summary refs log tree commit diff stats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/colo-compare.c2
-rw-r--r--net/colo.c11
-rw-r--r--net/filter-rewriter.c2
-rw-r--r--net/meson.build3
-rw-r--r--net/trace-events1
-rw-r--r--net/vhost-vdpa-stub.c21
-rw-r--r--net/vhost-vdpa.c357
7 files changed, 379 insertions, 18 deletions
diff --git a/net/colo-compare.c b/net/colo-compare.c
index d5d0965805..787c740f14 100644
--- a/net/colo-compare.c
+++ b/net/colo-compare.c
@@ -1323,7 +1323,7 @@ static void colo_compare_complete(UserCreatable *uc, Error **errp)
     s->connection_track_table = g_hash_table_new_full(connection_key_hash,
                                                       connection_key_equal,
                                                       g_free,
-                                                      connection_destroy);
+                                                      NULL);
 
     colo_compare_iothread(s);
 
diff --git a/net/colo.c b/net/colo.c
index 1f8162f59f..6b0ff562ad 100644
--- a/net/colo.c
+++ b/net/colo.c
@@ -46,7 +46,14 @@ int parse_packet_early(Packet *pkt)
     static const uint8_t vlan[] = {0x81, 0x00};
     uint8_t *data = pkt->data + pkt->vnet_hdr_len;
     uint16_t l3_proto;
-    ssize_t l2hdr_len = eth_get_l2_hdr_length(data);
+    ssize_t l2hdr_len;
+
+    if (data == NULL) {
+        trace_colo_proxy_main_vnet_info("This packet is not parsed correctly, "
+                                        "pkt->vnet_hdr_len", pkt->vnet_hdr_len);
+        return 1;
+    }
+    l2hdr_len = eth_get_l2_hdr_length(data);
 
     if (pkt->size < ETH_HLEN + pkt->vnet_hdr_len) {
         trace_colo_proxy_main("pkt->size < ETH_HLEN");
@@ -218,7 +225,7 @@ Connection *connection_get(GHashTable *connection_track_table,
             /*
              * clear the conn_list
              */
-            while (!g_queue_is_empty(conn_list)) {
+            while (conn_list && !g_queue_is_empty(conn_list)) {
                 connection_destroy(g_queue_pop_head(conn_list));
             }
         }
diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
index bf05023dc3..c18c4c2019 100644
--- a/net/filter-rewriter.c
+++ b/net/filter-rewriter.c
@@ -383,7 +383,7 @@ static void colo_rewriter_setup(NetFilterState *nf, Error **errp)
     s->connection_track_table = g_hash_table_new_full(connection_key_hash,
                                                       connection_key_equal,
                                                       g_free,
-                                                      connection_destroy);
+                                                      NULL);
     s->incoming_queue = qemu_new_net_queue(qemu_netfilter_pass_to_next, nf);
 }
 
diff --git a/net/meson.build b/net/meson.build
index 754e2d1d40..d1be76daf3 100644
--- a/net/meson.build
+++ b/net/meson.build
@@ -41,7 +41,8 @@ endif
 softmmu_ss.add(when: 'CONFIG_POSIX', if_true: files(tap_posix))
 softmmu_ss.add(when: 'CONFIG_WIN32', if_true: files('tap-win32.c'))
 if have_vhost_net_vdpa
-  softmmu_ss.add(files('vhost-vdpa.c'))
+  softmmu_ss.add(when: 'CONFIG_VIRTIO_NET', if_true: files('vhost-vdpa.c'), if_false: files('vhost-vdpa-stub.c'))
+  softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost-vdpa-stub.c'))
 endif
 
 vmnet_files = files(
diff --git a/net/trace-events b/net/trace-events
index d7a17256cc..6af927b4b9 100644
--- a/net/trace-events
+++ b/net/trace-events
@@ -9,6 +9,7 @@ vhost_user_event(const char *chr, int event) "chr: %s got event: %d"
 
 # colo.c
 colo_proxy_main(const char *chr) ": %s"
+colo_proxy_main_vnet_info(const char *sta, int size) ": %s = %d"
 
 # colo-compare.c
 colo_compare_main(const char *chr) ": %s"
diff --git a/net/vhost-vdpa-stub.c b/net/vhost-vdpa-stub.c
new file mode 100644
index 0000000000..1732ed2443
--- /dev/null
+++ b/net/vhost-vdpa-stub.c
@@ -0,0 +1,21 @@
+/*
+ * vhost-vdpa-stub.c
+ *
+ * Copyright (c) 2022 Red Hat, Inc.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "clients.h"
+#include "net/vhost-vdpa.h"
+#include "qapi/error.h"
+
+int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
+                        NetClientState *peer, Error **errp)
+{
+    error_setg(errp, "vhost-vdpa requires frontend driver virtio-net-*");
+    return -1;
+}
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index df1e69ee72..6abad276a6 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -11,11 +11,14 @@
 
 #include "qemu/osdep.h"
 #include "clients.h"
+#include "hw/virtio/virtio-net.h"
 #include "net/vhost_net.h"
 #include "net/vhost-vdpa.h"
 #include "hw/virtio/vhost-vdpa.h"
 #include "qemu/config-file.h"
 #include "qemu/error-report.h"
+#include "qemu/log.h"
+#include "qemu/memalign.h"
 #include "qemu/option.h"
 #include "qapi/error.h"
 #include <linux/vhost.h>
@@ -30,6 +33,9 @@ typedef struct VhostVDPAState {
     NetClientState nc;
     struct vhost_vdpa vhost_vdpa;
     VHostNetState *vhost_net;
+
+    /* Control commands shadow buffers */
+    void *cvq_cmd_out_buffer, *cvq_cmd_in_buffer;
     bool started;
 } VhostVDPAState;
 
@@ -69,6 +75,28 @@ const int vdpa_feature_bits[] = {
     VHOST_INVALID_FEATURE_BIT
 };
 
+/** Supported device specific feature bits with SVQ */
+static const uint64_t vdpa_svq_device_features =
+    BIT_ULL(VIRTIO_NET_F_CSUM) |
+    BIT_ULL(VIRTIO_NET_F_GUEST_CSUM) |
+    BIT_ULL(VIRTIO_NET_F_MTU) |
+    BIT_ULL(VIRTIO_NET_F_MAC) |
+    BIT_ULL(VIRTIO_NET_F_GUEST_TSO4) |
+    BIT_ULL(VIRTIO_NET_F_GUEST_TSO6) |
+    BIT_ULL(VIRTIO_NET_F_GUEST_ECN) |
+    BIT_ULL(VIRTIO_NET_F_GUEST_UFO) |
+    BIT_ULL(VIRTIO_NET_F_HOST_TSO4) |
+    BIT_ULL(VIRTIO_NET_F_HOST_TSO6) |
+    BIT_ULL(VIRTIO_NET_F_HOST_ECN) |
+    BIT_ULL(VIRTIO_NET_F_HOST_UFO) |
+    BIT_ULL(VIRTIO_NET_F_MRG_RXBUF) |
+    BIT_ULL(VIRTIO_NET_F_STATUS) |
+    BIT_ULL(VIRTIO_NET_F_CTRL_VQ) |
+    BIT_ULL(VIRTIO_F_ANY_LAYOUT) |
+    BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR) |
+    BIT_ULL(VIRTIO_NET_F_RSC_EXT) |
+    BIT_ULL(VIRTIO_NET_F_STANDBY);
+
 VHostNetState *vhost_vdpa_get_vhost_net(NetClientState *nc)
 {
     VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
@@ -127,7 +155,13 @@ err_init:
 static void vhost_vdpa_cleanup(NetClientState *nc)
 {
     VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
+    struct vhost_dev *dev = &s->vhost_net->dev;
 
+    qemu_vfree(s->cvq_cmd_out_buffer);
+    qemu_vfree(s->cvq_cmd_in_buffer);
+    if (dev->vq_index + dev->nvqs == dev->vq_index_end) {
+        g_clear_pointer(&s->vhost_vdpa.iova_tree, vhost_iova_tree_delete);
+    }
     if (s->vhost_net) {
         vhost_net_cleanup(s->vhost_net);
         g_free(s->vhost_net);
@@ -187,13 +221,251 @@ static NetClientInfo net_vhost_vdpa_info = {
         .check_peer_type = vhost_vdpa_check_peer_type,
 };
 
+static void vhost_vdpa_cvq_unmap_buf(struct vhost_vdpa *v, void *addr)
+{
+    VhostIOVATree *tree = v->iova_tree;
+    DMAMap needle = {
+        /*
+         * No need to specify size or to look for more translations since
+         * this contiguous chunk was allocated by us.
+         */
+        .translated_addr = (hwaddr)(uintptr_t)addr,
+    };
+    const DMAMap *map = vhost_iova_tree_find_iova(tree, &needle);
+    int r;
+
+    if (unlikely(!map)) {
+        error_report("Cannot locate expected map");
+        return;
+    }
+
+    r = vhost_vdpa_dma_unmap(v, map->iova, map->size + 1);
+    if (unlikely(r != 0)) {
+        error_report("Device cannot unmap: %s(%d)", g_strerror(r), r);
+    }
+
+    vhost_iova_tree_remove(tree, map);
+}
+
+static size_t vhost_vdpa_net_cvq_cmd_len(void)
+{
+    /*
+     * MAC_TABLE_SET is the ctrl command that produces the longer out buffer.
+     * In buffer is always 1 byte, so it should fit here
+     */
+    return sizeof(struct virtio_net_ctrl_hdr) +
+           2 * sizeof(struct virtio_net_ctrl_mac) +
+           MAC_TABLE_ENTRIES * ETH_ALEN;
+}
+
+static size_t vhost_vdpa_net_cvq_cmd_page_len(void)
+{
+    return ROUND_UP(vhost_vdpa_net_cvq_cmd_len(), qemu_real_host_page_size());
+}
+
+/** Copy and map a guest buffer. */
+static bool vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v,
+                                   const struct iovec *out_data,
+                                   size_t out_num, size_t data_len, void *buf,
+                                   size_t *written, bool write)
+{
+    DMAMap map = {};
+    int r;
+
+    if (unlikely(!data_len)) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid legnth of %s buffer\n",
+                      __func__, write ? "in" : "out");
+        return false;
+    }
+
+    *written = iov_to_buf(out_data, out_num, 0, buf, data_len);
+    map.translated_addr = (hwaddr)(uintptr_t)buf;
+    map.size = vhost_vdpa_net_cvq_cmd_page_len() - 1;
+    map.perm = write ? IOMMU_RW : IOMMU_RO,
+    r = vhost_iova_tree_map_alloc(v->iova_tree, &map);
+    if (unlikely(r != IOVA_OK)) {
+        error_report("Cannot map injected element");
+        return false;
+    }
+
+    r = vhost_vdpa_dma_map(v, map.iova, vhost_vdpa_net_cvq_cmd_page_len(), buf,
+                           !write);
+    if (unlikely(r < 0)) {
+        goto dma_map_err;
+    }
+
+    return true;
+
+dma_map_err:
+    vhost_iova_tree_remove(v->iova_tree, &map);
+    return false;
+}
+
+/**
+ * Copy the guest element into a dedicated buffer suitable to be sent to NIC
+ *
+ * @iov: [0] is the out buffer, [1] is the in one
+ */
+static bool vhost_vdpa_net_cvq_map_elem(VhostVDPAState *s,
+                                        VirtQueueElement *elem,
+                                        struct iovec *iov)
+{
+    size_t in_copied;
+    bool ok;
+
+    iov[0].iov_base = s->cvq_cmd_out_buffer;
+    ok = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, elem->out_sg, elem->out_num,
+                                vhost_vdpa_net_cvq_cmd_len(), iov[0].iov_base,
+                                &iov[0].iov_len, false);
+    if (unlikely(!ok)) {
+        return false;
+    }
+
+    iov[1].iov_base = s->cvq_cmd_in_buffer;
+    ok = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, NULL, 0,
+                                sizeof(virtio_net_ctrl_ack), iov[1].iov_base,
+                                &in_copied, true);
+    if (unlikely(!ok)) {
+        vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer);
+        return false;
+    }
+
+    iov[1].iov_len = sizeof(virtio_net_ctrl_ack);
+    return true;
+}
+
+/**
+ * Do not forward commands not supported by SVQ. Otherwise, the device could
+ * accept it and qemu would not know how to update the device model.
+ */
+static bool vhost_vdpa_net_cvq_validate_cmd(const struct iovec *out,
+                                            size_t out_num)
+{
+    struct virtio_net_ctrl_hdr ctrl;
+    size_t n;
+
+    n = iov_to_buf(out, out_num, 0, &ctrl, sizeof(ctrl));
+    if (unlikely(n < sizeof(ctrl))) {
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "%s: invalid legnth of out buffer %zu\n", __func__, n);
+        return false;
+    }
+
+    switch (ctrl.class) {
+    case VIRTIO_NET_CTRL_MAC:
+        switch (ctrl.cmd) {
+        case VIRTIO_NET_CTRL_MAC_ADDR_SET:
+            return true;
+        default:
+            qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid mac cmd %u\n",
+                          __func__, ctrl.cmd);
+        };
+        break;
+    default:
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid control class %u\n",
+                      __func__, ctrl.class);
+    };
+
+    return false;
+}
+
+/**
+ * Validate and copy control virtqueue commands.
+ *
+ * Following QEMU guidelines, we offer a copy of the buffers to the device to
+ * prevent TOCTOU bugs.
+ */
+static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq,
+                                            VirtQueueElement *elem,
+                                            void *opaque)
+{
+    VhostVDPAState *s = opaque;
+    size_t in_len, dev_written;
+    virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
+    /* out and in buffers sent to the device */
+    struct iovec dev_buffers[2] = {
+        { .iov_base = s->cvq_cmd_out_buffer },
+        { .iov_base = s->cvq_cmd_in_buffer },
+    };
+    /* in buffer used for device model */
+    const struct iovec in = {
+        .iov_base = &status,
+        .iov_len = sizeof(status),
+    };
+    int r = -EINVAL;
+    bool ok;
+
+    ok = vhost_vdpa_net_cvq_map_elem(s, elem, dev_buffers);
+    if (unlikely(!ok)) {
+        goto out;
+    }
+
+    ok = vhost_vdpa_net_cvq_validate_cmd(&dev_buffers[0], 1);
+    if (unlikely(!ok)) {
+        goto out;
+    }
+
+    r = vhost_svq_add(svq, &dev_buffers[0], 1, &dev_buffers[1], 1, elem);
+    if (unlikely(r != 0)) {
+        if (unlikely(r == -ENOSPC)) {
+            qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n",
+                          __func__);
+        }
+        goto out;
+    }
+
+    /*
+     * We can poll here since we've had BQL from the time we sent the
+     * descriptor. Also, we need to take the answer before SVQ pulls by itself,
+     * when BQL is released
+     */
+    dev_written = vhost_svq_poll(svq);
+    if (unlikely(dev_written < sizeof(status))) {
+        error_report("Insufficient written data (%zu)", dev_written);
+        goto out;
+    }
+
+    memcpy(&status, dev_buffers[1].iov_base, sizeof(status));
+    if (status != VIRTIO_NET_OK) {
+        goto out;
+    }
+
+    status = VIRTIO_NET_ERR;
+    virtio_net_handle_ctrl_iov(svq->vdev, &in, 1, dev_buffers, 1);
+    if (status != VIRTIO_NET_OK) {
+        error_report("Bad CVQ processing in model");
+    }
+
+out:
+    in_len = iov_from_buf(elem->in_sg, elem->in_num, 0, &status,
+                          sizeof(status));
+    if (unlikely(in_len < sizeof(status))) {
+        error_report("Bad device CVQ written length");
+    }
+    vhost_svq_push_elem(svq, elem, MIN(in_len, sizeof(status)));
+    g_free(elem);
+    if (dev_buffers[0].iov_base) {
+        vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, dev_buffers[0].iov_base);
+    }
+    if (dev_buffers[1].iov_base) {
+        vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, dev_buffers[1].iov_base);
+    }
+    return r;
+}
+
+static const VhostShadowVirtqueueOps vhost_vdpa_net_svq_ops = {
+    .avail_handler = vhost_vdpa_net_handle_ctrl_avail,
+};
+
 static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
                                            const char *device,
                                            const char *name,
                                            int vdpa_device_fd,
                                            int queue_pair_index,
                                            int nvqs,
-                                           bool is_datapath)
+                                           bool is_datapath,
+                                           bool svq,
+                                           VhostIOVATree *iova_tree)
 {
     NetClientState *nc = NULL;
     VhostVDPAState *s;
@@ -211,6 +483,21 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
 
     s->vhost_vdpa.device_fd = vdpa_device_fd;
     s->vhost_vdpa.index = queue_pair_index;
+    s->vhost_vdpa.shadow_vqs_enabled = svq;
+    s->vhost_vdpa.iova_tree = iova_tree;
+    if (!is_datapath) {
+        s->cvq_cmd_out_buffer = qemu_memalign(qemu_real_host_page_size(),
+                                            vhost_vdpa_net_cvq_cmd_page_len());
+        memset(s->cvq_cmd_out_buffer, 0, vhost_vdpa_net_cvq_cmd_page_len());
+        s->cvq_cmd_in_buffer = qemu_memalign(qemu_real_host_page_size(),
+                                            vhost_vdpa_net_cvq_cmd_page_len());
+        memset(s->cvq_cmd_in_buffer, 0, vhost_vdpa_net_cvq_cmd_page_len());
+
+        s->vhost_vdpa.shadow_vq_ops = &vhost_vdpa_net_svq_ops;
+        s->vhost_vdpa.shadow_vq_ops_opaque = s;
+        error_setg(&s->vhost_vdpa.migration_blocker,
+                   "Migration disabled: vhost-vdpa uses CVQ.");
+    }
     ret = vhost_vdpa_add(nc, (void *)&s->vhost_vdpa, queue_pair_index, nvqs);
     if (ret) {
         qemu_del_net_client(nc);
@@ -219,20 +506,32 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
     return nc;
 }
 
-static int vhost_vdpa_get_max_queue_pairs(int fd, int *has_cvq, Error **errp)
+static int vhost_vdpa_get_iova_range(int fd,
+                                     struct vhost_vdpa_iova_range *iova_range)
+{
+    int ret = ioctl(fd, VHOST_VDPA_GET_IOVA_RANGE, iova_range);
+
+    return ret < 0 ? -errno : 0;
+}
+
+static int vhost_vdpa_get_features(int fd, uint64_t *features, Error **errp)
+{
+    int ret = ioctl(fd, VHOST_GET_FEATURES, features);
+    if (unlikely(ret < 0)) {
+        error_setg_errno(errp, errno,
+                         "Fail to query features from vhost-vDPA device");
+    }
+    return ret;
+}
+
+static int vhost_vdpa_get_max_queue_pairs(int fd, uint64_t features,
+                                          int *has_cvq, Error **errp)
 {
     unsigned long config_size = offsetof(struct vhost_vdpa_config, buf);
     g_autofree struct vhost_vdpa_config *config = NULL;
     __virtio16 *max_queue_pairs;
-    uint64_t features;
     int ret;
 
-    ret = ioctl(fd, VHOST_GET_FEATURES, &features);
-    if (ret) {
-        error_setg(errp, "Fail to query features from vhost-vDPA device");
-        return ret;
-    }
-
     if (features & (1 << VIRTIO_NET_F_CTRL_VQ)) {
         *has_cvq = 1;
     } else {
@@ -262,10 +561,12 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
                         NetClientState *peer, Error **errp)
 {
     const NetdevVhostVDPAOptions *opts;
+    uint64_t features;
     int vdpa_device_fd;
     g_autofree NetClientState **ncs = NULL;
+    g_autoptr(VhostIOVATree) iova_tree = NULL;
     NetClientState *nc;
-    int queue_pairs, i, has_cvq = 0;
+    int queue_pairs, r, i, has_cvq = 0;
 
     assert(netdev->type == NET_CLIENT_DRIVER_VHOST_VDPA);
     opts = &netdev->u.vhost_vdpa;
@@ -279,29 +580,57 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
         return -errno;
     }
 
-    queue_pairs = vhost_vdpa_get_max_queue_pairs(vdpa_device_fd,
+    r = vhost_vdpa_get_features(vdpa_device_fd, &features, errp);
+    if (unlikely(r < 0)) {
+        return r;
+    }
+
+    queue_pairs = vhost_vdpa_get_max_queue_pairs(vdpa_device_fd, features,
                                                  &has_cvq, errp);
     if (queue_pairs < 0) {
         qemu_close(vdpa_device_fd);
         return queue_pairs;
     }
 
+    if (opts->x_svq) {
+        struct vhost_vdpa_iova_range iova_range;
+
+        uint64_t invalid_dev_features =
+            features & ~vdpa_svq_device_features &
+            /* Transport are all accepted at this point */
+            ~MAKE_64BIT_MASK(VIRTIO_TRANSPORT_F_START,
+                             VIRTIO_TRANSPORT_F_END - VIRTIO_TRANSPORT_F_START);
+
+        if (invalid_dev_features) {
+            error_setg(errp, "vdpa svq does not work with features 0x%" PRIx64,
+                       invalid_dev_features);
+            goto err_svq;
+        }
+
+        vhost_vdpa_get_iova_range(vdpa_device_fd, &iova_range);
+        iova_tree = vhost_iova_tree_new(iova_range.first, iova_range.last);
+    }
+
     ncs = g_malloc0(sizeof(*ncs) * queue_pairs);
 
     for (i = 0; i < queue_pairs; i++) {
         ncs[i] = net_vhost_vdpa_init(peer, TYPE_VHOST_VDPA, name,
-                                     vdpa_device_fd, i, 2, true);
+                                     vdpa_device_fd, i, 2, true, opts->x_svq,
+                                     iova_tree);
         if (!ncs[i])
             goto err;
     }
 
     if (has_cvq) {
         nc = net_vhost_vdpa_init(peer, TYPE_VHOST_VDPA, name,
-                                 vdpa_device_fd, i, 1, false);
+                                 vdpa_device_fd, i, 1, false,
+                                 opts->x_svq, iova_tree);
         if (!nc)
             goto err;
     }
 
+    /* iova_tree ownership belongs to last NetClientState */
+    g_steal_pointer(&iova_tree);
     return 0;
 
 err:
@@ -310,6 +639,8 @@ err:
             qemu_del_net_client(ncs[i]);
         }
     }
+
+err_svq:
     qemu_close(vdpa_device_fd);
 
     return -1;