qemu-kvm/SOURCES/kvm-vdpa-net-move-iova-tree-creation-from-init-to-start.patch

From 293e249644c14b2bd19dd6a3f08a0e18ec040200 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Fri, 3 Mar 2023 18:24:32 +0100
Subject: [PATCH 1/4] vdpa net: move iova tree creation from init to start
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

RH-Author: Laurent Vivier <lvivier@redhat.com>
RH-MergeRequest: 298: Fix qemu core dump with "x-svq=on" when hot-plugging a NIC
RH-Jira: RHEL-1060
RH-Acked-by: Eugenio Pérez <eperezma@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/3] f85a05eb528820adf4a3c0cad2950b4ab500d5fe

JIRA: https://issues.redhat.com/browse/RHEL-1060

Only create iova_tree if and when it is needed.

The cleanup keeps being responsible for the last VQ but this change
allows it to merge both cleanup functions.

Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20230303172445.1089785-2-eperezma@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 00ef422e9fbfef1fb40447b08826db0951d788dd)

Conflicts

    because of missing commit

    bf7a2ad8b6df ("vdpa: harden the error path if get_iova_range failed")

Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---
 net/vhost-vdpa.c | 113 ++++++++++++++++++++++++++++++++++-------------
 1 file changed, 83 insertions(+), 30 deletions(-)

diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index 1b4fec59a2..a914348e2a 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -178,7 +178,6 @@ err_init:
 static void vhost_vdpa_cleanup(NetClientState *nc)
 {
     VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
-    struct vhost_dev *dev = &s->vhost_net->dev;
 
     /*
      * If a peer NIC is attached, do not cleanup anything.
@@ -190,9 +189,6 @@ static void vhost_vdpa_cleanup(NetClientState *nc)
     }
     qemu_vfree(s->cvq_cmd_out_buffer);
     qemu_vfree(s->status);
-    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);
@@ -242,10 +238,64 @@ static ssize_t vhost_vdpa_receive(NetClientState *nc, const uint8_t *buf,
     return size;
 }
 
+/** From any vdpa net client, get the netclient of the first queue pair */
+static VhostVDPAState *vhost_vdpa_net_first_nc_vdpa(VhostVDPAState *s)
+{
+    NICState *nic = qemu_get_nic(s->nc.peer);
+    NetClientState *nc0 = qemu_get_peer(nic->ncs, 0);
+
+    return DO_UPCAST(VhostVDPAState, nc, nc0);
+}
+
+static void vhost_vdpa_net_data_start_first(VhostVDPAState *s)
+{
+    struct vhost_vdpa *v = &s->vhost_vdpa;
+
+    if (v->shadow_vqs_enabled) {
+        v->iova_tree = vhost_iova_tree_new(v->iova_range.first,
+                                           v->iova_range.last);
+    }
+}
+
+static int vhost_vdpa_net_data_start(NetClientState *nc)
+{
+    VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
+    struct vhost_vdpa *v = &s->vhost_vdpa;
+
+    assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
+
+    if (v->index == 0) {
+        vhost_vdpa_net_data_start_first(s);
+        return 0;
+    }
+
+    if (v->shadow_vqs_enabled) {
+        VhostVDPAState *s0 = vhost_vdpa_net_first_nc_vdpa(s);
+        v->iova_tree = s0->vhost_vdpa.iova_tree;
+    }
+
+    return 0;
+}
+
+static void vhost_vdpa_net_client_stop(NetClientState *nc)
+{
+    VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
+    struct vhost_dev *dev;
+
+    assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
+
+    dev = s->vhost_vdpa.dev;
+    if (dev->vq_index + dev->nvqs == dev->vq_index_end) {
+        g_clear_pointer(&s->vhost_vdpa.iova_tree, vhost_iova_tree_delete);
+    }
+}
+
 static NetClientInfo net_vhost_vdpa_info = {
         .type = NET_CLIENT_DRIVER_VHOST_VDPA,
         .size = sizeof(VhostVDPAState),
         .receive = vhost_vdpa_receive,
+        .start = vhost_vdpa_net_data_start,
+        .stop = vhost_vdpa_net_client_stop,
         .cleanup = vhost_vdpa_cleanup,
         .has_vnet_hdr = vhost_vdpa_has_vnet_hdr,
         .has_ufo = vhost_vdpa_has_ufo,
@@ -359,7 +409,7 @@ dma_map_err:
 
 static int vhost_vdpa_net_cvq_start(NetClientState *nc)
 {
-    VhostVDPAState *s;
+    VhostVDPAState *s, *s0;
     struct vhost_vdpa *v;
     uint64_t backend_features;
     int64_t cvq_group;
@@ -423,8 +473,6 @@ static int vhost_vdpa_net_cvq_start(NetClientState *nc)
         return r;
     }
 
-    v->iova_tree = vhost_iova_tree_new(v->iova_range.first,
-                                       v->iova_range.last);
     v->shadow_vqs_enabled = true;
     s->vhost_vdpa.address_space_id = VHOST_VDPA_NET_CVQ_ASID;
 
@@ -433,6 +481,27 @@ out:
         return 0;
     }
 
+    s0 = vhost_vdpa_net_first_nc_vdpa(s);
+    if (s0->vhost_vdpa.iova_tree) {
+        /*
+         * SVQ is already configured for all virtqueues.  Reuse IOVA tree for
+         * simplicity, whether CVQ shares ASID with guest or not, because:
+         * - Memory listener need access to guest's memory addresses allocated
+         *   in the IOVA tree.
+         * - There should be plenty of IOVA address space for both ASID not to
+         *   worry about collisions between them.  Guest's translations are
+         *   still validated with virtio virtqueue_pop so there is no risk for
+         *   the guest to access memory that it shouldn't.
+         *
+         * To allocate a iova tree per ASID is doable but it complicates the
+         * code and it is not worth it for the moment.
+         */
+        v->iova_tree = s0->vhost_vdpa.iova_tree;
+    } else {
+        v->iova_tree = vhost_iova_tree_new(v->iova_range.first,
+                                           v->iova_range.last);
+    }
+
     r = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer,
                                vhost_vdpa_net_cvq_cmd_page_len(), false);
     if (unlikely(r < 0)) {
@@ -457,15 +526,9 @@ static void vhost_vdpa_net_cvq_stop(NetClientState *nc)
     if (s->vhost_vdpa.shadow_vqs_enabled) {
         vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer);
         vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->status);
-        if (!s->always_svq) {
-            /*
-             * If only the CVQ is shadowed we can delete this safely.
-             * If all the VQs are shadows this will be needed by the time the
-             * device is started again to register SVQ vrings and similar.
-             */
-            g_clear_pointer(&s->vhost_vdpa.iova_tree, vhost_iova_tree_delete);
-        }
     }
+
+    vhost_vdpa_net_client_stop(nc);
 }
 
 static ssize_t vhost_vdpa_net_cvq_add(VhostVDPAState *s, size_t out_len,
@@ -675,8 +738,7 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
                                        int nvqs,
                                        bool is_datapath,
                                        bool svq,
-                                       struct vhost_vdpa_iova_range iova_range,
-                                       VhostIOVATree *iova_tree)
+                                       struct vhost_vdpa_iova_range iova_range)
 {
     NetClientState *nc = NULL;
     VhostVDPAState *s;
@@ -698,7 +760,6 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
     s->vhost_vdpa.shadow_vqs_enabled = svq;
     s->vhost_vdpa.iova_range = iova_range;
     s->vhost_vdpa.shadow_data = 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());
@@ -776,7 +837,6 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
     uint64_t features;
     int vdpa_device_fd;
     g_autofree NetClientState **ncs = NULL;
-    g_autoptr(VhostIOVATree) iova_tree = NULL;
     struct vhost_vdpa_iova_range iova_range;
     NetClientState *nc;
     int queue_pairs, r, i = 0, has_cvq = 0;
@@ -822,12 +882,8 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
     }
 
     vhost_vdpa_get_iova_range(vdpa_device_fd, &iova_range);
-    if (opts->x_svq) {
-        if (!vhost_vdpa_net_valid_svq_features(features, errp)) {
-            goto err_svq;
-        }
-
-        iova_tree = vhost_iova_tree_new(iova_range.first, iova_range.last);
+    if (opts->x_svq && !vhost_vdpa_net_valid_svq_features(features, errp)) {
+        goto err;
     }
 
     ncs = g_malloc0(sizeof(*ncs) * queue_pairs);
@@ -835,7 +891,7 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
     for (i = 0; i < queue_pairs; i++) {
         ncs[i] = net_vhost_vdpa_init(peer, TYPE_VHOST_VDPA, name,
                                      vdpa_device_fd, i, 2, true, opts->x_svq,
-                                     iova_range, iova_tree);
+                                     iova_range);
         if (!ncs[i])
             goto err;
     }
@@ -843,13 +899,11 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
     if (has_cvq) {
         nc = net_vhost_vdpa_init(peer, TYPE_VHOST_VDPA, name,
                                  vdpa_device_fd, i, 1, false,
-                                 opts->x_svq, iova_range, iova_tree);
+                                 opts->x_svq, iova_range);
         if (!nc)
             goto err;
     }
 
-    /* iova_tree ownership belongs to last NetClientState */
-    g_steal_pointer(&iova_tree);
     return 0;
 
 err:
@@ -859,7 +913,6 @@ err:
         }
     }
 
-err_svq:
     qemu_close(vdpa_device_fd);
 
     return -1;
-- 
2.39.3