Xen: Use the ioreq-server API when available

The ioreq-server API added to Xen 4.5 offers better security than
the existing Xen/QEMU interface because the shared pages that are
used to pass emulation request/results back and forth are removed
from the guest's memory space before any requests are serviced.
This prevents the guest from mapping these pages (they are in a
well known location) and attempting to attack QEMU by synthesizing
its own request structures. Hence, this patch modifies configure
to detect whether the API is available, and adds the necessary
code to use the API if it is.

Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
diff --git a/xen-hvm.c b/xen-hvm.c
index e2e575b..315864c 100644
--- a/xen-hvm.c
+++ b/xen-hvm.c
@@ -85,9 +85,6 @@
 }
 #  define FMT_ioreq_size "u"
 #endif
-#ifndef HVM_PARAM_BUFIOREQ_EVTCHN
-#define HVM_PARAM_BUFIOREQ_EVTCHN 26
-#endif
 
 #define BUFFER_IO_MAX_DELAY  100
 /* Leave some slack so that hvmloader does not complain about lack of
@@ -107,6 +104,7 @@
 } XenPhysmap;
 
 typedef struct XenIOState {
+    ioservid_t ioservid;
     shared_iopage_t *shared_page;
     shared_vmport_iopage_t *shared_vmport_page;
     buffered_iopage_t *buffered_io_page;
@@ -123,6 +121,8 @@
 
     struct xs_handle *xenstore;
     MemoryListener memory_listener;
+    MemoryListener io_listener;
+    DeviceListener device_listener;
     QLIST_HEAD(, XenPhysmap) physmap;
     hwaddr free_phys_offset;
     const XenPhysmap *log_for_dirtybit;
@@ -491,12 +491,23 @@
     bool log_dirty = memory_region_is_logging(section->mr);
     hvmmem_type_t mem_type;
 
+    if (section->mr == &ram_memory) {
+        return;
+    } else {
+        if (add) {
+            xen_map_memory_section(xen_xc, xen_domid, state->ioservid,
+                                   section);
+        } else {
+            xen_unmap_memory_section(xen_xc, xen_domid, state->ioservid,
+                                     section);
+        }
+    }
+
     if (!memory_region_is_ram(section->mr)) {
         return;
     }
 
-    if (!(section->mr != &ram_memory
-          && ( (log_dirty && add) || (!log_dirty && !add)))) {
+    if (log_dirty != add) {
         return;
     }
 
@@ -539,6 +550,50 @@
     memory_region_unref(section->mr);
 }
 
+static void xen_io_add(MemoryListener *listener,
+                       MemoryRegionSection *section)
+{
+    XenIOState *state = container_of(listener, XenIOState, io_listener);
+
+    memory_region_ref(section->mr);
+
+    xen_map_io_section(xen_xc, xen_domid, state->ioservid, section);
+}
+
+static void xen_io_del(MemoryListener *listener,
+                       MemoryRegionSection *section)
+{
+    XenIOState *state = container_of(listener, XenIOState, io_listener);
+
+    xen_unmap_io_section(xen_xc, xen_domid, state->ioservid, section);
+
+    memory_region_unref(section->mr);
+}
+
+static void xen_device_realize(DeviceListener *listener,
+			       DeviceState *dev)
+{
+    XenIOState *state = container_of(listener, XenIOState, device_listener);
+
+    if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
+        PCIDevice *pci_dev = PCI_DEVICE(dev);
+
+        xen_map_pcidev(xen_xc, xen_domid, state->ioservid, pci_dev);
+    }
+}
+
+static void xen_device_unrealize(DeviceListener *listener,
+				 DeviceState *dev)
+{
+    XenIOState *state = container_of(listener, XenIOState, device_listener);
+
+    if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
+        PCIDevice *pci_dev = PCI_DEVICE(dev);
+
+        xen_unmap_pcidev(xen_xc, xen_domid, state->ioservid, pci_dev);
+    }
+}
+
 static void xen_sync_dirty_bitmap(XenIOState *state,
                                   hwaddr start_addr,
                                   ram_addr_t size)
@@ -639,6 +694,17 @@
     .priority = 10,
 };
 
+static MemoryListener xen_io_listener = {
+    .region_add = xen_io_add,
+    .region_del = xen_io_del,
+    .priority = 10,
+};
+
+static DeviceListener xen_device_listener = {
+    .realize = xen_device_realize,
+    .unrealize = xen_device_unrealize,
+};
+
 /* get the ioreq packets from share mem */
 static ioreq_t *cpu_get_ioreq_from_shared_memory(XenIOState *state, int vcpu)
 {
@@ -887,6 +953,27 @@
         case IOREQ_TYPE_INVALIDATE:
             xen_invalidate_map_cache();
             break;
+        case IOREQ_TYPE_PCI_CONFIG: {
+            uint32_t sbdf = req->addr >> 32;
+            uint32_t val;
+
+            /* Fake a write to port 0xCF8 so that
+             * the config space access will target the
+             * correct device model.
+             */
+            val = (1u << 31) |
+                  ((req->addr & 0x0f00) << 16) |
+                  ((sbdf & 0xffff) << 8) |
+                  (req->addr & 0xfc);
+            do_outp(0xcf8, 4, val);
+
+            /* Now issue the config space access via
+             * port 0xCFC
+             */
+            req->addr = 0xcfc | (req->addr & 0x03);
+            cpu_ioreq_pio(req);
+            break;
+        }
         default:
             hw_error("Invalid ioreq type 0x%x\n", req->type);
     }
@@ -1017,9 +1104,15 @@
 static void xen_hvm_change_state_handler(void *opaque, int running,
                                          RunState rstate)
 {
+    XenIOState *state = opaque;
+
     if (running) {
-        xen_main_loop_prepare((XenIOState *)opaque);
+        xen_main_loop_prepare(state);
     }
+
+    xen_set_ioreq_server_state(xen_xc, xen_domid,
+                               state->ioservid,
+                               (rstate == RUN_STATE_RUNNING));
 }
 
 static void xen_exit_notifier(Notifier *n, void *data)
@@ -1088,8 +1181,9 @@
                  MemoryRegion **ram_memory)
 {
     int i, rc;
-    unsigned long ioreq_pfn;
-    unsigned long bufioreq_evtchn;
+    xen_pfn_t ioreq_pfn;
+    xen_pfn_t bufioreq_pfn;
+    evtchn_port_t bufioreq_evtchn;
     XenIOState *state;
 
     state = g_malloc0(sizeof (XenIOState));
@@ -1106,6 +1200,12 @@
         return -1;
     }
 
+    rc = xen_create_ioreq_server(xen_xc, xen_domid, &state->ioservid);
+    if (rc < 0) {
+        perror("xen: ioreq server create");
+        return -1;
+    }
+
     state->exit.notify = xen_exit_notifier;
     qemu_add_exit_notifier(&state->exit);
 
@@ -1115,8 +1215,18 @@
     state->wakeup.notify = xen_wakeup_notifier;
     qemu_register_wakeup_notifier(&state->wakeup);
 
-    xc_get_hvm_param(xen_xc, xen_domid, HVM_PARAM_IOREQ_PFN, &ioreq_pfn);
+    rc = xen_get_ioreq_server_info(xen_xc, xen_domid, state->ioservid,
+                                   &ioreq_pfn, &bufioreq_pfn,
+                                   &bufioreq_evtchn);
+    if (rc < 0) {
+        hw_error("failed to get ioreq server info: error %d handle=" XC_INTERFACE_FMT,
+                 errno, xen_xc);
+    }
+
     DPRINTF("shared page at pfn %lx\n", ioreq_pfn);
+    DPRINTF("buffered io page at pfn %lx\n", bufioreq_pfn);
+    DPRINTF("buffered io evtchn is %x\n", bufioreq_evtchn);
+
     state->shared_page = xc_map_foreign_range(xen_xc, xen_domid, XC_PAGE_SIZE,
                                               PROT_READ|PROT_WRITE, ioreq_pfn);
     if (state->shared_page == NULL) {
@@ -1138,10 +1248,10 @@
         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,
-                                                   PROT_READ|PROT_WRITE, ioreq_pfn);
+    state->buffered_io_page = xc_map_foreign_range(xen_xc, xen_domid,
+                                                   XC_PAGE_SIZE,
+                                                   PROT_READ|PROT_WRITE,
+                                                   bufioreq_pfn);
     if (state->buffered_io_page == NULL) {
         hw_error("map buffered IO page returned error %d", errno);
     }
@@ -1149,6 +1259,12 @@
     /* Note: cpus is empty at this point in init */
     state->cpu_by_vcpu_id = g_malloc0(max_cpus * sizeof(CPUState *));
 
+    rc = xen_set_ioreq_server_state(xen_xc, xen_domid, state->ioservid, true);
+    if (rc < 0) {
+        hw_error("failed to enable ioreq server info: error %d handle=" XC_INTERFACE_FMT,
+                 errno, xen_xc);
+    }
+
     state->ioreq_local_port = g_malloc0(max_cpus * sizeof (evtchn_port_t));
 
     /* FIXME: how about if we overflow the page here? */
@@ -1156,22 +1272,16 @@
         rc = xc_evtchn_bind_interdomain(state->xce_handle, xen_domid,
                                         xen_vcpu_eport(state->shared_page, i));
         if (rc == -1) {
-            fprintf(stderr, "bind interdomain ioctl error %d\n", errno);
+            fprintf(stderr, "shared evtchn %d bind error %d\n", i, errno);
             return -1;
         }
         state->ioreq_local_port[i] = rc;
     }
 
-    rc = xc_get_hvm_param(xen_xc, xen_domid, HVM_PARAM_BUFIOREQ_EVTCHN,
-            &bufioreq_evtchn);
-    if (rc < 0) {
-        fprintf(stderr, "failed to get HVM_PARAM_BUFIOREQ_EVTCHN\n");
-        return -1;
-    }
     rc = xc_evtchn_bind_interdomain(state->xce_handle, xen_domid,
-            (uint32_t)bufioreq_evtchn);
+                                    bufioreq_evtchn);
     if (rc == -1) {
-        fprintf(stderr, "bind interdomain ioctl error %d\n", errno);
+        fprintf(stderr, "buffered evtchn bind error %d\n", errno);
         return -1;
     }
     state->bufioreq_local_port = rc;
@@ -1187,6 +1297,12 @@
     memory_listener_register(&state->memory_listener, &address_space_memory);
     state->log_for_dirtybit = NULL;
 
+    state->io_listener = xen_io_listener;
+    memory_listener_register(&state->io_listener, &address_space_io);
+
+    state->device_listener = xen_device_listener;
+    device_listener_register(&state->device_listener);
+
     /* Initialize backend core & drivers */
     if (xen_be_init() != 0) {
         fprintf(stderr, "%s: xen backend core setup failed\n", __FUNCTION__);