[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[xen staging-4.14] x86/pv: Fix ABAC cmpxchg() race in _get_page_type()



commit 758f40d7fa7e98ef2d2772ef8f0f57eabde028bd
Author:     Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
AuthorDate: Thu Jun 9 15:50:16 2022 +0200
Commit:     Jan Beulich <jbeulich@xxxxxxxx>
CommitDate: Thu Jun 9 15:50:16 2022 +0200

    x86/pv: Fix ABAC cmpxchg() race in _get_page_type()
    
    _get_page_type() suffers from a race condition where it incorrectly assumes
    that because 'x' was read and a subsequent a cmpxchg() succeeds, the type
    cannot have changed in-between.  Consider:
    
    CPU A:
      1. Creates an L2e referencing pg
         `-> _get_page_type(pg, PGT_l1_page_table), sees count 0, type 
PGT_writable_page
      2.     Issues flush_tlb_mask()
    CPU B:
      3. Creates a writeable mapping of pg
         `-> _get_page_type(pg, PGT_writable_page), count increases to 1
      4. Writes into new mapping, creating a TLB entry for pg
      5. Removes the writeable mapping of pg
         `-> _put_page_type(pg), count goes back down to 0
    CPU A:
      7.     Issues cmpxchg(), setting count 1, type PGT_l1_page_table
    
    CPU B now has a writeable mapping to pg, which Xen believes is a pagetable 
and
    suitably protected (i.e. read-only).  The TLB flush in step 2 must be 
deferred
    until after the guest is prohibited from creating new writeable mappings,
    which is after step 7.
    
    Defer all safety actions until after the cmpxchg() has successfully taken 
the
    intended typeref, because that is what prevents concurrent users from using
    the old type.
    
    Also remove the early validation for writeable and shared pages.  This 
removes
    race conditions where one half of a parallel mapping attempt can return
    successfully before:
     * The IOMMU pagetables are in sync with the new page type
     * Writeable mappings to shared pages have been torn down
    
    This is part of XSA-401 / CVE-2022-26362.
    
    Reported-by: Jann Horn <jannh@xxxxxxxxxx>
    Signed-off-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
    Reviewed-by: Jan Beulich <jbeulich@xxxxxxxx>
    Reviewed-by: George Dunlap <george.dunlap@xxxxxxxxxx>
    master commit: 8cc5036bc385112a82f1faff27a0970e6440dfed
    master date: 2022-06-09 14:21:04 +0200
---
 xen/arch/x86/mm.c | 116 +++++++++++++++++++++++++++++++-----------------------
 1 file changed, 67 insertions(+), 49 deletions(-)

diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 709eea2ee9..0b75b6371d 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -2919,56 +2919,12 @@ static int _get_page_type(struct page_info *page, 
unsigned long type,
              * Type changes are permitted when the typeref is 0.  If the type
              * actually changes, the page needs re-validating.
              */
-            struct domain *d = page_get_owner(page);
-
-            if ( d && shadow_mode_enabled(d) )
-               shadow_prepare_page_type_change(d, page, type);
 
             ASSERT(!(x & PGT_pae_xen_l2));
             if ( (x & PGT_type_mask) != type )
             {
-                /*
-                 * On type change we check to flush stale TLB entries. It is
-                 * vital that no other CPUs are left with writeable mappings
-                 * to a frame which is intending to become pgtable/segdesc.
-                 */
-                cpumask_t *mask = this_cpu(scratch_cpumask);
-
-                BUG_ON(in_irq());
-                cpumask_copy(mask, d->dirty_cpumask);
-
-                /* Don't flush if the timestamp is old enough */
-                tlbflush_filter(mask, page->tlbflush_timestamp);
-
-                if ( unlikely(!cpumask_empty(mask)) &&
-                     /* Shadow mode: track only writable pages. */
-                     (!shadow_mode_enabled(d) ||
-                      ((nx & PGT_type_mask) == PGT_writable_page)) )
-                {
-                    perfc_incr(need_flush_tlb_flush);
-                    /*
-                     * If page was a page table make sure the flush is
-                     * performed using an IPI in order to avoid changing the
-                     * type of a page table page under the feet of
-                     * spurious_page_fault().
-                     */
-                    flush_mask(mask,
-                               (x & PGT_type_mask) &&
-                               (x & PGT_type_mask) <= PGT_root_page_table
-                               ? FLUSH_TLB | FLUSH_FORCE_IPI
-                               : FLUSH_TLB);
-                }
-
-                /* We lose existing type and validity. */
                 nx &= ~(PGT_type_mask | PGT_validated);
                 nx |= type;
-
-                /*
-                 * No special validation needed for writable pages.
-                 * Page tables and GDT/LDT need to be scanned for validity.
-                 */
-                if ( type == PGT_writable_page || type == PGT_shared_page )
-                    nx |= PGT_validated;
             }
         }
         else if ( unlikely((x & (PGT_type_mask|PGT_pae_xen_l2)) != type) )
@@ -3049,6 +3005,56 @@ static int _get_page_type(struct page_info *page, 
unsigned long type,
             return -EINTR;
     }
 
+    /*
+     * One typeref has been taken and is now globally visible.
+     *
+     * The page is either in the "validate locked" state (PGT_[type] | 1) or
+     * fully validated (PGT_[type] | PGT_validated | >0).
+     */
+
+    if ( unlikely((x & PGT_count_mask) == 0) )
+    {
+        struct domain *d = page_get_owner(page);
+
+        if ( d && shadow_mode_enabled(d) )
+            shadow_prepare_page_type_change(d, page, type);
+
+        if ( (x & PGT_type_mask) != type )
+        {
+            /*
+             * On type change we check to flush stale TLB entries. It is
+             * vital that no other CPUs are left with writeable mappings
+             * to a frame which is intending to become pgtable/segdesc.
+             */
+            cpumask_t *mask = this_cpu(scratch_cpumask);
+
+            BUG_ON(in_irq());
+            cpumask_copy(mask, d->dirty_cpumask);
+
+            /* Don't flush if the timestamp is old enough */
+            tlbflush_filter(mask, page->tlbflush_timestamp);
+
+            if ( unlikely(!cpumask_empty(mask)) &&
+                 /* Shadow mode: track only writable pages. */
+                 (!shadow_mode_enabled(d) ||
+                  ((nx & PGT_type_mask) == PGT_writable_page)) )
+            {
+                perfc_incr(need_flush_tlb_flush);
+                /*
+                 * If page was a page table make sure the flush is
+                 * performed using an IPI in order to avoid changing the
+                 * type of a page table page under the feet of
+                 * spurious_page_fault().
+                 */
+                flush_mask(mask,
+                           (x & PGT_type_mask) &&
+                           (x & PGT_type_mask) <= PGT_root_page_table
+                           ? FLUSH_TLB | FLUSH_FORCE_IPI
+                           : FLUSH_TLB);
+            }
+        }
+    }
+
     if ( unlikely(((x & PGT_type_mask) == PGT_writable_page) !=
                   (type == PGT_writable_page)) )
     {
@@ -3075,13 +3081,25 @@ static int _get_page_type(struct page_info *page, 
unsigned long type,
 
     if ( unlikely(!(nx & PGT_validated)) )
     {
-        if ( !(x & PGT_partial) )
+        /*
+         * No special validation needed for writable or shared pages.  Page
+         * tables and GDT/LDT need to have their contents audited.
+         *
+         * per validate_page(), non-atomic updates are fine here.
+         */
+        if ( type == PGT_writable_page || type == PGT_shared_page )
+            page->u.inuse.type_info |= PGT_validated;
+        else
         {
-            page->nr_validated_ptes = 0;
-            page->partial_flags = 0;
-            page->linear_pt_count = 0;
+            if ( !(x & PGT_partial) )
+            {
+                page->nr_validated_ptes = 0;
+                page->partial_flags = 0;
+                page->linear_pt_count = 0;
+            }
+
+            rc = validate_page(page, type, preemptible);
         }
-        rc = validate_page(page, type, preemptible);
     }
 
  out:
--
generated by git-patchbot for /home/xen/git/xen.git#staging-4.14



 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.