[Qemu-devel] [PATCH V4] spapr: Fix stale HTAB during live migration

[Samuel Mendoza-Jonas <sam.mj@au1.ibm.com>]

If a guest reboots during a running migration, changes to the
hash page table are not necessarily updated on the destination.
Opening a new file descriptor to the HTAB forces the migration
handler to resend the entire table.

Signed-off-by: Samuel Mendoza-Jonas <sam.mj@au1.ibm.com>
---
Changes in v4: Readability: need_reset to htab_fd_stale
        Add spapr_check_htab_fd() and use error_report()
Changes in v3: Pointed out by David, htab_save_iterate could
	potentially try to read before htab_fd is open again.
	Leave opening the fd to the functions trying to read.
Changes in v2: Forgot check on kvmppc_get_htab_fd return value

 hw/ppc/spapr.c         | 37 +++++++++++++++++++++++++++++++++++++
 include/hw/ppc/spapr.h |  1 +
 2 files changed, 38 insertions(+)

diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index 3a6d26d..68f97a9 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -997,6 +997,11 @@ static void spapr_reset_htab(sPAPREnvironment *spapr)
         /* Kernel handles htab, we don't need to allocate one */
         spapr->htab_shift = shift;
         kvmppc_kern_htab = true;
+
+        /* Check if we are overlapping a migration */
+        if (spapr->htab_fd > 0) {
+            spapr->htab_fd_stale = true;
+        }
     } else {
         if (!spapr->htab) {
             /* Allocate an htab if we don't yet have one */
@@ -1014,6 +1019,27 @@ static void spapr_reset_htab(sPAPREnvironment *spapr)
     }
 }
 
+/* A guest reset will cause spapr->htab_fd to become stale if being used.
+ * Reopen the file descriptor to make sure the whole HTAB is properly read.
+ */
+static int spapr_check_htab_fd(sPAPREnvironment *spapr)
+{
+    int rc = 0;
+
+    if (atomic_cmpxchg(&spapr->htab_fd_stale, true, false) == true) {
+        close(spapr->htab_fd);
+        spapr->htab_fd = kvmppc_get_htab_fd(false);
+
+        if (spapr->htab_fd < 0) {
+            error_report("Unable to open fd for reading hash table from KVM: "
+                    "%s", strerror(errno));
+            rc = -1;;
+        }
+    }
+
+    return rc;
+}
+
 static void ppc_spapr_reset(void)
 {
     PowerPCCPU *first_ppc_cpu;
@@ -1156,6 +1182,7 @@ static int htab_save_setup(QEMUFile *f, void *opaque)
     } else {
         assert(kvm_enabled());
 
+        spapr->htab_fd_stale = false;
         spapr->htab_fd = kvmppc_get_htab_fd(false);
         if (spapr->htab_fd < 0) {
             fprintf(stderr, "Unable to open fd for reading hash table from KVM: %s\n",
@@ -1309,6 +1336,11 @@ static int htab_save_iterate(QEMUFile *f, void *opaque)
     if (!spapr->htab) {
         assert(kvm_enabled());
 
+        rc = spapr_check_htab_fd(spapr);
+        if (rc < 0) {
+            return rc;
+        }
+
         rc = kvmppc_save_htab(f, spapr->htab_fd,
                               MAX_KVM_BUF_SIZE, MAX_ITERATION_NS);
         if (rc < 0) {
@@ -1340,6 +1372,11 @@ static int htab_save_complete(QEMUFile *f, void *opaque)
 
         assert(kvm_enabled());
 
+        rc = spapr_check_htab_fd(spapr);
+        if (rc < 0) {
+            return rc;
+        }
+
         rc = kvmppc_save_htab(f, spapr->htab_fd, MAX_KVM_BUF_SIZE, -1);
         if (rc < 0) {
             return rc;
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index 0c2e3c5..0421d9a 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -71,6 +71,7 @@ typedef struct sPAPREnvironment {
     int htab_save_index;
     bool htab_first_pass;
     int htab_fd;
+    bool htab_fd_stale;
 
     /* state for Dynamic Reconfiguration Connectors */
     sPAPRDrcEntry drc_table[SPAPR_DRC_TABLE_SIZE];
-- 
1.9.3