Re: [PATCH] x86/PV: fix unintended dependency of m2p-strict mode on migration-v2

[Andrew Cooper <andrew.cooper3@citrix.com>]

[-- Attachment #1.1: Type: text/plain, Size: 5375 bytes --]

On 12/01/16 10:08, Jan Beulich wrote:
> This went unnoticed until a backport of this to an older Xen got used,
> causing migration of guests enabling this VM assist to fail, because
> page table pinning there preceeds vCPU context loading, and hence L4
> tables get initialized for the wrong mode. Fix this by post-processing
> L4 tables when setting the intended VM assist flags for the guest.
>
> Note that this leaves in place a dependency on vCPU 0 getting its guest
> context restored first, but afaict the logic here is not the only thing
> depending on that.
>
> Signed-off-by: Jan Beulich <jbeulich@suse.com>
>
> --- a/xen/arch/x86/domain.c
> +++ b/xen/arch/x86/domain.c
> @@ -1067,8 +1067,48 @@ int arch_set_info_guest(
>          goto out;
>  
>      if ( v->vcpu_id == 0 )
> +    {
>          d->vm_assist = c(vm_assist);
>  
> +        /*
> +         * In the restore case we need to deal with L4 pages which got
> +         * initialized with m2p_strict still clear (and which hence lack the
> +         * correct initial RO_MPT_VIRT_{START,END} L4 entry).
> +         */
> +        if ( d != current->domain && VM_ASSIST(d, m2p_strict) &&
> +             is_pv_domain(d) && !is_pv_32bit_domain(d) &&
> +             atomic_read(&d->arch.pv_domain.nr_l4_pages) )
> +        {
> +            bool_t done = 0;
> +
> +            spin_lock_recursive(&d->page_alloc_lock);
> +
> +            for ( i = 0; ; )
> +            {
> +                struct page_info *page = page_list_remove_head(&d->page_list);
> +
> +                if ( page_lock(page) )
> +                {
> +                    if ( (page->u.inuse.type_info & PGT_type_mask) ==
> +                         PGT_l4_page_table )
> +                        done = !fill_ro_mpt(page_to_mfn(page));
> +
> +                    page_unlock(page);
> +                }
> +
> +                page_list_add_tail(page, &d->page_list);
> +
> +                if ( done || (!(++i & 0xff) && hypercall_preempt_check()) )
> +                    break;
> +            }
> +
> +            spin_unlock_recursive(&d->page_alloc_lock);
> +
> +            if ( !done )
> +                return -ERESTART;

This is a long loop.  It is preemptible, but will incur a time delay
proportional to the size of the domain during the VM downtime. 

Could you defer the loop until after %cr3 has set been set up, and only
enter the loop if the kernel l4 table is missing the RO mappings?  That
way, domains migrated with migration v2 will skip the loop entirely.

> +        }
> +    }
> +
>      rc = put_old_guest_table(current);
>      if ( rc )
>          return rc;
> --- a/xen/arch/x86/mm.c
> +++ b/xen/arch/x86/mm.c
> @@ -1463,13 +1463,20 @@ void init_guest_l4_table(l4_pgentry_t l4
>          l4tab[l4_table_offset(RO_MPT_VIRT_START)] = l4e_empty();
>  }
>  
> -void fill_ro_mpt(unsigned long mfn)
> +bool_t fill_ro_mpt(unsigned long mfn)
>  {
>      l4_pgentry_t *l4tab = map_domain_page(_mfn(mfn));
> +    bool_t ret = 0;
>  
> -    l4tab[l4_table_offset(RO_MPT_VIRT_START)] =
> -        idle_pg_table[l4_table_offset(RO_MPT_VIRT_START)];
> +    if ( !l4e_get_intpte(l4tab[l4_table_offset(RO_MPT_VIRT_START)]) )
> +    {
> +        l4tab[l4_table_offset(RO_MPT_VIRT_START)] =
> +            idle_pg_table[l4_table_offset(RO_MPT_VIRT_START)];
> +        ret = 1;

This is a behavioural change.  Previously, the old value was clobbered.

It appears that you are now using this return value to indicate when the
entire pagelist has been walked, but it it relies on the slots being
zero, which is a fragile assumption.

~Andrew

> +    }
>      unmap_domain_page(l4tab);
> +
> +    return ret;
>  }
>  
>  void zap_ro_mpt(unsigned long mfn)
> @@ -1527,10 +1534,15 @@ static int alloc_l4_table(struct page_in
>          adjust_guest_l4e(pl4e[i], d);
>      }
>  
> -    init_guest_l4_table(pl4e, d, !VM_ASSIST(d, m2p_strict));
> +    if ( rc >= 0 )
> +    {
> +        init_guest_l4_table(pl4e, d, !VM_ASSIST(d, m2p_strict));
> +        atomic_inc(&d->arch.pv_domain.nr_l4_pages);
> +        rc = 0;
> +    }
>      unmap_domain_page(pl4e);
>  
> -    return rc > 0 ? 0 : rc;
> +    return rc;
>  }
>  
>  static void free_l1_table(struct page_info *page)
> @@ -1648,7 +1660,13 @@ static int free_l4_table(struct page_inf
>  
>      unmap_domain_page(pl4e);
>  
> -    return rc > 0 ? 0 : rc;
> +    if ( rc >= 0 )
> +    {
> +        atomic_dec(&d->arch.pv_domain.nr_l4_pages);
> +        rc = 0;
> +    }
> +
> +    return rc;
>  }
>  
>  int page_lock(struct page_info *page)
> --- a/xen/include/asm-x86/domain.h
> +++ b/xen/include/asm-x86/domain.h
> @@ -248,6 +248,8 @@ struct pv_domain
>  {
>      l1_pgentry_t **gdt_ldt_l1tab;
>  
> +    atomic_t nr_l4_pages;
> +
>      /* map_domain_page() mapping cache. */
>      struct mapcache_domain mapcache;
>  };
> --- a/xen/include/asm-x86/mm.h
> +++ b/xen/include/asm-x86/mm.h
> @@ -322,7 +322,7 @@ int free_page_type(struct page_info *pag
>  
>  void init_guest_l4_table(l4_pgentry_t[], const struct domain *,
>                           bool_t zap_ro_mpt);
> -void fill_ro_mpt(unsigned long mfn);
> +bool_t fill_ro_mpt(unsigned long mfn);
>  void zap_ro_mpt(unsigned long mfn);
>  
>  int is_iomem_page(unsigned long mfn);
>
>
>
>
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xen.org
> http://lists.xen.org/xen-devel


[-- Attachment #1.2: Type: text/html, Size: 6617 bytes --]

[-- Attachment #2: Type: text/plain, Size: 126 bytes --]

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