Merge remote-tracking branch 'remotes/awilliam/tags/vfio-updates-20190221.0' into staging

VFIO updates 2019-02-21

 - Workaround kernel overflow bug in vfio type1 DMA unmap
   (Alex Williamson)

 - Refactor vfio container initialization (Eric Auger)

# gpg: Signature made Fri 22 Feb 2019 05:21:07 GMT
# gpg:                using RSA key 239B9B6E3BB08B22
# gpg: Good signature from "Alex Williamson <alex.williamson@redhat.com>" [full]
# gpg:                 aka "Alex Williamson <alex@shazbot.org>" [full]
# gpg:                 aka "Alex Williamson <alwillia@redhat.com>" [full]
# gpg:                 aka "Alex Williamson <alex.l.williamson@gmail.com>" [full]
# Primary key fingerprint: 42F6 C04E 540B D1A9 9E7B  8A90 239B 9B6E 3BB0 8B22

* remotes/awilliam/tags/vfio-updates-20190221.0:
  hw/vfio/common: Refactor container initialization
  vfio/common: Work around kernel overflow bug in DMA unmap

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

2 files changed, 90 insertions, 45 deletions

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 4262b80c44..df2b4721bf 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -220,7 +220,25 @@ static int vfio_dma_unmap(VFIOContainer *container,
         .size = size,
     };
 
-    if (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) {
+    while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) {
+        /*
+         * The type1 backend has an off-by-one bug in the kernel (71a7d3d78e3c
+         * v4.15) where an overflow in its wrap-around check prevents us from
+         * unmapping the last page of the address space.  Test for the error
+         * condition and re-try the unmap excluding the last page.  The
+         * expectation is that we've never mapped the last page anyway and this
+         * unmap request comes via vIOMMU support which also makes it unlikely
+         * that this page is used.  This bug was introduced well after type1 v2
+         * support was introduced, so we shouldn't need to test for v1.  A fix
+         * is queued for kernel v5.0 so this workaround can be removed once
+         * affected kernels are sufficiently deprecated.
+         */
+        if (errno == EINVAL && unmap.size && !(unmap.iova + unmap.size) &&
+            container->iommu_type == VFIO_TYPE1v2_IOMMU) {
+            trace_vfio_dma_unmap_overflow_workaround();
+            unmap.size -= 1ULL << ctz64(container->pgsizes);
+            continue;
+        }
         error_report("VFIO_UNMAP_DMA: %d", -errno);
         return -errno;
     }
@@ -1036,6 +1054,60 @@ static void vfio_put_address_space(VFIOAddressSpace *space)
     }
 }
 
+/*
+ * vfio_get_iommu_type - selects the richest iommu_type (v2 first)
+ */
+static int vfio_get_iommu_type(VFIOContainer *container,
+                               Error **errp)
+{
+    int iommu_types[] = { VFIO_TYPE1v2_IOMMU, VFIO_TYPE1_IOMMU,
+                          VFIO_SPAPR_TCE_v2_IOMMU, VFIO_SPAPR_TCE_IOMMU };
+    int i;
+
+    for (i = 0; i < ARRAY_SIZE(iommu_types); i++) {
+        if (ioctl(container->fd, VFIO_CHECK_EXTENSION, iommu_types[i])) {
+            return iommu_types[i];
+        }
+    }
+    error_setg(errp, "No available IOMMU models");
+    return -EINVAL;
+}
+
+static int vfio_init_container(VFIOContainer *container, int group_fd,
+                               Error **errp)
+{
+    int iommu_type, ret;
+
+    iommu_type = vfio_get_iommu_type(container, errp);
+    if (iommu_type < 0) {
+        return iommu_type;
+    }
+
+    ret = ioctl(group_fd, VFIO_GROUP_SET_CONTAINER, &container->fd);
+    if (ret) {
+        error_setg_errno(errp, errno, "Failed to set group container");
+        return -errno;
+    }
+
+    while (ioctl(container->fd, VFIO_SET_IOMMU, iommu_type)) {
+        if (iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
+            /*
+             * On sPAPR, despite the IOMMU subdriver always advertises v1 and
+             * v2, the running platform may not support v2 and there is no
+             * way to guess it until an IOMMU group gets added to the container.
+             * So in case it fails with v2, try v1 as a fallback.
+             */
+            iommu_type = VFIO_SPAPR_TCE_IOMMU;
+            continue;
+        }
+        error_setg_errno(errp, errno, "Failed to set iommu for container");
+        return -errno;
+    }
+
+    container->iommu_type = iommu_type;
+    return 0;
+}
+
 static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
                                   Error **errp)
 {
@@ -1101,25 +1173,17 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
     container->fd = fd;
     QLIST_INIT(&container->giommu_list);
     QLIST_INIT(&container->hostwin_list);
-    if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1_IOMMU) ||
-        ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1v2_IOMMU)) {
-        bool v2 = !!ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1v2_IOMMU);
-        struct vfio_iommu_type1_info info;
 
-        ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd);
-        if (ret) {
-            error_setg_errno(errp, errno, "failed to set group container");
-            ret = -errno;
-            goto free_container_exit;
-        }
+    ret = vfio_init_container(container, group->fd, errp);
+    if (ret) {
+        goto free_container_exit;
+    }
 
-        container->iommu_type = v2 ? VFIO_TYPE1v2_IOMMU : VFIO_TYPE1_IOMMU;
-        ret = ioctl(fd, VFIO_SET_IOMMU, container->iommu_type);
-        if (ret) {
-            error_setg_errno(errp, errno, "failed to set iommu for container");
-            ret = -errno;
-            goto free_container_exit;
-        }
+    switch (container->iommu_type) {
+    case VFIO_TYPE1v2_IOMMU:
+    case VFIO_TYPE1_IOMMU:
+    {
+        struct vfio_iommu_type1_info info;
 
         /*
          * FIXME: This assumes that a Type1 IOMMU can map any 64-bit
@@ -1137,30 +1201,13 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
         }
         vfio_host_win_add(container, 0, (hwaddr)-1, info.iova_pgsizes);
         container->pgsizes = info.iova_pgsizes;
-    } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU) ||
-               ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_v2_IOMMU)) {
+        break;
+    }
+    case VFIO_SPAPR_TCE_v2_IOMMU:
+    case VFIO_SPAPR_TCE_IOMMU:
+    {
         struct vfio_iommu_spapr_tce_info info;
-        bool v2 = !!ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_v2_IOMMU);
-
-        ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd);
-        if (ret) {
-            error_setg_errno(errp, errno, "failed to set group container");
-            ret = -errno;
-            goto free_container_exit;
-        }
-        container->iommu_type =
-            v2 ? VFIO_SPAPR_TCE_v2_IOMMU : VFIO_SPAPR_TCE_IOMMU;
-        ret = ioctl(fd, VFIO_SET_IOMMU, container->iommu_type);
-        if (ret) {
-            container->iommu_type = VFIO_SPAPR_TCE_IOMMU;
-            v2 = false;
-            ret = ioctl(fd, VFIO_SET_IOMMU, container->iommu_type);
-        }
-        if (ret) {
-            error_setg_errno(errp, errno, "failed to set iommu for container");
-            ret = -errno;
-            goto free_container_exit;
-        }
+        bool v2 = container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU;
 
         /*
          * The host kernel code implementing VFIO_IOMMU_DISABLE is called
@@ -1222,10 +1269,7 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
                               info.dma32_window_size - 1,
                               0x1000);
         }
-    } else {
-        error_setg(errp, "No available IOMMU models");
-        ret = -EINVAL;
-        goto free_container_exit;
+    }
     }
 
     vfio_kvm_device_add_group(group);
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index f41ca96160..ed2f333ad7 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -110,6 +110,7 @@ vfio_region_mmaps_set_enabled(const char *name, bool enabled) "Region %s mmaps e
 vfio_region_sparse_mmap_header(const char *name, int index, int nr_areas) "Device %s region %d: %d sparse mmap entries"
 vfio_region_sparse_mmap_entry(int i, unsigned long start, unsigned long end) "sparse entry %d [0x%lx - 0x%lx]"
 vfio_get_dev_region(const char *name, int index, uint32_t type, uint32_t subtype) "%s index %d, %08x/%0x8"
+vfio_dma_unmap_overflow_workaround(void) ""
 
 # hw/vfio/platform.c
 vfio_platform_base_device_init(char *name, int groupid) "%s belongs to group #%d"