_size_mask(IOMMUMemoryRegion *mr,
     return 0;
 }
 
+/**
+ * rebuild_resv_regions: rebuild resv regions with both the
+ * info of host resv ranges and property set resv ranges
+ */
+static int rebuild_resv_regions(IOMMUDevice *sdev)
+{
+    GList *l;
+    int i = 0;
+
+    /* free the existing list and rebuild it from scratch */
+    g_list_free_full(sdev->resv_regions, g_free);
+    sdev->resv_regions = NULL;
+
+    /* First add host reserved regions if any, all tagged as RESERVED */
+    for (l = sdev->host_resv_ranges; l; l = l->next) {
+        ReservedRegion *reg = g_new0(ReservedRegion, 1);
+        Range *r = (Range *)l->data;
+
+        reg->type = VIRTIO_IOMMU_RESV_MEM_T_RESERVED;
+        range_set_bounds(&reg->range, range_lob(r), range_upb(r));
+        sdev->resv_regions = resv_region_list_insert(sdev->resv_regions, reg);
+        trace_virtio_iommu_host_resv_regions(sdev->iommu_mr.parent_obj.name, i,
+                                             range_lob(&reg->range),
+                                             range_upb(&reg->range));
+        i++;
+    }
+    /*
+     * then add higher priority reserved regions set by the machine
+     * through properties
+     */
+    add_prop_resv_regions(sdev);
+    return 0;
+}
+
+/**
+ * virtio_iommu_set_iova_ranges: Conveys the usable IOVA ranges
+ *
+ * The function turns those into reserved ranges. Once some
+ * reserved ranges have been set, new reserved regions cannot be
+ * added outside of the original ones.
+ *
+ * @mr: IOMMU MR
+ * @iova_ranges: list of usable IOVA ranges
+ * @errp: error handle
+ */
+static int virtio_iommu_set_iova_ranges(IOMMUMemoryRegion *mr,
+                                        GList *iova_ranges,
+                                        Error **errp)
+{
+    IOMMUDevice *sdev = container_of(mr, IOMMUDevice, iommu_mr);
+    GList *current_ranges = sdev->host_resv_ranges;
+    GList *l, *tmp, *new_ranges = NULL;
+    int ret = -EINVAL;
+
+    /* check that each new resv region is included in an existing one */
+    if (sdev->host_resv_ranges) {
+        range_inverse_array(iova_ranges,
+                            &new_ranges,
+                            0, UINT64_MAX);
+
+        for (tmp = new_ranges; tmp; tmp = tmp->next) {
+            Range *newr = (Range *)tmp->data;
+            bool included = false;
+
+            for (l = current_ranges; l; l = l->next) {
+                Range * r = (Range *)l->data;
+
+                if (range_contains_range(r, newr)) {
+                    included = true;
+                    break;
+                }
+            }
+            if (!included) {
+                goto error;
+            }
+        }
+        /* all new reserved ranges are included in existing ones */
+        ret = 0;
+        goto out;
+    }
+
+    if (sdev->probe_done) {
+        warn_report("%s: Notified about new host reserved regions after probe",
+                    mr->parent_obj.name);
+    }
+
+    range_inverse_array(iova_ranges,
+                        &sdev->host_resv_ranges,
+                        0, UINT64_MAX);
+    rebuild_resv_regions(sdev);
+
+    return 0;
+error:
+    error_setg(errp, "IOMMU mr=%s Conflicting host reserved ranges set!",
+               mr->parent_obj.name);
+out:
+    g_list_free_full(new_ranges, g_free);
+    return ret;
+}
+
 static void virtio_iommu_system_reset(void *opaque)
 {
     VirtIOIOMMU *s = opaque;
@@ -1206,7 +1336,7 @@ static void virtio_iommu_device_realize(DeviceState *dev, Error **errp)
     s->as_by_busptr = g_hash_table_new_full(NULL, NULL, NULL, g_free);
 
     if (s->primary_bus) {
-        pci_setup_iommu(s->primary_bus, virtio_iommu_find_add_as, s);
+        pci_setup_iommu(s->primary_bus, &virtio_iommu_ops, s);
     } else {
         error_setg(errp, "VIRTIO-IOMMU is not attached to any PCI bus!");
     }
@@ -1426,6 +1556,7 @@ static void virtio_iommu_memory_region_class_init(ObjectClass *klass,
     imrc->replay = virtio_iommu_replay;
     imrc->notify_flag_changed = virtio_iommu_notify_flag_changed;
     imrc->iommu_set_page_size_mask = virtio_iommu_set_page_size_mask;
+    imrc->iommu_set_iova_ranges = virtio_iommu_set_iova_ranges;
 }
 
 static const TypeInfo virtio_iommu_info = {