Merge remote-tracking branch 'remotes/dgibson/tags/ppc-for-2.6-20160218' into staging

ppc patch queue for 2016-02-18

Currently accumulated patches for target-ppc, pseries machine type and
related devices.
  * Some cleanups to management of SDR1 and the hashed page table
  * Implementations of a number of simple PAPR hypercalls
  * Significant improvements to the Macintosh CUDA device
  * Several bugfixes

# gpg: Signature made Thu 18 Feb 2016 04:16:51 GMT using RSA key ID 20D9B392
# gpg: Good signature from "David Gibson <david@gibson.dropbear.id.au>"
# gpg:                 aka "David Gibson (Red Hat) <dgibson@redhat.com>"
# gpg:                 aka "David Gibson (ozlabs.org) <dgibson@ozlabs.org>"
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain that the signature belongs to the owner.
# Primary key fingerprint: 75F4 6586 AE61 A66C C44E  87DC 6C38 CACA 20D9 B392

* remotes/dgibson/tags/ppc-for-2.6-20160218: (26 commits)
  hw/ppc/spapr: Halt CPU when powering off via RTAS call
  pseries: Include missing pseries-2.5 compat properties in pseries-2.4
  cuda: remove CUDA_GET_SET_IIC/CUDA_COMBINED_FORMAT_IIC commands
  cuda: remove GET_6805_ADDR command
  cuda: port SET_TIME command to new framework
  cuda: port GET_TIME command to new framework
  cuda: port SET_POWER_MESSAGES command to new framework
  cuda: port FILE_SERVER_FLAG command to new framework
  cuda: port RESET_SYSTEM command to new framework
  cuda: port POWERDOWN command to new framework
  cuda: port SET_DEVICE_LIST command to new framework
  cuda: port SET_AUTO_RATE command to new framework
  cuda: port AUTOPOLL command to new framework
  cuda: move unknown commands reject out of switch
  cuda: add a framework to handle commands
  hw/ppc/spapr: Implement the h_set_xdabr hypercall
  hw/ppc/spapr: Implement h_set_dabr
  hw/ppc/spapr: Add h_set_sprg0 hypercall
  migration: ensure htab_save_first completes after timeout
  target-ppc: Remove hack for ppc_hash64_load_hpte*() with HV KVM
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

13 files changed, 393 insertions, 232 deletions

diff --git a/hw/input/adb.c b/hw/input/adb.c
index c384856c13..f0ad0d4471 100644
--- a/hw/input/adb.c
+++ b/hw/input/adb.c
@@ -89,7 +89,7 @@ int adb_request(ADBBusState *s, uint8_t *obuf, const uint8_t *buf, int len)
 }
 
 /* XXX: move that to cuda ? */
-int adb_poll(ADBBusState *s, uint8_t *obuf)
+int adb_poll(ADBBusState *s, uint8_t *obuf, uint16_t poll_mask)
 {
     ADBDevice *d;
     int olen, i;
@@ -100,13 +100,15 @@ int adb_poll(ADBBusState *s, uint8_t *obuf)
         if (s->poll_index >= s->nb_devices)
             s->poll_index = 0;
         d = s->devices[s->poll_index];
-        buf[0] = ADB_READREG | (d->devaddr << 4);
-        olen = adb_request(s, obuf + 1, buf, 1);
-        /* if there is data, we poll again the same device */
-        if (olen > 0) {
-            obuf[0] = buf[0];
-            olen++;
-            break;
+        if ((1 << d->devaddr) & poll_mask) {
+            buf[0] = ADB_READREG | (d->devaddr << 4);
+            olen = adb_request(s, obuf + 1, buf, 1);
+            /* if there is data, we poll again the same device */
+            if (olen > 0) {
+                obuf[0] = buf[0];
+                olen++;
+                break;
+            }
         }
         s->poll_index++;
     }
diff --git a/hw/misc/macio/cuda.c b/hw/misc/macio/cuda.c
index 316c1ac8da..481abdb754 100644
--- a/hw/misc/macio/cuda.c
+++ b/hw/misc/macio/cuda.c
@@ -106,7 +106,6 @@
 #define CUDA_COMBINED_FORMAT_IIC	0x25
 
 #define CUDA_TIMER_FREQ (4700000 / 6)
-#define CUDA_ADB_POLL_FREQ 50
 
 /* CUDA returns time_t's offset from Jan 1, 1904, not 1970 */
 #define RTC_OFFSET                      2082844800
@@ -524,7 +523,7 @@ static void cuda_adb_poll(void *opaque)
     uint8_t obuf[ADB_MAX_OUT_LEN + 2];
     int olen;
 
-    olen = adb_poll(&s->adb_bus, obuf + 2);
+    olen = adb_poll(&s->adb_bus, obuf + 2, s->adb_poll_mask);
     if (olen > 0) {
         obuf[0] = ADB_PACKET;
         obuf[1] = 0x40; /* polled data */
@@ -532,87 +531,213 @@ static void cuda_adb_poll(void *opaque)
     }
     timer_mod(s->adb_poll_timer,
                    qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
-                   (get_ticks_per_sec() / CUDA_ADB_POLL_FREQ));
+                   (get_ticks_per_sec() / (1000 / s->autopoll_rate_ms)));
 }
 
-static void cuda_receive_packet(CUDAState *s,
-                                const uint8_t *data, int len)
+/* description of commands */
+typedef struct CudaCommand {
+    uint8_t command;
+    const char *name;
+    bool (*handler)(CUDAState *s,
+                    const uint8_t *in_args, int in_len,
+                    uint8_t *out_args, int *out_len);
+} CudaCommand;
+
+static bool cuda_cmd_autopoll(CUDAState *s,
+                              const uint8_t *in_data, int in_len,
+                              uint8_t *out_data, int *out_len)
 {
-    uint8_t obuf[16] = { CUDA_PACKET, 0, data[0] };
     int autopoll;
+
+    if (in_len != 1) {
+        return false;
+    }
+
+    autopoll = (in_data[0] != 0);
+    if (autopoll != s->autopoll) {
+        s->autopoll = autopoll;
+        if (autopoll) {
+            timer_mod(s->adb_poll_timer,
+                      qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
+                      (get_ticks_per_sec() / (1000 / s->autopoll_rate_ms)));
+        } else {
+            timer_del(s->adb_poll_timer);
+        }
+    }
+    return true;
+}
+
+static bool cuda_cmd_set_autorate(CUDAState *s,
+                                  const uint8_t *in_data, int in_len,
+                                  uint8_t *out_data, int *out_len)
+{
+    if (in_len != 1) {
+        return false;
+    }
+
+    /* we don't want a period of 0 ms */
+    /* FIXME: check what real hardware does */
+    if (in_data[0] == 0) {
+        return false;
+    }
+
+    s->autopoll_rate_ms = in_data[0];
+    if (s->autopoll) {
+        timer_mod(s->adb_poll_timer,
+                  qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
+                  (get_ticks_per_sec() / (1000 / s->autopoll_rate_ms)));
+    }
+    return true;
+}
+
+static bool cuda_cmd_set_device_list(CUDAState *s,
+                                     const uint8_t *in_data, int in_len,
+                                     uint8_t *out_data, int *out_len)
+{
+    if (in_len != 2) {
+        return false;
+    }
+
+    s->adb_poll_mask = (((uint16_t)in_data[0]) << 8) | in_data[1];
+    return true;
+}
+
+static bool cuda_cmd_powerdown(CUDAState *s,
+                               const uint8_t *in_data, int in_len,
+                               uint8_t *out_data, int *out_len)
+{
+    if (in_len != 0) {
+        return false;
+    }
+
+    qemu_system_shutdown_request();
+    return true;
+}
+
+static bool cuda_cmd_reset_system(CUDAState *s,
+                                  const uint8_t *in_data, int in_len,
+                                  uint8_t *out_data, int *out_len)
+{
+    if (in_len != 0) {
+        return false;
+    }
+
+    qemu_system_reset_request();
+    return true;
+}
+
+static bool cuda_cmd_set_file_server_flag(CUDAState *s,
+                                          const uint8_t *in_data, int in_len,
+                                          uint8_t *out_data, int *out_len)
+{
+    if (in_len != 1) {
+        return false;
+    }
+
+    qemu_log_mask(LOG_UNIMP,
+                  "CUDA: unimplemented command FILE_SERVER_FLAG %d\n",
+                  in_data[0]);
+    return true;
+}
+
+static bool cuda_cmd_set_power_message(CUDAState *s,
+                                       const uint8_t *in_data, int in_len,
+                                       uint8_t *out_data, int *out_len)
+{
+    if (in_len != 1) {
+        return false;
+    }
+
+    qemu_log_mask(LOG_UNIMP,
+                  "CUDA: unimplemented command SET_POWER_MESSAGE %d\n",
+                  in_data[0]);
+    return true;
+}
+
+static bool cuda_cmd_get_time(CUDAState *s,
+                              const uint8_t *in_data, int in_len,
+                              uint8_t *out_data, int *out_len)
+{
     uint32_t ti;
 
-    switch(data[0]) {
-    case CUDA_AUTOPOLL:
-        autopoll = (data[1] != 0);
-        if (autopoll != s->autopoll) {
-            s->autopoll = autopoll;
-            if (autopoll) {
-                timer_mod(s->adb_poll_timer,
-                               qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
-                               (get_ticks_per_sec() / CUDA_ADB_POLL_FREQ));
+    if (in_len != 0) {
+        return false;
+    }
+
+    ti = s->tick_offset + (qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL)
+                           / get_ticks_per_sec());
+    out_data[0] = ti >> 24;
+    out_data[1] = ti >> 16;
+    out_data[2] = ti >> 8;
+    out_data[3] = ti;
+    *out_len = 4;
+    return true;
+}
+
+static bool cuda_cmd_set_time(CUDAState *s,
+                              const uint8_t *in_data, int in_len,
+                              uint8_t *out_data, int *out_len)
+{
+    uint32_t ti;
+
+    if (in_len != 4) {
+        return false;
+    }
+
+    ti = (((uint32_t)in_data[1]) << 24) + (((uint32_t)in_data[2]) << 16)
+         + (((uint32_t)in_data[3]) << 8) + in_data[4];
+    s->tick_offset = ti - (qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL)
+                           / get_ticks_per_sec());
+    return true;
+}
+
+static const CudaCommand handlers[] = {
+    { CUDA_AUTOPOLL, "AUTOPOLL", cuda_cmd_autopoll },
+    { CUDA_SET_AUTO_RATE, "SET_AUTO_RATE",  cuda_cmd_set_autorate },
+    { CUDA_SET_DEVICE_LIST, "SET_DEVICE_LIST", cuda_cmd_set_device_list },
+    { CUDA_POWERDOWN, "POWERDOWN", cuda_cmd_powerdown },
+    { CUDA_RESET_SYSTEM, "RESET_SYSTEM", cuda_cmd_reset_system },
+    { CUDA_FILE_SERVER_FLAG, "FILE_SERVER_FLAG",
+      cuda_cmd_set_file_server_flag },
+    { CUDA_SET_POWER_MESSAGES, "SET_POWER_MESSAGES",
+      cuda_cmd_set_power_message },
+    { CUDA_GET_TIME, "GET_TIME", cuda_cmd_get_time },
+    { CUDA_SET_TIME, "SET_TIME", cuda_cmd_set_time },
+};
+
+static void cuda_receive_packet(CUDAState *s,
+                                const uint8_t *data, int len)
+{
+    uint8_t obuf[16] = { CUDA_PACKET, 0, data[0] };
+    int i, out_len = 0;
+
+    for (i = 0; i < ARRAY_SIZE(handlers); i++) {
+        const CudaCommand *desc = &handlers[i];
+        if (desc->command == data[0]) {
+            CUDA_DPRINTF("handling command %s\n", desc->name);
+            out_len = 0;
+            if (desc->handler(s, data + 1, len - 1, obuf + 3, &out_len)) {
+                cuda_send_packet_to_host(s, obuf, 3 + out_len);
             } else {
-                timer_del(s->adb_poll_timer);
+                qemu_log_mask(LOG_GUEST_ERROR,
+                              "CUDA: %s: wrong parameters %d\n",
+                              desc->name, len);
+                obuf[0] = ERROR_PACKET;
+                obuf[1] = 0x5; /* bad parameters */
+                obuf[2] = CUDA_PACKET;
+                obuf[3] = data[0];
+                cuda_send_packet_to_host(s, obuf, 4);
             }
+            return;
         }
-        cuda_send_packet_to_host(s, obuf, 3);
-        break;
-    case CUDA_GET_6805_ADDR:
-        cuda_send_packet_to_host(s, obuf, 3);
-        break;
-    case CUDA_SET_TIME:
-        ti = (((uint32_t)data[1]) << 24) + (((uint32_t)data[2]) << 16) + (((uint32_t)data[3]) << 8) + data[4];
-        s->tick_offset = ti - (qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) / get_ticks_per_sec());
-        cuda_send_packet_to_host(s, obuf, 3);
-        break;
-    case CUDA_GET_TIME:
-        ti = s->tick_offset + (qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) / get_ticks_per_sec());
-        obuf[3] = ti >> 24;
-        obuf[4] = ti >> 16;
-        obuf[5] = ti >> 8;
-        obuf[6] = ti;
-        cuda_send_packet_to_host(s, obuf, 7);
-        break;
-    case CUDA_FILE_SERVER_FLAG:
-    case CUDA_SET_DEVICE_LIST:
-    case CUDA_SET_AUTO_RATE:
-    case CUDA_SET_POWER_MESSAGES:
-        cuda_send_packet_to_host(s, obuf, 3);
-        break;
-    case CUDA_POWERDOWN:
-        cuda_send_packet_to_host(s, obuf, 3);
-        qemu_system_shutdown_request();
-        break;
-    case CUDA_RESET_SYSTEM:
-        cuda_send_packet_to_host(s, obuf, 3);
-        qemu_system_reset_request();
-        break;
-    case CUDA_COMBINED_FORMAT_IIC:
-        obuf[0] = ERROR_PACKET;
-        obuf[1] = 0x5;
-        obuf[2] = CUDA_PACKET;
-        obuf[3] = data[0];
-        cuda_send_packet_to_host(s, obuf, 4);
-        break;
-    case CUDA_GET_SET_IIC:
-        if (len == 4) {
-            cuda_send_packet_to_host(s, obuf, 3);
-        } else {
-            obuf[0] = ERROR_PACKET;
-            obuf[1] = 0x2;
-            obuf[2] = CUDA_PACKET;
-            obuf[3] = data[0];
-            cuda_send_packet_to_host(s, obuf, 4);
-        }
-        break;
-    default:
-        obuf[0] = ERROR_PACKET;
-        obuf[1] = 0x2;
-        obuf[2] = CUDA_PACKET;
-        obuf[3] = data[0];
-        cuda_send_packet_to_host(s, obuf, 4);
-        break;
     }
+
+    qemu_log_mask(LOG_GUEST_ERROR, "CUDA: unknown command 0x%02x\n", data[0]);
+    obuf[0] = ERROR_PACKET;
+    obuf[1] = 0x2; /* unknown command */
+    obuf[2] = CUDA_PACKET;
+    obuf[3] = data[0];
+    cuda_send_packet_to_host(s, obuf, 4);
 }
 
 static void cuda_receive_packet_from_host(CUDAState *s,
@@ -710,8 +835,8 @@ static const VMStateDescription vmstate_cuda_timer = {
 
 static const VMStateDescription vmstate_cuda = {
     .name = "cuda",
-    .version_id = 3,
-    .minimum_version_id = 3,
+    .version_id = 4,
+    .minimum_version_id = 4,
     .fields = (VMStateField[]) {
         VMSTATE_UINT8(a, CUDAState),
         VMSTATE_UINT8(b, CUDAState),
@@ -729,6 +854,8 @@ static const VMStateDescription vmstate_cuda = {
         VMSTATE_INT32(data_in_index, CUDAState),
         VMSTATE_INT32(data_out_index, CUDAState),
         VMSTATE_UINT8(autopoll, CUDAState),
+        VMSTATE_UINT8(autopoll_rate_ms, CUDAState),
+        VMSTATE_UINT16(adb_poll_mask, CUDAState),
         VMSTATE_BUFFER(data_in, CUDAState),
         VMSTATE_BUFFER(data_out, CUDAState),
         VMSTATE_UINT32(tick_offset, CUDAState),
@@ -782,6 +909,8 @@ static void cuda_realizefn(DeviceState *dev, Error **errp)
     s->tick_offset = (uint32_t)mktimegm(&tm) + RTC_OFFSET;
 
     s->adb_poll_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, cuda_adb_poll, s);
+    s->autopoll_rate_ms = 20;
+    s->adb_poll_mask = 0xffff;
 }
 
 static void cuda_initfn(Object *obj)
diff --git a/hw/nvram/mac_nvram.c b/hw/nvram/mac_nvram.c
index 564ef936d1..1671f4686e 100644
--- a/hw/nvram/mac_nvram.c
+++ b/hw/nvram/mac_nvram.c
@@ -49,7 +49,8 @@ static void macio_nvram_writeb(void *opaque, hwaddr addr,
 
     addr = (addr >> s->it_shift) & (s->size - 1);
     s->data[addr] = value;
-    NVR_DPRINTF("writeb addr %04" PHYS_PRIx " val %" PRIx64 "\n", addr, value);
+    NVR_DPRINTF("writeb addr %04" HWADDR_PRIx " val %" PRIx64 "\n",
+                addr, value);
 }
 
 static uint64_t macio_nvram_readb(void *opaque, hwaddr addr,
@@ -60,7 +61,8 @@ static uint64_t macio_nvram_readb(void *opaque, hwaddr addr,
 
     addr = (addr >> s->it_shift) & (s->size - 1);
     value = s->data[addr];
-    NVR_DPRINTF("readb addr %04x val %x\n", (int)addr, value);
+    NVR_DPRINTF("readb addr %04" HWADDR_PRIx " val %" PRIx32 "\n",
+                addr, value);
 
     return value;
 }
diff --git a/hw/pci-host/uninorth.c b/hw/pci-host/uninorth.c
index 40a2e3e6b4..15b1054232 100644
--- a/hw/pci-host/uninorth.c
+++ b/hw/pci-host/uninorth.c
@@ -120,7 +120,7 @@ static void unin_data_write(void *opaque, hwaddr addr,
 {
     UNINState *s = opaque;
     PCIHostState *phb = PCI_HOST_BRIDGE(s);
-    UNIN_DPRINTF("write addr %" TARGET_FMT_plx " len %d val %"PRIx64"\n",
+    UNIN_DPRINTF("write addr " TARGET_FMT_plx " len %d val %"PRIx64"\n",
                  addr, len, val);
     pci_data_write(phb->bus,
                    unin_get_config_reg(phb->config_reg, addr),
@@ -137,7 +137,7 @@ static uint64_t unin_data_read(void *opaque, hwaddr addr,
     val = pci_data_read(phb->bus,
                         unin_get_config_reg(phb->config_reg, addr),
                         len);
-    UNIN_DPRINTF("read addr %" TARGET_FMT_plx " len %d val %x\n",
+    UNIN_DPRINTF("read addr " TARGET_FMT_plx " len %d val %x\n",
                  addr, len, val);
     return val;
 }
diff --git a/hw/ppc/mac.h b/hw/ppc/mac.h
index ecf7792bc9..5764b86c28 100644
--- a/hw/ppc/mac.h
+++ b/hw/ppc/mac.h
@@ -111,6 +111,8 @@ typedef struct CUDAState {
     int data_out_index;
 
     qemu_irq irq;
+    uint16_t adb_poll_mask;
+    uint8_t autopoll_rate_ms;
     uint8_t autopoll;
     uint8_t data_in[128];
     uint8_t data_out[16];
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index 5bd8fd3ef8..e214a34257 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -1024,83 +1024,93 @@ static void emulate_spapr_hypercall(PowerPCCPU *cpu)
 #define CLEAN_HPTE(_hpte)  ((*(uint64_t *)(_hpte)) &= tswap64(~HPTE64_V_HPTE_DIRTY))
 #define DIRTY_HPTE(_hpte)  ((*(uint64_t *)(_hpte)) |= tswap64(HPTE64_V_HPTE_DIRTY))
 
-static void spapr_alloc_htab(sPAPRMachineState *spapr)
+/*
+ * Get the fd to access the kernel htab, re-opening it if necessary
+ */
+static int get_htab_fd(sPAPRMachineState *spapr)
 {
-    long shift;
-    int index;
+    if (spapr->htab_fd >= 0) {
+        return spapr->htab_fd;
+    }
 
-    /* allocate hash page table.  For now we always make this 16mb,
-     * later we should probably make it scale to the size of guest
-     * RAM */
+    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));
+    }
 
-    shift = kvmppc_reset_htab(spapr->htab_shift);
-    if (shift < 0) {
-        /*
-         * For HV KVM, host kernel will return -ENOMEM when requested
-         * HTAB size can't be allocated.
-         */
-        error_setg(&error_abort, "Failed to allocate HTAB of requested size, try with smaller maxmem");
-    } else if (shift > 0) {
-        /*
-         * Kernel handles htab, we don't need to allocate one
-         *
-         * Older kernels can fall back to lower HTAB shift values,
-         * but we don't allow booting of such guests.
-         */
-        if (shift != spapr->htab_shift) {
-            error_setg(&error_abort, "Failed to allocate HTAB of requested size, try with smaller maxmem");
-        }
+    return spapr->htab_fd;
+}
 
-        spapr->htab_shift = shift;
-        kvmppc_kern_htab = true;
-    } else {
-        /* Allocate htab */
-        spapr->htab = qemu_memalign(HTAB_SIZE(spapr), HTAB_SIZE(spapr));
+static void close_htab_fd(sPAPRMachineState *spapr)
+{
+    if (spapr->htab_fd >= 0) {
+        close(spapr->htab_fd);
+    }
+    spapr->htab_fd = -1;
+}
 
-        /* And clear it */
-        memset(spapr->htab, 0, HTAB_SIZE(spapr));
+static int spapr_hpt_shift_for_ramsize(uint64_t ramsize)
+{
+    int shift;
 
-        for (index = 0; index < HTAB_SIZE(spapr) / HASH_PTE_SIZE_64; index++) {
-            DIRTY_HPTE(HPTE(spapr->htab, index));
-        }
-    }
+    /* We aim for a hash table of size 1/128 the size of RAM (rounded
+     * up).  The PAPR recommendation is actually 1/64 of RAM size, but
+     * that's much more than is needed for Linux guests */
+    shift = ctz64(pow2ceil(ramsize)) - 7;
+    shift = MAX(shift, 18); /* Minimum architected size */
+    shift = MIN(shift, 46); /* Maximum architected size */
+    return shift;
 }
 
-/*
- * Clear HTAB entries during reset.
- *
- * If host kernel has allocated HTAB, KVM_PPC_ALLOCATE_HTAB ioctl is
- * used to clear HTAB. Otherwise QEMU-allocated HTAB is cleared manually.
- */
-static void spapr_reset_htab(sPAPRMachineState *spapr)
+static void spapr_reallocate_hpt(sPAPRMachineState *spapr, int shift,
+                                 Error **errp)
 {
-    long shift;
-    int index;
+    long rc;
 
-    shift = kvmppc_reset_htab(spapr->htab_shift);
-    if (shift < 0) {
-        error_setg(&error_abort, "Failed to reset HTAB");
-    } else if (shift > 0) {
-        if (shift != spapr->htab_shift) {
-            error_setg(&error_abort, "Requested HTAB allocation failed during reset");
-        }
+    /* Clean up any HPT info from a previous boot */
+    g_free(spapr->htab);
+    spapr->htab = NULL;
+    spapr->htab_shift = 0;
+    close_htab_fd(spapr);
 
-        /* Tell readers to update their file descriptor */
-        if (spapr->htab_fd >= 0) {
-            spapr->htab_fd_stale = true;
+    rc = kvmppc_reset_htab(shift);
+    if (rc < 0) {
+        /* kernel-side HPT needed, but couldn't allocate one */
+        error_setg_errno(errp, errno,
+                         "Failed to allocate KVM HPT of order %d (try smaller maxmem?)",
+                         shift);
+        /* This is almost certainly fatal, but if the caller really
+         * wants to carry on with shift == 0, it's welcome to try */
+    } else if (rc > 0) {
+        /* kernel-side HPT allocated */
+        if (rc != shift) {
+            error_setg(errp,
+                       "Requested order %d HPT, but kernel allocated order %ld (try smaller maxmem?)",
+                       shift, rc);
         }
+
+        spapr->htab_shift = shift;
+        kvmppc_kern_htab = true;
     } else {
-        memset(spapr->htab, 0, HTAB_SIZE(spapr));
+        /* kernel-side HPT not needed, allocate in userspace instead */
+        size_t size = 1ULL << shift;
+        int i;
 
-        for (index = 0; index < HTAB_SIZE(spapr) / HASH_PTE_SIZE_64; index++) {
-            DIRTY_HPTE(HPTE(spapr->htab, index));
+        spapr->htab = qemu_memalign(size, size);
+        if (!spapr->htab) {
+            error_setg_errno(errp, errno,
+                             "Could not allocate HPT of order %d", shift);
+            return;
         }
-    }
 
-    /* Update the RMA size if necessary */
-    if (spapr->vrma_adjust) {
-        spapr->rma_size = kvmppc_rma_size(spapr_node0_size(),
-                                          spapr->htab_shift);
+        memset(spapr->htab, 0, size);
+        spapr->htab_shift = shift;
+        kvmppc_kern_htab = false;
+
+        for (i = 0; i < size / HASH_PTE_SIZE_64; i++) {
+            DIRTY_HPTE(HPTE(spapr->htab, i));
+        }
     }
 }
 
@@ -1121,39 +1131,26 @@ static int find_unknown_sysbus_device(SysBusDevice *sbdev, void *opaque)
     return 0;
 }
 
-/*
- * 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(sPAPRMachineState *spapr)
-{
-    int rc = 0;
-
-    if (spapr->htab_fd_stale) {
-        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;
-        }
-        spapr->htab_fd_stale = false;
-    }
-
-    return rc;
-}
-
 static void ppc_spapr_reset(void)
 {
-    sPAPRMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
+    MachineState *machine = MACHINE(qdev_get_machine());
+    sPAPRMachineState *spapr = SPAPR_MACHINE(machine);
     PowerPCCPU *first_ppc_cpu;
     uint32_t rtas_limit;
 
     /* Check for unknown sysbus devices */
     foreach_dynamic_sysbus_device(find_unknown_sysbus_device, NULL);
 
-    /* Reset the hash table & recalc the RMA */
-    spapr_reset_htab(spapr);
+    /* Allocate and/or reset the hash page table */
+    spapr_reallocate_hpt(spapr,
+                         spapr_hpt_shift_for_ramsize(machine->maxram_size),
+                         &error_fatal);
+
+    /* Update the RMA size if necessary */
+    if (spapr->vrma_adjust) {
+        spapr->rma_size = kvmppc_rma_size(spapr_node0_size(),
+                                          spapr->htab_shift);
+    }
 
     qemu_devices_reset();
 
@@ -1200,13 +1197,6 @@ static void spapr_cpu_reset(void *opaque)
     env->spr[SPR_HIOR] = 0;
 
     env->external_htab = (uint8_t *)spapr->htab;
-    if (kvm_enabled() && !env->external_htab) {
-        /*
-         * HV KVM, set external_htab to 1 so our ppc_hash64_load_hpte*
-         * functions do the right thing.
-         */
-        env->external_htab = (void *)1;
-    }
     env->htab_base = -1;
     /*
      * htab_mask is the mask used to normalize hash value to PTEG index.
@@ -1313,14 +1303,6 @@ static int htab_save_setup(QEMUFile *f, void *opaque)
         spapr->htab_first_pass = true;
     } else {
         assert(kvm_enabled());
-
-        spapr->htab_fd = kvmppc_get_htab_fd(false);
-        spapr->htab_fd_stale = false;
-        if (spapr->htab_fd < 0) {
-            fprintf(stderr, "Unable to open fd for reading hash table from KVM: %s\n",
-                    strerror(errno));
-            return -1;
-        }
     }
 
 
@@ -1330,6 +1312,7 @@ static int htab_save_setup(QEMUFile *f, void *opaque)
 static void htab_save_first_pass(QEMUFile *f, sPAPRMachineState *spapr,
                                  int64_t max_ns)
 {
+    bool has_timeout = max_ns != -1;
     int htabslots = HTAB_SIZE(spapr) / HASH_PTE_SIZE_64;
     int index = spapr->htab_save_index;
     int64_t starttime = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
@@ -1363,7 +1346,8 @@ static void htab_save_first_pass(QEMUFile *f, sPAPRMachineState *spapr,
             qemu_put_buffer(f, HPTE(spapr->htab, chunkstart),
                             HASH_PTE_SIZE_64 * n_valid);
 
-            if ((qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - starttime) > max_ns) {
+            if (has_timeout &&
+                (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - starttime) > max_ns) {
                 break;
             }
         }
@@ -1460,6 +1444,7 @@ static int htab_save_later_pass(QEMUFile *f, sPAPRMachineState *spapr,
 static int htab_save_iterate(QEMUFile *f, void *opaque)
 {
     sPAPRMachineState *spapr = opaque;
+    int fd;
     int rc = 0;
 
     /* Iteration header */
@@ -1468,13 +1453,12 @@ 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;
+        fd = get_htab_fd(spapr);
+        if (fd < 0) {
+            return fd;
         }
 
-        rc = kvmppc_save_htab(f, spapr->htab_fd,
-                              MAX_KVM_BUF_SIZE, MAX_ITERATION_NS);
+        rc = kvmppc_save_htab(f, fd, MAX_KVM_BUF_SIZE, MAX_ITERATION_NS);
         if (rc < 0) {
             return rc;
         }
@@ -1495,6 +1479,7 @@ static int htab_save_iterate(QEMUFile *f, void *opaque)
 static int htab_save_complete(QEMUFile *f, void *opaque)
 {
     sPAPRMachineState *spapr = opaque;
+    int fd;
 
     /* Iteration header */
     qemu_put_be32(f, 0);
@@ -1504,18 +1489,20 @@ static int htab_save_complete(QEMUFile *f, void *opaque)
 
         assert(kvm_enabled());
 
-        rc = spapr_check_htab_fd(spapr);
-        if (rc < 0) {
-            return rc;
+        fd = get_htab_fd(spapr);
+        if (fd < 0) {
+            return fd;
         }
 
-        rc = kvmppc_save_htab(f, spapr->htab_fd, MAX_KVM_BUF_SIZE, -1);
+        rc = kvmppc_save_htab(f, fd, MAX_KVM_BUF_SIZE, -1);
         if (rc < 0) {
             return rc;
         }
-        close(spapr->htab_fd);
-        spapr->htab_fd = -1;
+        close_htab_fd(spapr);
     } else {
+        if (spapr->htab_first_pass) {
+            htab_save_first_pass(f, spapr, -1);
+        }
         htab_save_later_pass(f, spapr, -1);
     }
 
@@ -1541,10 +1528,12 @@ static int htab_load(QEMUFile *f, void *opaque, int version_id)
     section_hdr = qemu_get_be32(f);
 
     if (section_hdr) {
-        /* First section, just the hash shift */
-        if (spapr->htab_shift != section_hdr) {
-            error_report("htab_shift mismatch: source %d target %d",
-                         section_hdr, spapr->htab_shift);
+        Error *local_err;
+
+        /* First section gives the htab size */
+        spapr_reallocate_hpt(spapr, section_hdr, &local_err);
+        if (local_err) {
+            error_report_err(local_err);
             return -EINVAL;
         }
         return 0;
@@ -1797,18 +1786,6 @@ static void ppc_spapr_init(MachineState *machine)
     /* Setup a load limit for the ramdisk leaving room for SLOF and FDT */
     load_limit = MIN(spapr->rma_size, RTAS_MAX_ADDR) - FW_OVERHEAD;
 
-    /* We aim for a hash table of size 1/128 the size of RAM.  The
-     * normal rule of thumb is 1/64 the size of RAM, but that's much
-     * more than needed for the Linux guests we support. */
-    spapr->htab_shift = 18; /* Minimum architected size */
-    while (spapr->htab_shift <= 46) {
-        if ((1ULL << (spapr->htab_shift + 7)) >= machine->maxram_size) {
-            break;
-        }
-        spapr->htab_shift++;
-    }
-    spapr_alloc_htab(spapr);
-
     /* Set up Interrupt Controller before we create the VCPUs */
     spapr->icp = xics_system_init(machine,
                                   DIV_ROUND_UP(max_cpus * kvmppc_smt_threads(),
@@ -2125,6 +2102,9 @@ static void spapr_set_kvm_type(Object *obj, const char *value, Error **errp)
 
 static void spapr_machine_initfn(Object *obj)
 {
+    sPAPRMachineState *spapr = SPAPR_MACHINE(obj);
+
+    spapr->htab_fd = -1;
     object_property_add_str(obj, "kvm-type",
                             spapr_get_kvm_type, spapr_set_kvm_type, NULL);
     object_property_set_description(obj, "kvm-type",
@@ -2411,6 +2391,7 @@ DEFINE_SPAPR_MACHINE(2_5, "2.5", false);
  * pseries-2.4
  */
 #define SPAPR_COMPAT_2_4 \
+        SPAPR_COMPAT_2_5 \
         HW_COMPAT_2_4
 
 static void spapr_machine_2_4_instance_options(MachineState *machine)
diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c
index 12f8c33db7..6e9b6be58c 100644
--- a/hw/ppc/spapr_hcall.c
+++ b/hw/ppc/spapr_hcall.c
@@ -38,6 +38,12 @@ static void set_spr(CPUState *cs, int spr, target_ulong value,
     run_on_cpu(cs, do_spr_sync, &s);
 }
 
+static bool has_spr(PowerPCCPU *cpu, int spr)
+{
+    /* We can test whether the SPR is defined by checking for a valid name */
+    return cpu->env.spr_cb[spr].name != NULL;
+}
+
 static inline bool valid_pte_index(CPUPPCState *env, target_ulong pte_index)
 {
     /*
@@ -332,11 +338,52 @@ static target_ulong h_read(PowerPCCPU *cpu, sPAPRMachineState *spapr,
     return H_SUCCESS;
 }
 
+static target_ulong h_set_sprg0(PowerPCCPU *cpu, sPAPRMachineState *spapr,
+                                target_ulong opcode, target_ulong *args)
+{
+    cpu_synchronize_state(CPU(cpu));
+    cpu->env.spr[SPR_SPRG0] = args[0];
+
+    return H_SUCCESS;
+}
+
 static target_ulong h_set_dabr(PowerPCCPU *cpu, sPAPRMachineState *spapr,
                                target_ulong opcode, target_ulong *args)
 {
-    /* FIXME: actually implement this */
-    return H_HARDWARE;
+    if (!has_spr(cpu, SPR_DABR)) {
+        return H_HARDWARE;              /* DABR register not available */
+    }
+    cpu_synchronize_state(CPU(cpu));
+
+    if (has_spr(cpu, SPR_DABRX)) {
+        cpu->env.spr[SPR_DABRX] = 0x3;  /* Use Problem and Privileged state */
+    } else if (!(args[0] & 0x4)) {      /* Breakpoint Translation set? */
+        return H_RESERVED_DABR;
+    }
+
+    cpu->env.spr[SPR_DABR] = args[0];
+    return H_SUCCESS;
+}
+
+static target_ulong h_set_xdabr(PowerPCCPU *cpu, sPAPRMachineState *spapr,
+                                target_ulong opcode, target_ulong *args)
+{
+    target_ulong dabrx = args[1];
+
+    if (!has_spr(cpu, SPR_DABR) || !has_spr(cpu, SPR_DABRX)) {
+        return H_HARDWARE;
+    }
+
+    if ((dabrx & ~0xfULL) != 0 || (dabrx & H_DABRX_HYPERVISOR) != 0
+        || (dabrx & (H_DABRX_KERNEL | H_DABRX_USER)) == 0) {
+        return H_PARAMETER;
+    }
+
+    cpu_synchronize_state(CPU(cpu));
+    cpu->env.spr[SPR_DABRX] = dabrx;
+    cpu->env.spr[SPR_DABR] = args[0];
+
+    return H_SUCCESS;
 }
 
 #define FLAGS_REGISTER_VPA         0x0000200000000000ULL
@@ -990,13 +1037,16 @@ static void hypercall_register_types(void)
     /* hcall-bulk */
     spapr_register_hypercall(H_BULK_REMOVE, h_bulk_remove);
 
-    /* hcall-dabr */
-    spapr_register_hypercall(H_SET_DABR, h_set_dabr);
-
     /* hcall-splpar */
     spapr_register_hypercall(H_REGISTER_VPA, h_register_vpa);
     spapr_register_hypercall(H_CEDE, h_cede);
 
+    /* processor register resource access h-calls */
+    spapr_register_hypercall(H_SET_SPRG0, h_set_sprg0);
+    spapr_register_hypercall(H_SET_DABR, h_set_dabr);
+    spapr_register_hypercall(H_SET_XDABR, h_set_xdabr);
+    spapr_register_hypercall(H_SET_MODE, h_set_mode);
+
     /* "debugger" hcalls (also used by SLOF). Note: We do -not- differenciate
      * here between the "CI" and the "CACHE" variants, they will use whatever
      * mapping attributes qemu is using. When using KVM, the kernel will
@@ -1013,8 +1063,6 @@ static void hypercall_register_types(void)
     /* qemu/KVM-PPC specific hcalls */
     spapr_register_hypercall(KVMPPC_H_RTAS, h_rtas);
 
-    spapr_register_hypercall(H_SET_MODE, h_set_mode);
-
     /* ibm,client-architecture-support support */
     spapr_register_hypercall(KVMPPC_H_CAS, h_client_architecture_support);
 }
diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c
index 07ad672e5a..b7c5ebde40 100644
--- a/hw/ppc/spapr_rtas.c
+++ b/hw/ppc/spapr_rtas.c
@@ -113,6 +113,7 @@ static void rtas_power_off(PowerPCCPU *cpu, sPAPRMachineState *spapr,
         return;
     }
     qemu_system_shutdown_request();
+    cpu_stop_current();
     rtas_st(rets, 0, RTAS_OUT_SUCCESS);
 }
 
diff --git a/include/hw/input/adb.h b/include/hw/input/adb.h
index bdfccd4041..db51d03804 100644
--- a/include/hw/input/adb.h
+++ b/include/hw/input/adb.h
@@ -79,7 +79,7 @@ struct ADBBusState {
 
 int adb_request(ADBBusState *s, uint8_t *buf_out,
                 const uint8_t *buf, int len);
-int adb_poll(ADBBusState *s, uint8_t *buf_out);
+int adb_poll(ADBBusState *s, uint8_t *buf_out, uint16_t poll_mask);
 
 #define TYPE_ADB_KEYBOARD "adb-keyboard"
 #define TYPE_ADB_MOUSE "adb-mouse"
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index 1f9e722545..098d85d1a1 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -72,7 +72,6 @@ struct sPAPRMachineState {
     int htab_save_index;
     bool htab_first_pass;
     int htab_fd;
-    bool htab_fd_stale;
 
     /* RTAS state */
     QTAILQ_HEAD(, sPAPRConfigureConnectorState) ccs_list;
diff --git a/target-ppc/kvm_ppc.h b/target-ppc/kvm_ppc.h
index 62406ce4e1..aaa828c055 100644
--- a/target-ppc/kvm_ppc.h
+++ b/target-ppc/kvm_ppc.h
@@ -184,11 +184,6 @@ static inline uint64_t kvmppc_rma_size(uint64_t current_size,
     return ram_size;
 }
 
-static inline int kvmppc_update_sdr1(CPUPPCState *env)
-{
-    return 0;
-}
-
 #endif /* !CONFIG_USER_ONLY */
 
 static inline bool kvmppc_has_cap_epr(void)
diff --git a/target-ppc/mmu-hash64.h b/target-ppc/mmu-hash64.h
index ab0f86b222..e7d9925411 100644
--- a/target-ppc/mmu-hash64.h
+++ b/target-ppc/mmu-hash64.h
@@ -102,7 +102,7 @@ static inline target_ulong ppc_hash64_load_hpte0(PowerPCCPU *cpu,
     uint64_t addr;
 
     addr = token + (index * HASH_PTE_SIZE_64);
-    if (env->external_htab) {
+    if (kvmppc_kern_htab || env->external_htab) {
         return  ldq_p((const void *)(uintptr_t)addr);
     } else {
         return ldq_phys(CPU(cpu)->as, addr);
@@ -116,7 +116,7 @@ static inline target_ulong ppc_hash64_load_hpte1(PowerPCCPU *cpu,
     uint64_t addr;
 
     addr = token + (index * HASH_PTE_SIZE_64) + HASH_PTE_SIZE_64/2;
-    if (env->external_htab) {
+    if (kvmppc_kern_htab || env->external_htab) {
         return  ldq_p((const void *)(uintptr_t)addr);
     } else {
         return ldq_phys(CPU(cpu)->as, addr);
diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index ffef754fe0..ecc85f0e6d 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -11352,7 +11352,9 @@ void ppc_cpu_dump_state(CPUState *cs, FILE *f, fprintf_function cpu_fprintf,
     case POWERPC_MMU_64B:
     case POWERPC_MMU_2_03:
     case POWERPC_MMU_2_06:
+    case POWERPC_MMU_2_06a:
     case POWERPC_MMU_2_07:
+    case POWERPC_MMU_2_07a:
 #endif
         cpu_fprintf(f, " SDR1 " TARGET_FMT_lx "   DAR " TARGET_FMT_lx
                        "  DSISR " TARGET_FMT_lx "\n", env->spr[SPR_SDR1],