From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:51176) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ey7md-0006zM-I8 for qemu-devel@nongnu.org; Mon, 19 Mar 2018 23:17:58 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1ey7mc-0008LU-4m for qemu-devel@nongnu.org; Mon, 19 Mar 2018 23:17:55 -0400 Received: from mx3-rdu2.redhat.com ([66.187.233.73]:34282 helo=mx1.redhat.com) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1ey7mb-0008LB-U2 for qemu-devel@nongnu.org; Mon, 19 Mar 2018 23:17:54 -0400 Date: Tue, 20 Mar 2018 05:17:53 +0200 From: "Michael S. Tsirkin" Message-ID: <1521515720-612046-37-git-send-email-mst@redhat.com> References: <1521515720-612046-1-git-send-email-mst@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline In-Reply-To: <1521515720-612046-1-git-send-email-mst@redhat.com> Content-Transfer-Encoding: quoted-printable Subject: [Qemu-devel] [PULL v2 36/50] vhost+postcopy: Send address back to qemu List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: Peter Maydell , "Dr. David Alan Gilbert" , =?utf-8?Q?Marc-Andr=C3=A9?= Lureau From: "Dr. David Alan Gilbert" We need a better way, but at the moment we need the address of the mappings sent back to qemu so it can interpret the messages on the userfaultfd it reads. This is done as a 3 stage set: QEMU -> client set_mem_table mmap stuff, get addresses client -> qemu here are the addresses qemu -> client OK - now you can use them That ensures that qemu has registered the new addresses in it's userfault code before the client starts accessing them. Note: We don't ask for the default 'ack' reply since we've got our own. Signed-off-by: Dr. David Alan Gilbert Reviewed-by: Marc-Andr=C3=A9 Lureau Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- docs/interop/vhost-user.txt | 9 +++++ contrib/libvhost-user/libvhost-user.c | 24 ++++++++++++- hw/virtio/vhost-user.c | 67 +++++++++++++++++++++++++++++= ++++-- hw/virtio/trace-events | 1 + 4 files changed, 98 insertions(+), 3 deletions(-) diff --git a/docs/interop/vhost-user.txt b/docs/interop/vhost-user.txt index 0d24203..e295ef1 100644 --- a/docs/interop/vhost-user.txt +++ b/docs/interop/vhost-user.txt @@ -455,12 +455,21 @@ Master message types Id: 5 Equivalent ioctl: VHOST_SET_MEM_TABLE Master payload: memory regions description + Slave payload: (postcopy only) memory regions description =20 Sets the memory map regions on the slave so it can translate the v= ring addresses. In the ancillary data there is an array of file descrip= tors for each memory mapped region. The size and ordering of the fds ma= tches the number and ordering of memory regions. =20 + When VHOST_USER_POSTCOPY_LISTEN has been received, SET_MEM_TABLE r= eplies with + the bases of the memory mapped regions to the master. The slave m= ust + have mmap'd the regions but not yet accessed them and should not y= et generate + a userfault event. Note NEED_REPLY_MASK is not set in this case. + QEMU will then reply back to the list of mappings with an empty + VHOST_USER_SET_MEM_TABLE as an acknowledgment; only upon reception= of this + message may the guest start accessing the memory and generating fa= ults. + * VHOST_USER_SET_LOG_BASE =20 Id: 6 diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-use= r/libvhost-user.c index 7c8cd587..6314549 100644 --- a/contrib/libvhost-user/libvhost-user.c +++ b/contrib/libvhost-user/libvhost-user.c @@ -491,10 +491,32 @@ vu_set_mem_table_exec_postcopy(VuDev *dev, VhostUse= rMsg *vmsg) dev_region->mmap_addr); } =20 + /* Return the address to QEMU so that it can translate the ufd + * fault addresses back. + */ + msg_region->userspace_addr =3D (uintptr_t)(mmap_addr + + dev_region->mmap_offset= ); close(vmsg->fds[i]); } =20 - /* TODO: Get address back to QEMU */ + /* Send the message back to qemu with the addresses filled in */ + vmsg->fd_num =3D 0; + if (!vu_message_write(dev, dev->sock, vmsg)) { + vu_panic(dev, "failed to respond to set-mem-table for postcopy")= ; + return false; + } + + /* Wait for QEMU to confirm that it's registered the handler for the + * faults. + */ + if (!vu_message_read(dev, dev->sock, vmsg) || + vmsg->size !=3D sizeof(vmsg->payload.u64) || + vmsg->payload.u64 !=3D 0) { + vu_panic(dev, "failed to receive valid ack for postcopy set-mem-= table"); + return false; + } + + /* OK, now we can go and register the memory and generate faults */ for (i =3D 0; i < dev->nregions; i++) { VuDevRegion *dev_region =3D &dev->regions[i]; #ifdef UFFDIO_REGISTER diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index b6757eb..1603d70 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -174,6 +174,7 @@ struct vhost_user { int slave_fd; NotifierWithReturn postcopy_notifier; struct PostCopyFD postcopy_fd; + uint64_t postcopy_client_bases[VHOST_MEMORY_MAX_NREGIONS]; /* True once we've entered postcopy_listen */ bool postcopy_listen; }; @@ -343,12 +344,15 @@ static int vhost_user_set_log_base(struct vhost_dev= *dev, uint64_t base, static int vhost_user_set_mem_table_postcopy(struct vhost_dev *dev, struct vhost_memory *mem) { + struct vhost_user *u =3D dev->opaque; int fds[VHOST_MEMORY_MAX_NREGIONS]; int i, fd; size_t fd_num =3D 0; bool reply_supported =3D virtio_has_feature(dev->protocol_features, VHOST_USER_PROTOCOL_F_REPL= Y_ACK); - /* TODO: Add actual postcopy differences */ + VhostUserMsg msg_reply; + int region_i, msg_i; + VhostUserMsg msg =3D { .hdr.request =3D VHOST_USER_SET_MEM_TABLE, .hdr.flags =3D VHOST_USER_VERSION, @@ -395,6 +399,64 @@ static int vhost_user_set_mem_table_postcopy(struct = vhost_dev *dev, return -1; } =20 + if (vhost_user_read(dev, &msg_reply) < 0) { + return -1; + } + + if (msg_reply.hdr.request !=3D VHOST_USER_SET_MEM_TABLE) { + error_report("%s: Received unexpected msg type." + "Expected %d received %d", __func__, + VHOST_USER_SET_MEM_TABLE, msg_reply.hdr.request); + return -1; + } + /* We're using the same structure, just reusing one of the + * fields, so it should be the same size. + */ + if (msg_reply.hdr.size !=3D msg.hdr.size) { + error_report("%s: Unexpected size for postcopy reply " + "%d vs %d", __func__, msg_reply.hdr.size, msg.hdr.s= ize); + return -1; + } + + memset(u->postcopy_client_bases, 0, + sizeof(uint64_t) * VHOST_MEMORY_MAX_NREGIONS); + + /* They're in the same order as the regions that were sent + * but some of the regions were skipped (above) if they + * didn't have fd's + */ + for (msg_i =3D 0, region_i =3D 0; + region_i < dev->mem->nregions; + region_i++) { + if (msg_i < fd_num && + msg_reply.payload.memory.regions[msg_i].guest_phys_addr =3D=3D + dev->mem->regions[region_i].guest_phys_addr) { + u->postcopy_client_bases[region_i] =3D + msg_reply.payload.memory.regions[msg_i].userspace_addr; + trace_vhost_user_set_mem_table_postcopy( + msg_reply.payload.memory.regions[msg_i].userspace_addr, + msg.payload.memory.regions[msg_i].userspace_addr, + msg_i, region_i); + msg_i++; + } + } + if (msg_i !=3D fd_num) { + error_report("%s: postcopy reply not fully consumed " + "%d vs %zd", + __func__, msg_i, fd_num); + return -1; + } + /* Now we've registered this with the postcopy code, we ack to the c= lient, + * because now we're in the position to be able to deal with any fau= lts + * it generates. + */ + /* TODO: Use this for failure cases as well with a bad value */ + msg.hdr.size =3D sizeof(msg.payload.u64); + msg.payload.u64 =3D 0; /* OK */ + if (vhost_user_write(dev, &msg, NULL, 0) < 0) { + return -1; + } + if (reply_supported) { return process_message_reply(dev, &msg); } @@ -411,7 +473,8 @@ static int vhost_user_set_mem_table(struct vhost_dev = *dev, size_t fd_num =3D 0; bool do_postcopy =3D u->postcopy_listen && u->postcopy_fd.handler; bool reply_supported =3D virtio_has_feature(dev->protocol_features, - VHOST_USER_PROTOCOL_F_REPL= Y_ACK); + VHOST_USER_PROTOCOL_F_REPLY_AC= K) && + !do_postcopy; =20 if (do_postcopy) { /* Postcopy has enough differences that it's best done in it's o= wn diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events index 06ec03d..05d18ad 100644 --- a/hw/virtio/trace-events +++ b/hw/virtio/trace-events @@ -8,6 +8,7 @@ vhost_section(const char *name, int r) "%s:%d" =20 # hw/virtio/vhost-user.c vhost_user_postcopy_listen(void) "" +vhost_user_set_mem_table_postcopy(uint64_t client_addr, uint64_t qhva, i= nt reply_i, int region_i) "client:0x%"PRIx64" for hva: 0x%"PRIx64" reply = %d region %d" =20 # hw/virtio/virtio.c virtqueue_alloc_element(void *elem, size_t sz, unsigned in_num, unsigned= out_num) "elem %p size %zd in_num %u out_num %u" --=20 MST