From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:41243) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1esv7H-0003Qo-6f for qemu-devel@nongnu.org; Mon, 05 Mar 2018 13:45:44 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1esv7D-00011B-5M for qemu-devel@nongnu.org; Mon, 05 Mar 2018 13:45:43 -0500 Received: from mx3-rdu2.redhat.com ([66.187.233.73]:53872 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 1esv7C-00010q-UN for qemu-devel@nongnu.org; Mon, 05 Mar 2018 13:45:39 -0500 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 7CE234063640 for ; Mon, 5 Mar 2018 18:45:36 +0000 (UTC) Date: Mon, 5 Mar 2018 18:45:21 +0000 From: "Dr. David Alan Gilbert" Message-ID: <20180305184521.GT3131@work-vm> References: <20180216131625.9639-1-dgilbert@redhat.com> <20180216131625.9639-13-dgilbert@redhat.com> <20180228084945.GC27381@xz-mi> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20180228084945.GC27381@xz-mi> Subject: Re: [Qemu-devel] [PATCH v3 12/29] postcopy+vhost-user: Split set_mem_table for postcopy List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Peter Xu Cc: qemu-devel@nongnu.org, maxime.coquelin@redhat.com, marcandre.lureau@redhat.com, imammedo@redhat.com, mst@redhat.com, quintela@redhat.com, aarcange@redhat.com * Peter Xu (peterx@redhat.com) wrote: > On Fri, Feb 16, 2018 at 01:16:08PM +0000, Dr. David Alan Gilbert (git) wrote: > > From: "Dr. David Alan Gilbert" > > > > Split the set_mem_table routines in both qemu and libvhost-user > > because the postcopy versions are going to be quite different > > once changes in the later patches are added. > > > > Signed-off-by: Dr. David Alan Gilbert > > --- > > contrib/libvhost-user/libvhost-user.c | 53 ++++++++++++++++++++++++ > > hw/virtio/vhost-user.c | 77 ++++++++++++++++++++++++++++++++++- > > 2 files changed, 128 insertions(+), 2 deletions(-) > > > > diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c > > index beec7695a8..4922b2c722 100644 > > --- a/contrib/libvhost-user/libvhost-user.c > > +++ b/contrib/libvhost-user/libvhost-user.c > > @@ -448,6 +448,55 @@ vu_reset_device_exec(VuDev *dev, VhostUserMsg *vmsg) > > return false; > > } > > > > +static bool > > +vu_set_mem_table_exec_postcopy(VuDev *dev, VhostUserMsg *vmsg) > > +{ > > + int i; > > + VhostUserMemory *memory = &vmsg->payload.memory; > > + dev->nregions = memory->nregions; > > + /* TODO: Postcopy specific code */ > > + DPRINT("Nregions: %d\n", memory->nregions); > > + for (i = 0; i < dev->nregions; i++) { > > + void *mmap_addr; > > + VhostUserMemoryRegion *msg_region = &memory->regions[i]; > > + VuDevRegion *dev_region = &dev->regions[i]; > > + > > + DPRINT("Region %d\n", i); > > + DPRINT(" guest_phys_addr: 0x%016"PRIx64"\n", > > + msg_region->guest_phys_addr); > > + DPRINT(" memory_size: 0x%016"PRIx64"\n", > > + msg_region->memory_size); > > + DPRINT(" userspace_addr 0x%016"PRIx64"\n", > > + msg_region->userspace_addr); > > + DPRINT(" mmap_offset 0x%016"PRIx64"\n", > > + msg_region->mmap_offset); > > + > > + dev_region->gpa = msg_region->guest_phys_addr; > > + dev_region->size = msg_region->memory_size; > > + dev_region->qva = msg_region->userspace_addr; > > + dev_region->mmap_offset = msg_region->mmap_offset; > > + > > + /* We don't use offset argument of mmap() since the > > + * mapped address has to be page aligned, and we use huge > > + * pages. */ > > + mmap_addr = mmap(0, dev_region->size + dev_region->mmap_offset, > > + PROT_READ | PROT_WRITE, MAP_SHARED, > > + vmsg->fds[i], 0); > > + > > + if (mmap_addr == MAP_FAILED) { > > + vu_panic(dev, "region mmap error: %s", strerror(errno)); > > + } else { > > + dev_region->mmap_addr = (uint64_t)(uintptr_t)mmap_addr; > > + DPRINT(" mmap_addr: 0x%016"PRIx64"\n", > > + dev_region->mmap_addr); > > + } > > + > > + close(vmsg->fds[i]); > > + } > > + > > + return false; > > +} > > + > > static bool > > vu_set_mem_table_exec(VuDev *dev, VhostUserMsg *vmsg) > > { > > @@ -464,6 +513,10 @@ vu_set_mem_table_exec(VuDev *dev, VhostUserMsg *vmsg) > > } > > dev->nregions = memory->nregions; > > > > + if (dev->postcopy_listening) { > > + return vu_set_mem_table_exec_postcopy(dev, vmsg); > > + } > > + > > DPRINT("Nregions: %d\n", memory->nregions); > > for (i = 0; i < dev->nregions; i++) { > > void *mmap_addr; > > diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c > > index ec6a4a82fd..64f4b3b3f9 100644 > > --- a/hw/virtio/vhost-user.c > > +++ b/hw/virtio/vhost-user.c > > @@ -325,15 +325,86 @@ static int vhost_user_set_log_base(struct vhost_dev *dev, uint64_t base, > > return 0; > > } > > > > +static int vhost_user_set_mem_table_postcopy(struct vhost_dev *dev, > > + struct vhost_memory *mem) > > +{ > > + int fds[VHOST_MEMORY_MAX_NREGIONS]; > > + int i, fd; > > + size_t fd_num = 0; > > + bool reply_supported = virtio_has_feature(dev->protocol_features, > > + VHOST_USER_PROTOCOL_F_REPLY_ACK); > > + /* TODO: Add actual postcopy differences */ > > + VhostUserMsg msg = { > > + .hdr.request = VHOST_USER_SET_MEM_TABLE, > > + .hdr.flags = VHOST_USER_VERSION, > > + }; > > + > > + if (reply_supported) { > > + msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK; > > + } > > + > > + for (i = 0; i < dev->mem->nregions; ++i) { > > + struct vhost_memory_region *reg = dev->mem->regions + i; > > + ram_addr_t offset; > > + MemoryRegion *mr; > > + > > + assert((uintptr_t)reg->userspace_addr == reg->userspace_addr); > > + mr = memory_region_from_host((void *)(uintptr_t)reg->userspace_addr, > > + &offset); > > + fd = memory_region_get_fd(mr); > > + if (fd > 0) { > > + msg.payload.memory.regions[fd_num].userspace_addr = > > + reg->userspace_addr; > > + msg.payload.memory.regions[fd_num].memory_size = reg->memory_size; > > + msg.payload.memory.regions[fd_num].guest_phys_addr = > > + reg->guest_phys_addr; > > + msg.payload.memory.regions[fd_num].mmap_offset = offset; > > + assert(fd_num < VHOST_MEMORY_MAX_NREGIONS); > > + fds[fd_num++] = fd; > > + } > > + } > > + > > + msg.payload.memory.nregions = fd_num; > > + > > + if (!fd_num) { > > + error_report("Failed initializing vhost-user memory map, " > > + "consider using -object memory-backend-file share=on"); > > + return -1; > > + } > > + > > + msg.hdr.size = sizeof(msg.payload.memory.nregions); > > + msg.hdr.size += sizeof(msg.payload.memory.padding); > > + msg.hdr.size += fd_num * sizeof(VhostUserMemoryRegion); > > + > > + if (vhost_user_write(dev, &msg, fds, fd_num) < 0) { > > + return -1; > > + } > > + > > + if (reply_supported) { > > + return process_message_reply(dev, &msg); > > + } > > + > > + return 0; > > +} > > + > > static int vhost_user_set_mem_table(struct vhost_dev *dev, > > struct vhost_memory *mem) > > { > > + struct vhost_user *u = dev->opaque; > > int fds[VHOST_MEMORY_MAX_NREGIONS]; > > int i, fd; > > size_t fd_num = 0; > > + bool do_postcopy = u->postcopy_listen && u->postcopy_fd.handler; > > bool reply_supported = virtio_has_feature(dev->protocol_features, > > VHOST_USER_PROTOCOL_F_REPLY_ACK); > > > > + if (do_postcopy) { > > + /* Postcopy has enough differences that it's best done in it's own > > + * version > > + */ > > + return vhost_user_set_mem_table_postcopy(dev, mem); > > + } > > + > > VhostUserMsg msg = { > > .hdr.request = VHOST_USER_SET_MEM_TABLE, > > .hdr.flags = VHOST_USER_VERSION, > > @@ -357,9 +428,11 @@ static int vhost_user_set_mem_table(struct vhost_dev *dev, > > error_report("Failed preparing vhost-user memory table msg"); > > return -1; > > } > > - msg.payload.memory.regions[fd_num].userspace_addr = reg->userspace_addr; > > + msg.payload.memory.regions[fd_num].userspace_addr = > > + reg->userspace_addr; > > msg.payload.memory.regions[fd_num].memory_size = reg->memory_size; > > - msg.payload.memory.regions[fd_num].guest_phys_addr = reg->guest_phys_addr; > > + msg.payload.memory.regions[fd_num].guest_phys_addr = > > + reg->guest_phys_addr; > > These newline changes might be avoided? They could, but they're over 80 chars long, so while I was taking a copy of the code I fixed the style on this copy so they were consistent. > So after this patch there's no functional change, only the code > splittion of set_mem_table operation, right? Right; the changes to the postcopy version come later. Dave > Thanks, > > > msg.payload.memory.regions[fd_num].mmap_offset = offset; > > fds[fd_num++] = fd; > > } > > -- > > 2.14.3 > > > > -- > Peter Xu -- Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK