Re: [Qemu-devel] [RFC v2 16/32] vhost+postcopy: Send address back to qemu

[Dr. David Alan Gilbert]

* Peter Xu (address@hidden) wrote:
> On Thu, Aug 24, 2017 at 08:27:14PM +0100, Dr. David Alan Gilbert (git) wrote:
> > From: "Dr. David Alan Gilbert" <address@hidden>
> > 
> > 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.
> > 
> > Note: We don't ask for the default 'ack' reply since we've got our own.
> > 
> > Signed-off-by: Dr. David Alan Gilbert <address@hidden>
> > ---
> >  contrib/libvhost-user/libvhost-user.c | 15 ++++++++-
> >  docs/interop/vhost-user.txt           |  6 ++++
> >  hw/virtio/trace-events                |  1 +
> >  hw/virtio/vhost-user.c                | 57 
> > ++++++++++++++++++++++++++++++++++-
> >  4 files changed, 77 insertions(+), 2 deletions(-)
> > 
> > diff --git a/contrib/libvhost-user/libvhost-user.c 
> > b/contrib/libvhost-user/libvhost-user.c
> > index e6ab059a03..5ec54f7d60 100644
> > --- a/contrib/libvhost-user/libvhost-user.c
> > +++ b/contrib/libvhost-user/libvhost-user.c
> > @@ -477,13 +477,26 @@ vu_set_mem_table_exec(VuDev *dev, VhostUserMsg *vmsg)
> >              DPRINT("%s: region %d: Registered userfault for %llx + %llx\n",
> >                      __func__, i, reg_struct.range.start, 
> > reg_struct.range.len);
> >              /* TODO: Stash 'zero' support flags somewhere */
> > -            /* TODO: Get address back to QEMU */
> >  
> > +            /* TODO: We need to find a way for the qemu not to see the 
> > virtual
> > +             * addresses of the clients, so as to keep better separation.
> > +             */
> > +            /* Return the address to QEMU so that it can translate the ufd
> > +             * fault addresses back.
> > +             */
> > +            msg_region->userspace_addr = (uintptr_t)(mmap_addr +
> > +                                                     
> > dev_region->mmap_offset);
> >          }
> >  
> >          close(vmsg->fds[i]);
> >      }
> >  
> > +    if (dev->postcopy_listening) {
> > +        /* Need to return the addresses - send the updated message back */
> > +        vmsg->fd_num = 0;
> > +        return true;
> > +    }
> > +
> >      return false;
> >  }
> >  
> > diff --git a/docs/interop/vhost-user.txt b/docs/interop/vhost-user.txt
> > index 73c3dd74db..b2a548c94d 100644
> > --- a/docs/interop/vhost-user.txt
> > +++ b/docs/interop/vhost-user.txt
> > @@ -413,12 +413,18 @@ Master message types
> >        Id: 5
> >        Equivalent ioctl: VHOST_SET_MEM_TABLE
> >        Master payload: memory regions description
> > +      Slave payload: (postcopy only) memory regions description
> >  
> >        Sets the memory map regions on the slave so it can translate the 
> > vring
> >        addresses. In the ancillary data there is an array of file 
> > descriptors
> >        for each memory mapped region. The size and ordering of the fds 
> > matches
> >        the number and ordering of memory regions.
> >  
> > +      When postcopy-listening has been received, SET_MEM_TABLE replies with
> > +      the bases of the memory mapped regions to the master.  It must have 
> > mmap'd
> > +      the regions and enabled userfaultfd on them.  Note NEED_REPLY_MASK
> > +      is not set in this case.
> > +
> >   * VHOST_USER_SET_LOG_BASE
> >  
> >        Id: 6
> > diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events
> > index f736c7c84f..63fd4a79cf 100644
> > --- a/hw/virtio/trace-events
> > +++ b/hw/virtio/trace-events
> > @@ -2,6 +2,7 @@
> >  
> >  # hw/virtio/vhost-user.c
> >  vhost_user_postcopy_listen(void) ""
> > +vhost_user_set_mem_table_postcopy(uint64_t client_addr, uint64_t qhva, int 
> > reply_i, int region_i) "client:0x%"PRIx64" for hva: 0x%"PRIx64" reply %d 
> > region %d"
> >  
> >  # 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"
> > diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
> > index 9178271ab2..2e4eb0864a 100644
> > --- a/hw/virtio/vhost-user.c
> > +++ b/hw/virtio/vhost-user.c
> > @@ -19,6 +19,7 @@
> >  #include "qemu/sockets.h"
> >  #include "migration/migration.h"
> >  #include "migration/postcopy-ram.h"
> > +#include "trace.h"
> >  
> >  #include <sys/ioctl.h>
> >  #include <sys/socket.h>
> > @@ -133,6 +134,7 @@ struct vhost_user {
> >      int slave_fd;
> >      NotifierWithReturn postcopy_notifier;
> >      struct PostCopyFD  postcopy_fd;
> > +    uint64_t           postcopy_client_bases[VHOST_MEMORY_MAX_NREGIONS];
> >  };
> >  
> >  static bool ioeventfd_enabled(void)
> > @@ -300,11 +302,13 @@ static int vhost_user_set_log_base(struct vhost_dev 
> > *dev, uint64_t base,
> >  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 reply_supported = virtio_has_feature(dev->protocol_features,
> > -                                              
> > VHOST_USER_PROTOCOL_F_REPLY_ACK);
> > +                                          VHOST_USER_PROTOCOL_F_REPLY_ACK) 
> > &&
> > +                           !u->postcopy_fd.handler;
> 
> (indent)

Fixed

> >  
> >      VhostUserMsg msg = {
> >          .request = VHOST_USER_SET_MEM_TABLE,
> > @@ -350,6 +354,57 @@ static int vhost_user_set_mem_table(struct vhost_dev 
> > *dev,
> >          return -1;
> >      }
> >  
> > +    if (u->postcopy_fd.handler) {
> 
> It seems that after this handler is set, we never clean it up.  Do we
> need to unset it somewhere? (maybe vhost_user_postcopy_end?)

Hmm yes I'll have a look at that.

> > +        VhostUserMsg msg_reply;
> > +        int region_i, reply_i;
> > +        if (vhost_user_read(dev, &msg_reply) < 0) {
> > +            return -1;
> > +        }
> > +
> > +        if (msg_reply.request != VHOST_USER_SET_MEM_TABLE) {
> > +            error_report("%s: Received unexpected msg type."
> > +                         "Expected %d received %d", __func__,
> > +                         VHOST_USER_SET_MEM_TABLE, msg_reply.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.size != msg.size) {
> > +            error_report("%s: Unexpected size for postcopy reply "
> > +                         "%d vs %d", __func__, msg_reply.size, msg.size);
> > +            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 (reply_i = 0, region_i = 0;
> > +             region_i < dev->mem->nregions;
> > +             region_i++) {
> > +            if (reply_i < fd_num &&
> > +                msg_reply.payload.memory.regions[region_i].guest_phys_addr 
> > ==
>                                                     ^^^^^^^^
>                                           should this be reply_i?

Yes it should - nicely spotted

> (And maybe we can use pointers for the regions for better readability?)

I'm nervous of doing that since VhostUserMsg is 'packed' - and I'm not
convinced it's legal to take a pointer to a member (although I think
we do it in a whole bunch of places and clang moans about it).

> > +                dev->mem->regions[region_i].guest_phys_addr) {
> > +                u->postcopy_client_bases[region_i] =
> > +                    
> > msg_reply.payload.memory.regions[reply_i].userspace_addr;
> > +                trace_vhost_user_set_mem_table_postcopy(
> > +                    
> > msg_reply.payload.memory.regions[reply_i].userspace_addr,
> > +                    msg.payload.memory.regions[reply_i].userspace_addr,
                                                    ^^^^^^^
                        and I think this one is region_i

Dave

> > +                    reply_i, region_i);
> > +                reply_i++;
> > +            }
> > +        }
> > +        if (reply_i != fd_num) {
> > +            error_report("%s: postcopy reply not fully consumed "
> > +                         "%d vs %zd",
> > +                         __func__, reply_i, fd_num);
> > +            return -1;
> > +        }
> > +    }
> >      if (reply_supported) {
> >          return process_message_reply(dev, &msg);
> >      }
> > -- 
> > 2.13.5
> > 
> 
> -- 
> Peter Xu
--
Dr. David Alan Gilbert / address@hidden / Manchester, UK