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, 109 insertions, 3 deletions

diff --git a/hw/ppc/ppc440_pcix.c b/hw/ppc/ppc440_pcix.c
index 672090de94..df4ee374d0 100644
--- a/hw/ppc/ppc440_pcix.c
+++ b/hw/ppc/ppc440_pcix.c
@@ -449,6 +449,10 @@ static AddressSpace *ppc440_pcix_set_iommu(PCIBus *b, void *opaque, int devfn)
     return &s->bm_as;
 }
 
+static const PCIIOMMUOps ppc440_iommu_ops = {
+    .get_address_space = ppc440_pcix_set_iommu,
+};
+
 /*
  * Some guests on sam460ex write all kinds of garbage here such as
  * missing enable bit and low bits set and still expect this to work
@@ -503,7 +507,7 @@ static void ppc440_pcix_realize(DeviceState *dev, Error **errp)
     memory_region_init(&s->bm, OBJECT(s), "bm-ppc440-pcix", UINT64_MAX);
     memory_region_add_subregion(&s->bm, 0x0, &s->busmem);
     address_space_init(&s->bm_as, &s->bm, "pci-bm");
-    pci_setup_iommu(h->bus, ppc440_pcix_set_iommu, s);
+    pci_setup_iommu(h->bus, &ppc440_iommu_ops, s);
 
     memory_region_init(&s->container, OBJECT(s), "pci-container", PCI_ALL_SIZE);
     memory_region_init_io(&h->conf_mem, OBJECT(s), &ppc440_pcix_host_conf_ops,
diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c
index 370c5a90f2..a27024e45a 100644
--- a/hw/ppc/spapr_pci.c
+++ b/hw/ppc/spapr_pci.c
@@ -780,6 +780,10 @@ static AddressSpace *spapr_pci_dma_iommu(PCIBus *bus, void *opaque, int devfn)
     return &phb->iommu_as;
 }
 
+static const PCIIOMMUOps spapr_iommu_ops = {
+    .get_address_space = spapr_pci_dma_iommu,
+};
+
 static char *spapr_phb_vfio_get_loc_code(SpaprPhbState *sphb,  PCIDevice *pdev)
 {
     g_autofree char *path = NULL;
@@ -1978,7 +1982,7 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp)
     memory_region_add_subregion(&sphb->iommu_root, SPAPR_PCI_MSI_WINDOW,
                                 &sphb->msiwindow);
 
-    pci_setup_iommu(bus, spapr_pci_dma_iommu, sphb);
+    pci_setup_iommu(bus, &spapr_iommu_ops, sphb);
 
     pci_bus_set_route_irq_fn(bus, spapr_route_intx_pin_to_irq);
 
diff --git a/hw/ppc/spapr_pci_vfio.c b/hw/ppc/spapr_pci_vfio.c
index 9016720547..f283f7e38d 100644
--- a/hw/ppc/spapr_pci_vfio.c
+++ b/hw/ppc/spapr_pci_vfio.c
@@ -18,14 +18,112 @@
  */
 
 #include "qemu/osdep.h"
+#include <sys/ioctl.h>
 #include <linux/vfio.h>
 #include "hw/ppc/spapr.h"
 #include "hw/pci-host/spapr.h"
 #include "hw/pci/msix.h"
 #include "hw/pci/pci_device.h"
-#include "hw/vfio/vfio.h"
+#include "hw/vfio/vfio-common.h"
 #include "qemu/error-report.h"
 
+/*
+ * Interfaces for IBM EEH (Enhanced Error Handling)
+ */
+static bool vfio_eeh_container_ok(VFIOContainer *container)
+{
+    /*
+     * As of 2016-03-04 (linux-4.5) the host kernel EEH/VFIO
+     * implementation is broken if there are multiple groups in a
+     * container.  The hardware works in units of Partitionable
+     * Endpoints (== IOMMU groups) and the EEH operations naively
+     * iterate across all groups in the container, without any logic
+     * to make sure the groups have their state synchronized.  For
+     * certain operations (ENABLE) that might be ok, until an error
+     * occurs, but for others (GET_STATE) it's clearly broken.
+     */
+
+    /*
+     * XXX Once fixed kernels exist, test for them here
+     */
+
+    if (QLIST_EMPTY(&container->group_list)) {
+        return false;
+    }
+
+    if (QLIST_NEXT(QLIST_FIRST(&container->group_list), container_next)) {
+        return false;
+    }
+
+    return true;
+}
+
+static int vfio_eeh_container_op(VFIOContainer *container, uint32_t op)
+{
+    struct vfio_eeh_pe_op pe_op = {
+        .argsz = sizeof(pe_op),
+        .op = op,
+    };
+    int ret;
+
+    if (!vfio_eeh_container_ok(container)) {
+        error_report("vfio/eeh: EEH_PE_OP 0x%x: "
+                     "kernel requires a container with exactly one group", op);
+        return -EPERM;
+    }
+
+    ret = ioctl(container->fd, VFIO_EEH_PE_OP, &pe_op);
+    if (ret < 0) {
+        error_report("vfio/eeh: EEH_PE_OP 0x%x failed: %m", op);
+        return -errno;
+    }
+
+    return ret;
+}
+
+static VFIOContainer *vfio_eeh_as_container(AddressSpace *as)
+{
+    VFIOAddressSpace *space = vfio_get_address_space(as);
+    VFIOContainer *container = NULL;
+
+    if (QLIST_EMPTY(&space->containers)) {
+        /* No containers to act on */
+        goto out;
+    }
+
+    container = QLIST_FIRST(&space->containers);
+
+    if (QLIST_NEXT(container, next)) {
+        /*
+         * We don't yet have logic to synchronize EEH state across
+         * multiple containers
+         */
+        container = NULL;
+        goto out;
+    }
+
+out:
+    vfio_put_address_space(space);
+    return container;
+}
+
+static bool vfio_eeh_as_ok(AddressSpace *as)
+{
+    VFIOContainer *container = vfio_eeh_as_container(as);
+
+    return (container != NULL) && vfio_eeh_container_ok(container);
+}
+
+static int vfio_eeh_as_op(AddressSpace *as, uint32_t op)
+{
+    VFIOContainer *container = vfio_eeh_as_container(as);
+
+    if (!container) {
+        return -ENODEV;
+    }
+    return vfio_eeh_container_op(container, op);
+}
+
 bool spapr_phb_eeh_available(SpaprPhbState *sphb)
 {
     return vfio_eeh_as_ok(&sphb->iommu_as);