Re: [PATCH v5 1/2] x86/mem-sharing: Bulk mem-sharing entire domains

[Tamas K Lengyel <tamas@tklengyel.com>]

On Sat, Jun 11, 2016 at 5:24 PM, Tamas K Lengyel <tamas@tklengyel.com> wrote:
> Currently mem-sharing can be performed on a page-by-page base from the control
> domain. However, when completely deduplicating (cloning) a VM, this requires
> at least 3 hypercalls per page. As the user has to loop through all pages up
> to max_gpfn, this process is very slow and wasteful.
>
> This patch introduces a new mem_sharing memop for bulk deduplication where
> the user doesn't have to separately nominate each page in both the source and
> destination domain, and the looping over all pages happen in the hypervisor.
> This significantly reduces the overhead of completely deduplicating entire
> domains.
>
> Signed-off-by: Tamas K Lengyel <tamas@tklengyel.com>
> Acked-by: Wei Liu <wei.liu2@citrix.com>
> ---
> Ian Jackson <ian.jackson@eu.citrix.com>
> George Dunlap <george.dunlap@eu.citrix.com>
> Jan Beulich <jbeulich@suse.com>
> Andrew Cooper <andrew.cooper3@citrix.com>

Missed Cc: here.

>
> v4: Add padding to bulk op and enforce it being 0
>     Use correct XSM permission check
> ---
>  tools/libxc/include/xenctrl.h |  15 ++++++
>  tools/libxc/xc_memshr.c       |  19 +++++++
>  xen/arch/x86/mm/mem_sharing.c | 121 ++++++++++++++++++++++++++++++++++++++++++
>  xen/include/public/memory.h   |  15 +++++-
>  4 files changed, 169 insertions(+), 1 deletion(-)
>
> diff --git a/tools/libxc/include/xenctrl.h b/tools/libxc/include/xenctrl.h
> index 6ae1a2b..34dcc72 100644
> --- a/tools/libxc/include/xenctrl.h
> +++ b/tools/libxc/include/xenctrl.h
> @@ -2327,6 +2327,21 @@ int xc_memshr_add_to_physmap(xc_interface *xch,
>                      domid_t client_domain,
>                      unsigned long client_gfn);
>
> +/* Allows to deduplicate the entire memory of a client domain in bulk. Using
> + * this function is equivalent of calling xc_memshr_nominate_gfn for each gfn
> + * in the two domains followed by xc_memshr_share_gfns. If successfull,
> + * returns the number of shared pages in 'shared'. Both domains must be paused.
> + *
> + * May fail with -EINVAL if the source and client domain have different
> + * memory size or if memory sharing is not enabled on either of the domains.
> + * May also fail with -ENOMEM if there isn't enough memory available to store
> + * the sharing metadata before deduplication can happen.
> + */
> +int xc_memshr_bulk_share(xc_interface *xch,
> +                         domid_t source_domain,
> +                         domid_t client_domain,
> +                         uint64_t *shared);
> +
>  /* Debug calls: return the number of pages referencing the shared frame backing
>   * the input argument. Should be one or greater.
>   *
> diff --git a/tools/libxc/xc_memshr.c b/tools/libxc/xc_memshr.c
> index deb0aa4..71350d2 100644
> --- a/tools/libxc/xc_memshr.c
> +++ b/tools/libxc/xc_memshr.c
> @@ -181,6 +181,25 @@ int xc_memshr_add_to_physmap(xc_interface *xch,
>      return xc_memshr_memop(xch, source_domain, &mso);
>  }
>
> +int xc_memshr_bulk_share(xc_interface *xch,
> +                         domid_t source_domain,
> +                         domid_t client_domain,
> +                         uint64_t *shared)
> +{
> +    int rc;
> +    xen_mem_sharing_op_t mso;
> +
> +    memset(&mso, 0, sizeof(mso));
> +
> +    mso.op = XENMEM_sharing_op_bulk_share;
> +    mso.u.bulk.client_domain = client_domain;
> +
> +    rc = xc_memshr_memop(xch, source_domain, &mso);
> +    if ( !rc && shared ) *shared = mso.u.bulk.shared;
> +
> +    return rc;
> +}
> +
>  int xc_memshr_domain_resume(xc_interface *xch,
>                              domid_t domid)
>  {
> diff --git a/xen/arch/x86/mm/mem_sharing.c b/xen/arch/x86/mm/mem_sharing.c
> index a522423..ba06fb0 100644
> --- a/xen/arch/x86/mm/mem_sharing.c
> +++ b/xen/arch/x86/mm/mem_sharing.c
> @@ -1294,6 +1294,54 @@ int relinquish_shared_pages(struct domain *d)
>      return rc;
>  }
>
> +static int bulk_share(struct domain *d, struct domain *cd, unsigned long limit,
> +                      struct mem_sharing_op_bulk *bulk)
> +{
> +    int rc = 0;
> +    shr_handle_t sh, ch;
> +
> +    while( limit > bulk->start )
> +    {
> +        /*
> +         * We only break out if we run out of memory as individual pages may
> +         * legitimately be unsharable and we just want to skip over those.
> +         */
> +        rc = mem_sharing_nominate_page(d, bulk->start, 0, &sh);
> +        if ( rc == -ENOMEM )
> +            break;
> +        if ( !rc )
> +        {
> +            rc = mem_sharing_nominate_page(cd, bulk->start, 0, &ch);
> +            if ( rc == -ENOMEM )
> +                break;
> +            if ( !rc )
> +            {
> +                /* If we get here this should be guaranteed to succeed. */
> +                rc = mem_sharing_share_pages(d, bulk->start, sh,
> +                                             cd, bulk->start, ch);
> +                ASSERT(!rc);
> +            }
> +        }
> +
> +        /* Check for continuation if it's not the last iteration. */
> +        if ( limit > ++bulk->start && hypercall_preempt_check() )
> +        {
> +            rc = 1;
> +            break;
> +        }
> +    }
> +
> +    /*
> +     * We only propagate -ENOMEM as individual pages may fail with -EINVAL,
> +     * and for bulk sharing we only care if -ENOMEM was encountered so we reset
> +     * rc here.
> +     */
> +    if ( rc < 0 && rc != -ENOMEM )
> +        rc = 0;
> +
> +    return rc;
> +}
> +
>  int mem_sharing_memop(XEN_GUEST_HANDLE_PARAM(xen_mem_sharing_op_t) arg)
>  {
>      int rc;
> @@ -1468,6 +1516,79 @@ int mem_sharing_memop(XEN_GUEST_HANDLE_PARAM(xen_mem_sharing_op_t) arg)
>          }
>          break;
>
> +        case XENMEM_sharing_op_bulk_share:
> +        {
> +            unsigned long max_sgfn, max_cgfn;
> +            struct domain *cd;
> +
> +            rc = -EINVAL;
> +            if( mso.u.bulk._pad[0] || mso.u.bulk._pad[1] || mso.u.bulk._pad[2] )
> +                goto out;
> +
> +            if ( !mem_sharing_enabled(d) )
> +                goto out;
> +
> +            rc = rcu_lock_live_remote_domain_by_id(mso.u.bulk.client_domain,
> +                                                   &cd);
> +            if ( rc )
> +                goto out;
> +
> +            /*
> +             * We reuse XENMEM_sharing_op_share XSM check here as this is essentially
> +             * the same concept repeated over multiple pages.
> +             */
> +            rc = xsm_mem_sharing_op(XSM_DM_PRIV, d, cd, XENMEM_sharing_op_share);
> +            if ( rc )
> +            {
> +                rcu_unlock_domain(cd);
> +                goto out;
> +            }
> +
> +            if ( !mem_sharing_enabled(cd) )
> +            {
> +                rcu_unlock_domain(cd);
> +                rc = -EINVAL;
> +                goto out;
> +            }
> +
> +            if ( !atomic_read(&d->pause_count) ||
> +                 !atomic_read(&cd->pause_count) )
> +            {
> +                rcu_unlock_domain(cd);
> +                rc = -EINVAL;
> +                goto out;
> +            }
> +
> +            max_sgfn = domain_get_maximum_gpfn(d);
> +            max_cgfn = domain_get_maximum_gpfn(cd);
> +
> +            if ( max_sgfn != max_cgfn || max_sgfn < mso.u.bulk.start )
> +            {
> +                rcu_unlock_domain(cd);
> +                rc = -EINVAL;
> +                goto out;
> +            }
> +
> +            rc = bulk_share(d, cd, max_sgfn + 1, &mso.u.bulk);
> +            if ( rc > 0 )
> +            {
> +                if ( __copy_to_guest(arg, &mso, 1) )
> +                    rc = -EFAULT;
> +                else
> +                    rc = hypercall_create_continuation(__HYPERVISOR_memory_op,
> +                                                       "lh", XENMEM_sharing_op,
> +                                                       arg);
> +            }
> +            else
> +            {
> +                mso.u.bulk.start = 0;
> +                mso.u.bulk.shared = atomic_read(&cd->shr_pages);
> +            }
> +
> +            rcu_unlock_domain(cd);
> +        }
> +        break;
> +
>          case XENMEM_sharing_op_debug_gfn:
>          {
>              unsigned long gfn = mso.u.debug.u.gfn;
> diff --git a/xen/include/public/memory.h b/xen/include/public/memory.h
> index 29ec571..084f06e 100644
> --- a/xen/include/public/memory.h
> +++ b/xen/include/public/memory.h
> @@ -465,6 +465,7 @@ DEFINE_XEN_GUEST_HANDLE(xen_mem_access_op_t);
>  #define XENMEM_sharing_op_debug_gref        5
>  #define XENMEM_sharing_op_add_physmap       6
>  #define XENMEM_sharing_op_audit             7
> +#define XENMEM_sharing_op_bulk_share        8
>
>  #define XENMEM_SHARING_OP_S_HANDLE_INVALID  (-10)
>  #define XENMEM_SHARING_OP_C_HANDLE_INVALID  (-9)
> @@ -500,7 +501,19 @@ struct xen_mem_sharing_op {
>              uint64_aligned_t client_gfn;    /* IN: the client gfn */
>              uint64_aligned_t client_handle; /* IN: handle to the client page */
>              domid_t  client_domain; /* IN: the client domain id */
> -        } share;
> +        } share;
> +        struct mem_sharing_op_bulk {         /* OP_BULK_SHARE */
> +            uint64_aligned_t start;          /* IN: start gfn. Set to 0 for
> +                                                full deduplication. Field is
> +                                                reset to 0 when hypercall
> +                                                completes */
> +            uint64_aligned_t shared;         /* OUT: the number of gfns
> +                                                that are shared after this
> +                                                operation, including pages
> +                                                that were already shared */
> +            domid_t client_domain;           /* IN: the client domain id */
> +            uint16_t _pad[3];
> +        } bulk;
>          struct mem_sharing_op_debug {     /* OP_DEBUG_xxx */
>              union {
>                  uint64_aligned_t gfn;      /* IN: gfn to debug          */
> --
> 2.8.1
>

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel