On 2/13/2023 3:14 AM, Eugenio Perez Martin wrote:
OK, so this corresponds to the case where live migration is not started and CVQ starts in its own address space of VHOST_VDPA_NET_CVQ_ASID. Thanks for explaining it!On Mon, Feb 13, 2023 at 7:51 AM Si-Wei Liu <si-wei.liu@xxxxxxxxxx> wrote:On 2/8/2023 1:42 AM, Eugenio Pérez wrote:Only create iova_tree if and when it is needed. The cleanup keeps being responsible of last VQ but this change allows it to merge both cleanup functions. Signed-off-by: Eugenio Pérez <eperezma@xxxxxxxxxx> Acked-by: Jason Wang <jasowang@xxxxxxxxxx> --- net/vhost-vdpa.c | 99 ++++++++++++++++++++++++++++++++++-------------- 1 file changed, 71 insertions(+), 28 deletions(-) diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c index de5ed8ff22..a9e6c8f28e 100644 --- a/net/vhost-vdpa.c +++ b/net/vhost-vdpa.c @@ -178,13 +178,9 @@ 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->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); @@ -234,10 +230,64 @@ static ssize_t vhost_vdpa_receive(NetClientState *nc, const uint8_t *buf, return size; } +/** From any vdpa net client, get the netclient of 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, @@ -351,7 +401,7 @@ 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; @@ -425,6 +475,15 @@ out: return 0; } + s0 = vhost_vdpa_net_first_nc_vdpa(s); + if (s0->vhost_vdpa.iova_tree) { + /* SVQ is already configured for all virtqueues */ + v->iova_tree = s0->vhost_vdpa.iova_tree; + } else { + v->iova_tree = vhost_iova_tree_new(v->iova_range.first, + v->iova_range.last);I wonder how this case could happen, vhost_vdpa_net_data_start_first() should've allocated an iova tree on the first data vq. Is zero data vq ever possible on net vhost-vdpa?It's the case of the current qemu master when only CVQ is being shadowed. It's not that "there are no data vq": If that case were possible, CVQ vhost-vdpa state would be s0. The case is that since only CVQ vhost-vdpa is the one being migrated, only CVQ has an iova tree.
I wonder what is the reason to share the iova tree when migration starts, I think CVQ may stay on its own VHOST_VDPA_NET_CVQ_ASID still?With this series applied and with no migration running, the case is the same as before: only SVQ gets shadowed. When migration starts, all vqs are migrated, and share iova tree.
Actually there's discrepancy in vhost_vdpa_net_log_global_enable(), I don't see explicit code to switch from VHOST_VDPA_NET_CVQ_ASID to VHOST_VDPA_GUEST_PA_ASID for the CVQ. This is the address space I collision I mentioned earlier:
9585@1676093788.259201:vhost_vdpa_dma_map vdpa:0x7ff13088a190 fd: 16 msg_type: 2 asid: 0 iova: 0x1000 size: 0x2000 uaddr: 0x55a5a7ff3000 perm: 0x1 type: 2 9585@1676093788.279923:vhost_vdpa_dma_map vdpa:0x7ff13088a190 fd: 16 msg_type: 2 asid: 0 iova: 0x3000 size: 0x1000 uaddr: 0x55a5a7ff6000 perm: 0x3 type: 2 9585@1676093788.290529:vhost_vdpa_set_vring_addr dev: 0x55a5a77cec20 index: 0 flags: 0x0 desc_user_addr: 0x1000 used_user_addr: 0x3000 avail_user_addr: 0x2000 log_guest_addr: 0x0
: :9585@1676093788.543567:vhost_vdpa_dma_map vdpa:0x7ff1302b6190 fd: 16 msg_type: 2 asid: 0 iova: 0x16000 size: 0x2000 uaddr: 0x55a5a7959000 perm: 0x1 type: 2 9585@1676093788.576923:vhost_vdpa_dma_map vdpa:0x7ff1302b6190 fd: 16 msg_type: 2 asid: 0 iova: 0x18000 size: 0x1000 uaddr: 0x55a5a795c000 perm: 0x3 type: 2 9585@1676093788.593881:vhost_vdpa_set_vring_addr dev: 0x55a5a7580930 index: 7 flags: 0x0 desc_user_addr: 0x16000 used_user_addr: 0x18000 avail_user_addr: 0x17000 log_guest_addr: 0x0 9585@1676093788.593904:vhost_vdpa_dma_map vdpa:0x7ff13026d190 fd: 16 msg_type: 2 asid: 1 iova: 0x19000 size: 0x1000 uaddr: 0x55a5a77f8000 perm: 0x1 type: 2 9585@1676093788.606448:vhost_vdpa_dma_map vdpa:0x7ff13026d190 fd: 16 msg_type: 2 asid: 1 iova: 0x1a000 size: 0x1000 uaddr: 0x55a5a77fa000 perm: 0x3 type: 2 9585@1676093788.616253:vhost_vdpa_dma_map vdpa:0x7ff13026d190 fd: 16 msg_type: 2 asid: 1 iova: 0x1b000 size: 0x1000 uaddr: 0x55a5a795f000 perm: 0x1 type: 2 9585@1676093788.625956:vhost_vdpa_dma_map vdpa:0x7ff13026d190 fd: 16 msg_type: 2 asid: 1 iova: 0x1c000 size: 0x1000 uaddr: 0x55a5a7f4e000 perm: 0x3 type: 2 9585@1676093788.635655:vhost_vdpa_set_vring_addr dev: 0x55a5a7580ec0 index: 8 flags: 0x0 desc_user_addr: 0x1b000 used_user_addr: 0x1c000 avail_user_addr: 0x1b400 log_guest_addr: 0x0 9585@1676093788.635667:vhost_vdpa_listener_region_add vdpa: 0x7ff13026d190 iova 0x0 llend 0xa0000 vaddr: 0x7fef1fe00000 read-only: 0 9585@1676093788.635670:vhost_vdpa_listener_begin_batch vdpa:0x7ff13026d190 fd: 16 msg_type: 2 type: 5 9585@1676093788.635677:vhost_vdpa_dma_map vdpa:0x7ff13026d190 fd: 16 msg_type: 2 asid: 0 iova: 0x0 size: 0xa0000 uaddr: 0x7fef1fe00000 perm: 0x3 type: 2 2023-02-11T05:36:28.635686Z qemu-system-x86_64: failed to write, fd=16, errno=14 (Bad address)
2023-02-11T05:36:28.635721Z qemu-system-x86_64: vhost vdpa map fail!2023-02-11T05:36:28.635744Z qemu-system-x86_64: vhost-vdpa: DMA mapping failed, unable to continue
Regards, -Siwei
Thanks!Thanks, -Siwei+ } + 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)) { @@ -449,15 +508,9 @@ 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, @@ -667,8 +720,7 @@ 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; @@ -690,7 +742,6 @@ 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()); @@ -760,7 +811,6 @@ 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; @@ -812,12 +862,8 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name, goto err; } - 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); @@ -825,7 +871,7 @@ 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; } @@ -833,13 +879,11 @@ 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: @@ -849,7 +893,6 @@ err: } } -err_svq: qemu_close(vdpa_device_fd); return -1;
_______________________________________________ Virtualization mailing list Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linuxfoundation.org/mailman/listinfo/virtualization
