Merge branch 'ppc-for-upstream' of git://repo.or.cz/qemu/agraf

* 'ppc-for-upstream' of git://repo.or.cz/qemu/agraf: (35 commits)
  PPC: KVM: Fix BAT put
  PPC: e500: Only expose even TLB sizes in initial TLB
  ppc/pseries: Reset VPA registration on CPU reset
  pseries: Don't test for MSR_PR for hypercalls under KVM
  PPC: e500: calculate initrd_base like dt_base
  PPC: e500: increase DTC_LOAD_PAD
  device tree: simplify dumpdtb code
  fdt: move dumpdtb interpretation code to device_tree.c
  target-ppc: Remove unused power_mode field from cpu state
  pseries: Set hash table size based on RAM size
  pseries: Remove unnecessary locking from PAPR hash table hcalls
  ppc405_uc: Fix buffer overflow
  target-ppc: KVM: Fix some kernel version edge cases for kvmppc_reset_htab()
  pseries: Fix semantics of RTAS int-on, int-off and set-xive functions
  pseries: Rework implementation of TCE bypass
  pseries: Remove never used flags field from spapr vio devices
  pseries: Remove XICS irq type enum type
  pseries: Remove C bitfields from xics code
  pseries: Small cleanup to H_CEDE implementation
  pseries: Fix XICS reset
  ...

12 files changed, 351 insertions, 283 deletions

diff --git a/hw/ppc/e500.c b/hw/ppc/e500.c
index 6f0de6d959..d23f9b2f60 100644
--- a/hw/ppc/e500.c
+++ b/hw/ppc/e500.c
@@ -36,7 +36,7 @@
 
 #define BINARY_DEVICE_TREE_FILE    "mpc8544ds.dtb"
 #define UIMAGE_LOAD_BASE           0
-#define DTC_LOAD_PAD               0x500000
+#define DTC_LOAD_PAD               0x1800000
 #define DTC_PAD_MASK               0xFFFFF
 #define INITRD_LOAD_PAD            0x2000000
 #define INITRD_PAD_MASK            0xFFFFFF
@@ -139,12 +139,10 @@ static int ppce500_load_device_tree(CPUPPCState *env,
             0x0, 0x10000,
         };
     QemuOpts *machine_opts;
-    const char *dumpdtb = NULL;
     const char *dtb_file = NULL;
 
     machine_opts = qemu_opts_find(qemu_find_opts("machine"), 0);
     if (machine_opts) {
-        dumpdtb = qemu_opt_get(machine_opts, "dumpdtb");
         dtb_file = qemu_opt_get(machine_opts, "dtb");
         toplevel_compat = qemu_opt_get(machine_opts, "dt_compatible");
     }
@@ -334,18 +332,7 @@ static int ppce500_load_device_tree(CPUPPCState *env,
     }
 
 done:
-    if (dumpdtb) {
-        /* Dump the dtb to a file and quit */
-        FILE *f = fopen(dumpdtb, "wb");
-        size_t len;
-        len = fwrite(fdt, fdt_size, 1, f);
-        fclose(f);
-        if (len != fdt_size) {
-            exit(1);
-        }
-        exit(0);
-    }
-
+    qemu_devtree_dumpdtb(fdt, fdt_size);
     ret = rom_add_blob_fixed(BINARY_DEVICE_TREE_FILE, fdt, fdt_size, addr);
     if (ret < 0) {
         goto out;
@@ -375,6 +362,10 @@ static void mmubooke_create_initial_mapping(CPUPPCState *env)
        the device tree top */
     dt_end = bi->dt_base + bi->dt_size;
     ps = booke206_page_size_to_tlb(dt_end) + 1;
+    if (ps & 1) {
+        /* e500v2 can only do even TLB size bits */
+        ps++;
+    }
     size = (ps << MAS1_TSIZE_SHIFT);
     tlb->mas1 = MAS1_VALID | size;
     tlb->mas2 = 0;
@@ -553,7 +544,8 @@ void ppce500_init(PPCE500Params *params)
 
     /* Load initrd. */
     if (params->initrd_filename) {
-        initrd_base = (kernel_size + INITRD_LOAD_PAD) & ~INITRD_PAD_MASK;
+        initrd_base = (loadaddr + kernel_size + INITRD_LOAD_PAD) &
+            ~INITRD_PAD_MASK;
         initrd_size = load_image_targphys(params->initrd_filename, initrd_base,
                                           ram_size - initrd_base);
 
diff --git a/hw/ppc405_uc.c b/hw/ppc405_uc.c
index 89e5013b57..b52ab2f179 100644
--- a/hw/ppc405_uc.c
+++ b/hw/ppc405_uc.c
@@ -191,7 +191,8 @@ enum {
 typedef struct ppc4xx_pob_t ppc4xx_pob_t;
 struct ppc4xx_pob_t {
     uint32_t bear;
-    uint32_t besr[2];
+    uint32_t besr0;
+    uint32_t besr1;
 };
 
 static uint32_t dcr_read_pob (void *opaque, int dcrn)
@@ -205,8 +206,10 @@ static uint32_t dcr_read_pob (void *opaque, int dcrn)
         ret = pob->bear;
         break;
     case POB0_BESR0:
+        ret = pob->besr0;
+        break;
     case POB0_BESR1:
-        ret = pob->besr[dcrn - POB0_BESR0];
+        ret = pob->besr1;
         break;
     default:
         /* Avoid gcc warning */
@@ -227,9 +230,12 @@ static void dcr_write_pob (void *opaque, int dcrn, uint32_t val)
         /* Read only */
         break;
     case POB0_BESR0:
+        /* Write-clear */
+        pob->besr0 &= ~val;
+        break;
     case POB0_BESR1:
         /* Write-clear */
-        pob->besr[dcrn - POB0_BESR0] &= ~val;
+        pob->besr1 &= ~val;
         break;
     }
 }
@@ -241,8 +247,8 @@ static void ppc4xx_pob_reset (void *opaque)
     pob = opaque;
     /* No error */
     pob->bear = 0x00000000;
-    pob->besr[0] = 0x0000000;
-    pob->besr[1] = 0x0000000;
+    pob->besr0 = 0x0000000;
+    pob->besr1 = 0x0000000;
 }
 
 static void ppc4xx_pob_init(CPUPPCState *env)
diff --git a/hw/spapr.c b/hw/spapr.c
index 8b0c390269..09b8e99221 100644
--- a/hw/spapr.c
+++ b/hw/spapr.c
@@ -84,9 +84,11 @@
 
 #define PHANDLE_XICP            0x00001111
 
+#define HTAB_SIZE(spapr)        (1ULL << ((spapr)->htab_shift))
+
 sPAPREnvironment *spapr;
 
-int spapr_allocate_irq(int hint, enum xics_irq_type type)
+int spapr_allocate_irq(int hint, bool lsi)
 {
     int irq;
 
@@ -102,13 +104,13 @@ int spapr_allocate_irq(int hint, enum xics_irq_type type)
         return 0;
     }
 
-    xics_set_irq_type(spapr->icp, irq, type);
+    xics_set_irq_type(spapr->icp, irq, lsi);
 
     return irq;
 }
 
 /* Allocate block of consequtive IRQs, returns a number of the first */
-int spapr_allocate_irq_block(int num, enum xics_irq_type type)
+int spapr_allocate_irq_block(int num, bool lsi)
 {
     int first = -1;
     int i;
@@ -116,7 +118,7 @@ int spapr_allocate_irq_block(int num, enum xics_irq_type type)
     for (i = 0; i < num; ++i) {
         int irq;
 
-        irq = spapr_allocate_irq(0, type);
+        irq = spapr_allocate_irq(0, lsi);
         if (!irq) {
             return -1;
         }
@@ -133,12 +135,13 @@ int spapr_allocate_irq_block(int num, enum xics_irq_type type)
     return first;
 }
 
-static int spapr_set_associativity(void *fdt, sPAPREnvironment *spapr)
+static int spapr_fixup_cpu_dt(void *fdt, sPAPREnvironment *spapr)
 {
     int ret = 0, offset;
     CPUPPCState *env;
     char cpu_model[32];
     int smt = kvmppc_smt_threads();
+    uint32_t pft_size_prop[] = {0, cpu_to_be32(spapr->htab_shift)};
 
     assert(spapr->cpu_model);
 
@@ -162,8 +165,16 @@ static int spapr_set_associativity(void *fdt, sPAPREnvironment *spapr)
             return offset;
         }
 
-        ret = fdt_setprop(fdt, offset, "ibm,associativity", associativity,
-                          sizeof(associativity));
+        if (nb_numa_nodes > 1) {
+            ret = fdt_setprop(fdt, offset, "ibm,associativity", associativity,
+                              sizeof(associativity));
+            if (ret < 0) {
+                return ret;
+            }
+        }
+
+        ret = fdt_setprop(fdt, offset, "ibm,pft-size",
+                          pft_size_prop, sizeof(pft_size_prop));
         if (ret < 0) {
             return ret;
         }
@@ -205,45 +216,36 @@ static size_t create_page_sizes_prop(CPUPPCState *env, uint32_t *prop,
     return (p - prop) * sizeof(uint32_t);
 }
 
+#define _FDT(exp) \
+    do { \
+        int ret = (exp);                                           \
+        if (ret < 0) {                                             \
+            fprintf(stderr, "qemu: error creating device tree: %s: %s\n", \
+                    #exp, fdt_strerror(ret));                      \
+            exit(1);                                               \
+        }                                                          \
+    } while (0)
+
+
 static void *spapr_create_fdt_skel(const char *cpu_model,
-                                   target_phys_addr_t rma_size,
                                    target_phys_addr_t initrd_base,
                                    target_phys_addr_t initrd_size,
                                    target_phys_addr_t kernel_size,
                                    const char *boot_device,
-                                   const char *kernel_cmdline,
-                                   long hash_shift)
+                                   const char *kernel_cmdline)
 {
     void *fdt;
     CPUPPCState *env;
-    uint64_t mem_reg_property[2];
     uint32_t start_prop = cpu_to_be32(initrd_base);
     uint32_t end_prop = cpu_to_be32(initrd_base + initrd_size);
-    uint32_t pft_size_prop[] = {0, cpu_to_be32(hash_shift)};
     char hypertas_prop[] = "hcall-pft\0hcall-term\0hcall-dabr\0hcall-interrupt"
         "\0hcall-tce\0hcall-vio\0hcall-splpar\0hcall-bulk";
     char qemu_hypertas_prop[] = "hcall-memop1";
+    uint32_t refpoints[] = {cpu_to_be32(0x4), cpu_to_be32(0x4)};
     uint32_t interrupt_server_ranges_prop[] = {0, cpu_to_be32(smp_cpus)};
-    int i;
     char *modelname;
-    int smt = kvmppc_smt_threads();
+    int i, smt = kvmppc_smt_threads();
     unsigned char vec5[] = {0x0, 0x0, 0x0, 0x0, 0x0, 0x80};
-    uint32_t refpoints[] = {cpu_to_be32(0x4), cpu_to_be32(0x4)};
-    uint32_t associativity[] = {cpu_to_be32(0x4), cpu_to_be32(0x0),
-                                cpu_to_be32(0x0), cpu_to_be32(0x0),
-                                cpu_to_be32(0x0)};
-    char mem_name[32];
-    target_phys_addr_t node0_size, mem_start;
-
-#define _FDT(exp) \
-    do { \
-        int ret = (exp);                                           \
-        if (ret < 0) {                                             \
-            fprintf(stderr, "qemu: error creating device tree: %s: %s\n", \
-                    #exp, fdt_strerror(ret));                      \
-            exit(1);                                               \
-        }                                                          \
-    } while (0)
 
     fdt = g_malloc0(FDT_MAX_SIZE);
     _FDT((fdt_create(fdt, FDT_MAX_SIZE)));
@@ -288,55 +290,6 @@ static void *spapr_create_fdt_skel(const char *cpu_model,
 
     _FDT((fdt_end_node(fdt)));
 
-    /* memory node(s) */
-    node0_size = (nb_numa_nodes > 1) ? node_mem[0] : ram_size;
-    if (rma_size > node0_size) {
-        rma_size = node0_size;
-    }
-
-    /* RMA */
-    mem_reg_property[0] = 0;
-    mem_reg_property[1] = cpu_to_be64(rma_size);
-    _FDT((fdt_begin_node(fdt, "memory@0")));
-    _FDT((fdt_property_string(fdt, "device_type", "memory")));
-    _FDT((fdt_property(fdt, "reg", mem_reg_property,
-        sizeof(mem_reg_property))));
-    _FDT((fdt_property(fdt, "ibm,associativity", associativity,
-        sizeof(associativity))));
-    _FDT((fdt_end_node(fdt)));
-
-    /* RAM: Node 0 */
-    if (node0_size > rma_size) {
-        mem_reg_property[0] = cpu_to_be64(rma_size);
-        mem_reg_property[1] = cpu_to_be64(node0_size - rma_size);
-
-        sprintf(mem_name, "memory@" TARGET_FMT_lx, rma_size);
-        _FDT((fdt_begin_node(fdt, mem_name)));
-        _FDT((fdt_property_string(fdt, "device_type", "memory")));
-        _FDT((fdt_property(fdt, "reg", mem_reg_property,
-                           sizeof(mem_reg_property))));
-        _FDT((fdt_property(fdt, "ibm,associativity", associativity,
-                           sizeof(associativity))));
-        _FDT((fdt_end_node(fdt)));
-    }
-
-    /* RAM: Node 1 and beyond */
-    mem_start = node0_size;
-    for (i = 1; i < nb_numa_nodes; i++) {
-        mem_reg_property[0] = cpu_to_be64(mem_start);
-        mem_reg_property[1] = cpu_to_be64(node_mem[i]);
-        associativity[3] = associativity[4] = cpu_to_be32(i);
-        sprintf(mem_name, "memory@" TARGET_FMT_lx, mem_start);
-        _FDT((fdt_begin_node(fdt, mem_name)));
-        _FDT((fdt_property_string(fdt, "device_type", "memory")));
-        _FDT((fdt_property(fdt, "reg", mem_reg_property,
-            sizeof(mem_reg_property))));
-        _FDT((fdt_property(fdt, "ibm,associativity", associativity,
-            sizeof(associativity))));
-        _FDT((fdt_end_node(fdt)));
-        mem_start += node_mem[i];
-    }
-
     /* cpus */
     _FDT((fdt_begin_node(fdt, "cpus")));
 
@@ -388,8 +341,6 @@ static void *spapr_create_fdt_skel(const char *cpu_model,
         _FDT((fdt_property_cell(fdt, "timebase-frequency", tbfreq)));
         _FDT((fdt_property_cell(fdt, "clock-frequency", cpufreq)));
         _FDT((fdt_property_cell(fdt, "ibm,slb-size", env->slb_nr)));
-        _FDT((fdt_property(fdt, "ibm,pft-size",
-                           pft_size_prop, sizeof(pft_size_prop))));
         _FDT((fdt_property_string(fdt, "status", "okay")));
         _FDT((fdt_property(fdt, "64-bit", NULL, 0)));
 
@@ -488,6 +439,68 @@ static void *spapr_create_fdt_skel(const char *cpu_model,
     return fdt;
 }
 
+static int spapr_populate_memory(sPAPREnvironment *spapr, void *fdt)
+{
+    uint32_t associativity[] = {cpu_to_be32(0x4), cpu_to_be32(0x0),
+                                cpu_to_be32(0x0), cpu_to_be32(0x0),
+                                cpu_to_be32(0x0)};
+    char mem_name[32];
+    target_phys_addr_t node0_size, mem_start;
+    uint64_t mem_reg_property[2];
+    int i, off;
+
+    /* memory node(s) */
+    node0_size = (nb_numa_nodes > 1) ? node_mem[0] : ram_size;
+    if (spapr->rma_size > node0_size) {
+        spapr->rma_size = node0_size;
+    }
+
+    /* RMA */
+    mem_reg_property[0] = 0;
+    mem_reg_property[1] = cpu_to_be64(spapr->rma_size);
+    off = fdt_add_subnode(fdt, 0, "memory@0");
+    _FDT(off);
+    _FDT((fdt_setprop_string(fdt, off, "device_type", "memory")));
+    _FDT((fdt_setprop(fdt, off, "reg", mem_reg_property,
+                      sizeof(mem_reg_property))));
+    _FDT((fdt_setprop(fdt, off, "ibm,associativity", associativity,
+                      sizeof(associativity))));
+
+    /* RAM: Node 0 */
+    if (node0_size > spapr->rma_size) {
+        mem_reg_property[0] = cpu_to_be64(spapr->rma_size);
+        mem_reg_property[1] = cpu_to_be64(node0_size - spapr->rma_size);
+
+        sprintf(mem_name, "memory@" TARGET_FMT_lx, spapr->rma_size);
+        off = fdt_add_subnode(fdt, 0, mem_name);
+        _FDT(off);
+        _FDT((fdt_setprop_string(fdt, off, "device_type", "memory")));
+        _FDT((fdt_setprop(fdt, off, "reg", mem_reg_property,
+                          sizeof(mem_reg_property))));
+        _FDT((fdt_setprop(fdt, off, "ibm,associativity", associativity,
+                          sizeof(associativity))));
+    }
+
+    /* RAM: Node 1 and beyond */
+    mem_start = node0_size;
+    for (i = 1; i < nb_numa_nodes; i++) {
+        mem_reg_property[0] = cpu_to_be64(mem_start);
+        mem_reg_property[1] = cpu_to_be64(node_mem[i]);
+        associativity[3] = associativity[4] = cpu_to_be32(i);
+        sprintf(mem_name, "memory@" TARGET_FMT_lx, mem_start);
+        off = fdt_add_subnode(fdt, 0, mem_name);
+        _FDT(off);
+        _FDT((fdt_setprop_string(fdt, off, "device_type", "memory")));
+        _FDT((fdt_setprop(fdt, off, "reg", mem_reg_property,
+                          sizeof(mem_reg_property))));
+        _FDT((fdt_setprop(fdt, off, "ibm,associativity", associativity,
+                          sizeof(associativity))));
+        mem_start += node_mem[i];
+    }
+
+    return 0;
+}
+
 static void spapr_finalize_fdt(sPAPREnvironment *spapr,
                                target_phys_addr_t fdt_addr,
                                target_phys_addr_t rtas_addr,
@@ -502,6 +515,12 @@ static void spapr_finalize_fdt(sPAPREnvironment *spapr,
     /* open out the base tree into a temp buffer for the final tweaks */
     _FDT((fdt_open_into(spapr->fdt_skel, fdt, FDT_MAX_SIZE)));
 
+    ret = spapr_populate_memory(spapr, fdt);
+    if (ret < 0) {
+        fprintf(stderr, "couldn't setup memory nodes in fdt\n");
+        exit(1);
+    }
+
     ret = spapr_populate_vdevice(spapr->vio_bus, fdt);
     if (ret < 0) {
         fprintf(stderr, "couldn't setup vio devices in fdt\n");
@@ -524,11 +543,9 @@ static void spapr_finalize_fdt(sPAPREnvironment *spapr,
     }
 
     /* Advertise NUMA via ibm,associativity */
-    if (nb_numa_nodes > 1) {
-        ret = spapr_set_associativity(fdt, spapr);
-        if (ret < 0) {
-            fprintf(stderr, "Couldn't set up NUMA device tree properties\n");
-        }
+    ret = spapr_fixup_cpu_dt(fdt, spapr);
+    if (ret < 0) {
+        fprintf(stderr, "Couldn't finalize CPU device tree properties\n");
     }
 
     if (!spapr->has_graphics) {
@@ -555,15 +572,49 @@ static uint64_t translate_kernel_address(void *opaque, uint64_t addr)
 
 static void emulate_spapr_hypercall(CPUPPCState *env)
 {
-    env->gpr[3] = spapr_hypercall(env, env->gpr[3], &env->gpr[4]);
+    if (msr_pr) {
+        hcall_dprintf("Hypercall made with MSR[PR]=1\n");
+        env->gpr[3] = H_PRIVILEGE;
+    } else {
+        env->gpr[3] = spapr_hypercall(env, env->gpr[3], &env->gpr[4]);
+    }
+}
+
+static void spapr_reset_htab(sPAPREnvironment *spapr)
+{
+    long shift;
+
+    /* allocate hash page table.  For now we always make this 16mb,
+     * later we should probably make it scale to the size of guest
+     * RAM */
+
+    shift = kvmppc_reset_htab(spapr->htab_shift);
+
+    if (shift > 0) {
+        /* Kernel handles htab, we don't need to allocate one */
+        spapr->htab_shift = shift;
+    } else {
+        if (!spapr->htab) {
+            /* Allocate an htab if we don't yet have one */
+            spapr->htab = qemu_memalign(HTAB_SIZE(spapr), HTAB_SIZE(spapr));
+        }
+
+        /* And clear it */
+        memset(spapr->htab, 0, HTAB_SIZE(spapr));
+    }
+
+    /* Update the RMA size if necessary */
+    if (spapr->vrma_adjust) {
+        spapr->rma_size = kvmppc_rma_size(ram_size, spapr->htab_shift);
+    }
 }
 
-static void spapr_reset(void *opaque)
+static void ppc_spapr_reset(void)
 {
-    sPAPREnvironment *spapr = (sPAPREnvironment *)opaque;
+    /* Reset the hash table & recalc the RMA */
+    spapr_reset_htab(spapr);
 
-    /* flush out the hash table */
-    memset(spapr->htab, 0, spapr->htab_size);
+    qemu_devices_reset();
 
     /* Load the fdt */
     spapr_finalize_fdt(spapr, spapr->fdt_addr, spapr->rtas_addr,
@@ -580,8 +631,22 @@ static void spapr_reset(void *opaque)
 static void spapr_cpu_reset(void *opaque)
 {
     PowerPCCPU *cpu = opaque;
+    CPUPPCState *env = &cpu->env;
 
     cpu_reset(CPU(cpu));
+
+    /* All CPUs start halted.  CPU0 is unhalted from the machine level
+     * reset code and the rest are explicitly started up by the guest
+     * using an RTAS call */
+    env->halted = 1;
+
+    env->spr[SPR_HIOR] = 0;
+
+    env->external_htab = spapr->htab;
+    env->htab_base = -1;
+    env->htab_mask = HTAB_SIZE(spapr) - 1;
+    env->spr[SPR_SDR1] = (unsigned long)spapr->htab |
+        (spapr->htab_shift - 18);
 }
 
 /* Returns whether we want to use VGA or not */
@@ -613,11 +678,10 @@ static void ppc_spapr_init(ram_addr_t ram_size,
     int i;
     MemoryRegion *sysmem = get_system_memory();
     MemoryRegion *ram = g_new(MemoryRegion, 1);
-    target_phys_addr_t rma_alloc_size, rma_size;
+    target_phys_addr_t rma_alloc_size;
     uint32_t initrd_base = 0;
     long kernel_size = 0, initrd_size = 0;
     long load_limit, rtas_limit, fw_size;
-    long pteg_shift = 17;
     char *filename;
 
     msi_supported = true;
@@ -634,20 +698,46 @@ static void ppc_spapr_init(ram_addr_t ram_size,
         hw_error("qemu: Unable to create RMA\n");
         exit(1);
     }
+
     if (rma_alloc_size && (rma_alloc_size < ram_size)) {
-        rma_size = rma_alloc_size;
+        spapr->rma_size = rma_alloc_size;
     } else {
-        rma_size = ram_size;
+        spapr->rma_size = ram_size;
+
+        /* With KVM, we don't actually know whether KVM supports an
+         * unbounded RMA (PR KVM) or is limited by the hash table size
+         * (HV KVM using VRMA), so we always assume the latter
+         *
+         * In that case, we also limit the initial allocations for RTAS
+         * etc... to 256M since we have no way to know what the VRMA size
+         * is going to be as it depends on the size of the hash table
+         * isn't determined yet.
+         */
+        if (kvm_enabled()) {
+            spapr->vrma_adjust = 1;
+            spapr->rma_size = MIN(spapr->rma_size, 0x10000000);
+        }
     }
 
     /* We place the device tree and RTAS just below either the top of the RMA,
      * or just below 2GB, whichever is lowere, so that it can be
      * processed with 32-bit real mode code if necessary */
-    rtas_limit = MIN(rma_size, 0x80000000);
+    rtas_limit = MIN(spapr->rma_size, 0x80000000);
     spapr->rtas_addr = rtas_limit - RTAS_MAX_SIZE;
     spapr->fdt_addr = spapr->rtas_addr - FDT_MAX_SIZE;
     load_limit = spapr->fdt_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)) >= ram_size) {
+            break;
+        }
+        spapr->htab_shift++;
+    }
+
     /* init CPUs */
     if (cpu_model == NULL) {
         cpu_model = kvm_enabled() ? "host" : "POWER7";
@@ -662,11 +752,16 @@ static void ppc_spapr_init(ram_addr_t ram_size,
 
         /* Set time-base frequency to 512 MHz */
         cpu_ppc_tb_init(env, TIMEBASE_FREQ);
-        qemu_register_reset(spapr_cpu_reset, cpu);
 
-        env->hreset_vector = 0x60;
+        /* PAPR always has exception vectors in RAM not ROM */
         env->hreset_excp_prefix = 0;
-        env->gpr[3] = env->cpu_index;
+
+        /* Tell KVM that we're in PAPR mode */
+        if (kvm_enabled()) {
+            kvmppc_set_papr(env);
+        }
+
+        qemu_register_reset(spapr_cpu_reset, cpu);
     }
 
     /* allocate RAM */
@@ -680,27 +775,6 @@ static void ppc_spapr_init(ram_addr_t ram_size,
         memory_region_add_subregion(sysmem, nonrma_base, ram);
     }
 
-    /* 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_size = 1ULL << (pteg_shift + 7);
-    spapr->htab = qemu_memalign(spapr->htab_size, spapr->htab_size);
-
-    for (env = first_cpu; env != NULL; env = env->next_cpu) {
-        env->external_htab = spapr->htab;
-        env->htab_base = -1;
-        env->htab_mask = spapr->htab_size - 1;
-
-        /* Tell KVM that we're in PAPR mode */
-        env->spr[SPR_SDR1] = (unsigned long)spapr->htab |
-                             ((pteg_shift + 7) - 18);
-        env->spr[SPR_HIOR] = 0;
-
-        if (kvm_enabled()) {
-            kvmppc_set_papr(env);
-        }
-    }
-
     filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, "spapr-rtas.bin");
     spapr->rtas_size = load_image_targphys(filename, spapr->rtas_addr,
                                            rtas_limit - spapr->rtas_addr);
@@ -773,7 +847,7 @@ static void ppc_spapr_init(ram_addr_t ram_size,
         }
     }
 
-    if (rma_size < (MIN_RMA_SLOF << 20)) {
+    if (spapr->rma_size < (MIN_RMA_SLOF << 20)) {
         fprintf(stderr, "qemu: pSeries SLOF firmware requires >= "
                 "%ldM guest RMA (Real Mode Area memory)\n", MIN_RMA_SLOF);
         exit(1);
@@ -824,26 +898,19 @@ static void ppc_spapr_init(ram_addr_t ram_size,
 
     spapr->entry_point = 0x100;
 
-    /* SLOF will startup the secondary CPUs using RTAS */
-    for (env = first_cpu; env != NULL; env = env->next_cpu) {
-        env->halted = 1;
-    }
-
     /* Prepare the device tree */
-    spapr->fdt_skel = spapr_create_fdt_skel(cpu_model, rma_size,
+    spapr->fdt_skel = spapr_create_fdt_skel(cpu_model,
                                             initrd_base, initrd_size,
                                             kernel_size,
-                                            boot_device, kernel_cmdline,
-                                            pteg_shift + 7);
+                                            boot_device, kernel_cmdline);
     assert(spapr->fdt_skel != NULL);
-
-    qemu_register_reset(spapr_reset, spapr);
 }
 
 static QEMUMachine spapr_machine = {
     .name = "pseries",
     .desc = "pSeries Logical Partition (PAPR compliant)",
     .init = ppc_spapr_init,
+    .reset = ppc_spapr_reset,
     .max_cpus = MAX_CPUS,
     .no_parallel = 1,
     .use_scsi = 1,
diff --git a/hw/spapr.h b/hw/spapr.h
index ac34a171e3..e984e3fc3c 100644
--- a/hw/spapr.h
+++ b/hw/spapr.h
@@ -15,7 +15,9 @@ typedef struct sPAPREnvironment {
 
     target_phys_addr_t ram_limit;
     void *htab;
-    long htab_size;
+    long htab_shift;
+    target_phys_addr_t rma_size;
+    int vrma_adjust;
     target_phys_addr_t fdt_addr, rtas_addr;
     long rtas_size;
     void *fdt_skel;
@@ -289,17 +291,17 @@ void spapr_register_hypercall(target_ulong opcode, spapr_hcall_fn fn);
 target_ulong spapr_hypercall(CPUPPCState *env, target_ulong opcode,
                              target_ulong *args);
 
-int spapr_allocate_irq(int hint, enum xics_irq_type type);
-int spapr_allocate_irq_block(int num, enum xics_irq_type type);
+int spapr_allocate_irq(int hint, bool lsi);
+int spapr_allocate_irq_block(int num, bool lsi);
 
 static inline int spapr_allocate_msi(int hint)
 {
-    return spapr_allocate_irq(hint, XICS_MSI);
+    return spapr_allocate_irq(hint, false);
 }
 
 static inline int spapr_allocate_lsi(int hint)
 {
-    return spapr_allocate_irq(hint, XICS_LSI);
+    return spapr_allocate_irq(hint, true);
 }
 
 static inline uint32_t rtas_ld(target_ulong phys, int n)
@@ -336,6 +338,8 @@ typedef struct sPAPRTCE {
 void spapr_iommu_init(void);
 DMAContext *spapr_tce_new_dma_context(uint32_t liobn, size_t window_size);
 void spapr_tce_free(DMAContext *dma);
+void spapr_tce_reset(DMAContext *dma);
+void spapr_tce_set_bypass(DMAContext *dma, bool bypass);
 int spapr_dma_dt(void *fdt, int node_off, const char *propname,
                  uint32_t liobn, uint64_t window, uint32_t size);
 int spapr_tcet_dma_dt(void *fdt, int node_off, const char *propname,
diff --git a/hw/spapr_hcall.c b/hw/spapr_hcall.c
index abd847f96c..194d9c24b5 100644
--- a/hw/spapr_hcall.c
+++ b/hw/spapr_hcall.c
@@ -39,22 +39,6 @@
 #define HPTE_V_1TB_SEG          0x4000000000000000ULL
 #define HPTE_V_VRMA_MASK        0x4001ffffff000000ULL
 
-#define HPTE_V_HVLOCK           0x40ULL
-
-static inline int lock_hpte(void *hpte, target_ulong bits)
-{
-    uint64_t pteh;
-
-    pteh = ldq_p(hpte);
-
-    /* We're protected by qemu's global lock here */
-    if (pteh & bits) {
-        return 0;
-    }
-    stq_p(hpte, pteh | HPTE_V_HVLOCK);
-    return 1;
-}
-
 static target_ulong compute_tlbie_rb(target_ulong v, target_ulong r,
                                      target_ulong pte_index)
 {
@@ -151,8 +135,7 @@ static target_ulong h_enter(CPUPPCState *env, sPAPREnvironment *spapr,
             if (i == 8) {
                 return H_PTEG_FULL;
             }
-            if (((ldq_p(hpte) & HPTE_V_VALID) == 0) &&
-                lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID)) {
+            if ((ldq_p(hpte) & HPTE_V_VALID) == 0) {
                 break;
             }
             hpte += HASH_PTE_SIZE_64;
@@ -160,7 +143,7 @@ static target_ulong h_enter(CPUPPCState *env, sPAPREnvironment *spapr,
     } else {
         i = 0;
         hpte = env->external_htab + (pte_index * HASH_PTE_SIZE_64);
-        if (!lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID)) {
+        if (ldq_p(hpte) & HPTE_V_VALID) {
             return H_PTEG_FULL;
         }
     }
@@ -168,7 +151,6 @@ static target_ulong h_enter(CPUPPCState *env, sPAPREnvironment *spapr,
     /* eieio();  FIXME: need some sort of barrier for smp? */
     stq_p(hpte, pteh);
 
-    assert(!(ldq_p(hpte) & HPTE_V_HVLOCK));
     args[0] = pte_index + i;
     return H_SUCCESS;
 }
@@ -193,11 +175,6 @@ static target_ulong remove_hpte(CPUPPCState *env, target_ulong ptex,
     }
 
     hpte = env->external_htab + (ptex * HASH_PTE_SIZE_64);
-    while (!lock_hpte(hpte, HPTE_V_HVLOCK)) {
-        /* We have no real concurrency in qemu soft-emulation, so we
-         * will never actually have a contested lock */
-        assert(0);
-    }
 
     v = ldq_p(hpte);
     r = ldq_p(hpte + (HASH_PTE_SIZE_64/2));
@@ -205,16 +182,13 @@ static target_ulong remove_hpte(CPUPPCState *env, target_ulong ptex,
     if ((v & HPTE_V_VALID) == 0 ||
         ((flags & H_AVPN) && (v & ~0x7fULL) != avpn) ||
         ((flags & H_ANDCOND) && (v & avpn) != 0)) {
-        stq_p(hpte, v & ~HPTE_V_HVLOCK);
-        assert(!(ldq_p(hpte) & HPTE_V_HVLOCK));
         return REMOVE_NOT_FOUND;
     }
-    *vp = v & ~HPTE_V_HVLOCK;
+    *vp = v;
     *rp = r;
     stq_p(hpte, 0);
     rb = compute_tlbie_rb(v, r, ptex);
     ppc_tlb_invalidate_one(env, rb);
-    assert(!(ldq_p(hpte) & HPTE_V_HVLOCK));
     return REMOVE_SUCCESS;
 }
 
@@ -324,19 +298,12 @@ static target_ulong h_protect(CPUPPCState *env, sPAPREnvironment *spapr,
     }
 
     hpte = env->external_htab + (pte_index * HASH_PTE_SIZE_64);
-    while (!lock_hpte(hpte, HPTE_V_HVLOCK)) {
-        /* We have no real concurrency in qemu soft-emulation, so we
-         * will never actually have a contested lock */
-        assert(0);
-    }
 
     v = ldq_p(hpte);
     r = ldq_p(hpte + (HASH_PTE_SIZE_64/2));
 
     if ((v & HPTE_V_VALID) == 0 ||
         ((flags & H_AVPN) && (v & ~0x7fULL) != avpn)) {
-        stq_p(hpte, v & ~HPTE_V_HVLOCK);
-        assert(!(ldq_p(hpte) & HPTE_V_HVLOCK));
         return H_NOT_FOUND;
     }
 
@@ -350,8 +317,7 @@ static target_ulong h_protect(CPUPPCState *env, sPAPREnvironment *spapr,
     ppc_tlb_invalidate_one(env, rb);
     stq_p(hpte + (HASH_PTE_SIZE_64/2), r);
     /* Don't need a memory barrier, due to qemu's global lock */
-    stq_p(hpte, v & ~HPTE_V_HVLOCK);
-    assert(!(ldq_p(hpte) & HPTE_V_HVLOCK));
+    stq_p(hpte, v);
     return H_SUCCESS;
 }
 
@@ -544,6 +510,8 @@ static target_ulong h_cede(CPUPPCState *env, sPAPREnvironment *spapr,
     hreg_compute_hflags(env);
     if (!cpu_has_work(env)) {
         env->halted = 1;
+        env->exception_index = EXCP_HLT;
+        env->exit_request = 1;
     }
     return H_SUCCESS;
 }
@@ -713,11 +681,6 @@ void spapr_register_hypercall(target_ulong opcode, spapr_hcall_fn fn)
 target_ulong spapr_hypercall(CPUPPCState *env, target_ulong opcode,
                              target_ulong *args)
 {
-    if (msr_pr) {
-        hcall_dprintf("Hypercall made with MSR[PR]=1\n");
-        return H_PRIVILEGE;
-    }
-
     if ((opcode <= MAX_HCALL_OPCODE)
         && ((opcode & 0x3) == 0)) {
         spapr_hcall_fn fn = papr_hypercall_table[opcode / 4];
diff --git a/hw/spapr_iommu.c b/hw/spapr_iommu.c
index 53b731773a..38034c07bd 100644
--- a/hw/spapr_iommu.c
+++ b/hw/spapr_iommu.c
@@ -42,6 +42,7 @@ struct sPAPRTCETable {
     uint32_t liobn;
     uint32_t window_size;
     sPAPRTCE *table;
+    bool bypass;
     int fd;
     QLIST_ENTRY(sPAPRTCETable) list;
 };
@@ -78,6 +79,12 @@ static int spapr_tce_translate(DMAContext *dma,
             DMA_ADDR_FMT "\n", tcet->liobn, addr);
 #endif
 
+    if (tcet->bypass) {
+        *paddr = addr;
+        *len = (target_phys_addr_t)-1;
+        return 0;
+    }
+
     /* Check if we are in bound */
     if (addr >= tcet->window_size) {
 #ifdef DEBUG_TCE
@@ -162,6 +169,23 @@ void spapr_tce_free(DMAContext *dma)
     }
 }
 
+void spapr_tce_set_bypass(DMAContext *dma, bool bypass)
+{
+    sPAPRTCETable *tcet = DO_UPCAST(sPAPRTCETable, dma, dma);
+
+    tcet->bypass = bypass;
+}
+
+void spapr_tce_reset(DMAContext *dma)
+{
+    sPAPRTCETable *tcet = DO_UPCAST(sPAPRTCETable, dma, dma);
+    size_t table_size = (tcet->window_size >> SPAPR_TCE_PAGE_SHIFT)
+        * sizeof(sPAPRTCE);
+
+    tcet->bypass = false;
+    memset(tcet->table, 0, table_size);
+}
+
 static target_ulong put_tce_emu(sPAPRTCETable *tcet, target_ulong ioba,
                                 target_ulong tce)
 {
diff --git a/hw/spapr_pci.c b/hw/spapr_pci.c
index 661c05bc30..b628f89a02 100644
--- a/hw/spapr_pci.c
+++ b/hw/spapr_pci.c
@@ -351,7 +351,7 @@ static void rtas_ibm_change_msi(sPAPREnvironment *spapr,
 
     /* There is no cached config, allocate MSIs */
     if (!phb->msi_table[ndev].nvec) {
-        irq = spapr_allocate_irq_block(req_num, XICS_MSI);
+        irq = spapr_allocate_irq_block(req_num, true);
         if (irq < 0) {
             fprintf(stderr, "Cannot allocate MSIs for device#%d", ndev);
             rtas_st(rets, 0, -1); /* Hardware error */
@@ -595,6 +595,15 @@ static int spapr_phb_init(SysBusDevice *s)
     return 0;
 }
 
+static void spapr_phb_reset(DeviceState *qdev)
+{
+    SysBusDevice *s = sysbus_from_qdev(qdev);
+    sPAPRPHBState *sphb = SPAPR_PCI_HOST_BRIDGE(s);
+
+    /* Reset the IOMMU state */
+    spapr_tce_reset(sphb->dma);
+}
+
 static Property spapr_phb_properties[] = {
     DEFINE_PROP_HEX64("buid", sPAPRPHBState, buid, 0),
     DEFINE_PROP_STRING("busname", sPAPRPHBState, busname),
@@ -613,6 +622,7 @@ static void spapr_phb_class_init(ObjectClass *klass, void *data)
 
     sdc->init = spapr_phb_init;
     dc->props = spapr_phb_properties;
+    dc->reset = spapr_phb_reset;
 }
 
 static const TypeInfo spapr_phb_info = {
diff --git a/hw/spapr_rtas.c b/hw/spapr_rtas.c
index ae18595150..b808f80017 100644
--- a/hw/spapr_rtas.c
+++ b/hw/spapr_rtas.c
@@ -184,6 +184,11 @@ static void rtas_start_cpu(sPAPREnvironment *spapr,
             return;
         }
 
+        /* This will make sure qemu state is up to date with kvm, and
+         * mark it dirty so our changes get flushed back before the
+         * new cpu enters */
+        kvm_cpu_synchronize_state(env);
+
         env->msr = (1ULL << MSR_SF) | (1ULL << MSR_ME);
         env->nip = start;
         env->gpr[3] = r3;
diff --git a/hw/spapr_vio.c b/hw/spapr_vio.c
index 7ca445216d..848806d3f1 100644
--- a/hw/spapr_vio.c
+++ b/hw/spapr_vio.c
@@ -316,17 +316,10 @@ int spapr_vio_send_crq(VIOsPAPRDevice *dev, uint8_t *crq)
 
 static void spapr_vio_quiesce_one(VIOsPAPRDevice *dev)
 {
-    VIOsPAPRDeviceClass *pc = VIO_SPAPR_DEVICE_GET_CLASS(dev);
-    uint32_t liobn = SPAPR_VIO_BASE_LIOBN | dev->reg;
-
     if (dev->dma) {
-        spapr_tce_free(dev->dma);
+        spapr_tce_reset(dev->dma);
     }
-    dev->dma = spapr_tce_new_dma_context(liobn, pc->rtce_window_size);
-
-    dev->crq.qladdr = 0;
-    dev->crq.qsize = 0;
-    dev->crq.qnext = 0;
+    free_crq(dev);
 }
 
 static void rtas_set_tce_bypass(sPAPREnvironment *spapr, uint32_t token,
@@ -348,16 +341,14 @@ static void rtas_set_tce_bypass(sPAPREnvironment *spapr, uint32_t token,
         rtas_st(rets, 0, -3);
         return;
     }
-    if (enable) {
-        spapr_tce_free(dev->dma);
-        dev->dma = NULL;
-    } else {
-        VIOsPAPRDeviceClass *pc = VIO_SPAPR_DEVICE_GET_CLASS(dev);
-        uint32_t liobn = SPAPR_VIO_BASE_LIOBN | dev->reg;
 
-        dev->dma = spapr_tce_new_dma_context(liobn, pc->rtce_window_size);
+    if (!dev->dma) {
+        rtas_st(rets, 0, -3);
+        return;
     }
 
+    spapr_tce_set_bypass(dev->dma, !!enable);
+
     rtas_st(rets, 0, 0);
 }
 
@@ -409,9 +400,10 @@ static void spapr_vio_busdev_reset(DeviceState *qdev)
     VIOsPAPRDevice *dev = DO_UPCAST(VIOsPAPRDevice, qdev, qdev);
     VIOsPAPRDeviceClass *pc = VIO_SPAPR_DEVICE_GET_CLASS(dev);
 
-    if (dev->crq.qsize) {
-        free_crq(dev);
-    }
+    /* Shut down the request queue and TCEs if necessary */
+    spapr_vio_quiesce_one(dev);
+
+    dev->signal_state = 0;
 
     if (pc->reset) {
         pc->reset(dev);
@@ -422,7 +414,6 @@ static int spapr_vio_busdev_init(DeviceState *qdev)
 {
     VIOsPAPRDevice *dev = (VIOsPAPRDevice *)qdev;
     VIOsPAPRDeviceClass *pc = VIO_SPAPR_DEVICE_GET_CLASS(dev);
-    uint32_t liobn;
     char *id;
 
     if (dev->reg != -1) {
@@ -464,8 +455,10 @@ static int spapr_vio_busdev_init(DeviceState *qdev)
         return -1;
     }
 
-    liobn = SPAPR_VIO_BASE_LIOBN | dev->reg;
-    dev->dma = spapr_tce_new_dma_context(liobn, pc->rtce_window_size);
+    if (pc->rtce_window_size) {
+        uint32_t liobn = SPAPR_VIO_BASE_LIOBN | dev->reg;
+        dev->dma = spapr_tce_new_dma_context(liobn, pc->rtce_window_size);
+    }
 
     return pc->init(dev);
 }
diff --git a/hw/spapr_vio.h b/hw/spapr_vio.h
index ea6aa43e26..cc85d26101 100644
--- a/hw/spapr_vio.h
+++ b/hw/spapr_vio.h
@@ -60,7 +60,6 @@ typedef struct VIOsPAPRDeviceClass {
 struct VIOsPAPRDevice {
     DeviceState qdev;
     uint32_t reg;
-    uint32_t flags;
     uint32_t irq;
     target_ulong signal_state;
     VIOsPAPR_CRQ crq;
@@ -132,7 +131,6 @@ void spapr_vscsi_create(VIOsPAPRBus *bus);
 
 VIOsPAPRDevice *spapr_vty_get_default(VIOsPAPRBus *bus);
 
-int spapr_tce_set_bypass(uint32_t unit, uint32_t enable);
 void spapr_vio_quiesce(void);
 
 #endif /* _HW_SPAPR_VIO_H */
diff --git a/hw/xics.c b/hw/xics.c
index b674771dc4..ce88aa750b 100644
--- a/hw/xics.c
+++ b/hw/xics.c
@@ -165,11 +165,12 @@ struct ics_irq_state {
     int server;
     uint8_t priority;
     uint8_t saved_priority;
-    enum xics_irq_type type;
-    int asserted:1;
-    int sent:1;
-    int rejected:1;
-    int masked_pending:1;
+#define XICS_STATUS_ASSERTED           0x1
+#define XICS_STATUS_SENT               0x2
+#define XICS_STATUS_REJECTED           0x4
+#define XICS_STATUS_MASKED_PENDING     0x8
+    uint8_t status;
+    bool lsi;
 };
 
 struct ics_state {
@@ -191,8 +192,8 @@ static void resend_msi(struct ics_state *ics, int srcno)
     struct ics_irq_state *irq = ics->irqs + srcno;
 
     /* FIXME: filter by server#? */
-    if (irq->rejected) {
-        irq->rejected = 0;
+    if (irq->status & XICS_STATUS_REJECTED) {
+        irq->status &= ~XICS_STATUS_REJECTED;
         if (irq->priority != 0xff) {
             icp_irq(ics->icp, irq->server, srcno + ics->offset,
                     irq->priority);
@@ -204,8 +205,10 @@ static void resend_lsi(struct ics_state *ics, int srcno)
 {
     struct ics_irq_state *irq = ics->irqs + srcno;
 
-    if ((irq->priority != 0xff) && irq->asserted && !irq->sent) {
-        irq->sent = 1;
+    if ((irq->priority != 0xff)
+        && (irq->status & XICS_STATUS_ASSERTED)
+        && !(irq->status & XICS_STATUS_SENT)) {
+        irq->status |= XICS_STATUS_SENT;
         icp_irq(ics->icp, irq->server, srcno + ics->offset, irq->priority);
     }
 }
@@ -216,7 +219,7 @@ static void set_irq_msi(struct ics_state *ics, int srcno, int val)
 
     if (val) {
         if (irq->priority == 0xff) {
-            irq->masked_pending = 1;
+            irq->status |= XICS_STATUS_MASKED_PENDING;
             /* masked pending */ ;
         } else  {
             icp_irq(ics->icp, irq->server, srcno + ics->offset, irq->priority);
@@ -228,7 +231,11 @@ static void set_irq_lsi(struct ics_state *ics, int srcno, int val)
 {
     struct ics_irq_state *irq = ics->irqs + srcno;
 
-    irq->asserted = val;
+    if (val) {
+        irq->status |= XICS_STATUS_ASSERTED;
+    } else {
+        irq->status &= ~XICS_STATUS_ASSERTED;
+    }
     resend_lsi(ics, srcno);
 }
 
@@ -237,7 +244,7 @@ static void ics_set_irq(void *opaque, int srcno, int val)
     struct ics_state *ics = (struct ics_state *)opaque;
     struct ics_irq_state *irq = ics->irqs + srcno;
 
-    if (irq->type == XICS_LSI) {
+    if (irq->lsi) {
         set_irq_lsi(ics, srcno, val);
     } else {
         set_irq_msi(ics, srcno, val);
@@ -248,11 +255,12 @@ static void write_xive_msi(struct ics_state *ics, int srcno)
 {
     struct ics_irq_state *irq = ics->irqs + srcno;
 
-    if (!irq->masked_pending || (irq->priority == 0xff)) {
+    if (!(irq->status & XICS_STATUS_MASKED_PENDING)
+        || (irq->priority == 0xff)) {
         return;
     }
 
-    irq->masked_pending = 0;
+    irq->status &= ~XICS_STATUS_MASKED_PENDING;
     icp_irq(ics->icp, irq->server, srcno + ics->offset, irq->priority);
 }
 
@@ -262,15 +270,16 @@ static void write_xive_lsi(struct ics_state *ics, int srcno)
 }
 
 static void ics_write_xive(struct ics_state *ics, int nr, int server,
-                           uint8_t priority)
+                           uint8_t priority, uint8_t saved_priority)
 {
     int srcno = nr - ics->offset;
     struct ics_irq_state *irq = ics->irqs + srcno;
 
     irq->server = server;
     irq->priority = priority;
+    irq->saved_priority = saved_priority;
 
-    if (irq->type == XICS_LSI) {
+    if (irq->lsi) {
         write_xive_lsi(ics, srcno);
     } else {
         write_xive_msi(ics, srcno);
@@ -281,8 +290,8 @@ static void ics_reject(struct ics_state *ics, int nr)
 {
     struct ics_irq_state *irq = ics->irqs + nr - ics->offset;
 
-    irq->rejected = 1; /* Irrelevant but harmless for LSI */
-    irq->sent = 0; /* Irrelevant but harmless for MSI */
+    irq->status |= XICS_STATUS_REJECTED; /* Irrelevant but harmless for LSI */
+    irq->status &= ~XICS_STATUS_SENT; /* Irrelevant but harmless for MSI */
 }
 
 static void ics_resend(struct ics_state *ics)
@@ -293,7 +302,7 @@ static void ics_resend(struct ics_state *ics)
         struct ics_irq_state *irq = ics->irqs + i;
 
         /* FIXME: filter by server#? */
-        if (irq->type == XICS_LSI) {
+        if (irq->lsi) {
             resend_lsi(ics, i);
         } else {
             resend_msi(ics, i);
@@ -306,8 +315,8 @@ static void ics_eoi(struct ics_state *ics, int nr)
     int srcno = nr - ics->offset;
     struct ics_irq_state *irq = ics->irqs + srcno;
 
-    if (irq->type == XICS_LSI) {
-        irq->sent = 0;
+    if (irq->lsi) {
+        irq->status &= ~XICS_STATUS_SENT;
     }
 }
 
@@ -325,14 +334,12 @@ qemu_irq xics_get_qirq(struct icp_state *icp, int irq)
     return icp->ics->qirqs[irq - icp->ics->offset];
 }
 
-void xics_set_irq_type(struct icp_state *icp, int irq,
-                       enum xics_irq_type type)
+void xics_set_irq_type(struct icp_state *icp, int irq, bool lsi)
 {
     assert((irq >= icp->ics->offset)
            && (irq < (icp->ics->offset + icp->ics->nr_irqs)));
-    assert((type == XICS_MSI) || (type == XICS_LSI));
 
-    icp->ics->irqs[irq - icp->ics->offset].type = type;
+    icp->ics->irqs[irq - icp->ics->offset].lsi = lsi;
 }
 
 static target_ulong h_cppr(CPUPPCState *env, sPAPREnvironment *spapr,
@@ -399,7 +406,7 @@ static void rtas_set_xive(sPAPREnvironment *spapr, uint32_t token,
         return;
     }
 
-    ics_write_xive(ics, nr, server, priority);
+    ics_write_xive(ics, nr, server, priority, priority);
 
     rtas_st(rets, 0, 0); /* Success */
 }
@@ -447,14 +454,8 @@ static void rtas_int_off(sPAPREnvironment *spapr, uint32_t token,
         return;
     }
 
-    /* This is a NOP for now, since the described PAPR semantics don't
-     * seem to gel with what Linux does */
-#if 0
-    struct ics_irq_state *irq = xics->irqs + (nr - xics->offset);
-
-    irq->saved_priority = irq->priority;
-    ics_write_xive_msi(xics, nr, irq->server, 0xff);
-#endif
+    ics_write_xive(ics, nr, ics->irqs[nr - ics->offset].server, 0xff,
+                   ics->irqs[nr - ics->offset].priority);
 
     rtas_st(rets, 0, 0); /* Success */
 }
@@ -478,22 +479,40 @@ static void rtas_int_on(sPAPREnvironment *spapr, uint32_t token,
         return;
     }
 
-    /* This is a NOP for now, since the described PAPR semantics don't
-     * seem to gel with what Linux does */
-#if 0
-    struct ics_irq_state *irq = xics->irqs + (nr - xics->offset);
-
-    ics_write_xive_msi(xics, nr, irq->server, irq->saved_priority);
-#endif
+    ics_write_xive(ics, nr, ics->irqs[nr - ics->offset].server,
+                   ics->irqs[nr - ics->offset].saved_priority,
+                   ics->irqs[nr - ics->offset].saved_priority);
 
     rtas_st(rets, 0, 0); /* Success */
 }
 
+static void xics_reset(void *opaque)
+{
+    struct icp_state *icp = (struct icp_state *)opaque;
+    struct ics_state *ics = icp->ics;
+    int i;
+
+    for (i = 0; i < icp->nr_servers; i++) {
+        icp->ss[i].xirr = 0;
+        icp->ss[i].pending_priority = 0;
+        icp->ss[i].mfrr = 0xff;
+        /* Make all outputs are deasserted */
+        qemu_set_irq(icp->ss[i].output, 0);
+    }
+
+    for (i = 0; i < ics->nr_irqs; i++) {
+        /* Reset everything *except* the type */
+        ics->irqs[i].server = 0;
+        ics->irqs[i].status = 0;
+        ics->irqs[i].priority = 0xff;
+        ics->irqs[i].saved_priority = 0xff;
+    }
+}
+
 struct icp_state *xics_system_init(int nr_irqs)
 {
     CPUPPCState *env;
     int max_server_num;
-    int i;
     struct icp_state *icp;
     struct ics_state *ics;
 
@@ -508,10 +527,6 @@ struct icp_state *xics_system_init(int nr_irqs)
     icp->nr_servers = max_server_num + 1;
     icp->ss = g_malloc0(icp->nr_servers*sizeof(struct icp_server_state));
 
-    for (i = 0; i < icp->nr_servers; i++) {
-        icp->ss[i].mfrr = 0xff;
-    }
-
     for (env = first_cpu; env != NULL; env = env->next_cpu) {
         struct icp_server_state *ss = &icp->ss[env->cpu_index];
 
@@ -539,11 +554,6 @@ struct icp_state *xics_system_init(int nr_irqs)
     icp->ics = ics;
     ics->icp = icp;
 
-    for (i = 0; i < nr_irqs; i++) {
-        ics->irqs[i].priority = 0xff;
-        ics->irqs[i].saved_priority = 0xff;
-    }
-
     ics->qirqs = qemu_allocate_irqs(ics_set_irq, ics, nr_irqs);
 
     spapr_register_hypercall(H_CPPR, h_cppr);
@@ -556,5 +566,7 @@ struct icp_state *xics_system_init(int nr_irqs)
     spapr_rtas_register("ibm,int-off", rtas_int_off);
     spapr_rtas_register("ibm,int-on", rtas_int_on);
 
+    qemu_register_reset(xics_reset, icp);
+
     return icp;
 }
diff --git a/hw/xics.h b/hw/xics.h
index 99b96ac85a..6817268697 100644
--- a/hw/xics.h
+++ b/hw/xics.h
@@ -31,14 +31,8 @@
 
 struct icp_state;
 
-enum xics_irq_type {
-    XICS_MSI,        /* Message-signalled (edge) interrupt */
-    XICS_LSI,        /* Level-signalled interrupt */
-};
-
 qemu_irq xics_get_qirq(struct icp_state *icp, int irq);
-void xics_set_irq_type(struct icp_state *icp, int irq,
-                       enum xics_irq_type type);
+void xics_set_irq_type(struct icp_state *icp, int irq, bool lsi);
 
 struct icp_state *xics_system_init(int nr_irqs);