diff mbox

[RFC,v2,15/32] vhost+postcopy: Register new regions with the ufd

Message ID 20170824192730.8440-16-dgilbert@redhat.com
State New
Headers show

Commit Message

Dr. David Alan Gilbert Aug. 24, 2017, 7:27 p.m. UTC 
From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>

When new regions are sent to the client using SET_MEM_TABLE, register
them with the userfaultfd.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
 contrib/libvhost-user/libvhost-user.c | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

Comments

Marc-André Lureau Aug. 30, 2017, 10:42 a.m. UTC | #1 
Use "libvhost-user: " commit title tag/prefix?

On Thu, Aug 24, 2017 at 12:27 PM, Dr. David Alan Gilbert (git)
<dgilbert@redhat.com> wrote:
> From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
>
> When new regions are sent to the client using SET_MEM_TABLE, register
> them with the userfaultfd.
>
> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
> ---
>  contrib/libvhost-user/libvhost-user.c | 32 ++++++++++++++++++++++++++++++++
>  1 file changed, 32 insertions(+)
>
> diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c
> index e8accf11db..e6ab059a03 100644
> --- a/contrib/libvhost-user/libvhost-user.c
> +++ b/contrib/libvhost-user/libvhost-user.c
> @@ -449,6 +449,38 @@ vu_set_mem_table_exec(VuDev *dev, VhostUserMsg *vmsg)
>                     dev_region->mmap_addr);
>          }
>
> +        if (dev->postcopy_listening) {
> +            /* We should already have an open ufd need to mark each memory
> +             * range as ufd.
> +             * Note: Do we need any madvises? Well it's not been accessed
> +             * yet, still probably need no THP to be safe, discard to be safe?
> +             */
> +            struct uffdio_register reg_struct;
> +            reg_struct.range.start = (uintptr_t)dev_region->mmap_addr;
> +            reg_struct.range.len = dev_region->size + dev_region->mmap_offset;
> +            reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING;
> +
> +            if (ioctl(dev->postcopy_ufd, UFFDIO_REGISTER, &reg_struct)) {
> +                vu_panic(dev, "%s: Failed to userfault region %d "
> +                              "@%p + %zx: (ufd=%d)%s\n",
> +                         __func__, i,
> +                         dev_region->mmap_addr,
> +                         dev_region->size + dev_region->mmap_offset,
> +                         dev->postcopy_ufd, strerror(errno));
> +                continue;

panic is supposed to be unrecoverable errors, so I would suggest to return here

> +            }
> +            if (!(reg_struct.ioctls & ((__u64)1 << _UFFDIO_COPY))) {
> +                vu_panic(dev, "%s Region (%d) doesn't support COPY",
> +                         __func__, i);
> +                continue;
> +            }
> +            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 */
> +
> +        }
> +
>          close(vmsg->fds[i]);
>      }

This patch would be nicer if it compiles on !Linux / without userfault.
Dr. David Alan Gilbert Sept. 8, 2017, 2:50 p.m. UTC | #2 
* Marc-André Lureau (marcandre.lureau@gmail.com) wrote:
> Use "libvhost-user: " commit title tag/prefix?
> 
> On Thu, Aug 24, 2017 at 12:27 PM, Dr. David Alan Gilbert (git)
> <dgilbert@redhat.com> wrote:
> > From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
> >
> > When new regions are sent to the client using SET_MEM_TABLE, register
> > them with the userfaultfd.
> >
> > Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
> > ---
> >  contrib/libvhost-user/libvhost-user.c | 32 ++++++++++++++++++++++++++++++++
> >  1 file changed, 32 insertions(+)
> >
> > diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c
> > index e8accf11db..e6ab059a03 100644
> > --- a/contrib/libvhost-user/libvhost-user.c
> > +++ b/contrib/libvhost-user/libvhost-user.c
> > @@ -449,6 +449,38 @@ vu_set_mem_table_exec(VuDev *dev, VhostUserMsg *vmsg)
> >                     dev_region->mmap_addr);
> >          }
> >
> > +        if (dev->postcopy_listening) {
> > +            /* We should already have an open ufd need to mark each memory
> > +             * range as ufd.
> > +             * Note: Do we need any madvises? Well it's not been accessed
> > +             * yet, still probably need no THP to be safe, discard to be safe?
> > +             */
> > +            struct uffdio_register reg_struct;
> > +            reg_struct.range.start = (uintptr_t)dev_region->mmap_addr;
> > +            reg_struct.range.len = dev_region->size + dev_region->mmap_offset;
> > +            reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING;
> > +
> > +            if (ioctl(dev->postcopy_ufd, UFFDIO_REGISTER, &reg_struct)) {
> > +                vu_panic(dev, "%s: Failed to userfault region %d "
> > +                              "@%p + %zx: (ufd=%d)%s\n",
> > +                         __func__, i,
> > +                         dev_region->mmap_addr,
> > +                         dev_region->size + dev_region->mmap_offset,
> > +                         dev->postcopy_ufd, strerror(errno));
> > +                continue;
> 
> panic is supposed to be unrecoverable errors, so I would suggest to return here

Done.

> > +            }
> > +            if (!(reg_struct.ioctls & ((__u64)1 << _UFFDIO_COPY))) {
> > +                vu_panic(dev, "%s Region (%d) doesn't support COPY",
> > +                         __func__, i);
> > +                continue;
> > +            }
> > +            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 */
> > +
> > +        }
> > +
> >          close(vmsg->fds[i]);
> >      }
> 
> This patch would be nicer if it compiles on !Linux / without userfault.

Done; I've just ifdef UFFDIO_REGISTER the inside of this if;
I'll add other code that makes sure it doesn't get as far as setting
postcopy_listening either.

Dave

> -- 
> Marc-André Lureau
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
diff mbox

Patch

diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c
index e8accf11db..e6ab059a03 100644
--- a/contrib/libvhost-user/libvhost-user.c
+++ b/contrib/libvhost-user/libvhost-user.c
@@ -449,6 +449,38 @@  vu_set_mem_table_exec(VuDev *dev, VhostUserMsg *vmsg)
                    dev_region->mmap_addr);
         }
 
+        if (dev->postcopy_listening) {
+            /* We should already have an open ufd need to mark each memory
+             * range as ufd.
+             * Note: Do we need any madvises? Well it's not been accessed
+             * yet, still probably need no THP to be safe, discard to be safe?
+             */
+            struct uffdio_register reg_struct;
+            reg_struct.range.start = (uintptr_t)dev_region->mmap_addr;
+            reg_struct.range.len = dev_region->size + dev_region->mmap_offset;
+            reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING;
+
+            if (ioctl(dev->postcopy_ufd, UFFDIO_REGISTER, &reg_struct)) {
+                vu_panic(dev, "%s: Failed to userfault region %d "
+                              "@%p + %zx: (ufd=%d)%s\n",
+                         __func__, i,
+                         dev_region->mmap_addr,
+                         dev_region->size + dev_region->mmap_offset,
+                         dev->postcopy_ufd, strerror(errno));
+                continue;
+            }
+            if (!(reg_struct.ioctls & ((__u64)1 << _UFFDIO_COPY))) {
+                vu_panic(dev, "%s Region (%d) doesn't support COPY",
+                         __func__, i);
+                continue;
+            }
+            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 */
+
+        }
+
         close(vmsg->fds[i]);
     }