x86/svm: do not try to handle recalc NPT faults immediately

A recalculation NPT fault doesn't always require additional handling
in hvm_hap_nested_page_fault(), moreover in general case if there is no
explicit handling done there - the fault is wrongly considered fatal.

This covers a specific case of migration with vGPU assigned which
uses direct MMIO mappings made by XEN_DOMCTL_memory_mapping hypercall:
at a moment log-dirty is enabled globally, recalculation is requested
for the whole guest memory including those mapped MMIO regions
which causes a page fault being raised at the first access to them;
but due to MMIO P2M type not having any explicit handling in
hvm_hap_nested_page_fault() a domain is erroneously crashed with unhandled
SVM violation.

Instead of trying to be opportunistic - use safer approach and handle
P2M recalculation in a separate NPT fault by attempting to retry after
making the necessary adjustments. This is aligned with Intel behavior
where there are separate VMEXITs for recalculation and EPT violations
(faults) and only faults are handled in hvm_hap_nested_page_fault().
Do it by also unifying do_recalc return code with Intel implementation
where returning 1 means P2M was actually changed.

Since there was no case previously where p2m_pt_handle_deferred_changes()
could return a positive value - it's safe to replace ">= 0" with just "== 0"
in VMEXIT_NPF handler. finish_type_change() is also not affected by the
change as being able to deal with >0 return value of p2m->recalc from
EPT implementation.

Signed-off-by: Igor Druzhinin <igor.druzhinin@citrix.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
master commit: 51ca66c37371b10b378513af126646de22eddb17
master date: 2020-06-05 17:12:11 +0200

diff --git a/xen/arch/x86/hvm/svm/svm.c b/xen/arch/x86/hvm/svm/svm.c
index 9128e923b061a6fefe7d2113222f720f2387f965..d74701718b1f3acf2498a87ab2cd8a983810cc02 100644 (file)
--- a/xen/arch/x86/hvm/svm/svm.c
+++ b/xen/arch/x86/hvm/svm/svm.c
@@ -3042,9 +3042,10 @@ void svm_vmexit_handler(struct cpu_user_regs *regs)
             v->arch.hvm.svm.cached_insn_len = vmcb->guest_ins_len & 0xf;
         rc = vmcb->exitinfo1 & PFEC_page_present
              ? p2m_pt_handle_deferred_changes(vmcb->exitinfo2) : 0;
-        if ( rc >= 0 )
+        if ( rc == 0 )
+            /* If no recal adjustments were being made - handle this fault */
             svm_do_nested_pgfault(v, regs, vmcb->exitinfo1, vmcb->exitinfo2);
-        else
+        else if ( rc < 0 )
         {
             printk(XENLOG_G_ERR
                    "%pv: Error %d handling NPF (gpa=%08lx ec=%04lx)\n",

diff --git a/xen/arch/x86/mm/p2m-pt.c b/xen/arch/x86/mm/p2m-pt.c
index 87bf74ed92a5e5e85d2a99542b50f6bccf6a18c5..0629cd530e301159e4bbdee48dc5b92b2a303ebf 100644 (file)
--- a/xen/arch/x86/mm/p2m-pt.c
+++ b/xen/arch/x86/mm/p2m-pt.c
@@ -370,6 +370,7 @@ static int do_recalc(struct p2m_domain *p2m, unsigned long gfn)
     unsigned int level = 4;
     l1_pgentry_t *pent;
     int err = 0;
+    bool recalc_done = false;
 
     table = map_domain_page(pagetable_get_mfn(p2m_get_pagetable(p2m)));
     while ( --level )
@@ -431,6 +432,8 @@ static int do_recalc(struct p2m_domain *p2m, unsigned long gfn)
                 clear_recalc(l1, e);
                 err = p2m->write_p2m_entry(p2m, gfn, pent, e, level + 1);
                 ASSERT(!err);
+
+                recalc_done = true;
             }
         }
         unmap_domain_page((void *)((unsigned long)pent & PAGE_MASK));
@@ -480,12 +483,14 @@ static int do_recalc(struct p2m_domain *p2m, unsigned long gfn)
             clear_recalc(l1, e);
         err = p2m->write_p2m_entry(p2m, gfn, pent, e, level + 1);
         ASSERT(!err);
+
+        recalc_done = true;
     }
 
  out:
     unmap_domain_page(table);
 
-    return err;
+    return err ?: recalc_done;
 }
 
 int p2m_pt_handle_deferred_changes(uint64_t gpa)

diff --git a/xen/arch/x86/mm/p2m.c b/xen/arch/x86/mm/p2m.c
index 16608098b158127c5cce8fc9e90472cd7bbbf58b..25ce19f20b90cc53e83a107f179717327f76be1e 100644 (file)
--- a/xen/arch/x86/mm/p2m.c
+++ b/xen/arch/x86/mm/p2m.c
@@ -1178,7 +1178,7 @@ static int finish_type_change(struct p2m_domain *p2m,
         rc = p2m->recalc(p2m, gfn);
         /*
          * ept->recalc could return 0/1/-ENOMEM. pt->recalc could return
-         * 0/-ENOMEM/-ENOENT, -ENOENT isn't an error as we are looping
+         * 0/1/-ENOMEM/-ENOENT, -ENOENT isn't an error as we are looping
          * gfn here.
          */
         if ( rc == -ENOENT )