20 files changed, 626 insertions, 118 deletions
diff --git a/hw/arm/boot.c b/hw/arm/boot.c
index ff621e4b6a..c2720c8046 100644
--- a/hw/arm/boot.c
+++ b/hw/arm/boot.c
@@ -31,6 +31,9 @@
 #define KERNEL_LOAD_ADDR 0x00010000
 #define KERNEL64_LOAD_ADDR 0x00080000
 
+#define ARM64_TEXT_OFFSET_OFFSET    8
+#define ARM64_MAGIC_OFFSET          56
+
 typedef enum {
     FIXUP_NONE = 0,     /* do nothing */
     FIXUP_TERMINATOR,   /* end of insns */
@@ -768,6 +771,49 @@ static uint64_t arm_load_elf(struct arm_boot_info *info, uint64_t *pentry,
     return ret;
 }
 
+static uint64_t load_aarch64_image(const char *filename, hwaddr mem_base,
+                                   hwaddr *entry)
+{
+    hwaddr kernel_load_offset = KERNEL64_LOAD_ADDR;
+    uint8_t *buffer;
+    int size;
+
+    /* On aarch64, it's the bootloader's job to uncompress the kernel. */
+    size = load_image_gzipped_buffer(filename, LOAD_IMAGE_MAX_GUNZIP_BYTES,
+                                     &buffer);
+
+    if (size < 0) {
+        gsize len;
+
+        /* Load as raw file otherwise */
+        if (!g_file_get_contents(filename, (char **)&buffer, &len, NULL)) {
+            return -1;
+        }
+        size = len;
+    }
+
+    /* check the arm64 magic header value -- very old kernels may not have it */
+    if (memcmp(buffer + ARM64_MAGIC_OFFSET, "ARM\x64", 4) == 0) {
+        uint64_t hdrvals[2];
+
+        /* The arm64 Image header has text_offset and image_size fields at 8 and
+         * 16 bytes into the Image header, respectively. The text_offset field
+         * is only valid if the image_size is non-zero.
+         */
+        memcpy(&hdrvals, buffer + ARM64_TEXT_OFFSET_OFFSET, sizeof(hdrvals));
+        if (hdrvals[1] != 0) {
+            kernel_load_offset = le64_to_cpu(hdrvals[0]);
+        }
+    }
+
+    *entry = mem_base + kernel_load_offset;
+    rom_add_blob_fixed(filename, buffer, size, *entry);
+
+    g_free(buffer);
+
+    return size;
+}
+
 static void arm_load_kernel_notify(Notifier *notifier, void *data)
 {
     CPUState *cs;
@@ -776,7 +822,7 @@ static void arm_load_kernel_notify(Notifier *notifier, void *data)
     int is_linux = 0;
     uint64_t elf_entry, elf_low_addr, elf_high_addr;
     int elf_machine;
-    hwaddr entry, kernel_load_offset;
+    hwaddr entry;
     static const ARMInsnFixup *primary_loader;
     ArmLoadKernelNotifier *n = DO_UPCAST(ArmLoadKernelNotifier,
                                          notifier, notifier);
@@ -841,14 +887,12 @@ static void arm_load_kernel_notify(Notifier *notifier, void *data)
 
     if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) {
         primary_loader = bootloader_aarch64;
-        kernel_load_offset = KERNEL64_LOAD_ADDR;
         elf_machine = EM_AARCH64;
     } else {
         primary_loader = bootloader;
         if (!info->write_board_setup) {
             primary_loader += BOOTLOADER_NO_BOARD_SETUP_OFFSET;
         }
-        kernel_load_offset = KERNEL_LOAD_ADDR;
         elf_machine = EM_ARM;
     }
 
@@ -900,17 +944,15 @@ static void arm_load_kernel_notify(Notifier *notifier, void *data)
         kernel_size = load_uimage(info->kernel_filename, &entry, NULL,
                                   &is_linux, NULL, NULL);
     }
-    /* On aarch64, it's the bootloader's job to uncompress the kernel. */
     if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64) && kernel_size < 0) {
-        entry = info->loader_start + kernel_load_offset;
-        kernel_size = load_image_gzipped(info->kernel_filename, entry,
-                                         info->ram_size - kernel_load_offset);
+        kernel_size = load_aarch64_image(info->kernel_filename,
+                                         info->loader_start, &entry);
         is_linux = 1;
-    }
-    if (kernel_size < 0) {
-        entry = info->loader_start + kernel_load_offset;
+    } else if (kernel_size < 0) {
+        /* 32-bit ARM */
+        entry = info->loader_start + KERNEL_LOAD_ADDR;
         kernel_size = load_image_targphys(info->kernel_filename, entry,
-                                          info->ram_size - kernel_load_offset);
+                                          info->ram_size - KERNEL_LOAD_ADDR);
         is_linux = 1;
     }
     if (kernel_size < 0) {
diff --git a/hw/arm/exynos4_boards.c b/hw/arm/exynos4_boards.c
index 0efa194054..4853c31802 100644
--- a/hw/arm/exynos4_boards.c
+++ b/hw/arm/exynos4_boards.c
@@ -22,6 +22,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/error-report.h"
 #include "qemu-common.h"
 #include "cpu.h"
 #include "sysemu/sysemu.h"
@@ -101,9 +102,9 @@ static Exynos4210State *exynos4_boards_init_common(MachineState *machine,
     MachineClass *mc = MACHINE_GET_CLASS(machine);
 
     if (smp_cpus != EXYNOS4210_NCPUS && !qtest_enabled()) {
-        fprintf(stderr, "%s board supports only %d CPU cores. Ignoring smp_cpus"
-                " value.\n",
-                mc->name, EXYNOS4210_NCPUS);
+        error_report("%s board supports only %d CPU cores, ignoring smp_cpus"
+                     " value",
+                     mc->name, EXYNOS4210_NCPUS);
     }
 
     exynos4_board_binfo.ram_size = exynos4_board_ram_size[board_type];
diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c
index cfee3929d9..eea551dc16 100644
--- a/hw/arm/pxa2xx.c
+++ b/hw/arm/pxa2xx.c
@@ -755,19 +755,18 @@ static void pxa2xx_ssp_reset(DeviceState *d)
     s->rx_start = s->rx_level = 0;
 }
 
-static int pxa2xx_ssp_init(SysBusDevice *sbd)
+static void pxa2xx_ssp_init(Object *obj)
 {
-    DeviceState *dev = DEVICE(sbd);
-    PXA2xxSSPState *s = PXA2XX_SSP(dev);
-
+    DeviceState *dev = DEVICE(obj);
+    PXA2xxSSPState *s = PXA2XX_SSP(obj);
+    SysBusDevice *sbd = SYS_BUS_DEVICE(obj);
     sysbus_init_irq(sbd, &s->irq);
 
-    memory_region_init_io(&s->iomem, OBJECT(s), &pxa2xx_ssp_ops, s,
+    memory_region_init_io(&s->iomem, obj, &pxa2xx_ssp_ops, s,
                           "pxa2xx-ssp", 0x1000);
     sysbus_init_mmio(sbd, &s->iomem);
 
     s->bus = ssi_create_bus(dev, "ssi");
-    return 0;
 }
 
 /* Real-Time Clock */
@@ -2321,10 +2320,8 @@ PXA2xxState *pxa255_init(MemoryRegion *address_space, unsigned int sdram_size)
 
 static void pxa2xx_ssp_class_init(ObjectClass *klass, void *data)
 {
-    SysBusDeviceClass *sdc = SYS_BUS_DEVICE_CLASS(klass);
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    sdc->init = pxa2xx_ssp_init;
     dc->reset = pxa2xx_ssp_reset;
     dc->vmsd = &vmstate_pxa2xx_ssp;
 }
@@ -2333,6 +2330,7 @@ static const TypeInfo pxa2xx_ssp_info = {
     .name          = TYPE_PXA2XX_SSP,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(PXA2xxSSPState),
+    .instance_init = pxa2xx_ssp_init,
     .class_init    = pxa2xx_ssp_class_init,
 };
 
diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c
index 9edcd49740..ea7a8094e1 100644
--- a/hw/arm/stellaris.c
+++ b/hw/arm/stellaris.c
@@ -108,7 +108,10 @@ static void gptm_reload(gptm_state *s, int n, int reset)
     } else if (s->mode[n] == 0xa) {
         /* PWM mode.  Not implemented.  */
     } else {
-        hw_error("TODO: 16-bit timer mode 0x%x\n", s->mode[n]);
+        qemu_log_mask(LOG_UNIMP,
+                      "GPTM: 16-bit timer mode unimplemented: 0x%x\n",
+                      s->mode[n]);
+        return;
     }
     s->tick[n] = tick;
     timer_mod(s->timer[n], tick);
@@ -149,7 +152,9 @@ static void gptm_tick(void *opaque)
     } else if (s->mode[n] == 0xa) {
         /* PWM mode.  Not implemented.  */
     } else {
-        hw_error("TODO: 16-bit timer mode 0x%x\n", s->mode[n]);
+        qemu_log_mask(LOG_UNIMP,
+                      "GPTM: 16-bit timer mode unimplemented: 0x%x\n",
+                      s->mode[n]);
     }
     gptm_update_irq(s);
 }
@@ -286,7 +291,8 @@ static void gptm_write(void *opaque, hwaddr offset,
         s->match_prescale[0] = value;
         break;
     default:
-        hw_error("gptm_write: Bad offset 0x%x\n", (int)offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "GPTM: read at bad offset 0x%x\n", (int)offset);
     }
     gptm_update_irq(s);
 }
@@ -425,7 +431,10 @@ static int ssys_board_class(const ssys_state *s)
         }
         /* for unknown classes, fall through */
     default:
-        hw_error("ssys_board_class: Unknown class 0x%08x\n", did0);
+        /* This can only happen if the hardwired constant did0 value
+         * in this board's stellaris_board_info struct is wrong.
+         */
+        g_assert_not_reached();
     }
 }
 
@@ -479,8 +488,7 @@ static uint64_t ssys_read(void *opaque, hwaddr offset,
             case DID0_CLASS_SANDSTORM:
                 return pllcfg_sandstorm[xtal];
             default:
-                hw_error("ssys_read: Unhandled class for PLLCFG read.\n");
-                return 0;
+                g_assert_not_reached();
             }
         }
     case 0x070: /* RCC2 */
@@ -512,7 +520,8 @@ static uint64_t ssys_read(void *opaque, hwaddr offset,
     case 0x1e4: /* USER1 */
         return s->user1;
     default:
-        hw_error("ssys_read: Bad offset 0x%x\n", (int)offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "SSYS: read at bad offset 0x%x\n", (int)offset);
         return 0;
     }
 }
@@ -614,7 +623,8 @@ static void ssys_write(void *opaque, hwaddr offset,
         s->ldoarst = value;
         break;
     default:
-        hw_error("ssys_write: Bad offset 0x%x\n", (int)offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "SSYS: write at bad offset 0x%x\n", (int)offset);
     }
     ssys_update(s);
 }
@@ -748,7 +758,8 @@ static uint64_t stellaris_i2c_read(void *opaque, hwaddr offset,
     case 0x20: /* MCR */
         return s->mcr;
     default:
-        hw_error("strllaris_i2c_read: Bad offset 0x%x\n", (int)offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "stellaris_i2c: read at bad offset 0x%x\n", (int)offset);
         return 0;
     }
 }
@@ -823,17 +834,18 @@ static void stellaris_i2c_write(void *opaque, hwaddr offset,
         s->mris &= ~value;
         break;
     case 0x20: /* MCR */
-        if (value & 1)
-            hw_error(
-                      "stellaris_i2c_write: Loopback not implemented\n");
-        if (value & 0x20)
-            hw_error(
-                      "stellaris_i2c_write: Slave mode not implemented\n");
+        if (value & 1) {
+            qemu_log_mask(LOG_UNIMP, "stellaris_i2c: Loopback not implemented");
+        }
+        if (value & 0x20) {
+            qemu_log_mask(LOG_UNIMP,
+                          "stellaris_i2c: Slave mode not implemented");
+        }
         s->mcr = value & 0x31;
         break;
     default:
-        hw_error("stellaris_i2c_write: Bad offset 0x%x\n",
-                  (int)offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "stellaris_i2c: write at bad offset 0x%x\n", (int)offset);
     }
     stellaris_i2c_update(s);
 }
@@ -1057,8 +1069,8 @@ static uint64_t stellaris_adc_read(void *opaque, hwaddr offset,
     case 0x30: /* SAC */
         return s->sac;
     default:
-        hw_error("strllaris_adc_read: Bad offset 0x%x\n",
-                  (int)offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "stellaris_adc: read at bad offset 0x%x\n", (int)offset);
         return 0;
     }
 }
@@ -1078,8 +1090,9 @@ static void stellaris_adc_write(void *opaque, hwaddr offset,
             return;
         case 0x04: /* SSCTL */
             if (value != 6) {
-                hw_error("ADC: Unimplemented sequence %" PRIx64 "\n",
-                          value);
+                qemu_log_mask(LOG_UNIMP,
+                              "ADC: Unimplemented sequence %" PRIx64 "\n",
+                              value);
             }
             s->ssctl[n] = value;
             return;
@@ -1110,13 +1123,14 @@ static void stellaris_adc_write(void *opaque, hwaddr offset,
         s->sspri = value;
         break;
     case 0x28: /* PSSI */
-        hw_error("Not implemented:  ADC sample initiate\n");
+        qemu_log_mask(LOG_UNIMP, "ADC: sample initiate unimplemented");
         break;
     case 0x30: /* SAC */
         s->sac = value;
         break;
     default:
-        hw_error("stellaris_adc_write: Bad offset 0x%x\n", (int)offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "stellaris_adc: write at bad offset 0x%x\n", (int)offset);
     }
     stellaris_adc_update(s);
 }
diff --git a/hw/arm/xlnx-zynqmp.c b/hw/arm/xlnx-zynqmp.c
index 4f671588b0..64f52f80a5 100644
--- a/hw/arm/xlnx-zynqmp.c
+++ b/hw/arm/xlnx-zynqmp.c
@@ -30,6 +30,8 @@
 #define ARM_PHYS_TIMER_PPI  30
 #define ARM_VIRT_TIMER_PPI  27
 
+#define GEM_REVISION        0x40070106
+
 #define GIC_BASE_ADDR       0xf9000000
 #define GIC_DIST_ADDR       0xf9010000
 #define GIC_CPU_ADDR        0xf9020000
@@ -334,8 +336,10 @@ static void xlnx_zynqmp_realize(DeviceState *dev, Error **errp)
             qemu_check_nic_model(nd, TYPE_CADENCE_GEM);
             qdev_set_nic_properties(DEVICE(&s->gem[i]), nd);
         }
+        object_property_set_int(OBJECT(&s->gem[i]), GEM_REVISION, "revision",
+                                &error_abort);
         object_property_set_int(OBJECT(&s->gem[i]), 2, "num-priority-queues",
-                                  &error_abort);
+                                &error_abort);
         object_property_set_bool(OBJECT(&s->gem[i]), true, "realized", &err);
         if (err) {
             error_propagate(errp, err);
diff --git a/hw/char/exynos4210_uart.c b/hw/char/exynos4210_uart.c
index b75f28d473..bff706ab3a 100644
--- a/hw/char/exynos4210_uart.c
+++ b/hw/char/exynos4210_uart.c
@@ -102,7 +102,7 @@ typedef struct Exynos4210UartReg {
     uint32_t            reset_value;
 } Exynos4210UartReg;
 
-static Exynos4210UartReg exynos4210_uart_regs[] = {
+static const Exynos4210UartReg exynos4210_uart_regs[] = {
     {"ULCON",    ULCON,    0x00000000},
     {"UCON",     UCON,     0x00003000},
     {"UFCON",    UFCON,    0x00000000},
@@ -220,7 +220,7 @@ static uint8_t fifo_retrieve(Exynos4210UartFIFO *q)
     return  ret;
 }
 
-static int fifo_elements_number(Exynos4210UartFIFO *q)
+static int fifo_elements_number(const Exynos4210UartFIFO *q)
 {
     if (q->sp < q->rp) {
         return q->size - q->rp + q->sp;
@@ -229,7 +229,7 @@ static int fifo_elements_number(Exynos4210UartFIFO *q)
     return q->sp - q->rp;
 }
 
-static int fifo_empty_elements_number(Exynos4210UartFIFO *q)
+static int fifo_empty_elements_number(const Exynos4210UartFIFO *q)
 {
     return q->size - fifo_elements_number(q);
 }
@@ -245,7 +245,7 @@ static void fifo_reset(Exynos4210UartFIFO *q)
     q->rp = 0;
 }
 
-static uint32_t exynos4210_uart_Tx_FIFO_trigger_level(Exynos4210UartState *s)
+static uint32_t exynos4210_uart_Tx_FIFO_trigger_level(const Exynos4210UartState *s)
 {
     uint32_t level = 0;
     uint32_t reg;
diff --git a/hw/core/null-machine.c b/hw/core/null-machine.c
index 27c8369b57..864832db34 100644
--- a/hw/core/null-machine.c
+++ b/hw/core/null-machine.c
@@ -40,6 +40,12 @@ static void machine_none_init(MachineState *mch)
         memory_region_allocate_system_memory(ram, NULL, "ram", mch->ram_size);
         memory_region_add_subregion(get_system_memory(), 0, ram);
     }
+
+    if (mch->kernel_filename) {
+        error_report("The -kernel parameter is not supported "
+                     "(use the generic 'loader' device instead).");
+        exit(1);
+    }
 }
 
 static void machine_none_machine_init(MachineClass *mc)
diff --git a/hw/core/qdev-properties-system.c b/hw/core/qdev-properties-system.c
index e885e650fb..79c2014135 100644
--- a/hw/core/qdev-properties-system.c
+++ b/hw/core/qdev-properties-system.c
@@ -409,7 +409,7 @@ void qdev_prop_set_drive(DeviceState *dev, const char *name,
     if (value) {
         ref = blk_name(value);
         if (!*ref) {
-            BlockDriverState *bs = blk_bs(value);
+            const BlockDriverState *bs = blk_bs(value);
             if (bs) {
                 ref = bdrv_get_node_name(bs);
             }
diff --git a/hw/core/qdev-properties.c b/hw/core/qdev-properties.c
index 6ab4265eb4..fa3617db2d 100644
--- a/hw/core/qdev-properties.c
+++ b/hw/core/qdev-properties.c
@@ -1010,7 +1010,8 @@ void qdev_prop_set_string(DeviceState *dev, const char *name, const char *value)
     object_property_set_str(OBJECT(dev), value, name, &error_abort);
 }
 
-void qdev_prop_set_macaddr(DeviceState *dev, const char *name, uint8_t *value)
+void qdev_prop_set_macaddr(DeviceState *dev, const char *name,
+                           const uint8_t *value)
 {
     char str[2 * 6 + 5 + 1];
     snprintf(str, sizeof(str), "%02x:%02x:%02x:%02x:%02x:%02x",
diff --git a/hw/core/qdev.c b/hw/core/qdev.c
index 1e7fb33246..695d7c4216 100644
--- a/hw/core/qdev.c
+++ b/hw/core/qdev.c
@@ -1037,13 +1037,6 @@ static bool device_get_hotplugged(Object *obj, Error **err)
     return dev->hotplugged;
 }
 
-static void device_set_hotplugged(Object *obj, bool value, Error **err)
-{
-    DeviceState *dev = DEVICE(obj);
-
-    dev->hotplugged = value;
-}
-
 static void device_initfn(Object *obj)
 {
     DeviceState *dev = DEVICE(obj);
@@ -1063,7 +1056,7 @@ static void device_initfn(Object *obj)
     object_property_add_bool(obj, "hotpluggable",
                              device_get_hotpluggable, NULL, NULL);
     object_property_add_bool(obj, "hotplugged",
-                             device_get_hotplugged, device_set_hotplugged,
+                             device_get_hotplugged, NULL,
                              &error_abort);
 
     class = object_get_class(OBJECT(dev));
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index 22d8226e43..02f047c8e3 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -595,6 +595,22 @@ static inline uint32_t vtd_get_agaw_from_context_entry(VTDContextEntry *ce)
     return 30 + (ce->hi & VTD_CONTEXT_ENTRY_AW) * 9;
 }
 
+static inline uint64_t vtd_iova_limit(VTDContextEntry *ce)
+{
+    uint32_t ce_agaw = vtd_get_agaw_from_context_entry(ce);
+    return 1ULL << MIN(ce_agaw, VTD_MGAW);
+}
+
+/* Return true if IOVA passes range check, otherwise false. */
+static inline bool vtd_iova_range_check(uint64_t iova, VTDContextEntry *ce)
+{
+    /*
+     * Check if @iova is above 2^X-1, where X is the minimum of MGAW
+     * in CAP_REG and AW in context-entry.
+     */
+    return !(iova & ~(vtd_iova_limit(ce) - 1));
+}
+
 static const uint64_t vtd_paging_entry_rsvd_field[] = {
     [0] = ~0ULL,
     /* For not large page */
@@ -630,13 +646,9 @@ static int vtd_iova_to_slpte(VTDContextEntry *ce, uint64_t iova, bool is_write,
     uint32_t level = vtd_get_level_from_context_entry(ce);
     uint32_t offset;
     uint64_t slpte;
-    uint32_t ce_agaw = vtd_get_agaw_from_context_entry(ce);
     uint64_t access_right_check;
 
-    /* Check if @iova is above 2^X-1, where X is the minimum of MGAW
-     * in CAP_REG and AW in context-entry.
-     */
-    if (iova & ~((1ULL << MIN(ce_agaw, VTD_MGAW)) - 1)) {
+    if (!vtd_iova_range_check(iova, ce)) {
         VTD_DPRINTF(GENERAL, "error: iova 0x%"PRIx64 " exceeds limits", iova);
         return -VTD_FR_ADDR_BEYOND_MGAW;
     }
@@ -684,6 +696,135 @@ static int vtd_iova_to_slpte(VTDContextEntry *ce, uint64_t iova, bool is_write,
     }
 }
 
+typedef int (*vtd_page_walk_hook)(IOMMUTLBEntry *entry, void *private);
+
+/**
+ * vtd_page_walk_level - walk over specific level for IOVA range
+ *
+ * @addr: base GPA addr to start the walk
+ * @start: IOVA range start address
+ * @end: IOVA range end address (start <= addr < end)
+ * @hook_fn: hook func to be called when detected page
+ * @private: private data to be passed into hook func
+ * @read: whether parent level has read permission
+ * @write: whether parent level has write permission
+ * @notify_unmap: whether we should notify invalid entries
+ */
+static int vtd_page_walk_level(dma_addr_t addr, uint64_t start,
+                               uint64_t end, vtd_page_walk_hook hook_fn,
+                               void *private, uint32_t level,
+                               bool read, bool write, bool notify_unmap)
+{
+    bool read_cur, write_cur, entry_valid;
+    uint32_t offset;
+    uint64_t slpte;
+    uint64_t subpage_size, subpage_mask;
+    IOMMUTLBEntry entry;
+    uint64_t iova = start;
+    uint64_t iova_next;
+    int ret = 0;
+
+    trace_vtd_page_walk_level(addr, level, start, end);
+
+    subpage_size = 1ULL << vtd_slpt_level_shift(level);
+    subpage_mask = vtd_slpt_level_page_mask(level);
+
+    while (iova < end) {
+        iova_next = (iova & subpage_mask) + subpage_size;
+
+        offset = vtd_iova_level_offset(iova, level);
+        slpte = vtd_get_slpte(addr, offset);
+
+        if (slpte == (uint64_t)-1) {
+            trace_vtd_page_walk_skip_read(iova, iova_next);
+            goto next;
+        }
+
+        if (vtd_slpte_nonzero_rsvd(slpte, level)) {
+            trace_vtd_page_walk_skip_reserve(iova, iova_next);
+            goto next;
+        }
+
+        /* Permissions are stacked with parents' */
+        read_cur = read && (slpte & VTD_SL_R);
+        write_cur = write && (slpte & VTD_SL_W);
+
+        /*
+         * As long as we have either read/write permission, this is a
+         * valid entry. The rule works for both page entries and page
+         * table entries.
+         */
+        entry_valid = read_cur | write_cur;
+
+        if (vtd_is_last_slpte(slpte, level)) {
+            entry.target_as = &address_space_memory;
+            entry.iova = iova & subpage_mask;
+            /* NOTE: this is only meaningful if entry_valid == true */
+            entry.translated_addr = vtd_get_slpte_addr(slpte);
+            entry.addr_mask = ~subpage_mask;
+            entry.perm = IOMMU_ACCESS_FLAG(read_cur, write_cur);
+            if (!entry_valid && !notify_unmap) {
+                trace_vtd_page_walk_skip_perm(iova, iova_next);
+                goto next;
+            }
+            trace_vtd_page_walk_one(level, entry.iova, entry.translated_addr,
+                                    entry.addr_mask, entry.perm);
+            if (hook_fn) {
+                ret = hook_fn(&entry, private);
+                if (ret < 0) {
+                    return ret;
+                }
+            }
+        } else {
+            if (!entry_valid) {
+                trace_vtd_page_walk_skip_perm(iova, iova_next);
+                goto next;
+            }
+            ret = vtd_page_walk_level(vtd_get_slpte_addr(slpte), iova,
+                                      MIN(iova_next, end), hook_fn, private,
+                                      level - 1, read_cur, write_cur,
+                                      notify_unmap);
+            if (ret < 0) {
+                return ret;
+            }
+        }
+
+next:
+        iova = iova_next;
+    }
+
+    return 0;
+}
+
+/**
+ * vtd_page_walk - walk specific IOVA range, and call the hook
+ *
+ * @ce: context entry to walk upon
+ * @start: IOVA address to start the walk
+ * @end: IOVA range end address (start <= addr < end)
+ * @hook_fn: the hook that to be called for each detected area
+ * @private: private data for the hook function
+ */
+static int vtd_page_walk(VTDContextEntry *ce, uint64_t start, uint64_t end,
+                         vtd_page_walk_hook hook_fn, void *private,
+                         bool notify_unmap)
+{
+    dma_addr_t addr = vtd_get_slpt_base_from_context(ce);
+    uint32_t level = vtd_get_level_from_context_entry(ce);
+
+    if (!vtd_iova_range_check(start, ce)) {
+        return -VTD_FR_ADDR_BEYOND_MGAW;
+    }
+
+    if (!vtd_iova_range_check(end, ce)) {
+        /* Fix end so that it reaches the maximum */
+        end = vtd_iova_limit(ce);
+    }
+
+    return vtd_page_walk_level(addr, start, end, hook_fn, private,
+                               level, true, true, notify_unmap);
+}
+
 /* Map a device to its corresponding domain (context-entry) */
 static int vtd_dev_to_context_entry(IntelIOMMUState *s, uint8_t bus_num,
                                     uint8_t devfn, VTDContextEntry *ce)
@@ -898,6 +1039,15 @@ static void vtd_interrupt_remap_table_setup(IntelIOMMUState *s)
                 s->intr_root, s->intr_size);
 }
 
+static void vtd_iommu_replay_all(IntelIOMMUState *s)
+{
+    IntelIOMMUNotifierNode *node;
+
+    QLIST_FOREACH(node, &s->notifiers_list, next) {
+        memory_region_iommu_replay_all(&node->vtd_as->iommu);
+    }
+}
+
 static void vtd_context_global_invalidate(IntelIOMMUState *s)
 {
     trace_vtd_inv_desc_cc_global();
@@ -905,6 +1055,14 @@ static void vtd_context_global_invalidate(IntelIOMMUState *s)
     if (s->context_cache_gen == VTD_CONTEXT_CACHE_GEN_MAX) {
         vtd_reset_context_cache(s);
     }
+    /*
+     * From VT-d spec 6.5.2.1, a global context entry invalidation
+     * should be followed by a IOTLB global invalidation, so we should
+     * be safe even without this. Hoewever, let's replay the region as
+     * well to be safer, and go back here when we need finer tunes for
+     * VT-d emulation codes.
+     */
+    vtd_iommu_replay_all(s);
 }
 
 
@@ -971,6 +1129,16 @@ static void vtd_context_device_invalidate(IntelIOMMUState *s,
                 trace_vtd_inv_desc_cc_device(bus_n, VTD_PCI_SLOT(devfn_it),
                                              VTD_PCI_FUNC(devfn_it));
                 vtd_as->context_cache_entry.context_cache_gen = 0;
+                /*
+                 * So a device is moving out of (or moving into) a
+                 * domain, a replay() suites here to notify all the
+                 * IOMMU_NOTIFIER_MAP registers about this change.
+                 * This won't bring bad even if we have no such
+                 * notifier registered - the IOMMU notification
+                 * framework will skip MAP notifications if that
+                 * happened.
+                 */
+                memory_region_iommu_replay_all(&vtd_as->iommu);
             }
         }
     }
@@ -1012,12 +1180,53 @@ static void vtd_iotlb_global_invalidate(IntelIOMMUState *s)
 {
     trace_vtd_iotlb_reset("global invalidation recved");
     vtd_reset_iotlb(s);
+    vtd_iommu_replay_all(s);
 }
 
 static void vtd_iotlb_domain_invalidate(IntelIOMMUState *s, uint16_t domain_id)
 {
+    IntelIOMMUNotifierNode *node;
+    VTDContextEntry ce;
+    VTDAddressSpace *vtd_as;
+
     g_hash_table_foreach_remove(s->iotlb, vtd_hash_remove_by_domain,
                                 &domain_id);
+
+    QLIST_FOREACH(node, &s->notifiers_list, next) {
+        vtd_as = node->vtd_as;
+        if (!vtd_dev_to_context_entry(s, pci_bus_num(vtd_as->bus),
+                                      vtd_as->devfn, &ce) &&
+            domain_id == VTD_CONTEXT_ENTRY_DID(ce.hi)) {
+            memory_region_iommu_replay_all(&vtd_as->iommu);
+        }
+    }
+}
+
+static int vtd_page_invalidate_notify_hook(IOMMUTLBEntry *entry,
+                                           void *private)
+{
+    memory_region_notify_iommu((MemoryRegion *)private, *entry);
+    return 0;
+}
+
+static void vtd_iotlb_page_invalidate_notify(IntelIOMMUState *s,
+                                           uint16_t domain_id, hwaddr addr,
+                                           uint8_t am)
+{
+    IntelIOMMUNotifierNode *node;
+    VTDContextEntry ce;
+    int ret;
+
+    QLIST_FOREACH(node, &(s->notifiers_list), next) {
+        VTDAddressSpace *vtd_as = node->vtd_as;
+        ret = vtd_dev_to_context_entry(s, pci_bus_num(vtd_as->bus),
+                                       vtd_as->devfn, &ce);
+        if (!ret && domain_id == VTD_CONTEXT_ENTRY_DID(ce.hi)) {
+            vtd_page_walk(&ce, addr, addr + (1 << am) * VTD_PAGE_SIZE,
+                          vtd_page_invalidate_notify_hook,
+                          (void *)&vtd_as->iommu, true);
+        }
+    }
 }
 
 static void vtd_iotlb_page_invalidate(IntelIOMMUState *s, uint16_t domain_id,
@@ -1030,6 +1239,7 @@ static void vtd_iotlb_page_invalidate(IntelIOMMUState *s, uint16_t domain_id,
     info.addr = addr;
     info.mask = ~((1 << am) - 1);
     g_hash_table_foreach_remove(s->iotlb, vtd_hash_remove_by_page, &info);
+    vtd_iotlb_page_invalidate_notify(s, domain_id, addr, am);
 }
 
 /* Flush IOTLB
@@ -1151,9 +1361,49 @@ static void vtd_handle_gcmd_sirtp(IntelIOMMUState *s)
     vtd_set_clear_mask_long(s, DMAR_GSTS_REG, 0, VTD_GSTS_IRTPS);
 }
 
+static void vtd_switch_address_space(VTDAddressSpace *as)
+{
+    assert(as);
+
+    trace_vtd_switch_address_space(pci_bus_num(as->bus),
+                                   VTD_PCI_SLOT(as->devfn),
+                                   VTD_PCI_FUNC(as->devfn),
+                                   as->iommu_state->dmar_enabled);
+
+    /* Turn off first then on the other */
+    if (as->iommu_state->dmar_enabled) {
+        memory_region_set_enabled(&as->sys_alias, false);
+        memory_region_set_enabled(&as->iommu, true);
+    } else {
+        memory_region_set_enabled(&as->iommu, false);
+        memory_region_set_enabled(&as->sys_alias, true);
+    }
+}
+
+static void vtd_switch_address_space_all(IntelIOMMUState *s)
+{
+    GHashTableIter iter;
+    VTDBus *vtd_bus;
+    int i;
+
+    g_hash_table_iter_init(&iter, s->vtd_as_by_busptr);
+    while (g_hash_table_iter_next(&iter, NULL, (void **)&vtd_bus)) {
+        for (i = 0; i < X86_IOMMU_PCI_DEVFN_MAX; i++) {
+            if (!vtd_bus->dev_as[i]) {
+                continue;
+            }
+            vtd_switch_address_space(vtd_bus->dev_as[i]);
+        }
+    }
+}
+
 /* Handle Translation Enable/Disable */
 static void vtd_handle_gcmd_te(IntelIOMMUState *s, bool en)
 {
+    if (s->dmar_enabled == en) {
+        return;
+    }
+
     VTD_DPRINTF(CSR, "Translation Enable %s", (en ? "on" : "off"));
 
     if (en) {
@@ -1168,6 +1418,8 @@ static void vtd_handle_gcmd_te(IntelIOMMUState *s, bool en)
         /* Ok - report back to driver */
         vtd_set_clear_mask_long(s, DMAR_GSTS_REG, VTD_GSTS_TES, 0);
     }
+
+    vtd_switch_address_space_all(s);
 }
 
 /* Handle Interrupt Remap Enable/Disable */
@@ -1457,7 +1709,7 @@ static bool vtd_process_device_iotlb_desc(IntelIOMMUState *s,
     entry.iova = addr;
     entry.perm = IOMMU_NONE;
     entry.translated_addr = 0;
-    memory_region_notify_iommu(entry.target_as->root, entry);
+    memory_region_notify_iommu(&vtd_dev_as->iommu, entry);
 
 done:
     return true;
@@ -2005,15 +2257,33 @@ static void vtd_iommu_notify_flag_changed(MemoryRegion *iommu,
                                           IOMMUNotifierFlag new)
 {
     VTDAddressSpace *vtd_as = container_of(iommu, VTDAddressSpace, iommu);
+    IntelIOMMUState *s = vtd_as->iommu_state;
+    IntelIOMMUNotifierNode *node = NULL;
+    IntelIOMMUNotifierNode *next_node = NULL;
 
-    if (new & IOMMU_NOTIFIER_MAP) {
-        error_report("Device at bus %s addr %02x.%d requires iommu "
-                     "notifier which is currently not supported by "
-                     "intel-iommu emulation",
-                     vtd_as->bus->qbus.name, PCI_SLOT(vtd_as->devfn),
-                     PCI_FUNC(vtd_as->devfn));
+    if (!s->caching_mode && new & IOMMU_NOTIFIER_MAP) {
+        error_report("We need to set cache_mode=1 for intel-iommu to enable "
+                     "device assignment with IOMMU protection.");
         exit(1);
     }
+
+    if (old == IOMMU_NOTIFIER_NONE) {
+        node = g_malloc0(sizeof(*node));
+        node->vtd_as = vtd_as;
+        QLIST_INSERT_HEAD(&s->notifiers_list, node, next);
+        return;
+    }
+
+    /* update notifier node with new flags */
+    QLIST_FOREACH_SAFE(node, &s->notifiers_list, next, next_node) {
+        if (node->vtd_as == vtd_as) {
+            if (new == IOMMU_NOTIFIER_NONE) {
+                QLIST_REMOVE(node, next);
+                g_free(node);
+            }
+            return;
+        }
+    }
 }
 
 static const VMStateDescription vtd_vmstate = {
@@ -2389,19 +2659,150 @@ VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus, int devfn)
         vtd_dev_as->devfn = (uint8_t)devfn;
         vtd_dev_as->iommu_state = s;
         vtd_dev_as->context_cache_entry.context_cache_gen = 0;
+
+        /*
+         * Memory region relationships looks like (Address range shows
+         * only lower 32 bits to make it short in length...):
+         *
+         * |-----------------+-------------------+----------|
+         * | Name            | Address range     | Priority |
+         * |-----------------+-------------------+----------+
+         * | vtd_root        | 00000000-ffffffff |        0 |
+         * |  intel_iommu    | 00000000-ffffffff |        1 |
+         * |  vtd_sys_alias  | 00000000-ffffffff |        1 |
+         * |  intel_iommu_ir | fee00000-feefffff |       64 |
+         * |-----------------+-------------------+----------|
+         *
+         * We enable/disable DMAR by switching enablement for
+         * vtd_sys_alias and intel_iommu regions. IR region is always
+         * enabled.
+         */
         memory_region_init_iommu(&vtd_dev_as->iommu, OBJECT(s),
-                                 &s->iommu_ops, "intel_iommu", UINT64_MAX);
+                                 &s->iommu_ops, "intel_iommu_dmar",
+                                 UINT64_MAX);
+        memory_region_init_alias(&vtd_dev_as->sys_alias, OBJECT(s),
+                                 "vtd_sys_alias", get_system_memory(),
+                                 0, memory_region_size(get_system_memory()));
         memory_region_init_io(&vtd_dev_as->iommu_ir, OBJECT(s),
                               &vtd_mem_ir_ops, s, "intel_iommu_ir",
                               VTD_INTERRUPT_ADDR_SIZE);
-        memory_region_add_subregion(&vtd_dev_as->iommu, VTD_INTERRUPT_ADDR_FIRST,
-                                    &vtd_dev_as->iommu_ir);
-        address_space_init(&vtd_dev_as->as,
-                           &vtd_dev_as->iommu, name);
+        memory_region_init(&vtd_dev_as->root, OBJECT(s),
+                           "vtd_root", UINT64_MAX);
+        memory_region_add_subregion_overlap(&vtd_dev_as->root,
+                                            VTD_INTERRUPT_ADDR_FIRST,
+                                            &vtd_dev_as->iommu_ir, 64);
+        address_space_init(&vtd_dev_as->as, &vtd_dev_as->root, name);
+        memory_region_add_subregion_overlap(&vtd_dev_as->root, 0,
+                                            &vtd_dev_as->sys_alias, 1);
+        memory_region_add_subregion_overlap(&vtd_dev_as->root, 0,
+                                            &vtd_dev_as->iommu, 1);
+        vtd_switch_address_space(vtd_dev_as);
     }
     return vtd_dev_as;
 }
 
+/* Unmap the whole range in the notifier's scope. */
+static void vtd_address_space_unmap(VTDAddressSpace *as, IOMMUNotifier *n)
+{
+    IOMMUTLBEntry entry;
+    hwaddr size;
+    hwaddr start = n->start;
+    hwaddr end = n->end;
+
+    /*
+     * Note: all the codes in this function has a assumption that IOVA
+     * bits are no more than VTD_MGAW bits (which is restricted by
+     * VT-d spec), otherwise we need to consider overflow of 64 bits.
+     */
+
+    if (end > VTD_ADDRESS_SIZE) {
+        /*
+         * Don't need to unmap regions that is bigger than the whole
+         * VT-d supported address space size
+         */
+        end = VTD_ADDRESS_SIZE;
+    }
+
+    assert(start <= end);
+    size = end - start;
+
+    if (ctpop64(size) != 1) {
+        /*
+         * This size cannot format a correct mask. Let's enlarge it to
+         * suite the minimum available mask.
+         */
+        int n = 64 - clz64(size);
+        if (n > VTD_MGAW) {
+            /* should not happen, but in case it happens, limit it */
+            n = VTD_MGAW;
+        }
+        size = 1ULL << n;
+    }
+
+    entry.target_as = &address_space_memory;
+    /* Adjust iova for the size */
+    entry.iova = n->start & ~(size - 1);
+    /* This field is meaningless for unmap */
+    entry.translated_addr = 0;
+    entry.perm = IOMMU_NONE;
+    entry.addr_mask = size - 1;
+
+    trace_vtd_as_unmap_whole(pci_bus_num(as->bus),
+                             VTD_PCI_SLOT(as->devfn),
+                             VTD_PCI_FUNC(as->devfn),
+                             entry.iova, size);
+
+    memory_region_notify_one(n, &entry);
+}
+
+static void vtd_address_space_unmap_all(IntelIOMMUState *s)
+{
+    IntelIOMMUNotifierNode *node;
+    VTDAddressSpace *vtd_as;
+    IOMMUNotifier *n;
+
+    QLIST_FOREACH(node, &s->notifiers_list, next) {
+        vtd_as = node->vtd_as;
+        IOMMU_NOTIFIER_FOREACH(n, &vtd_as->iommu) {
+            vtd_address_space_unmap(vtd_as, n);
+        }
+    }
+}
+
+static int vtd_replay_hook(IOMMUTLBEntry *entry, void *private)
+{
+    memory_region_notify_one((IOMMUNotifier *)private, entry);
+    return 0;
+}
+
+static void vtd_iommu_replay(MemoryRegion *mr, IOMMUNotifier *n)
+{
+    VTDAddressSpace *vtd_as = container_of(mr, VTDAddressSpace, iommu);
+    IntelIOMMUState *s = vtd_as->iommu_state;
+    uint8_t bus_n = pci_bus_num(vtd_as->bus);
+    VTDContextEntry ce;
+
+    /*
+     * The replay can be triggered by either a invalidation or a newly
+     * created entry. No matter what, we release existing mappings
+     * (it means flushing caches for UNMAP-only registers).
+     */
+    vtd_address_space_unmap(vtd_as, n);
+
+    if (vtd_dev_to_context_entry(s, bus_n, vtd_as->devfn, &ce) == 0) {
+        trace_vtd_replay_ce_valid(bus_n, PCI_SLOT(vtd_as->devfn),
+                                  PCI_FUNC(vtd_as->devfn),
+                                  VTD_CONTEXT_ENTRY_DID(ce.hi),
+                                  ce.hi, ce.lo);
+        vtd_page_walk(&ce, 0, ~0ULL, vtd_replay_hook, (void *)n, false);
+    } else {
+        trace_vtd_replay_ce_invalid(bus_n, PCI_SLOT(vtd_as->devfn),
+                                    PCI_FUNC(vtd_as->devfn));
+    }
+
+    return;
+}
+
 /* Do the initialization. It will also be called when reset, so pay
  * attention when adding new initialization stuff.
  */
@@ -2416,6 +2817,7 @@ static void vtd_init(IntelIOMMUState *s)
 
     s->iommu_ops.translate = vtd_iommu_translate;
     s->iommu_ops.notify_flag_changed = vtd_iommu_notify_flag_changed;
+    s->iommu_ops.replay = vtd_iommu_replay;
     s->root = 0;
     s->root_extended = false;
     s->dmar_enabled = false;
@@ -2511,6 +2913,11 @@ static void vtd_reset(DeviceState *dev)
 
     VTD_DPRINTF(GENERAL, "");
     vtd_init(s);
+
+    /*
+     * When device reset, throw away all mappings and external caches
+     */
+    vtd_address_space_unmap_all(s);
 }
 
 static AddressSpace *vtd_host_dma_iommu(PCIBus *bus, void *opaque, int devfn)
@@ -2574,6 +2981,7 @@ static void vtd_realize(DeviceState *dev, Error **errp)
         return;
     }
 
+    QLIST_INIT(&s->notifiers_list);
     memset(s->vtd_as_by_bus_num, 0, sizeof(s->vtd_as_by_bus_num));
     memory_region_init_io(&s->csrmem, OBJECT(s), &vtd_mem_ops, s,
                           "intel_iommu", DMAR_REG_SIZE);
diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h
index 41041219ba..29d67075f4 100644
--- a/hw/i386/intel_iommu_internal.h
+++ b/hw/i386/intel_iommu_internal.h
@@ -197,6 +197,7 @@
 #define VTD_DOMAIN_ID_MASK          ((1UL << VTD_DOMAIN_ID_SHIFT) - 1)
 #define VTD_CAP_ND                  (((VTD_DOMAIN_ID_SHIFT - 4) / 2) & 7ULL)
 #define VTD_MGAW                    39  /* Maximum Guest Address Width */
+#define VTD_ADDRESS_SIZE            (1ULL << VTD_MGAW)
 #define VTD_CAP_MGAW                (((VTD_MGAW - 1) & 0x3fULL) << 16)
 #define VTD_MAMV                    18ULL
 #define VTD_CAP_MAMV                (VTD_MAMV << 48)
diff --git a/hw/i386/trace-events b/hw/i386/trace-events
index baed874a80..04a6980800 100644
--- a/hw/i386/trace-events
+++ b/hw/i386/trace-events
@@ -4,7 +4,6 @@
 x86_iommu_iec_notify(bool global, uint32_t index, uint32_t mask) "Notify IEC invalidation: global=%d index=%" PRIu32 " mask=%" PRIu32
 
 # hw/i386/intel_iommu.c
-vtd_switch_address_space(uint8_t bus, uint8_t slot, uint8_t fn, bool on) "Device %02x:%02x.%x switching address space (iommu enabled=%d)"
 vtd_inv_desc(const char *type, uint64_t hi, uint64_t lo) "invalidate desc type %s high 0x%"PRIx64" low 0x%"PRIx64
 vtd_inv_desc_invalid(uint64_t hi, uint64_t lo) "invalid inv desc hi 0x%"PRIx64" lo 0x%"PRIx64
 vtd_inv_desc_cc_domain(uint16_t domain) "context invalidate domain 0x%"PRIx16
@@ -30,6 +29,15 @@ vtd_iotlb_cc_hit(uint8_t bus, uint8_t devfn, uint64_t high, uint64_t low, uint32
 vtd_iotlb_cc_update(uint8_t bus, uint8_t devfn, uint64_t high, uint64_t low, uint32_t gen1, uint32_t gen2) "IOTLB context update bus 0x%"PRIx8" devfn 0x%"PRIx8" high 0x%"PRIx64" low 0x%"PRIx64" gen %"PRIu32" -> gen %"PRIu32
 vtd_iotlb_reset(const char *reason) "IOTLB reset (reason: %s)"
 vtd_fault_disabled(void) "Fault processing disabled for context entry"
+vtd_replay_ce_valid(uint8_t bus, uint8_t dev, uint8_t fn, uint16_t domain, uint64_t hi, uint64_t lo) "replay valid context device %02"PRIx8":%02"PRIx8".%02"PRIx8" domain 0x%"PRIx16" hi 0x%"PRIx64" lo 0x%"PRIx64
+vtd_replay_ce_invalid(uint8_t bus, uint8_t dev, uint8_t fn) "replay invalid context device %02"PRIx8":%02"PRIx8".%02"PRIx8
+vtd_page_walk_level(uint64_t addr, uint32_t level, uint64_t start, uint64_t end) "walk (base=0x%"PRIx64", level=%"PRIu32") iova range 0x%"PRIx64" - 0x%"PRIx64
+vtd_page_walk_one(uint32_t level, uint64_t iova, uint64_t gpa, uint64_t mask, int perm) "detected page level 0x%"PRIx32" iova 0x%"PRIx64" -> gpa 0x%"PRIx64" mask 0x%"PRIx64" perm %d"
+vtd_page_walk_skip_read(uint64_t iova, uint64_t next) "Page walk skip iova 0x%"PRIx64" - 0x%"PRIx64" due to unable to read"
+vtd_page_walk_skip_perm(uint64_t iova, uint64_t next) "Page walk skip iova 0x%"PRIx64" - 0x%"PRIx64" due to perm empty"
+vtd_page_walk_skip_reserve(uint64_t iova, uint64_t next) "Page walk skip iova 0x%"PRIx64" - 0x%"PRIx64" due to rsrv set"
+vtd_switch_address_space(uint8_t bus, uint8_t slot, uint8_t fn, bool on) "Device %02x:%02x.%x switching address space (iommu enabled=%d)"
+vtd_as_unmap_whole(uint8_t bus, uint8_t slot, uint8_t fn, uint64_t iova, uint64_t size) "Device %02x:%02x.%x start 0x%"PRIx64" size 0x%"PRIx64
 
 # hw/i386/amd_iommu.c
 amdvi_evntlog_fail(uint64_t addr, uint32_t head) "error: fail to write at addr 0x%"PRIx64" +  offset 0x%"PRIx32
diff --git a/hw/misc/exynos4210_pmu.c b/hw/misc/exynos4210_pmu.c
index e30dbc7d3d..63a8ccd355 100644
--- a/hw/misc/exynos4210_pmu.c
+++ b/hw/misc/exynos4210_pmu.c
@@ -401,8 +401,8 @@ static uint64_t exynos4210_pmu_read(void *opaque, hwaddr offset,
                                     unsigned size)
 {
     Exynos4210PmuState *s = (Exynos4210PmuState *)opaque;
-    unsigned i;
     const Exynos4210PmuReg *reg_p = exynos4210_pmu_regs;
+    unsigned int i;
 
     for (i = 0; i < PMU_NUM_OF_REGISTERS; i++) {
         if (reg_p->offset == offset) {
@@ -420,8 +420,8 @@ static void exynos4210_pmu_write(void *opaque, hwaddr offset,
                                  uint64_t val, unsigned size)
 {
     Exynos4210PmuState *s = (Exynos4210PmuState *)opaque;
-    unsigned i;
     const Exynos4210PmuReg *reg_p = exynos4210_pmu_regs;
+    unsigned int i;
 
     for (i = 0; i < PMU_NUM_OF_REGISTERS; i++) {
         if (reg_p->offset == offset) {
diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c
index d4de8ad9f1..3943187572 100644
--- a/hw/net/cadence_gem.c
+++ b/hw/net/cadence_gem.c
@@ -300,6 +300,8 @@
 #define DESC_1_RX_SOF 0x00004000
 #define DESC_1_RX_EOF 0x00008000
 
+#define GEM_MODID_VALUE 0x00020118
+
 static inline unsigned tx_desc_get_buffer(unsigned *desc)
 {
     return desc[0];
@@ -481,14 +483,17 @@ static int gem_can_receive(NetClientState *nc)
     }
 
     for (i = 0; i < s->num_priority_queues; i++) {
-        if (rx_desc_get_ownership(s->rx_desc[i]) == 1) {
-            if (s->can_rx_state != 2) {
-                s->can_rx_state = 2;
-                DB_PRINT("can't receive - busy buffer descriptor (q%d) 0x%x\n",
-                         i, s->rx_desc_addr[i]);
-             }
-            return 0;
+        if (rx_desc_get_ownership(s->rx_desc[i]) != 1) {
+            break;
+        }
+    };
+
+    if (i == s->num_priority_queues) {
+        if (s->can_rx_state != 2) {
+            s->can_rx_state = 2;
+            DB_PRINT("can't receive - all the buffer descriptors are busy\n");
         }
+        return 0;
     }
 
     if (s->can_rx_state != 0) {
@@ -506,7 +511,18 @@ static void gem_update_int_status(CadenceGEMState *s)
 {
     int i;
 
-    if ((s->num_priority_queues == 1) && s->regs[GEM_ISR]) {
+    if (!s->regs[GEM_ISR]) {
+        /* ISR isn't set, clear all the interrupts */
+        for (i = 0; i < s->num_priority_queues; ++i) {
+            qemu_set_irq(s->irq[i], 0);
+        }
+        return;
+    }
+
+    /* If we get here we know s->regs[GEM_ISR] is set, so we don't need to
+     * check it again.
+     */
+    if (s->num_priority_queues == 1) {
         /* No priority queues, just trigger the interrupt */
         DB_PRINT("asserting int.\n");
         qemu_set_irq(s->irq[0], 1);
@@ -790,8 +806,8 @@ static void gem_get_rx_desc(CadenceGEMState *s, int q)
 {
     DB_PRINT("read descriptor 0x%x\n", (unsigned)s->rx_desc_addr[q]);
     /* read current descriptor */
-    cpu_physical_memory_read(s->rx_desc_addr[0],
-                             (uint8_t *)s->rx_desc[0], sizeof(s->rx_desc[0]));
+    cpu_physical_memory_read(s->rx_desc_addr[q],
+                             (uint8_t *)s->rx_desc[q], sizeof(s->rx_desc[q]));
 
     /* Descriptor owned by software ? */
     if (rx_desc_get_ownership(s->rx_desc[q]) == 1) {
@@ -1209,7 +1225,7 @@ static void gem_reset(DeviceState *d)
     s->regs[GEM_TXPAUSE] = 0x0000ffff;
     s->regs[GEM_TXPARTIALSF] = 0x000003ff;
     s->regs[GEM_RXPARTIALSF] = 0x000003ff;
-    s->regs[GEM_MODID] = 0x00020118;
+    s->regs[GEM_MODID] = s->revision;
     s->regs[GEM_DESCONF] = 0x02500111;
     s->regs[GEM_DESCONF2] = 0x2ab13fff;
     s->regs[GEM_DESCONF5] = 0x002f2145;
@@ -1271,7 +1287,6 @@ static uint64_t gem_read(void *opaque, hwaddr offset, unsigned size)
 {
     CadenceGEMState *s;
     uint32_t retval;
-    int i;
     s = (CadenceGEMState *)opaque;
 
     offset >>= 2;
@@ -1282,9 +1297,7 @@ static uint64_t gem_read(void *opaque, hwaddr offset, unsigned size)
     switch (offset) {
     case GEM_ISR:
         DB_PRINT("lowering irqs on ISR read\n");
-        for (i = 0; i < s->num_priority_queues; ++i) {
-            qemu_set_irq(s->irq[i], 0);
-        }
+        /* The interrupts get updated at the end of the function. */
         break;
     case GEM_PHYMNTNC:
         if (retval & GEM_PHYMNTNC_OP_R) {
@@ -1508,6 +1521,8 @@ static const VMStateDescription vmstate_cadence_gem = {
 
 static Property gem_properties[] = {
     DEFINE_NIC_PROPERTIES(CadenceGEMState, conf),
+    DEFINE_PROP_UINT32("revision", CadenceGEMState, revision,
+                       GEM_MODID_VALUE),
     DEFINE_PROP_UINT8("num-priority-queues", CadenceGEMState,
                       num_priority_queues, 1),
     DEFINE_PROP_UINT8("num-type1-screeners", CadenceGEMState,
diff --git a/hw/timer/exynos4210_mct.c b/hw/timer/exynos4210_mct.c
index 0c189348ae..a2ec3920f8 100644
--- a/hw/timer/exynos4210_mct.c
+++ b/hw/timer/exynos4210_mct.c
@@ -53,6 +53,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/log.h"
 #include "hw/sysbus.h"
 #include "qemu/timer.h"
 #include "qemu/main-loop.h"
@@ -1372,8 +1373,9 @@ break;
     case L0_TCNTO: case L1_TCNTO:
     case L0_ICNTO: case L1_ICNTO:
     case L0_FRCNTO: case L1_FRCNTO:
-        fprintf(stderr, "\n[exynos4210.mct: write to RO register "
-                TARGET_FMT_plx "]\n\n", offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "exynos4210.mct: write to RO register " TARGET_FMT_plx,
+                      offset);
         break;
 
     case L0_INT_CSTAT: case L1_INT_CSTAT:
diff --git a/hw/timer/exynos4210_pwm.c b/hw/timer/exynos4210_pwm.c
index f5765075c7..87f63f057e 100644
--- a/hw/timer/exynos4210_pwm.c
+++ b/hw/timer/exynos4210_pwm.c
@@ -21,6 +21,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/log.h"
 #include "hw/sysbus.h"
 #include "qemu/timer.h"
 #include "qemu-common.h"
@@ -252,9 +253,9 @@ static uint64_t exynos4210_pwm_read(void *opaque, hwaddr offset,
         break;
 
     default:
-        fprintf(stderr,
-                "[exynos4210.pwm: bad read offset " TARGET_FMT_plx "]\n",
-                offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "exynos4210.pwm: bad read offset " TARGET_FMT_plx,
+                      offset);
         break;
     }
     return value;
@@ -343,9 +344,9 @@ static void exynos4210_pwm_write(void *opaque, hwaddr offset,
         break;
 
     default:
-        fprintf(stderr,
-                "[exynos4210.pwm: bad write offset " TARGET_FMT_plx "]\n",
-                offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "exynos4210.pwm: bad write offset " TARGET_FMT_plx,
+                      offset);
         break;
 
     }
diff --git a/hw/timer/exynos4210_rtc.c b/hw/timer/exynos4210_rtc.c
index 1a648c5d9e..4607833e3e 100644
--- a/hw/timer/exynos4210_rtc.c
+++ b/hw/timer/exynos4210_rtc.c
@@ -26,6 +26,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/log.h"
 #include "hw/sysbus.h"
 #include "qemu/timer.h"
 #include "qemu-common.h"
@@ -370,9 +371,9 @@ static uint64_t exynos4210_rtc_read(void *opaque, hwaddr offset,
         break;
 
     default:
-        fprintf(stderr,
-                "[exynos4210.rtc: bad read offset " TARGET_FMT_plx "]\n",
-                offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "exynos4210.rtc: bad read offset " TARGET_FMT_plx,
+                      offset);
         break;
     }
     return value;
@@ -433,9 +434,9 @@ static void exynos4210_rtc_write(void *opaque, hwaddr offset,
         if (value > TICNT_THRESHOLD) {
             s->reg_ticcnt = value;
         } else {
-            fprintf(stderr,
-                    "[exynos4210.rtc: bad TICNT value %u ]\n",
-                    (uint32_t)value);
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "exynos4210.rtc: bad TICNT value %u",
+                          (uint32_t)value);
         }
         break;
 
@@ -500,9 +501,9 @@ static void exynos4210_rtc_write(void *opaque, hwaddr offset,
         break;
 
     default:
-        fprintf(stderr,
-                "[exynos4210.rtc: bad write offset " TARGET_FMT_plx "]\n",
-                offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "exynos4210.rtc: bad write offset " TARGET_FMT_plx,
+                      offset);
         break;
 
     }
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index f3ba9b9007..6b33b9f55d 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -478,8 +478,13 @@ static void vfio_listener_region_add(MemoryListener *listener,
         giommu->iommu_offset = section->offset_within_address_space -
                                section->offset_within_region;
         giommu->container = container;
-        giommu->n.notify = vfio_iommu_map_notify;
-        giommu->n.notifier_flags = IOMMU_NOTIFIER_ALL;
+        llend = int128_add(int128_make64(section->offset_within_region),
+                           section->size);
+        llend = int128_sub(llend, int128_one());
+        iommu_notifier_init(&giommu->n, vfio_iommu_map_notify,
+                            IOMMU_NOTIFIER_ALL,
+                            section->offset_within_region,
+                            int128_get64(llend));
         QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next);
 
         memory_region_register_iommu_notifier(giommu->iommu, &giommu->n);
@@ -550,7 +555,8 @@ static void vfio_listener_region_del(MemoryListener *listener,
         VFIOGuestIOMMU *giommu;
 
         QLIST_FOREACH(giommu, &container->giommu_list, giommu_next) {
-            if (giommu->iommu == section->mr) {
+            if (giommu->iommu == section->mr &&
+                giommu->n.start == section->offset_within_region) {
                 memory_region_unregister_iommu_notifier(giommu->iommu,
                                                         &giommu->n);
                 QLIST_REMOVE(giommu, giommu_next);
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index 613494dcc2..0001e60b77 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -736,14 +736,20 @@ static void vhost_iommu_region_add(MemoryListener *listener,
     struct vhost_dev *dev = container_of(listener, struct vhost_dev,
                                          iommu_listener);
     struct vhost_iommu *iommu;
+    Int128 end;
 
     if (!memory_region_is_iommu(section->mr)) {
         return;
     }
 
     iommu = g_malloc0(sizeof(*iommu));
-    iommu->n.notify = vhost_iommu_unmap_notify;
-    iommu->n.notifier_flags = IOMMU_NOTIFIER_UNMAP;
+    end = int128_add(int128_make64(section->offset_within_region),
+                     section->size);
+    end = int128_sub(end, int128_one());
+    iommu_notifier_init(&iommu->n, vhost_iommu_unmap_notify,
+                        IOMMU_NOTIFIER_UNMAP,
+                        section->offset_within_region,
+                        int128_get64(end));
     iommu->mr = section->mr;
     iommu->iommu_offset = section->offset_within_address_space -
                           section->offset_within_region;
@@ -765,7 +771,8 @@ static void vhost_iommu_region_del(MemoryListener *listener,
     }
 
     QLIST_FOREACH(iommu, &dev->iommu_list, iommu_next) {
-        if (iommu->mr == section->mr) {
+        if (iommu->mr == section->mr &&
+            iommu->n.start == section->offset_within_region) {
             memory_region_unregister_iommu_notifier(iommu->mr,
                                                     &iommu->n);
             QLIST_REMOVE(iommu, iommu_next);