[Qemu-devel] [PATCH 20/35] acpi: memory hotplug ACPI hardware implementation

[Igor Mammedov <imammedo@redhat.com>]

- implements QEMU hardware part of memory hotplug protocol
  described at "docs/specs/acpi_mem_hotplug.txt"
- handles only memory add notification event for now

Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
 docs/specs/acpi_mem_hotplug.txt  |  44 ++++++++++++
 hw/acpi/Makefile.objs            |   1 +
 hw/acpi/memory_hotplug.c         | 144 +++++++++++++++++++++++++++++++++++++++
 include/hw/acpi/acpi_defs.h      |   3 +
 include/hw/acpi/memory_hotplug.h |  29 ++++++++
 5 files changed, 221 insertions(+)
 create mode 100644 docs/specs/acpi_mem_hotplug.txt
 create mode 100644 hw/acpi/memory_hotplug.c
 create mode 100644 include/hw/acpi/memory_hotplug.h

diff --git a/docs/specs/acpi_mem_hotplug.txt b/docs/specs/acpi_mem_hotplug.txt
new file mode 100644
index 0000000..1290994
--- /dev/null
+++ b/docs/specs/acpi_mem_hotplug.txt
@@ -0,0 +1,44 @@
+QEMU<->ACPI BIOS memory hotplug interface
+--------------------------------------
+
+ACPI BIOS GPE.3 handler is dedicated for notifying OS about memory hot-add
+events.
+
+Memory hot-plug interface (IO port 0xa00-0xa17, 1-4 byte access):
+---------------------------------------------------------------
+0xa00:
+  read access:
+      [0x0-0x3] Lo part of memory device phys address
+      [0x4-0x7] Hi part of memory device phys address
+      [0x8-0xb] Lo part of memory device size in bytes
+      [0xc-0xf] Hi part of memory device size in bytes
+      [0x10-0x13] Memory device proximity domain
+      [0x14] Memory device status fields
+          bits:
+              0: Device is enabled and may be used by guest
+              1: Device insert event, used to distinguish device for which
+                 no device check event to OSPM was issued.
+                 It's valid only when bit 1 is set.
+              2-7: reserved and should be ignored by OSPM
+      [0x15-0x17] reserved
+
+  write access:
+      [0x0-0x3] Memory device slot selector, selects active memory device.
+                All following accesses to other registers in 0xa00-0xa17
+                region will read/store data from/to selected memory device.
+      [0x4-0x7] OST event code reported by OSPM
+      [0x8-0xb] OST status code reported by OSPM
+      [0xc-0x13] reserved, writes into it are ignored
+      [0x14] Memory device control fields
+          bits:
+              0: reserved, OSPM must clear it before writing to register
+              1: if set to 1 clears device insert event, set by OSPM
+                 after it has emitted device check event for the
+                 selected memory device
+              2-7: reserved, OSPM must clear them before writing to register
+
+Selecting memory device slot beyond present range has no effect on platform:
+   - write accesses to memory hot-plug registers not documented above are
+     ignored
+   - read accesses to memory hot-plug registers not documented above return
+     all bits set to 1.
diff --git a/hw/acpi/Makefile.objs b/hw/acpi/Makefile.objs
index 397d32b..004e1b2 100644
--- a/hw/acpi/Makefile.objs
+++ b/hw/acpi/Makefile.objs
@@ -1 +1,2 @@
 common-obj-$(CONFIG_ACPI) += core.o piix4.o ich9.o pcihp.o cpu_hotplug.o
+common-obj-$(CONFIG_ACPI) += memory_hotplug.o
diff --git a/hw/acpi/memory_hotplug.c b/hw/acpi/memory_hotplug.c
new file mode 100644
index 0000000..b0292c8
--- /dev/null
+++ b/hw/acpi/memory_hotplug.c
@@ -0,0 +1,144 @@
+#include "hw/acpi/memory_hotplug.h"
+#include "hw/acpi/acpi_defs.h"
+#include "hw/boards.h"
+
+static uint64_t acpi_memory_hotplug_read(void *opaque, hwaddr addr,
+                                         unsigned int size)
+{
+    uint32_t val = 0;
+    MemHotplugState *mem_st = opaque;
+    MemStatus *mdev;
+
+    if (mem_st->selector >= mem_st->dev_count) {
+        return 0;
+    }
+
+    mdev = &mem_st->devs[mem_st->selector];
+    switch (addr) {
+    case 0x0: /* Lo part of phys address where DIMM is mapped */
+        val = object_property_get_int(OBJECT(mdev->dimm), "start", NULL);
+        break;
+    case 0x4: /* Hi part of phys address where DIMM is mapped */
+        val = object_property_get_int(OBJECT(mdev->dimm), "start", NULL) >> 32;
+        break;
+    case 0x8: /* Lo part of DIMM size */
+        val = object_property_get_int(OBJECT(mdev->dimm), "size", NULL);
+        break;
+    case 0xc: /* Hi part of DIMM size */
+        val = object_property_get_int(OBJECT(mdev->dimm), "size", NULL) >> 32;
+        break;
+    case 0x10: /* node proximity for _PXM method */
+        val = object_property_get_int(OBJECT(mdev->dimm), "node", NULL);
+        break;
+    case 0x14: /* pack and return is_* fields */
+        val |= mdev->is_enabled   ? 1 : 0;
+        val |= mdev->is_inserting ? 2 : 0;
+        break;
+    default:
+        val = ~0;
+        break;
+    }
+    return val;
+}
+
+static void acpi_memory_hotplug_write(void *opaque, hwaddr addr, uint64_t data,
+                                      unsigned int size)
+{
+    MemHotplugState *mem_st = opaque;
+    MemStatus *mdev;
+
+    if (!mem_st->dev_count) {
+        return;
+    }
+
+    if (addr) {
+        if (mem_st->selector >= mem_st->dev_count) {
+            return;
+        }
+    }
+
+    switch (addr) {
+    case 0x0: /* DIMM slot selector */
+        mem_st->selector = data;
+        break;
+    case 0x4: /* _OST event  */
+        mdev = &mem_st->devs[mem_st->selector];
+        if (data == 1) {
+            /* TODO: handle device insert OST event */
+        } else if (data == 3) {
+            /* TODO: handle device remove OST event */
+        }
+        mdev->ost_event = data;
+        break;
+    case 0x8: /* _OST status */
+        mdev = &mem_st->devs[mem_st->selector];
+        mdev->ost_status = data;
+        /* TODO: report async error */
+        /* TODO: implement memory removal on guest signal */
+        break;
+    case 0x14:
+        mdev = &mem_st->devs[mem_st->selector];
+        if (data & 2) { /* clear insert event */
+            mdev->is_inserting  = false;
+        }
+        break;
+    }
+
+}
+static const MemoryRegionOps acpi_memory_hotplug_ops = {
+    .read = acpi_memory_hotplug_read,
+    .write = acpi_memory_hotplug_write,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+    .valid = {
+        .min_access_size = 1,
+        .max_access_size = 4,
+    },
+};
+
+void acpi_memory_hotplug_init(MemoryRegion *as, Object *owner,
+                              MemHotplugState *state)
+{
+    MachineState *machine = MACHINE(qdev_get_machine());
+
+    state->dev_count = machine->init_args.ram_slots;
+    if (!state->dev_count) {
+        return;
+    }
+
+    state->devs = g_malloc0(sizeof(*state->devs) * state->dev_count);
+    memory_region_init_io(&state->io, owner, &acpi_memory_hotplug_ops, state,
+                          "apci-mem-hotplug", ACPI_MEMORY_HOTPLUG_IO_LEN);
+    memory_region_add_subregion(as, ACPI_MEMORY_HOTPLUG_BASE, &state->io);
+}
+
+void acpi_memory_plug_cb(ACPIREGS *ar, qemu_irq irq, MemHotplugState *mem_st,
+                         DeviceState *dev, Error **errp)
+{
+    MemStatus *mdev;
+    Error *local_err = NULL;
+    int slot = object_property_get_int(OBJECT(dev), "slot", &local_err);
+
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    if (slot >= mem_st->dev_count) {
+        char *dev_path = object_get_canonical_path(OBJECT(dev));
+        error_setg(errp, "acpi_memory_plug_cb: "
+                   "device [%s] returned invalid memory slot[%d]",
+                    dev_path, slot);
+        g_free(dev_path);
+        return;
+    }
+
+    mdev = &mem_st->devs[slot];
+    mdev->dimm = dev;
+    mdev->is_enabled = true;
+    mdev->is_inserting = true;
+
+    /* do ACPI magic */
+    ar->gpe.sts[0] |= ACPI_MEMORY_HOTPLUG_STATUS;
+    acpi_update_sci(ar, irq);
+    return;
+}
diff --git a/include/hw/acpi/acpi_defs.h b/include/hw/acpi/acpi_defs.h
index 36b831f..a6e7219 100644
--- a/include/hw/acpi/acpi_defs.h
+++ b/include/hw/acpi/acpi_defs.h
@@ -29,4 +29,7 @@
 #define ICH9_CPU_HOTPLUG_IO_BASE 0x0CD8
 #define PIIX4_CPU_HOTPLUG_IO_BASE 0xaf00
 
+#define ACPI_MEMORY_HOTPLUG_IO_LEN 24
+#define ACPI_MEMORY_HOTPLUG_BASE 0x0a00
+
 #endif
diff --git a/include/hw/acpi/memory_hotplug.h b/include/hw/acpi/memory_hotplug.h
new file mode 100644
index 0000000..8f90f72
--- /dev/null
+++ b/include/hw/acpi/memory_hotplug.h
@@ -0,0 +1,29 @@
+#ifndef QEMU_HW_ACPI_MEMORY_HOTPLUG_H
+#define QEMU_HW_ACPI_MEMORY_HOTPLUG_H
+
+#include "hw/qdev-core.h"
+#include "hw/acpi/acpi.h"
+
+#define ACPI_MEMORY_HOTPLUG_STATUS 8
+
+typedef struct MemStatus {
+    DeviceState *dimm;
+    bool is_enabled;
+    bool is_inserting;
+    uint32_t ost_event;
+    uint32_t ost_status;
+} MemStatus;
+
+typedef struct MemHotplugState {
+    MemoryRegion io;
+    uint32_t selector;
+    uint32_t dev_count;
+    MemStatus *devs;
+} MemHotplugState;
+
+void acpi_memory_hotplug_init(MemoryRegion *as, Object *owner,
+                              MemHotplugState *state);
+
+void acpi_memory_plug_cb(ACPIREGS *ar, qemu_irq irq, MemHotplugState *mem_st,
+                         DeviceState *dev, Error **errp);
+#endif
-- 
1.9.0