[xen staging] x86/PoD: defer nested P2M flushes

[patchbot@xxxxxxx]

commit 6d187caae50284625af8799a79712c7a4c6a9a59
Author:     Jan Beulich <jbeulich@xxxxxxxx>
AuthorDate: Wed Oct 20 12:42:44 2021 +0200
Commit:     Jan Beulich <jbeulich@xxxxxxxx>
CommitDate: Wed Oct 20 12:42:44 2021 +0200

    x86/PoD: defer nested P2M flushes
    
    With NPT or shadow in use, the p2m_set_entry() -> p2m_pt_set_entry() ->
    write_p2m_entry() -> p2m_flush_nestedp2m() call sequence triggers a lock
    order violation when the PoD lock is held around it. Hence such flushing
    needs to be deferred. Steal the approach from p2m_change_type_range().
    (Note that strictly speaking the change at the out_of_memory label is
    not needed, as the domain gets crashed there anyway. The change is being
    made nevertheless to avoid setting up a trap from someone meaning to
    deal with that case better than by domain_crash().)
    
    Similarly for EPT I think ept_set_entry() -> ept_sync_domain() ->
    ept_sync_domain_prepare() -> p2m_flush_nestedp2m() is affected. Make its
    p2m_flush_nestedp2m() invocation conditional. Note that this then also
    alters behavior of p2m_change_type_range() on EPT, deferring the nested
    flushes there as well. I think this should have been that way from the
    introduction of the flag.
    
    Reported-by: Elliott Mitchell <ehem+xen@xxxxxxx>
    Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
    Acked-by: Roger Pau Monné <roger.pau@xxxxxxxxxx>
    Reviewed-by: Kevin Tian <kevin.tian@xxxxxxxxx>
---
 xen/arch/x86/mm/p2m-ept.c |  2 +-
 xen/arch/x86/mm/p2m-pod.c | 30 +++++++++++++++++++++++-------
 2 files changed, 24 insertions(+), 8 deletions(-)

diff --git a/xen/arch/x86/mm/p2m-ept.c b/xen/arch/x86/mm/p2m-ept.c
index e7e873dc28..b2d57a3ee8 100644
--- a/xen/arch/x86/mm/p2m-ept.c
+++ b/xen/arch/x86/mm/p2m-ept.c
@@ -1253,7 +1253,7 @@ static void ept_sync_domain_prepare(struct p2m_domain 
*p2m)
     {
         if ( p2m_is_nestedp2m(p2m) )
             ept = &p2m_get_hostp2m(d)->ept;
-        else
+        else if ( !p2m->defer_nested_flush )
             p2m_flush_nestedp2m(d);
     }
 
diff --git a/xen/arch/x86/mm/p2m-pod.c b/xen/arch/x86/mm/p2m-pod.c
index 8abc57265c..d0134755e5 100644
--- a/xen/arch/x86/mm/p2m-pod.c
+++ b/xen/arch/x86/mm/p2m-pod.c
@@ -24,6 +24,7 @@
 #include <xen/mm.h>
 #include <xen/sched.h>
 #include <xen/trace.h>
+#include <asm/hvm/nestedhvm.h>
 #include <asm/page.h>
 #include <asm/paging.h>
 #include <asm/p2m.h>
@@ -494,6 +495,13 @@ p2m_pod_offline_or_broken_replace(struct page_info *p)
 static int
 p2m_pod_zero_check_superpage(struct p2m_domain *p2m, gfn_t gfn);
 
+static void pod_unlock_and_flush(struct p2m_domain *p2m)
+{
+    pod_unlock(p2m);
+    p2m->defer_nested_flush = false;
+    if ( nestedhvm_enabled(p2m->domain) )
+        p2m_flush_nestedp2m(p2m->domain);
+}
 
 /*
  * This function is needed for two reasons:
@@ -514,6 +522,7 @@ p2m_pod_decrease_reservation(struct domain *d, gfn_t gfn, 
unsigned int order)
 
     gfn_lock(p2m, gfn, order);
     pod_lock(p2m);
+    p2m->defer_nested_flush = true;
 
     /*
      * If we don't have any outstanding PoD entries, let things take their
@@ -665,7 +674,7 @@ out_entry_check:
     }
 
 out_unlock:
-    pod_unlock(p2m);
+    pod_unlock_and_flush(p2m);
     gfn_unlock(p2m, gfn, order);
     return ret;
 }
@@ -1144,8 +1153,10 @@ p2m_pod_demand_populate(struct p2m_domain *p2m, gfn_t 
gfn,
      * won't start until we're done.
      */
     if ( unlikely(d->is_dying) )
-        goto out_fail;
-
+    {
+        pod_unlock(p2m);
+        return false;
+    }
 
     /*
      * Because PoD does not have cache list for 1GB pages, it has to remap
@@ -1167,6 +1178,8 @@ p2m_pod_demand_populate(struct p2m_domain *p2m, gfn_t gfn,
                               p2m_populate_on_demand, p2m->default_access);
     }
 
+    p2m->defer_nested_flush = true;
+
     /* Only reclaim if we're in actual need of more cache. */
     if ( p2m->pod.entry_count > p2m->pod.count )
         pod_eager_reclaim(p2m);
@@ -1229,22 +1242,25 @@ p2m_pod_demand_populate(struct p2m_domain *p2m, gfn_t 
gfn,
         __trace_var(TRC_MEM_POD_POPULATE, 0, sizeof(t), &t);
     }
 
-    pod_unlock(p2m);
+    pod_unlock_and_flush(p2m);
     return true;
+
 out_of_memory:
-    pod_unlock(p2m);
+    pod_unlock_and_flush(p2m);
 
     printk("%s: Dom%d out of PoD memory! (tot=%"PRIu32" ents=%ld dom%d)\n",
            __func__, d->domain_id, domain_tot_pages(d),
            p2m->pod.entry_count, current->domain->domain_id);
     domain_crash(d);
     return false;
+
 out_fail:
-    pod_unlock(p2m);
+    pod_unlock_and_flush(p2m);
     return false;
+
 remap_and_retry:
     BUG_ON(order != PAGE_ORDER_2M);
-    pod_unlock(p2m);
+    pod_unlock_and_flush(p2m);
 
     /*
      * Remap this 2-meg region in singleton chunks. See the comment on the
--
generated by git-patchbot for /home/xen/git/xen.git#staging