summary refs log tree commit diff stats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--MAINTAINERS25
-rw-r--r--contrib/vhost-user-blk/meson.build3
-rw-r--r--contrib/vhost-user-blk/vhost-user-blk.c6
-rw-r--r--docs/interop/vhost-user.rst16
-rw-r--r--hw/pci/msi.c4
-rw-r--r--hw/virtio/vhost-backend.c7
-rw-r--r--hw/virtio/vhost-user.c6
-rw-r--r--hw/virtio/vhost.c37
-rw-r--r--hw/virtio/virtio-iommu.c16
-rw-r--r--include/hw/virtio/vhost-backend.h3
-rw-r--r--include/hw/virtio/vhost.h22
-rw-r--r--meson.build2
-rw-r--r--subprojects/libvhost-user/libvhost-user.c19
13 files changed, 112 insertions, 54 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index 1cbd6b72fa..05cf84b58c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1840,7 +1840,6 @@ R: Ani Sinha <ani@anisinha.ca>
 S: Supported
 F: include/hw/acpi/*
 F: include/hw/firmware/smbios.h
-F: hw/mem/*
 F: hw/acpi/*
 F: hw/smbios/*
 F: hw/i386/acpi-build.[hc]
@@ -1851,6 +1850,7 @@ F: tests/qtest/acpi-utils.[hc]
 F: tests/data/acpi/
 F: docs/specs/acpi_cpu_hotplug.rst
 F: docs/specs/acpi_mem_hotplug.rst
+F: docs/specs/acpi_nvdimm.rst
 F: docs/specs/acpi_pci_hotplug.rst
 F: docs/specs/acpi_hw_reduced_hotplug.rst
 
@@ -2158,15 +2158,6 @@ F: qapi/rocker.json
 F: tests/rocker/
 F: docs/specs/rocker.txt
 
-NVDIMM
-M: Xiao Guangrong <xiaoguangrong.eric@gmail.com>
-S: Maintained
-F: hw/acpi/nvdimm.c
-F: hw/mem/nvdimm.c
-F: include/hw/mem/nvdimm.h
-F: docs/nvdimm.txt
-F: docs/specs/acpi_nvdimm.rst
-
 e1000x
 M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
 S: Maintained
@@ -2588,6 +2579,7 @@ M: Ben Widawsky <ben.widawsky@intel.com>
 M: Jonathan Cameron <jonathan.cameron@huawei.com>
 S: Supported
 F: hw/cxl/
+F: hw/mem/cxl_type3.c
 F: include/hw/cxl/
 
 Dirty Bitmaps
@@ -2704,6 +2696,19 @@ F: softmmu/physmem.c
 F: include/exec/memory-internal.h
 F: scripts/coccinelle/memory-region-housekeeping.cocci
 
+Memory devices
+M: David Hildenbrand <david@redhat.com>
+M: Igor Mammedov <imammedo@redhat.com>
+R: Xiao Guangrong <xiaoguangrong.eric@gmail.com>
+S: Supported
+F: hw/mem/memory-device.c
+F: hw/mem/nvdimm.c
+F: hw/mem/pc-dimm.c
+F: include/hw/mem/memory-device.h
+F: include/hw/mem/nvdimm.h
+F: include/hw/mem/pc-dimm.h
+F: docs/nvdimm.txt
+
 SPICE
 M: Gerd Hoffmann <kraxel@redhat.com>
 S: Odd Fixes
diff --git a/contrib/vhost-user-blk/meson.build b/contrib/vhost-user-blk/meson.build
index 601ea15ef5..dcb9e2ffcd 100644
--- a/contrib/vhost-user-blk/meson.build
+++ b/contrib/vhost-user-blk/meson.build
@@ -1,5 +1,4 @@
-# FIXME: broken on 32-bit architectures
 executable('vhost-user-blk', files('vhost-user-blk.c'),
            dependencies: [qemuutil, vhost_user],
-           build_by_default: false,
+           build_by_default: targetos == 'linux',
            install: false)
diff --git a/contrib/vhost-user-blk/vhost-user-blk.c b/contrib/vhost-user-blk/vhost-user-blk.c
index cd4a5d7335..9cb78ca1d0 100644
--- a/contrib/vhost-user-blk/vhost-user-blk.c
+++ b/contrib/vhost-user-blk/vhost-user-blk.c
@@ -146,7 +146,7 @@ vub_readv(VubReq *req, struct iovec *iov, uint32_t iovcnt)
     req->size = vub_iov_size(iov, iovcnt);
     rc = preadv(vdev_blk->blk_fd, iov, iovcnt, req->sector_num * 512);
     if (rc < 0) {
-        fprintf(stderr, "%s, Sector %"PRIu64", Size %lu failed with %s\n",
+        fprintf(stderr, "%s, Sector %"PRIu64", Size %zu failed with %s\n",
                 vdev_blk->blk_name, req->sector_num, req->size,
                 strerror(errno));
         return -1;
@@ -169,7 +169,7 @@ vub_writev(VubReq *req, struct iovec *iov, uint32_t iovcnt)
     req->size = vub_iov_size(iov, iovcnt);
     rc = pwritev(vdev_blk->blk_fd, iov, iovcnt, req->sector_num * 512);
     if (rc < 0) {
-        fprintf(stderr, "%s, Sector %"PRIu64", Size %lu failed with %s\n",
+        fprintf(stderr, "%s, Sector %"PRIu64", Size %zu failed with %s\n",
                 vdev_blk->blk_name, req->sector_num, req->size,
                 strerror(errno));
         return -1;
@@ -188,7 +188,7 @@ vub_discard_write_zeroes(VubReq *req, struct iovec *iov, uint32_t iovcnt,
 
     size = vub_iov_size(iov, iovcnt);
     if (size != sizeof(*desc)) {
-        fprintf(stderr, "Invalid size %ld, expect %ld\n", size, sizeof(*desc));
+        fprintf(stderr, "Invalid size %zd, expect %zd\n", size, sizeof(*desc));
         return -1;
     }
     buf = g_new0(char, size);
diff --git a/docs/interop/vhost-user.rst b/docs/interop/vhost-user.rst
index d7cf904f7f..3f18ab424e 100644
--- a/docs/interop/vhost-user.rst
+++ b/docs/interop/vhost-user.rst
@@ -1376,14 +1376,6 @@ Front-end message types
   For further details on postcopy, see ``VHOST_USER_SET_MEM_TABLE``.
   They apply to ``VHOST_USER_ADD_MEM_REG`` accordingly.
 
-  Exactly one file descriptor from which the memory is mapped is
-  passed in the ancillary data.
-
-  In postcopy mode (see ``VHOST_USER_POSTCOPY_LISTEN``), the back-end
-  replies with the bases of the memory mapped region to the front-end.
-  For further details on postcopy, see ``VHOST_USER_SET_MEM_TABLE``.
-  They apply to ``VHOST_USER_ADD_MEM_REG`` accordingly.
-
 ``VHOST_USER_REM_MEM_REG``
   :id: 38
   :equivalent ioctl: N/A
@@ -1408,14 +1400,6 @@ Front-end message types
   accept messages with one file descriptor. If a file descriptor is
   passed, the back-end MUST close it without using it otherwise.
 
-  The memory region to be removed is identified by its guest address,
-  user address and size. The mmap offset is ignored.
-
-  No file descriptors SHOULD be passed in the ancillary data. For
-  compatibility with existing incorrect implementations, the back-end MAY
-  accept messages with one file descriptor. If a file descriptor is
-  passed, the back-end MUST close it without using it otherwise.
-
 ``VHOST_USER_SET_STATUS``
   :id: 39
   :equivalent ioctl: VHOST_VDPA_SET_STATUS
diff --git a/hw/pci/msi.c b/hw/pci/msi.c
index 5c471b9616..058d1d1ef1 100644
--- a/hw/pci/msi.c
+++ b/hw/pci/msi.c
@@ -322,9 +322,9 @@ void msi_set_mask(PCIDevice *dev, int vector, bool mask, Error **errp)
     bool msi64bit = flags & PCI_MSI_FLAGS_64BIT;
     uint32_t irq_state, vector_mask, pending;
 
-    if (vector > PCI_MSI_VECTORS_MAX) {
+    if (vector >= PCI_MSI_VECTORS_MAX) {
         error_setg(errp, "msi: vector %d not allocated. max vector is %d",
-                   vector, PCI_MSI_VECTORS_MAX);
+                   vector, (PCI_MSI_VECTORS_MAX - 1));
         return;
     }
 
diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c
index 4de8b6b3b0..8e581575c9 100644
--- a/hw/virtio/vhost-backend.c
+++ b/hw/virtio/vhost-backend.c
@@ -146,6 +146,12 @@ static int vhost_kernel_set_vring_call(struct vhost_dev *dev,
     return vhost_kernel_call(dev, VHOST_SET_VRING_CALL, file);
 }
 
+static int vhost_kernel_set_vring_err(struct vhost_dev *dev,
+                                      struct vhost_vring_file *file)
+{
+    return vhost_kernel_call(dev, VHOST_SET_VRING_ERR, file);
+}
+
 static int vhost_kernel_set_vring_busyloop_timeout(struct vhost_dev *dev,
                                                    struct vhost_vring_state *s)
 {
@@ -309,6 +315,7 @@ const VhostOps kernel_ops = {
         .vhost_get_vring_base = vhost_kernel_get_vring_base,
         .vhost_set_vring_kick = vhost_kernel_set_vring_kick,
         .vhost_set_vring_call = vhost_kernel_set_vring_call,
+        .vhost_set_vring_err = vhost_kernel_set_vring_err,
         .vhost_set_vring_busyloop_timeout =
                                 vhost_kernel_set_vring_busyloop_timeout,
         .vhost_set_features = vhost_kernel_set_features,
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 4b9be26e84..75b8df21a4 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -1313,6 +1313,11 @@ static int vhost_user_set_vring_call(struct vhost_dev *dev,
     return vhost_set_vring_file(dev, VHOST_USER_SET_VRING_CALL, file);
 }
 
+static int vhost_user_set_vring_err(struct vhost_dev *dev,
+                                    struct vhost_vring_file *file)
+{
+    return vhost_set_vring_file(dev, VHOST_USER_SET_VRING_ERR, file);
+}
 
 static int vhost_user_get_u64(struct vhost_dev *dev, int request, uint64_t *u64)
 {
@@ -2616,6 +2621,7 @@ const VhostOps user_ops = {
         .vhost_get_vring_base = vhost_user_get_vring_base,
         .vhost_set_vring_kick = vhost_user_set_vring_kick,
         .vhost_set_vring_call = vhost_user_set_vring_call,
+        .vhost_set_vring_err = vhost_user_set_vring_err,
         .vhost_set_features = vhost_user_set_features,
         .vhost_get_features = vhost_user_get_features,
         .vhost_set_owner = vhost_user_set_owner,
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index 6c41fa13e3..0827d631c0 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -1278,6 +1278,19 @@ static int vhost_virtqueue_set_busyloop_timeout(struct vhost_dev *dev,
     return 0;
 }
 
+static void vhost_virtqueue_error_notifier(EventNotifier *n)
+{
+    struct vhost_virtqueue *vq = container_of(n, struct vhost_virtqueue,
+                                              error_notifier);
+    struct vhost_dev *dev = vq->dev;
+    int index = vq - dev->vqs;
+
+    if (event_notifier_test_and_clear(n) && dev->vdev) {
+        VHOST_OPS_DEBUG(-EINVAL,  "vhost vring error in virtqueue %d",
+                        dev->vq_index + index);
+    }
+}
+
 static int vhost_virtqueue_init(struct vhost_dev *dev,
                                 struct vhost_virtqueue *vq, int n)
 {
@@ -1299,7 +1312,27 @@ static int vhost_virtqueue_init(struct vhost_dev *dev,
 
     vq->dev = dev;
 
+    if (dev->vhost_ops->vhost_set_vring_err) {
+        r = event_notifier_init(&vq->error_notifier, 0);
+        if (r < 0) {
+            goto fail_call;
+        }
+
+        file.fd = event_notifier_get_fd(&vq->error_notifier);
+        r = dev->vhost_ops->vhost_set_vring_err(dev, &file);
+        if (r) {
+            VHOST_OPS_DEBUG(r, "vhost_set_vring_err failed");
+            goto fail_err;
+        }
+
+        event_notifier_set_handler(&vq->error_notifier,
+                                   vhost_virtqueue_error_notifier);
+    }
+
     return 0;
+
+fail_err:
+    event_notifier_cleanup(&vq->error_notifier);
 fail_call:
     event_notifier_cleanup(&vq->masked_notifier);
     return r;
@@ -1308,6 +1341,10 @@ fail_call:
 static void vhost_virtqueue_cleanup(struct vhost_virtqueue *vq)
 {
     event_notifier_cleanup(&vq->masked_notifier);
+    if (vq->dev->vhost_ops->vhost_set_vring_err) {
+        event_notifier_set_handler(&vq->error_notifier, NULL);
+        event_notifier_cleanup(&vq->error_notifier);
+    }
 }
 
 int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c
index 7c122ab957..281152d338 100644
--- a/hw/virtio/virtio-iommu.c
+++ b/hw/virtio/virtio-iommu.c
@@ -675,11 +675,10 @@ static int virtio_iommu_probe(VirtIOIOMMU *s,
 
 static int virtio_iommu_iov_to_req(struct iovec *iov,
                                    unsigned int iov_cnt,
-                                   void *req, size_t req_sz)
+                                   void *req, size_t payload_sz)
 {
-    size_t sz, payload_sz = req_sz - sizeof(struct virtio_iommu_req_tail);
+    size_t sz = iov_to_buf(iov, iov_cnt, 0, req, payload_sz);
 
-    sz = iov_to_buf(iov, iov_cnt, 0, req, payload_sz);
     if (unlikely(sz != payload_sz)) {
         return VIRTIO_IOMMU_S_INVAL;
     }
@@ -692,7 +691,8 @@ static int virtio_iommu_handle_ ## __req(VirtIOIOMMU *s,                \
                                          unsigned int iov_cnt)          \
 {                                                                       \
     struct virtio_iommu_req_ ## __req req;                              \
-    int ret = virtio_iommu_iov_to_req(iov, iov_cnt, &req, sizeof(req)); \
+    int ret = virtio_iommu_iov_to_req(iov, iov_cnt, &req,               \
+                    sizeof(req) - sizeof(struct virtio_iommu_req_tail));\
                                                                         \
     return ret ? ret : virtio_iommu_ ## __req(s, &req);                 \
 }
@@ -1322,6 +1322,14 @@ static int iommu_post_load(void *opaque, int version_id)
     VirtIOIOMMU *s = opaque;
 
     g_tree_foreach(s->domains, reconstruct_endpoints, s);
+
+    /*
+     * Memory regions are dynamically turned on/off depending on
+     * 'config.bypass' and attached domain type if there is. After
+     * migration, we need to make sure the memory regions are
+     * still correct.
+     */
+    virtio_iommu_switch_address_space_all(s);
     return 0;
 }
 
diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h
index 81bf3109f8..eab46d7f0b 100644
--- a/include/hw/virtio/vhost-backend.h
+++ b/include/hw/virtio/vhost-backend.h
@@ -69,6 +69,8 @@ typedef int (*vhost_set_vring_kick_op)(struct vhost_dev *dev,
                                        struct vhost_vring_file *file);
 typedef int (*vhost_set_vring_call_op)(struct vhost_dev *dev,
                                        struct vhost_vring_file *file);
+typedef int (*vhost_set_vring_err_op)(struct vhost_dev *dev,
+                                      struct vhost_vring_file *file);
 typedef int (*vhost_set_vring_busyloop_timeout_op)(struct vhost_dev *dev,
                                                    struct vhost_vring_state *r);
 typedef int (*vhost_set_features_op)(struct vhost_dev *dev,
@@ -145,6 +147,7 @@ typedef struct VhostOps {
     vhost_get_vring_base_op vhost_get_vring_base;
     vhost_set_vring_kick_op vhost_set_vring_kick;
     vhost_set_vring_call_op vhost_set_vring_call;
+    vhost_set_vring_err_op vhost_set_vring_err;
     vhost_set_vring_busyloop_timeout_op vhost_set_vring_busyloop_timeout;
     vhost_set_features_op vhost_set_features;
     vhost_get_features_op vhost_get_features;
diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h
index b291fe4e24..a346f23d13 100644
--- a/include/hw/virtio/vhost.h
+++ b/include/hw/virtio/vhost.h
@@ -29,6 +29,7 @@ struct vhost_virtqueue {
     unsigned long long used_phys;
     unsigned used_size;
     EventNotifier masked_notifier;
+    EventNotifier error_notifier;
     struct vhost_dev *dev;
 };
 
@@ -246,8 +247,29 @@ bool vhost_virtqueue_pending(struct vhost_dev *hdev, int n);
  */
 void vhost_virtqueue_mask(struct vhost_dev *hdev, VirtIODevice *vdev, int n,
                           bool mask);
+
+/**
+ * vhost_get_features() - return a sanitised set of feature bits
+ * @hdev: common vhost_dev structure
+ * @feature_bits: pointer to terminated table of feature bits
+ * @features: original feature set
+ *
+ * This returns a set of features bits that is an intersection of what
+ * is supported by the vhost backend (hdev->features), the supported
+ * feature_bits and the requested feature set.
+ */
 uint64_t vhost_get_features(struct vhost_dev *hdev, const int *feature_bits,
                             uint64_t features);
+
+/**
+ * vhost_ack_features() - set vhost acked_features
+ * @hdev: common vhost_dev structure
+ * @feature_bits: pointer to terminated table of feature bits
+ * @features: requested feature set
+ *
+ * This sets the internal hdev->acked_features to the intersection of
+ * the backends advertised features and the supported feature_bits.
+ */
 void vhost_ack_features(struct vhost_dev *hdev, const int *feature_bits,
                         uint64_t features);
 bool vhost_has_free_slot(void);
diff --git a/meson.build b/meson.build
index a113078f1a..65a885ea69 100644
--- a/meson.build
+++ b/meson.build
@@ -1516,7 +1516,7 @@ have_vhost_user_blk_server = get_option('vhost_user_blk_server') \
            error_message: 'vhost_user_blk_server requires linux') \
   .require(have_vhost_user,
            error_message: 'vhost_user_blk_server requires vhost-user support') \
-  .disable_auto_if(not have_system) \
+  .disable_auto_if(not have_tools and not have_system) \
   .allowed()
 
 if get_option('fuse').disabled() and get_option('fuse_lseek').enabled()
diff --git a/subprojects/libvhost-user/libvhost-user.c b/subprojects/libvhost-user/libvhost-user.c
index b4cc3c2d68..ffed4729a3 100644
--- a/subprojects/libvhost-user/libvhost-user.c
+++ b/subprojects/libvhost-user/libvhost-user.c
@@ -779,15 +779,9 @@ vu_add_mem_reg(VuDev *dev, VhostUserMsg *vmsg) {
 
         /* Send the message back to qemu with the addresses filled in. */
         vmsg->fd_num = 0;
-        if (!vu_send_reply(dev, dev->sock, vmsg)) {
-            vu_panic(dev, "failed to respond to add-mem-region for postcopy");
-            return false;
-        }
-
         DPRINT("Successfully added new region in postcopy\n");
         dev->nregions++;
-        return false;
-
+        return true;
     } else {
         for (i = 0; i < dev->max_queues; i++) {
             if (dev->vq[i].vring.desc) {
@@ -1827,18 +1821,11 @@ vu_handle_vring_kick(VuDev *dev, VhostUserMsg *vmsg)
 
 static bool vu_handle_get_max_memslots(VuDev *dev, VhostUserMsg *vmsg)
 {
-    vmsg->flags = VHOST_USER_REPLY_MASK | VHOST_USER_VERSION;
-    vmsg->size  = sizeof(vmsg->payload.u64);
-    vmsg->payload.u64 = VHOST_USER_MAX_RAM_SLOTS;
-    vmsg->fd_num = 0;
-
-    if (!vu_message_write(dev, dev->sock, vmsg)) {
-        vu_panic(dev, "Failed to send max ram slots: %s\n", strerror(errno));
-    }
+    vmsg_set_reply_u64(vmsg, VHOST_USER_MAX_RAM_SLOTS);
 
     DPRINT("u64: 0x%016"PRIx64"\n", (uint64_t) VHOST_USER_MAX_RAM_SLOTS);
 
-    return false;
+    return true;
 }
 
 static bool