File 5c7e70c6-x86-mm-L2-unvalidation-preemptible.patch of Package xen

Overview Repositories Revisions Requests Users Attributes Meta

File 5c7e70c6-x86-mm-L2-unvalidation-preemptible.patch of Package xen (Revision 0873801c1fef37fa1038530875ceabc7)

Currently displaying revision 0873801c1fef37fa1038530875ceabc7 , Show latest

# Commit 176ebf9c8bc2828f6637eb61cc1cf166e302c699
# Date 2019-03-05 13:51:18 +0100
# Author Jan Beulich <jbeulich@suse.com>
# Committer Jan Beulich <jbeulich@suse.com>
x86/mm: also allow L2 (un)validation to be fully preemptible

Commit c612481d1c ("x86/mm: Plumbing to allow any PTE update to fail
with -ERESTART") added assertions next to the {alloc,free}_l2_table()
invocations to document (and validate in debug builds) that L2
(un)validations are always preemptible.

The assertion in free_page_type() was now observed to trigger when
recursive L2 page tables get cleaned up.

In particular put_page_from_l2e()'s assumption that _put_page_type()
would always succeed is now wrong, resulting in a partially un-validated
page left in a domain, which has no other means of getting cleaned up
later on. If not causing any problems earlier, this would ultimately
trigger the check for ->u.inuse.type_info having a zero count when
freeing the page during cleanup after the domain has died.

As a result it should be considered a mistake to not have extended
preemption fully to L2 when it was added to L3/L4 table handling, which
this change aims to correct.

The validation side additions are done just for symmetry.

This is part of XSA-290.

Reported-by: Manuel Bouyer <bouyer@antioche.eu.org>
Tested-by: Manuel Bouyer <bouyer@antioche.eu.org>
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>

--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -1261,7 +1261,7 @@ get_page_from_l1e(
 define_get_linear_pagetable(l2);
 static int
 get_page_from_l2e(
-    l2_pgentry_t l2e, unsigned long pfn, struct domain *d)
+    l2_pgentry_t l2e, unsigned long pfn, struct domain *d, int partial)
 {
     unsigned long mfn = l2e_get_pfn(l2e);
     int rc;
@@ -1278,7 +1278,8 @@ get_page_from_l2e(
 
     if ( !(l2e_get_flags(l2e) & _PAGE_PSE) )
     {
-        rc = get_page_and_type_from_pagenr(mfn, PGT_l1_page_table, d, 0, 0);
+        rc = get_page_and_type_from_pagenr(mfn, PGT_l1_page_table, d,
+                                           partial, false);
         if ( unlikely(rc == -EINVAL) && get_l2_linear_pagetable(l2e, pfn, d) )
             rc = 0;
         return rc;
@@ -1477,8 +1478,11 @@ void put_page_from_l1e(l1_pgentry_t l1e,
  * NB. Virtual address 'l2e' maps to a machine address within frame 'pfn'.
  * Note also that this automatically deals correctly with linear p.t.'s.
  */
-static int put_page_from_l2e(l2_pgentry_t l2e, unsigned long pfn)
+static int put_page_from_l2e(l2_pgentry_t l2e, unsigned long pfn,
+                             int partial, bool defer)
 {
+    int rc = 0;
+
     if ( !(l2e_get_flags(l2e) & _PAGE_PRESENT) || (l2e_get_pfn(l2e) == pfn) )
         return 1;
 
@@ -1487,13 +1491,27 @@ static int put_page_from_l2e(l2_pgentry_
     else
     {
         struct page_info *pg = l2e_get_page(l2e);
-        int rc = _put_page_type(pg, false, mfn_to_page(pfn));
+        struct page_info *ptpg = mfn_to_page(pfn);
 
-        ASSERT(!rc);
-        put_page(pg);
+        if ( unlikely(partial > 0) )
+        {
+            ASSERT(!defer);
+            rc = _put_page_type(pg, true, ptpg);
+        }
+        else if ( defer )
+        {
+            current->arch.old_guest_ptpg = ptpg;
+            current->arch.old_guest_table = pg;
+        }
+        else
+        {
+            rc = _put_page_type(pg, true, ptpg);
+            if ( likely(!rc) )
+                put_page(pg);
+        }
     }
 
-    return 0;
+    return rc;
 }
 
 static int put_page_from_l3e(l3_pgentry_t l3e, unsigned long pfn,
@@ -1666,11 +1684,12 @@ static int alloc_l2_table(struct page_in
     unsigned long  pfn = page_to_mfn(page);
     l2_pgentry_t  *pl2e;
     unsigned int   i;
-    int            rc = 0;
+    int            rc = 0, partial = page->partial_pte;
 
     pl2e = map_domain_page(_mfn(pfn));
 
-    for ( i = page->nr_validated_ptes; i < L2_PAGETABLE_ENTRIES; i++ )
+    for ( i = page->nr_validated_ptes; i < L2_PAGETABLE_ENTRIES;
+          i++, partial = 0 )
     {
         if ( i > page->nr_validated_ptes && hypercall_preempt_check() )
         {
@@ -1680,23 +1699,33 @@ static int alloc_l2_table(struct page_in
         }
 
         if ( !is_guest_l2_slot(d, type, i) ||
-             (rc = get_page_from_l2e(pl2e[i], pfn, d)) > 0 )
+             (rc = get_page_from_l2e(pl2e[i], pfn, d, partial)) > 0 )
             continue;
 
-        if ( unlikely(rc == -ERESTART) )
+        if ( rc == -ERESTART )
         {
             page->nr_validated_ptes = i;
-            break;
+            page->partial_pte = partial ?: 1;
         }
-
-        if ( rc < 0 )
+        else if ( rc == -EINTR && i )
+        {
+            page->nr_validated_ptes = i;
+            page->partial_pte = 0;
+            rc = -ERESTART;
+        }
+        else if ( rc < 0 && rc != -EINTR )
         {
             gdprintk(XENLOG_WARNING, "Failure in alloc_l2_table: slot %#x\n", i);
-            while ( i-- > 0 )
-                if ( is_guest_l2_slot(d, type, i) )
-                    put_page_from_l2e(pl2e[i], pfn);
-            break;
+            if ( i )
+            {
+                page->nr_validated_ptes = i;
+                page->partial_pte = 0;
+                current->arch.old_guest_ptpg = NULL;
+                current->arch.old_guest_table = page;
+            }
         }
+        if ( rc < 0 )
+            break;
 
         adjust_guest_l2e(pl2e[i], d);
     }
@@ -1919,28 +1948,50 @@ static int free_l2_table(struct page_inf
     struct domain *d = page_get_owner(page);
     unsigned long pfn = page_to_mfn(page);
     l2_pgentry_t *pl2e;
-    unsigned int  i = page->nr_validated_ptes - 1;
-    int err = 0;
+    int rc = 0, partial = page->partial_pte;
+    unsigned int i = page->nr_validated_ptes - !partial;
 
     pl2e = map_domain_page(_mfn(pfn));
 
-    ASSERT(page->nr_validated_ptes);
-    do {
-        if ( is_guest_l2_slot(d, page->u.inuse.type_info, i) &&
-             put_page_from_l2e(pl2e[i], pfn) == 0 &&
-             i && hypercall_preempt_check() )
+    for ( ; ; )
+    {
+        if ( is_guest_l2_slot(d, page->u.inuse.type_info, i) )
+            rc = put_page_from_l2e(pl2e[i], pfn, partial, false);
+        if ( rc < 0 )
+            break;
+
+        partial = 0;
+
+        if ( !i-- )
+            break;
+
+        if ( hypercall_preempt_check() )
         {
-           page->nr_validated_ptes = i;
-           err = -ERESTART;
+            rc = -EINTR;
+            break;
         }
-    } while ( !err && i-- );
+    }
 
     unmap_domain_page(pl2e);
 
-    if ( !err )
+    if ( rc >= 0 )
+    {
         page->u.inuse.type_info &= ~PGT_pae_xen_l2;
+        rc = 0;
+    }
+    else if ( rc == -ERESTART )
+    {
+        page->nr_validated_ptes = i;
+        page->partial_pte = partial ?: -1;
+    }
+    else if ( rc == -EINTR && i < L2_PAGETABLE_ENTRIES - 1 )
+    {
+        page->nr_validated_ptes = i + 1;
+        page->partial_pte = 0;
+        rc = -ERESTART;
+    }
 
-    return err;
+    return rc;
 }
 
 static int free_l3_table(struct page_info *page)
@@ -2267,7 +2318,7 @@ static int mod_l2_entry(l2_pgentry_t *pl
             return -EBUSY;
         }
 
-        if ( unlikely((rc = get_page_from_l2e(nl2e, pfn, d)) < 0) )
+        if ( unlikely((rc = get_page_from_l2e(nl2e, pfn, d, 0)) < 0) )
             return rc;
 
         adjust_guest_l2e(nl2e, d);
@@ -2286,7 +2337,8 @@ static int mod_l2_entry(l2_pgentry_t *pl
         return -EBUSY;
     }
 
-    put_page_from_l2e(ol2e, pfn);
+    put_page_from_l2e(ol2e, pfn, 0, true);
+
     return rc;
 }

Places

File 5c7e70c6-x86-mm-L2-unvalidation-preemptible.patch of Package xen (Revision 0873801c1fef37fa1038530875ceabc7)

Places