[xen staging-4.14] x86/pv: Flush TLB in response to paging structure changes

[patchbot@xxxxxxx]

commit 10bb63c203f42d931fa1fa7dbbae7ce1765cecf2
Author:     Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
AuthorDate: Mon Oct 19 15:51:22 2020 +0100
Commit:     Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
CommitDate: Tue Oct 27 17:56:22 2020 +0000

    x86/pv: Flush TLB in response to paging structure changes
    
    With MMU_UPDATE, a PV guest can make changes to higher level pagetables.  
This
    is safe from Xen's point of view (as the update only affects guest 
mappings),
    and the guest is required to flush (if necessary) after making updates.
    
    However, Xen's use of linear pagetables (UPDATE_VA_MAPPING, GNTTABOP_map,
    writeable pagetables, etc.) is an implementation detail outside of the
    API/ABI.
    
    Changes in the paging structure require invalidations in the linear 
pagetable
    range for subsequent accesses into the linear pagetables to access non-stale
    mappings.  Xen must provide suitable flushing to prevent intermixed guest
    actions from accidentally accessing/modifying the wrong pagetable.
    
    For all L2 and higher modifications, flush the TLB.  PV guests cannot create
    L2 or higher entries with the Global bit set, so no mappings established in
    the linear range can be global.  (This could in principle be an order 39 
flush
    starting at LINEAR_PT_VIRT_START, but no such mechanism exists in practice.)
    
    Express the necessary flushes as a set of booleans which accumulate across 
the
    operation.  Comment the flushing logic extensively.
    
    This is XSA-286.
    
    Signed-off-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
    Reviewed-by: Jan Beulich <jbeulich@xxxxxxxx>
    (cherry picked from commit 16a20963b3209788f2c0d3a3eebb7d92f03f5883)
---
 xen/arch/x86/mm.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 59 insertions(+), 10 deletions(-)

diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 1caa2df0a5..61cf6a7b9b 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -3896,7 +3896,8 @@ long do_mmu_update(
     struct vcpu *curr = current, *v = curr;
     struct domain *d = v->domain, *pt_owner = d, *pg_owner;
     mfn_t map_mfn = INVALID_MFN, mfn;
-    bool sync_guest = false;
+    bool flush_linear_pt = false, flush_root_pt_local = false,
+        flush_root_pt_others = false;
     uint32_t xsm_needed = 0;
     uint32_t xsm_checked = 0;
     int rc = put_old_guest_table(curr);
@@ -4046,6 +4047,8 @@ long do_mmu_update(
                         break;
                     rc = mod_l2_entry(va, l2e_from_intpte(req.val), mfn,
                                       cmd == MMU_PT_UPDATE_PRESERVE_AD, v);
+                    if ( !rc )
+                        flush_linear_pt = true;
                     break;
 
                 case PGT_l3_page_table:
@@ -4053,6 +4056,8 @@ long do_mmu_update(
                         break;
                     rc = mod_l3_entry(va, l3e_from_intpte(req.val), mfn,
                                       cmd == MMU_PT_UPDATE_PRESERVE_AD, v);
+                    if ( !rc )
+                        flush_linear_pt = true;
                     break;
 
                 case PGT_l4_page_table:
@@ -4060,6 +4065,8 @@ long do_mmu_update(
                         break;
                     rc = mod_l4_entry(va, l4e_from_intpte(req.val), mfn,
                                       cmd == MMU_PT_UPDATE_PRESERVE_AD, v);
+                    if ( !rc )
+                        flush_linear_pt = true;
                     if ( !rc && pt_owner->arch.pv.xpti )
                     {
                         bool local_in_use = false;
@@ -4068,7 +4075,7 @@ long do_mmu_update(
                                     mfn) )
                         {
                             local_in_use = true;
-                            get_cpu_info()->root_pgt_changed = true;
+                            flush_root_pt_local = true;
                         }
 
                         /*
@@ -4080,7 +4087,7 @@ long do_mmu_update(
                              (1 + !!(page->u.inuse.type_info & PGT_pinned) +
                               
mfn_eq(pagetable_get_mfn(curr->arch.guest_table_user),
                                      mfn) + local_in_use) )
-                            sync_guest = true;
+                            flush_root_pt_others = true;
                     }
                     break;
 
@@ -4182,19 +4189,61 @@ long do_mmu_update(
     if ( va )
         unmap_domain_page(va);
 
-    if ( sync_guest )
+    /*
+     * Perform required TLB maintenance.
+     *
+     * This logic currently depend on flush_linear_pt being a superset of the
+     * flush_root_pt_* conditions.
+     *
+     * pt_owner may not be current->domain.  This may occur during
+     * construction of 32bit PV guests, or debugging of PV guests.  The
+     * behaviour cannot be correct with domain unpaused.  We therefore expect
+     * pt_owner->dirty_cpumask to be empty, but it is a waste of effort to
+     * explicitly check for, and exclude, this corner case.
+     *
+     * flush_linear_pt requires a FLUSH_TLB to all dirty CPUs.  The flush must
+     * be performed now to maintain correct behaviour across a multicall.
+     * i.e. we cannot relax FLUSH_TLB to FLUSH_ROOT_PGTBL, given that the
+     * former is a side effect of the latter, because the resync (which is in
+     * the return-to-guest path) happens too late.
+     *
+     * flush_root_pt_* requires FLUSH_ROOT_PGTBL on either the local CPU
+     * (implies pt_owner == current->domain and current->processor set in
+     * pt_owner->dirty_cpumask), and/or all *other* dirty CPUs as there are
+     * references we can't account for locally.
+     */
+    if ( flush_linear_pt /* || flush_root_pt_local || flush_root_pt_others */ )
     {
+        unsigned int cpu = smp_processor_id();
+        cpumask_t *mask = pt_owner->dirty_cpumask;
+
         /*
-         * Force other vCPU-s of the affected guest to pick up L4 entry
-         * changes (if any).
+         * Always handle local flushing separately (if applicable), to
+         * separate the flush invocations appropriately for scope of the two
+         * flush_root_pt_* variables.
          */
-        unsigned int cpu = smp_processor_id();
-        cpumask_t *mask = per_cpu(scratch_cpumask, cpu);
+        if ( likely(cpumask_test_cpu(cpu, mask)) )
+        {
+            mask = per_cpu(scratch_cpumask, cpu);
 
-        cpumask_andnot(mask, pt_owner->dirty_cpumask, cpumask_of(cpu));
+            cpumask_copy(mask, pt_owner->dirty_cpumask);
+            __cpumask_clear_cpu(cpu, mask);
+
+            flush_local(FLUSH_TLB |
+                        (flush_root_pt_local ? FLUSH_ROOT_PGTBL : 0));
+        }
+        else
+            /* Sanity check.  flush_root_pt_local implies local cpu is dirty. 
*/
+            ASSERT(!flush_root_pt_local);
+
+        /* Flush the remote dirty CPUs.  Does not include the local CPU. */
         if ( !cpumask_empty(mask) )
-            flush_mask(mask, FLUSH_ROOT_PGTBL);
+            flush_mask(mask, FLUSH_TLB |
+                       (flush_root_pt_others ? FLUSH_ROOT_PGTBL : 0));
     }
+    else
+        /* Sanity check.  flush_root_pt_* implies flush_linear_pt. */
+        ASSERT(!flush_root_pt_local && !flush_root_pt_others);
 
     perfc_add(num_page_updates, i);
 
--
generated by git-patchbot for /home/xen/git/xen.git#staging-4.14