spapr: Ensure all LMBs are represented in ibm,dynamic-memory

Memory hotplug can fail for some combinations of RAM and maxmem when
DDW is enabled in the presence of devices like nec-usb-xhci. DDW depends
on maximum addressable memory returned by guest and this value is currently
being calculated wrongly by the guest kernel routine memory_hotplug_max().
While there is an attempt to fix the guest kernel, this patch works
around the problem within QEMU itself.

memory_hotplug_max() routine in the guest kernel arrives at max
addressable memory by multiplying lmb-size with the lmb-count obtained
from ibm,dynamic-memory property. There are two assumptions here:

- All LMBs are part of ibm,dynamic memory: This is not true for PowerKVM
  where only hot-pluggable LMBs are present in this property.
- The memory area comprising of RAM and hotplug region is contiguous: This
  needn't be true always for PowerKVM as there can be gap between
  boot time RAM and hotplug region.

To work around this guest kernel bug, ensure that ibm,dynamic-memory
has information about all the LMBs (RMA, boot-time LMBs, future
hotpluggable LMBs, and dummy LMBs to cover the gap between RAM and
hotpluggable region).

RMA is represented separately by memory@0 node. Hence mark RMA LMBs
and also the LMBs for the gap b/n RAM and hotpluggable region as
reserved and as having no valid DRC so that these LMBs are not considered
by the guest.

Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
Reviewed-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Reviewed-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>

hw/ppc/spapr.c

@@ -762,14 +762,17 @@ static int spapr_populate_drconf_memory(sPAPRMachineState *spapr, void *fdt)
     int ret, i, offset;
     uint64_t lmb_size = SPAPR_MEMORY_BLOCK_SIZE;
     uint32_t prop_lmb_size[] = {0, cpu_to_be32(lmb_size)};
-    uint32_t nr_lmbs = (machine->maxram_size - machine->ram_size)/lmb_size;
+    uint32_t hotplug_lmb_start = spapr->hotplug_memory.base / lmb_size;
+    uint32_t nr_lmbs = (spapr->hotplug_memory.base +
+                       memory_region_size(&spapr->hotplug_memory.mr)) /
+                       lmb_size;
     uint32_t *int_buf, *cur_index, buf_len;
     int nr_nodes = nb_numa_nodes ? nb_numa_nodes : 1;
 
     /*
-     * Don't create the node if there are no DR LMBs.
+     * Don't create the node if there is no hotpluggable memory
      */
-    if (!nr_lmbs) {
+    if (machine->ram_size == machine->maxram_size) {
         return 0;
     }
 
@@ -803,26 +806,40 @@ static int spapr_populate_drconf_memory(sPAPRMachineState *spapr, void *fdt)
     int_buf[0] = cpu_to_be32(nr_lmbs);
     cur_index++;
     for (i = 0; i < nr_lmbs; i++) {
-        sPAPRDRConnector *drc;
+        uint64_t addr = i * lmb_size;
-        sPAPRDRConnectorClass *drck;
-        uint64_t addr = i * lmb_size + spapr->hotplug_memory.base;;
         uint32_t *dynamic_memory = cur_index;
 
-        drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_LMB,
+        if (i >= hotplug_lmb_start) {
-                                       addr/lmb_size);
+            sPAPRDRConnector *drc;
-        g_assert(drc);
+            sPAPRDRConnectorClass *drck;
-        drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
 
-        dynamic_memory[0] = cpu_to_be32(addr >> 32);
+            drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_LMB, i);
-        dynamic_memory[1] = cpu_to_be32(addr & 0xffffffff);
+            g_assert(drc);
-        dynamic_memory[2] = cpu_to_be32(drck->get_index(drc));
+            drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
-        dynamic_memory[3] = cpu_to_be32(0); /* reserved */
+
-        dynamic_memory[4] = cpu_to_be32(numa_get_node(addr, NULL));
+            dynamic_memory[0] = cpu_to_be32(addr >> 32);
-        if (addr < machine->ram_size ||
+            dynamic_memory[1] = cpu_to_be32(addr & 0xffffffff);
-                    memory_region_present(get_system_memory(), addr)) {
+            dynamic_memory[2] = cpu_to_be32(drck->get_index(drc));
-            dynamic_memory[5] = cpu_to_be32(SPAPR_LMB_FLAGS_ASSIGNED);
+            dynamic_memory[3] = cpu_to_be32(0); /* reserved */
+            dynamic_memory[4] = cpu_to_be32(numa_get_node(addr, NULL));
+            if (memory_region_present(get_system_memory(), addr)) {
+                dynamic_memory[5] = cpu_to_be32(SPAPR_LMB_FLAGS_ASSIGNED);
+            } else {
+                dynamic_memory[5] = cpu_to_be32(0);
+            }
         } else {
-            dynamic_memory[5] = cpu_to_be32(0);
+            /*
+             * LMB information for RMA, boot time RAM and gap b/n RAM and
+             * hotplug memory region -- all these are marked as reserved
+             * and as having no valid DRC.
+             */
+            dynamic_memory[0] = cpu_to_be32(addr >> 32);
+            dynamic_memory[1] = cpu_to_be32(addr & 0xffffffff);
+            dynamic_memory[2] = cpu_to_be32(0);
+            dynamic_memory[3] = cpu_to_be32(0); /* reserved */
+            dynamic_memory[4] = cpu_to_be32(-1);
+            dynamic_memory[5] = cpu_to_be32(SPAPR_LMB_FLAGS_RESERVED |
+                                            SPAPR_LMB_FLAGS_DRC_INVALID);
         }
 
         cur_index += SPAPR_DR_LMB_LIST_ENTRY_SIZE;

include/hw/ppc/spapr.h

@@ -620,9 +620,11 @@ int spapr_rng_populate_dt(void *fdt);
 #define SPAPR_DR_LMB_LIST_ENTRY_SIZE 6
 
 /*
- * This flag value defines the LMB as assigned in ibm,dynamic-memory
+ * Defines for flag value in ibm,dynamic-memory property under
- * property under ibm,dynamic-reconfiguration-memory node.
+ * ibm,dynamic-reconfiguration-memory node.
  */
 #define SPAPR_LMB_FLAGS_ASSIGNED 0x00000008
+#define SPAPR_LMB_FLAGS_DRC_INVALID 0x00000020
+#define SPAPR_LMB_FLAGS_RESERVED 0x00000080
 
 #endif /* !defined (__HW_SPAPR_H__) */