[Qemu-devel] [PULL 05/26] spapr_iommu: Migrate full state

[David Gibson <david@gibson.dropbear.id.au>]

From: Alexey Kardashevskiy <aik@ozlabs.ru>

The source guest could have reallocated the default TCE table and
migrate bigger/smaller table. This adds reallocation in post_load()
if the default table size is different on source and destination.

This adds @bus_offset, @page_shift to the migration stream as
a subsection so when DDW is added, migration to older machines will
still be possible. As @bus_offset and @page_shift are not used yet,
this makes no change in behavior.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
---
 hw/ppc/spapr_iommu.c   | 65 +++++++++++++++++++++++++++++++++++++++++++++++---
 include/hw/ppc/spapr.h |  3 +++
 trace-events           |  2 ++
 3 files changed, 67 insertions(+), 3 deletions(-)

diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c
index de63467..28991bc 100644
--- a/hw/ppc/spapr_iommu.c
+++ b/hw/ppc/spapr_iommu.c
@@ -138,33 +138,92 @@ static IOMMUTLBEntry spapr_tce_translate_iommu(MemoryRegion *iommu, hwaddr addr,
     return ret;
 }
 
+static void spapr_tce_table_pre_save(void *opaque)
+{
+    sPAPRTCETable *tcet = SPAPR_TCE_TABLE(opaque);
+
+    tcet->mig_table = tcet->table;
+    tcet->mig_nb_table = tcet->nb_table;
+
+    trace_spapr_iommu_pre_save(tcet->liobn, tcet->mig_nb_table,
+                               tcet->bus_offset, tcet->page_shift);
+}
+
 static int spapr_tce_table_post_load(void *opaque, int version_id)
 {
     sPAPRTCETable *tcet = SPAPR_TCE_TABLE(opaque);
+    uint32_t old_nb_table = tcet->nb_table;
+    uint64_t old_bus_offset = tcet->bus_offset;
+    uint32_t old_page_shift = tcet->page_shift;
 
     if (tcet->vdev) {
         spapr_vio_set_bypass(tcet->vdev, tcet->bypass);
     }
 
+    if (tcet->mig_nb_table != tcet->nb_table) {
+        spapr_tce_table_disable(tcet);
+    }
+
+    if (tcet->mig_nb_table) {
+        if (!tcet->nb_table) {
+            spapr_tce_table_enable(tcet, old_page_shift, old_bus_offset,
+                                   tcet->mig_nb_table);
+        }
+
+        memcpy(tcet->table, tcet->mig_table,
+               tcet->nb_table * sizeof(tcet->table[0]));
+
+        free(tcet->mig_table);
+        tcet->mig_table = NULL;
+    }
+
+    trace_spapr_iommu_post_load(tcet->liobn, old_nb_table, tcet->nb_table,
+                                tcet->bus_offset, tcet->page_shift);
+
     return 0;
 }
 
+static bool spapr_tce_table_ex_needed(void *opaque)
+{
+    sPAPRTCETable *tcet = opaque;
+
+    return tcet->bus_offset || tcet->page_shift != 0xC;
+}
+
+static const VMStateDescription vmstate_spapr_tce_table_ex = {
+    .name = "spapr_iommu_ex",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = spapr_tce_table_ex_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT64(bus_offset, sPAPRTCETable),
+        VMSTATE_UINT32(page_shift, sPAPRTCETable),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
 static const VMStateDescription vmstate_spapr_tce_table = {
     .name = "spapr_iommu",
     .version_id = 2,
     .minimum_version_id = 2,
+    .pre_save = spapr_tce_table_pre_save,
     .post_load = spapr_tce_table_post_load,
     .fields      = (VMStateField []) {
         /* Sanity check */
         VMSTATE_UINT32_EQUAL(liobn, sPAPRTCETable),
-        VMSTATE_UINT32_EQUAL(nb_table, sPAPRTCETable),
 
         /* IOMMU state */
+        VMSTATE_UINT32(mig_nb_table, sPAPRTCETable),
         VMSTATE_BOOL(bypass, sPAPRTCETable),
-        VMSTATE_VARRAY_UINT32(table, sPAPRTCETable, nb_table, 0, vmstate_info_uint64, uint64_t),
+        VMSTATE_VARRAY_UINT32_ALLOC(mig_table, sPAPRTCETable, mig_nb_table, 0,
+                                    vmstate_info_uint64, uint64_t),
 
         VMSTATE_END_OF_LIST()
     },
+    .subsections = (const VMStateDescription*[]) {
+        &vmstate_spapr_tce_table_ex,
+        NULL
+    }
 };
 
 static MemoryRegionIOMMUOps spapr_iommu_ops = {
@@ -264,7 +323,7 @@ void spapr_tce_table_enable(sPAPRTCETable *tcet,
                            (uint64_t)tcet->nb_table << tcet->page_shift);
 }
 
-static void spapr_tce_table_disable(sPAPRTCETable *tcet)
+void spapr_tce_table_disable(sPAPRTCETable *tcet)
 {
     if (!tcet->nb_table) {
         return;
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index 26c327d..f849714 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -539,6 +539,8 @@ struct sPAPRTCETable {
     uint64_t bus_offset;
     uint32_t page_shift;
     uint64_t *table;
+    uint32_t mig_nb_table;
+    uint64_t *mig_table;
     bool bypass;
     bool need_vfio;
     int fd;
@@ -565,6 +567,7 @@ sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn);
 void spapr_tce_table_enable(sPAPRTCETable *tcet,
                             uint32_t page_shift, uint64_t bus_offset,
                             uint32_t nb_table);
+void spapr_tce_table_disable(sPAPRTCETable *tcet);
 void spapr_tce_set_need_vfio(sPAPRTCETable *tcet, bool need_vfio);
 
 MemoryRegion *spapr_tce_get_iommu(sPAPRTCETable *tcet);
diff --git a/trace-events b/trace-events
index c50b870..44a8664 100644
--- a/trace-events
+++ b/trace-events
@@ -1431,6 +1431,8 @@ spapr_iommu_pci_indirect(uint64_t liobn, uint64_t ioba, uint64_t tce, uint64_t i
 spapr_iommu_pci_stuff(uint64_t liobn, uint64_t ioba, uint64_t tce_value, uint64_t npages, uint64_t ret) "liobn=%"PRIx64" ioba=0x%"PRIx64" tcevalue=0x%"PRIx64" npages=%"PRId64" ret=%"PRId64
 spapr_iommu_xlate(uint64_t liobn, uint64_t ioba, uint64_t tce, unsigned perm, unsigned pgsize) "liobn=%"PRIx64" 0x%"PRIx64" -> 0x%"PRIx64" perm=%u mask=%x"
 spapr_iommu_new_table(uint64_t liobn, void *table, int fd) "liobn=%"PRIx64" table=%p fd=%d"
+spapr_iommu_pre_save(uint64_t liobn, uint32_t nb, uint64_t offs, uint32_t ps) "liobn=%"PRIx64" %"PRIx32" bus_offset=%"PRIx64" ps=%"PRIu32
+spapr_iommu_post_load(uint64_t liobn, uint32_t pre_nb, uint32_t post_nb, uint64_t offs, uint32_t ps) "liobn=%"PRIx64" %"PRIx32" => %"PRIx32" bus_offset=%"PRIx64" ps=%"PRIu32
 
 # hw/ppc/ppc.c
 ppc_tb_adjust(uint64_t offs1, uint64_t offs2, int64_t diff, int64_t seconds) "adjusted from 0x%"PRIx64" to 0x%"PRIx64", diff %"PRId64" (%"PRId64"s)"
-- 
2.5.5