target-arm: Set CPU has_el3 prop during virt init

[qemu.git] / xen-hvm.c

diff --git a/xen-hvm.c b/xen-hvm.c
index aac38efb0951addd70d96a0ee65918af0cedd6a6..754879481e89a4e8d7b1603579045f6f7dfaffe2 100644 (file)
--- a/xen-hvm.c
+++ b/xen-hvm.c
@@ -41,6 +41,29 @@ static MemoryRegion *framebuffer;
 static bool xen_in_migration;
 
 /* Compatibility with older version */
 static bool xen_in_migration;
 
 /* Compatibility with older version */

+
+/* This allows QEMU to build on a system that has Xen 4.5 or earlier
+ * installed.  This here (not in hw/xen/xen_common.h) because xen/hvm/ioreq.h
+ * needs to be included before this block and hw/xen/xen_common.h needs to
+ * be included before xen/hvm/ioreq.h
+ */
+#ifndef IOREQ_TYPE_VMWARE_PORT
+#define IOREQ_TYPE_VMWARE_PORT  3
+struct vmware_regs {
+    uint32_t esi;
+    uint32_t edi;
+    uint32_t ebx;
+    uint32_t ecx;
+    uint32_t edx;
+};
+typedef struct vmware_regs vmware_regs_t;
+
+struct shared_vmport_iopage {
+    struct vmware_regs vcpu_vmport_regs[1];
+};
+typedef struct shared_vmport_iopage shared_vmport_iopage_t;
+#endif
+

 #if __XEN_LATEST_INTERFACE_VERSION__ < 0x0003020a
 static inline uint32_t xen_vcpu_eport(shared_iopage_t *shared_page, int i)
 {
 #if __XEN_LATEST_INTERFACE_VERSION__ < 0x0003020a
 static inline uint32_t xen_vcpu_eport(shared_iopage_t *shared_page, int i)
 {


@@ -71,7 +94,7 @@ static inline ioreq_t *xen_vcpu_ioreq(shared_iopage_t *shared_page, int vcpu)
 typedef struct XenPhysmap {
     hwaddr start_addr;
     ram_addr_t size;
 typedef struct XenPhysmap {
     hwaddr start_addr;
     ram_addr_t size;

-    char *name;
+    const char *name;

     hwaddr phys_offset;
 
     QLIST_ENTRY(XenPhysmap) list;
     hwaddr phys_offset;
 
     QLIST_ENTRY(XenPhysmap) list;


@@ -79,8 +102,10 @@ typedef struct XenPhysmap {
 
 typedef struct XenIOState {
     shared_iopage_t *shared_page;
 
 typedef struct XenIOState {
     shared_iopage_t *shared_page;

+    shared_vmport_iopage_t *shared_vmport_page;

     buffered_iopage_t *buffered_io_page;
     QEMUTimer *buffered_io_timer;
     buffered_iopage_t *buffered_io_page;
     QEMUTimer *buffered_io_timer;

+    CPUState **cpu_by_vcpu_id;

     /* the evtchn port for polling the notification, */
     evtchn_port_t *ioreq_local_port;
     /* evtchn local port for buffered io */
     /* the evtchn port for polling the notification, */
     evtchn_port_t *ioreq_local_port;
     /* evtchn local port for buffered io */


@@ -155,29 +180,43 @@ qemu_irq *xen_interrupt_controller_init(void)
 
 /* Memory Ops */
 
 
 /* Memory Ops */
 

-static void xen_ram_init(ram_addr_t ram_size, MemoryRegion **ram_memory_p)
+static void xen_ram_init(ram_addr_t *below_4g_mem_size,
+                         ram_addr_t *above_4g_mem_size,
+                         ram_addr_t ram_size, MemoryRegion **ram_memory_p)

 {
     MemoryRegion *sysmem = get_system_memory();
 {
     MemoryRegion *sysmem = get_system_memory();

-    ram_addr_t below_4g_mem_size, above_4g_mem_size = 0;

     ram_addr_t block_len;
     ram_addr_t block_len;

+    uint64_t user_lowmem = object_property_get_int(qdev_get_machine(),
+                                                   PC_MACHINE_MAX_RAM_BELOW_4G,
+                                                   &error_abort);

 
 

-    block_len = ram_size;
-    if (ram_size >= HVM_BELOW_4G_RAM_END) {
-        /* Xen does not allocate the memory continuously, and keep a hole at
-         * HVM_BELOW_4G_MMIO_START of HVM_BELOW_4G_MMIO_LENGTH
-         */
-        block_len += HVM_BELOW_4G_MMIO_LENGTH;
+    /* Handle the machine opt max-ram-below-4g.  It is basically doing
+     * min(xen limit, user limit).
+     */
+    if (HVM_BELOW_4G_RAM_END <= user_lowmem) {
+        user_lowmem = HVM_BELOW_4G_RAM_END;

     }
     }

-    memory_region_init_ram(&ram_memory, NULL, "xen.ram", block_len);
-    *ram_memory_p = &ram_memory;
-    vmstate_register_ram_global(&ram_memory);

 
 

-    if (ram_size >= HVM_BELOW_4G_RAM_END) {
-        above_4g_mem_size = ram_size - HVM_BELOW_4G_RAM_END;
-        below_4g_mem_size = HVM_BELOW_4G_RAM_END;
+    if (ram_size >= user_lowmem) {
+        *above_4g_mem_size = ram_size - user_lowmem;
+        *below_4g_mem_size = user_lowmem;
+    } else {
+        *above_4g_mem_size = 0;
+        *below_4g_mem_size = ram_size;
+    }
+    if (!*above_4g_mem_size) {
+        block_len = ram_size;

     } else {
     } else {

-        below_4g_mem_size = ram_size;
+        /*
+         * Xen does not allocate the memory continuously, it keeps a
+         * hole of the size computed above or passed in.
+         */
+        block_len = (1ULL << 32) + *above_4g_mem_size;

     }
     }

+    memory_region_init_ram(&ram_memory, NULL, "xen.ram", block_len,
+                           &error_abort);
+    *ram_memory_p = &ram_memory;
+    vmstate_register_ram_global(&ram_memory);

 
     memory_region_init_alias(&ram_640k, NULL, "xen.ram.640k",
                              &ram_memory, 0, 0xa0000);
 
     memory_region_init_alias(&ram_640k, NULL, "xen.ram.640k",
                              &ram_memory, 0, 0xa0000);


@@ -189,12 +228,13 @@ static void xen_ram_init(ram_addr_t ram_size, MemoryRegion **ram_memory_p)
      * the Options ROM, so it is registered here as RAM.
      */
     memory_region_init_alias(&ram_lo, NULL, "xen.ram.lo",
      * the Options ROM, so it is registered here as RAM.
      */
     memory_region_init_alias(&ram_lo, NULL, "xen.ram.lo",

-                             &ram_memory, 0xc0000, below_4g_mem_size - 0xc0000);
+                             &ram_memory, 0xc0000,
+                             *below_4g_mem_size - 0xc0000);

     memory_region_add_subregion(sysmem, 0xc0000, &ram_lo);
     memory_region_add_subregion(sysmem, 0xc0000, &ram_lo);

-    if (above_4g_mem_size > 0) {
+    if (*above_4g_mem_size > 0) {

         memory_region_init_alias(&ram_hi, NULL, "xen.ram.hi",
                                  &ram_memory, 0x100000000ULL,
         memory_region_init_alias(&ram_hi, NULL, "xen.ram.hi",
                                  &ram_memory, 0x100000000ULL,

-                                 above_4g_mem_size);
+                                 *above_4g_mem_size);

         memory_region_add_subregion(sysmem, 0x100000000ULL, &ram_hi);
     }
 }
         memory_region_add_subregion(sysmem, 0x100000000ULL, &ram_hi);
     }
 }


@@ -277,6 +317,7 @@ static int xen_add_to_physmap(XenIOState *state,
     hwaddr pfn, start_gpfn;
     hwaddr phys_offset = memory_region_get_ram_addr(mr);
     char path[80], value[17];
     hwaddr pfn, start_gpfn;
     hwaddr phys_offset = memory_region_get_ram_addr(mr);
     char path[80], value[17];

+    const char *mr_name;

 
     if (get_physmapping(state, start_addr, size)) {
         return 0;
 
     if (get_physmapping(state, start_addr, size)) {
         return 0;


@@ -312,11 +353,13 @@ go_physmap:
         }
     }
 
         }
     }
 

+    mr_name = memory_region_name(mr);
+

     physmap = g_malloc(sizeof (XenPhysmap));
 
     physmap->start_addr = start_addr;
     physmap->size = size;
     physmap = g_malloc(sizeof (XenPhysmap));
 
     physmap->start_addr = start_addr;
     physmap->size = size;

-    physmap->name = (char *)mr->name;
+    physmap->name = mr_name;

     physmap->phys_offset = phys_offset;
 
     QLIST_INSERT_HEAD(&state->physmap, physmap, list);
     physmap->phys_offset = phys_offset;
 
     QLIST_INSERT_HEAD(&state->physmap, physmap, list);


@@ -340,11 +383,11 @@ go_physmap:
     if (!xs_write(state->xenstore, 0, path, value, strlen(value))) {
         return -1;
     }
     if (!xs_write(state->xenstore, 0, path, value, strlen(value))) {
         return -1;
     }

-    if (mr->name) {
+    if (mr_name) {

         snprintf(path, sizeof(path),
                 "/local/domain/0/device-model/%d/physmap/%"PRIx64"/name",
                 xen_domid, (uint64_t)phys_offset);
         snprintf(path, sizeof(path),
                 "/local/domain/0/device-model/%d/physmap/%"PRIx64"/name",
                 xen_domid, (uint64_t)phys_offset);

-        if (!xs_write(state->xenstore, 0, path, mr->name, strlen(mr->name))) {
+        if (!xs_write(state->xenstore, 0, path, mr_name, strlen(mr_name))) {

             return -1;
         }
     }
             return -1;
         }
     }


@@ -376,7 +419,7 @@ static int xen_remove_from_physmap(XenIOState *state,
     start_addr >>= TARGET_PAGE_BITS;
     phys_offset >>= TARGET_PAGE_BITS;
     for (i = 0; i < size; i++) {
     start_addr >>= TARGET_PAGE_BITS;
     phys_offset >>= TARGET_PAGE_BITS;
     for (i = 0; i < size; i++) {

-        unsigned long idx = start_addr + i;
+        xen_pfn_t idx = start_addr + i;

         xen_pfn_t gpfn = phys_offset + i;
 
         rc = xc_domain_add_to_physmap(xen_xc, xen_domid, XENMAPSPACE_gmfn, idx, gpfn);
         xen_pfn_t gpfn = phys_offset + i;
 
         rc = xc_domain_add_to_physmap(xen_xc, xen_domid, XENMAPSPACE_gmfn, idx, gpfn);


@@ -499,11 +542,14 @@ static void xen_sync_dirty_bitmap(XenIOState *state,
                                  start_addr >> TARGET_PAGE_BITS, npages,
                                  bitmap);
     if (rc < 0) {
                                  start_addr >> TARGET_PAGE_BITS, npages,
                                  bitmap);
     if (rc < 0) {

-        if (rc != -ENODATA) {
+#ifndef ENODATA
+#define ENODATA  ENOENT
+#endif
+        if (errno == ENODATA) {

             memory_region_set_dirty(framebuffer, 0, size);
             DPRINTF("xen: track_dirty_vram failed (0x" TARGET_FMT_plx
                     ", 0x" TARGET_FMT_plx "): %s\n",
             memory_region_set_dirty(framebuffer, 0, size);
             DPRINTF("xen: track_dirty_vram failed (0x" TARGET_FMT_plx
                     ", 0x" TARGET_FMT_plx "): %s\n",

-                    start_addr, start_addr + size, strerror(-rc));
+                    start_addr, start_addr + size, strerror(errno));

         }
         return;
     }
         }
         return;
     }


@@ -752,7 +798,50 @@ static void cpu_ioreq_move(ioreq_t *req)
     }
 }
 
     }
 }
 

-static void handle_ioreq(ioreq_t *req)
+static void regs_to_cpu(vmware_regs_t *vmport_regs, ioreq_t *req)
+{
+    X86CPU *cpu;
+    CPUX86State *env;
+
+    cpu = X86_CPU(current_cpu);
+    env = &cpu->env;
+    env->regs[R_EAX] = req->data;
+    env->regs[R_EBX] = vmport_regs->ebx;
+    env->regs[R_ECX] = vmport_regs->ecx;
+    env->regs[R_EDX] = vmport_regs->edx;
+    env->regs[R_ESI] = vmport_regs->esi;
+    env->regs[R_EDI] = vmport_regs->edi;
+}
+
+static void regs_from_cpu(vmware_regs_t *vmport_regs)
+{
+    X86CPU *cpu = X86_CPU(current_cpu);
+    CPUX86State *env = &cpu->env;
+
+    vmport_regs->ebx = env->regs[R_EBX];
+    vmport_regs->ecx = env->regs[R_ECX];
+    vmport_regs->edx = env->regs[R_EDX];
+    vmport_regs->esi = env->regs[R_ESI];
+    vmport_regs->edi = env->regs[R_EDI];
+}
+
+static void handle_vmport_ioreq(XenIOState *state, ioreq_t *req)
+{
+    vmware_regs_t *vmport_regs;
+
+    assert(state->shared_vmport_page);
+    vmport_regs =
+        &state->shared_vmport_page->vcpu_vmport_regs[state->send_vcpu];
+    QEMU_BUILD_BUG_ON(sizeof(*req) < sizeof(*vmport_regs));
+
+    current_cpu = state->cpu_by_vcpu_id[state->send_vcpu];
+    regs_to_cpu(vmport_regs, req);
+    cpu_ioreq_pio(req);
+    regs_from_cpu(vmport_regs);
+    current_cpu = NULL;
+}
+
+static void handle_ioreq(XenIOState *state, ioreq_t *req)

 {
     if (!req->data_is_ptr && (req->dir == IOREQ_WRITE) &&
             (req->size < sizeof (target_ulong))) {
 {
     if (!req->data_is_ptr && (req->dir == IOREQ_WRITE) &&
             (req->size < sizeof (target_ulong))) {


@@ -766,6 +855,9 @@ static void handle_ioreq(ioreq_t *req)
         case IOREQ_TYPE_COPY:
             cpu_ioreq_move(req);
             break;
         case IOREQ_TYPE_COPY:
             cpu_ioreq_move(req);
             break;

+        case IOREQ_TYPE_VMWARE_PORT:
+            handle_vmport_ioreq(state, req);
+            break;

         case IOREQ_TYPE_TIMEOFFSET:
             break;
         case IOREQ_TYPE_INVALIDATE:
         case IOREQ_TYPE_TIMEOFFSET:
             break;
         case IOREQ_TYPE_INVALIDATE:


@@ -807,7 +899,7 @@ static int handle_buffered_iopage(XenIOState *state)
             req.data |= ((uint64_t)buf_req->data) << 32;
         }
 
             req.data |= ((uint64_t)buf_req->data) << 32;
         }
 

-        handle_ioreq(&req);
+        handle_ioreq(state, &req);

 
         xen_mb();
         state->buffered_io_page->read_pointer += qw ? 2 : 1;
 
         xen_mb();
         state->buffered_io_page->read_pointer += qw ? 2 : 1;


@@ -836,14 +928,16 @@ static void cpu_handle_ioreq(void *opaque)
 
     handle_buffered_iopage(state);
     if (req) {
 
     handle_buffered_iopage(state);
     if (req) {

-        handle_ioreq(req);
+        handle_ioreq(state, req);

 
         if (req->state != STATE_IOREQ_INPROCESS) {
             fprintf(stderr, "Badness in I/O request ... not in service?!: "
                     "%x, ptr: %x, port: %"PRIx64", "
 
         if (req->state != STATE_IOREQ_INPROCESS) {
             fprintf(stderr, "Badness in I/O request ... not in service?!: "
                     "%x, ptr: %x, port: %"PRIx64", "

-                    "data: %"PRIx64", count: %" FMT_ioreq_size ", size: %" FMT_ioreq_size "\n",
+                    "data: %"PRIx64", count: %" FMT_ioreq_size
+                    ", size: %" FMT_ioreq_size
+                    ", type: %"FMT_ioreq_size"\n",

                     req->state, req->data_is_ptr, req->addr,
                     req->state, req->data_is_ptr, req->addr,

-                    req->data, req->count, req->size);
+                    req->data, req->count, req->size, req->type);

             destroy_hvm_domain(false);
             return;
         }
             destroy_hvm_domain(false);
             return;
         }


@@ -883,6 +977,14 @@ static void xen_main_loop_prepare(XenIOState *state)
                                                  state);
 
     if (evtchn_fd != -1) {
                                                  state);
 
     if (evtchn_fd != -1) {

+        CPUState *cpu_state;
+
+        DPRINTF("%s: Init cpu_by_vcpu_id\n", __func__);
+        CPU_FOREACH(cpu_state) {
+            DPRINTF("%s: cpu_by_vcpu_id[%d]=%p\n",
+                    __func__, cpu_state->cpu_index, cpu_state);
+            state->cpu_by_vcpu_id[cpu_state->cpu_index] = cpu_state;
+        }

         qemu_set_fd_handler(evtchn_fd, cpu_handle_ioreq, NULL, state);
     }
 }
         qemu_set_fd_handler(evtchn_fd, cpu_handle_ioreq, NULL, state);
     }
 }


@@ -891,9 +993,8 @@ static void xen_main_loop_prepare(XenIOState *state)
 static void xen_hvm_change_state_handler(void *opaque, int running,
                                          RunState rstate)
 {
 static void xen_hvm_change_state_handler(void *opaque, int running,
                                          RunState rstate)
 {

-    XenIOState *xstate = opaque;

     if (running) {
     if (running) {

-        xen_main_loop_prepare(xstate);
+        xen_main_loop_prepare((XenIOState *)opaque);

     }
 }
 
     }
 }
 


@@ -958,7 +1059,9 @@ static void xen_wakeup_notifier(Notifier *notifier, void *data)
     xc_set_hvm_param(xen_xc, xen_domid, HVM_PARAM_ACPI_S_STATE, 0);
 }
 
     xc_set_hvm_param(xen_xc, xen_domid, HVM_PARAM_ACPI_S_STATE, 0);
 }
 

-int xen_hvm_init(MemoryRegion **ram_memory)
+/* return 0 means OK, or -1 means critical issue -- will exit(1) */
+int xen_hvm_init(ram_addr_t *below_4g_mem_size, ram_addr_t *above_4g_mem_size,
+                 MemoryRegion **ram_memory)

 {
     int i, rc;
     unsigned long ioreq_pfn;
 {
     int i, rc;
     unsigned long ioreq_pfn;


@@ -970,15 +1073,13 @@ int xen_hvm_init(MemoryRegion **ram_memory)
     state->xce_handle = xen_xc_evtchn_open(NULL, 0);
     if (state->xce_handle == XC_HANDLER_INITIAL_VALUE) {
         perror("xen: event channel open");
     state->xce_handle = xen_xc_evtchn_open(NULL, 0);
     if (state->xce_handle == XC_HANDLER_INITIAL_VALUE) {
         perror("xen: event channel open");

-        g_free(state);
-        return -errno;
+        return -1;

     }
 
     state->xenstore = xs_daemon_open();
     if (state->xenstore == NULL) {
         perror("xen: xenstore open");
     }
 
     state->xenstore = xs_daemon_open();
     if (state->xenstore == NULL) {
         perror("xen: xenstore open");

-        g_free(state);
-        return -errno;
+        return -1;

     }
 
     state->exit.notify = xen_exit_notifier;
     }
 
     state->exit.notify = xen_exit_notifier;


@@ -999,6 +1100,20 @@ int xen_hvm_init(MemoryRegion **ram_memory)
                  errno, xen_xc);
     }
 
                  errno, xen_xc);
     }
 

+    rc = xen_get_vmport_regs_pfn(xen_xc, xen_domid, &ioreq_pfn);
+    if (!rc) {
+        DPRINTF("shared vmport page at pfn %lx\n", ioreq_pfn);
+        state->shared_vmport_page =
+            xc_map_foreign_range(xen_xc, xen_domid, XC_PAGE_SIZE,
+                                 PROT_READ|PROT_WRITE, ioreq_pfn);
+        if (state->shared_vmport_page == NULL) {
+            hw_error("map shared vmport IO page returned error %d handle="
+                     XC_INTERFACE_FMT, errno, xen_xc);
+        }
+    } else if (rc != -ENOSYS) {
+        hw_error("get vmport regs pfn returned error %d, rc=%d", errno, rc);
+    }
+

     xc_get_hvm_param(xen_xc, xen_domid, HVM_PARAM_BUFIOREQ_PFN, &ioreq_pfn);
     DPRINTF("buffered io page at pfn %lx\n", ioreq_pfn);
     state->buffered_io_page = xc_map_foreign_range(xen_xc, xen_domid, XC_PAGE_SIZE,
     xc_get_hvm_param(xen_xc, xen_domid, HVM_PARAM_BUFIOREQ_PFN, &ioreq_pfn);
     DPRINTF("buffered io page at pfn %lx\n", ioreq_pfn);
     state->buffered_io_page = xc_map_foreign_range(xen_xc, xen_domid, XC_PAGE_SIZE,


@@ -1007,6 +1122,9 @@ int xen_hvm_init(MemoryRegion **ram_memory)
         hw_error("map buffered IO page returned error %d", errno);
     }
 
         hw_error("map buffered IO page returned error %d", errno);
     }
 

+    /* Note: cpus is empty at this point in init */
+    state->cpu_by_vcpu_id = g_malloc0(max_cpus * sizeof(CPUState *));
+

     state->ioreq_local_port = g_malloc0(max_cpus * sizeof (evtchn_port_t));
 
     /* FIXME: how about if we overflow the page here? */
     state->ioreq_local_port = g_malloc0(max_cpus * sizeof (evtchn_port_t));
 
     /* FIXME: how about if we overflow the page here? */


@@ -1036,7 +1154,7 @@ int xen_hvm_init(MemoryRegion **ram_memory)
 
     /* Init RAM management */
     xen_map_cache_init(xen_phys_offset_to_gaddr, state);
 
     /* Init RAM management */
     xen_map_cache_init(xen_phys_offset_to_gaddr, state);

-    xen_ram_init(ram_size, ram_memory);
+    xen_ram_init(below_4g_mem_size, above_4g_mem_size, ram_size, ram_memory);

 
     qemu_add_vm_change_state_handler(xen_hvm_change_state_handler, state);
 
 
     qemu_add_vm_change_state_handler(xen_hvm_change_state_handler, state);
 


@@ -1048,7 +1166,7 @@ int xen_hvm_init(MemoryRegion **ram_memory)
     /* Initialize backend core & drivers */
     if (xen_be_init() != 0) {
         fprintf(stderr, "%s: xen backend core setup failed\n", __FUNCTION__);
     /* Initialize backend core & drivers */
     if (xen_be_init() != 0) {
         fprintf(stderr, "%s: xen backend core setup failed\n", __FUNCTION__);

-        exit(1);
+        return -1;

     }
     xen_be_register("console", &xen_console_ops);
     xen_be_register("vkbd", &xen_kbdmouse_ops);
     }
     xen_be_register("console", &xen_console_ops);
     xen_be_register("vkbd", &xen_kbdmouse_ops);