[Qemu-ppc] [RFC PATCH v2] spapr: Ensure all LMBs are represented in ibm, dynamic-memory

[Bharata B Rao]

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 address@hidden node. Hence mark RMA LMBs
and also the LMBs for the gap b/n RAM and hotpluggable region as
reserved so that these LMBs are not recounted/counted by guest.

Signed-off-by: Bharata B Rao <address@hidden>
---
Changes in v2:

- Dropped the patch that removed alignment gap b/n RAM and hotplug
  region, but instead populated ibm,dynamic-memory with LMBs represented
  as RESERVED for that gap. We create DRC objects for these LMBs
  as it simplifies the logic of populating ibm,dynamic-memory. There can
  at max be 4 such DRC objects for the gap area (1GB max) and hence it should
  be fine.

v1: https://lists.gnu.org/archive/html/qemu-devel/2016-06/msg00627.html

 hw/ppc/spapr.c         | 51 ++++++++++++++++++++++++++++++++++++--------------
 include/hw/ppc/spapr.h |  5 +++--
 2 files changed, 40 insertions(+), 16 deletions(-)

diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index 0636642..0f4f7a3 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -762,18 +762,14 @@ 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.
-     */
-    if (!nr_lmbs) {
-        return 0;
-    }
-
-    /*
      * Allocate enough buffer size to fit in ibm,dynamic-memory
      * or ibm,associativity-lookup-arrays
      */
@@ -805,11 +801,18 @@ static int spapr_populate_drconf_memory(sPAPRMachineState 
*spapr, void *fdt)
     for (i = 0; i < nr_lmbs; i++) {
         sPAPRDRConnector *drc;
         sPAPRDRConnectorClass *drck;
-        uint64_t addr = i * lmb_size + spapr->hotplug_memory.base;;
+        uint64_t addr;
         uint32_t *dynamic_memory = cur_index;
 
+        if (i < hotplug_lmb_start) {
+            addr = i * lmb_size;
+        } else {
+            addr = (i - hotplug_lmb_start) * lmb_size +
+                   spapr->hotplug_memory.base;
+        }
+
         drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_LMB,
-                                       addr/lmb_size);
+                                       addr / lmb_size);
         g_assert(drc);
         drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
 
@@ -820,7 +823,14 @@ static int spapr_populate_drconf_memory(sPAPRMachineState 
*spapr, void *fdt)
         dynamic_memory[4] = cpu_to_be32(numa_get_node(addr, NULL));
         if (addr < machine->ram_size ||
                     memory_region_present(get_system_memory(), addr)) {
-            dynamic_memory[5] = cpu_to_be32(SPAPR_LMB_FLAGS_ASSIGNED);
+            if (addr < spapr->rma_size) {
+                dynamic_memory[5] = cpu_to_be32(SPAPR_LMB_FLAGS_RESERVED);
+            } else {
+                dynamic_memory[5] = cpu_to_be32(SPAPR_LMB_FLAGS_ASSIGNED);
+            }
+        } else if (addr >= machine->ram_size &&
+                   addr < spapr->hotplug_memory.base) {
+            dynamic_memory[5] = cpu_to_be32(SPAPR_LMB_FLAGS_RESERVED);
         } else {
             dynamic_memory[5] = cpu_to_be32(0);
         }
@@ -1652,16 +1662,29 @@ static void spapr_drc_reset(void *opaque)
 
 static void spapr_create_lmb_dr_connectors(sPAPRMachineState *spapr)
 {
-    MachineState *machine = MACHINE(spapr);
     uint64_t lmb_size = SPAPR_MEMORY_BLOCK_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;
     int i;
 
     for (i = 0; i < nr_lmbs; i++) {
         sPAPRDRConnector *drc;
         uint64_t addr;
 
-        addr = i * lmb_size + spapr->hotplug_memory.base;
+        /*
+         * Create DRC objects for entire memory range including RMA, boot-time
+         * memory and hotplug memory and for the gap b/n RAM and hotplug
+         * memory region.
+         */
+        if (i < hotplug_lmb_start) {
+            addr = i * lmb_size;
+        } else {
+            addr = (i - hotplug_lmb_start) * lmb_size +
+                   spapr->hotplug_memory.base;
+        }
+
         drc = spapr_dr_connector_new(OBJECT(spapr), 
SPAPR_DR_CONNECTOR_TYPE_LMB,
                                      addr/lmb_size);
         qemu_register_reset(spapr_drc_reset, drc);
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index 971df3d..bb265a2 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -620,9 +620,10 @@ 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
- * property under ibm,dynamic-reconfiguration-memory node.
+ * Defines for flag value in ibm,dynamic-memory property under
+ * ibm,dynamic-reconfiguration-memory node.
  */
 #define SPAPR_LMB_FLAGS_ASSIGNED 0x00000008
+#define SPAPR_LMB_FLAGS_RESERVED 0x00000080
 
 #endif /* !defined (__HW_SPAPR_H__) */
-- 
2.1.0