Merge remote-tracking branch 'remotes/awilliam/tags/vfio-update-20160219.1' into staging

VFIO updates 2016-02-19

 - AER pre-enable and misc fixes (Cao jin and Chen Fan)
 - PCI_CAP_LIST_NEXT & PCI_MSIX_FLAGS cleanup (Wei Yang)
 - AMD XGBE KVM platform passthrough (Eric Auger)

# gpg: Signature made Fri 19 Feb 2016 17:28:36 GMT using RSA key ID 3BB08B22
# gpg: Good signature from "Alex Williamson <alex.williamson@redhat.com>"
# gpg:                 aka "Alex Williamson <alex@shazbot.org>"
# gpg:                 aka "Alex Williamson <alwillia@redhat.com>"
# gpg:                 aka "Alex Williamson <alex.l.williamson@gmail.com>"

* remotes/awilliam/tags/vfio-update-20160219.1:
  vfio/pci: use PCI_MSIX_FLAGS on retrieving the MSIX entries
  hw/arm/sysbus-fdt: remove qemu_fdt_setprop returned value check
  hw/arm/sysbus-fdt: enable amd-xgbe dynamic instantiation
  hw/arm/sysbus-fdt: helpers for clock node generation
  device_tree: qemu_fdt_getprop_cell converted to use the error API
  device_tree: qemu_fdt_getprop converted to use the error API
  device_tree: introduce qemu_fdt_node_path
  device_tree: introduce load_device_tree_from_sysfs
  hw/vfio/platform: amd-xgbe device
  vfio/pci: replace 1 with PCI_CAP_LIST_NEXT to make code self-explain
  pcie_aer: expose pcie_aer_msg() interface
  aer: impove pcie_aer_init to support vfio device
  vfio: make the 4 bytes aligned for capability size
  pcie: modify the capability size assert

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

15 files changed, 660 insertions, 43 deletions

diff --git a/device_tree.c b/device_tree.c
index b1ad836073..6204af88c8 100644
--- a/device_tree.c
+++ b/device_tree.c
@@ -13,6 +13,10 @@
 
 #include "qemu/osdep.h"
 
+#ifdef CONFIG_LINUX
+#include <dirent.h>
+#endif
+
 #include "qemu-common.h"
 #include "qemu/error-report.h"
 #include "sysemu/device_tree.h"
@@ -112,6 +116,102 @@ fail:
     return NULL;
 }
 
+#ifdef CONFIG_LINUX
+
+#define SYSFS_DT_BASEDIR "/proc/device-tree"
+
+/**
+ * read_fstree: this function is inspired from dtc read_fstree
+ * @fdt: preallocated fdt blob buffer, to be populated
+ * @dirname: directory to scan under SYSFS_DT_BASEDIR
+ * the search is recursive and the tree is searched down to the
+ * leaves (property files).
+ *
+ * the function asserts in case of error
+ */
+static void read_fstree(void *fdt, const char *dirname)
+{
+    DIR *d;
+    struct dirent *de;
+    struct stat st;
+    const char *root_dir = SYSFS_DT_BASEDIR;
+    const char *parent_node;
+
+    if (strstr(dirname, root_dir) != dirname) {
+        error_setg(&error_fatal, "%s: %s must be searched within %s",
+                   __func__, dirname, root_dir);
+    }
+    parent_node = &dirname[strlen(SYSFS_DT_BASEDIR)];
+
+    d = opendir(dirname);
+    if (!d) {
+        error_setg(&error_fatal, "%s cannot open %s", __func__, dirname);
+    }
+
+    while ((de = readdir(d)) != NULL) {
+        char *tmpnam;
+
+        if (!g_strcmp0(de->d_name, ".")
+            || !g_strcmp0(de->d_name, "..")) {
+            continue;
+        }
+
+        tmpnam = g_strdup_printf("%s/%s", dirname, de->d_name);
+
+        if (lstat(tmpnam, &st) < 0) {
+            error_setg(&error_fatal, "%s cannot lstat %s", __func__, tmpnam);
+        }
+
+        if (S_ISREG(st.st_mode)) {
+            gchar *val;
+            gsize len;
+
+            if (!g_file_get_contents(tmpnam, &val, &len, NULL)) {
+                error_setg(&error_fatal, "%s not able to extract info from %s",
+                           __func__, tmpnam);
+            }
+
+            if (strlen(parent_node) > 0) {
+                qemu_fdt_setprop(fdt, parent_node,
+                                 de->d_name, val, len);
+            } else {
+                qemu_fdt_setprop(fdt, "/", de->d_name, val, len);
+            }
+            g_free(val);
+        } else if (S_ISDIR(st.st_mode)) {
+            char *node_name;
+
+            node_name = g_strdup_printf("%s/%s",
+                                        parent_node, de->d_name);
+            qemu_fdt_add_subnode(fdt, node_name);
+            g_free(node_name);
+            read_fstree(fdt, tmpnam);
+        }
+
+        g_free(tmpnam);
+    }
+
+    closedir(d);
+}
+
+/* load_device_tree_from_sysfs: extract the dt blob from host sysfs */
+void *load_device_tree_from_sysfs(void)
+{
+    void *host_fdt;
+    int host_fdt_size;
+
+    host_fdt = create_device_tree(&host_fdt_size);
+    read_fstree(host_fdt, SYSFS_DT_BASEDIR);
+    if (fdt_check_header(host_fdt)) {
+        error_setg(&error_fatal,
+                   "%s host device tree extracted into memory is invalid",
+                   __func__);
+    }
+    return host_fdt;
+}
+
+#endif /* CONFIG_LINUX */
+
 static int findnode_nofail(void *fdt, const char *node_path)
 {
     int offset;
@@ -126,6 +226,60 @@ static int findnode_nofail(void *fdt, const char *node_path)
     return offset;
 }
 
+char **qemu_fdt_node_path(void *fdt, const char *name, char *compat,
+                          Error **errp)
+{
+    int offset, len, ret;
+    const char *iter_name;
+    unsigned int path_len = 16, n = 0;
+    GSList *path_list = NULL, *iter;
+    char **path_array;
+
+    offset = fdt_node_offset_by_compatible(fdt, -1, compat);
+
+    while (offset >= 0) {
+        iter_name = fdt_get_name(fdt, offset, &len);
+        if (!iter_name) {
+            offset = len;
+            break;
+        }
+        if (!strcmp(iter_name, name)) {
+            char *path;
+
+            path = g_malloc(path_len);
+            while ((ret = fdt_get_path(fdt, offset, path, path_len))
+                  == -FDT_ERR_NOSPACE) {
+                path_len += 16;
+                path = g_realloc(path, path_len);
+            }
+            path_list = g_slist_prepend(path_list, path);
+            n++;
+        }
+        offset = fdt_node_offset_by_compatible(fdt, offset, compat);
+    }
+
+    if (offset < 0 && offset != -FDT_ERR_NOTFOUND) {
+        error_setg(errp, "%s: abort parsing dt for %s/%s: %s",
+                   __func__, name, compat, fdt_strerror(offset));
+        for (iter = path_list; iter; iter = iter->next) {
+            g_free(iter->data);
+        }
+        g_slist_free(path_list);
+        return NULL;
+    }
+
+    path_array = g_new(char *, n + 1);
+    path_array[n--] = NULL;
+
+    for (iter = path_list; iter; iter = iter->next) {
+        path_array[n--] = iter->data;
+    }
+
+    g_slist_free(path_list);
+
+    return path_array;
+}
+
 int qemu_fdt_setprop(void *fdt, const char *node_path,
                      const char *property, const void *val, int size)
 {
@@ -179,31 +333,39 @@ int qemu_fdt_setprop_string(void *fdt, const char *node_path,
 }
 
 const void *qemu_fdt_getprop(void *fdt, const char *node_path,
-                             const char *property, int *lenp)
+                             const char *property, int *lenp, Error **errp)
 {
     int len;
     const void *r;
+
     if (!lenp) {
         lenp = &len;
     }
     r = fdt_getprop(fdt, findnode_nofail(fdt, node_path), property, lenp);
     if (!r) {
-        error_report("%s: Couldn't get %s/%s: %s", __func__,
-                     node_path, property, fdt_strerror(*lenp));
-        exit(1);
+        error_setg(errp, "%s: Couldn't get %s/%s: %s", __func__,
+                  node_path, property, fdt_strerror(*lenp));
     }
     return r;
 }
 
 uint32_t qemu_fdt_getprop_cell(void *fdt, const char *node_path,
-                               const char *property)
+                               const char *property, int *lenp, Error **errp)
 {
     int len;
-    const uint32_t *p = qemu_fdt_getprop(fdt, node_path, property, &len);
-    if (len != 4) {
-        error_report("%s: %s/%s not 4 bytes long (not a cell?)",
-                     __func__, node_path, property);
-        exit(1);
+    const uint32_t *p;
+
+    if (!lenp) {
+        lenp = &len;
+    }
+    p = qemu_fdt_getprop(fdt, node_path, property, lenp, errp);
+    if (!p) {
+        return 0;
+    } else if (*lenp != 4) {
+        error_setg(errp, "%s: %s/%s not 4 bytes long (not a cell?)",
+                   __func__, node_path, property);
+        *lenp = -EINVAL;
+        return 0;
     }
     return be32_to_cpu(*p);
 }
diff --git a/hw/arm/boot.c b/hw/arm/boot.c
index cce8c7cd1c..0a56d34cfe 100644
--- a/hw/arm/boot.c
+++ b/hw/arm/boot.c
@@ -437,8 +437,10 @@ static int load_dtb(hwaddr addr, const struct arm_boot_info *binfo,
         return 0;
     }
 
-    acells = qemu_fdt_getprop_cell(fdt, "/", "#address-cells");
-    scells = qemu_fdt_getprop_cell(fdt, "/", "#size-cells");
+    acells = qemu_fdt_getprop_cell(fdt, "/", "#address-cells",
+                                   NULL, &error_fatal);
+    scells = qemu_fdt_getprop_cell(fdt, "/", "#size-cells",
+                                   NULL, &error_fatal);
     if (acells == 0 || scells == 0) {
         fprintf(stderr, "dtb file invalid (#address-cells or #size-cells 0)\n");
         goto fail;
diff --git a/hw/arm/sysbus-fdt.c b/hw/arm/sysbus-fdt.c
index 68a3de5cf8..04afeae226 100644
--- a/hw/arm/sysbus-fdt.c
+++ b/hw/arm/sysbus-fdt.c
@@ -22,6 +22,11 @@
  */
 
 #include "qemu/osdep.h"
+#include <libfdt.h>
+#include "qemu-common.h"
+#ifdef CONFIG_LINUX
+#include <linux/vfio.h>
+#endif
 #include "hw/arm/sysbus-fdt.h"
 #include "qemu/error-report.h"
 #include "sysemu/device_tree.h"
@@ -29,6 +34,7 @@
 #include "sysemu/sysemu.h"
 #include "hw/vfio/vfio-platform.h"
 #include "hw/vfio/vfio-calxeda-xgmac.h"
+#include "hw/vfio/vfio-amd-xgbe.h"
 #include "hw/arm/fdt.h"
 
 /*
@@ -57,6 +63,146 @@ typedef struct NodeCreationPair {
     int (*add_fdt_node_fn)(SysBusDevice *sbdev, void *opaque);
 } NodeCreationPair;
 
+/* helpers */
+
+typedef struct HostProperty {
+    const char *name;
+    bool optional;
+} HostProperty;
+
+#ifdef CONFIG_LINUX
+
+/**
+ * copy_properties_from_host
+ *
+ * copies properties listed in an array from host device tree to
+ * guest device tree. If a non optional property is not found, the
+ * function asserts. An optional property is ignored if not found
+ * in the host device tree.
+ * @props: array of HostProperty to copy
+ * @nb_props: number of properties in the array
+ * @host_dt: host device tree blob
+ * @guest_dt: guest device tree blob
+ * @node_path: host dt node path where the property is supposed to be
+              found
+ * @nodename: guest node name the properties should be added to
+ */
+static void copy_properties_from_host(HostProperty *props, int nb_props,
+                                      void *host_fdt, void *guest_fdt,
+                                      char *node_path, char *nodename)
+{
+    int i, prop_len;
+    const void *r;
+    Error *err = NULL;
+
+    for (i = 0; i < nb_props; i++) {
+        r = qemu_fdt_getprop(host_fdt, node_path,
+                             props[i].name,
+                             &prop_len,
+                             props[i].optional ? &err : &error_fatal);
+        if (r) {
+            qemu_fdt_setprop(guest_fdt, nodename,
+                             props[i].name, r, prop_len);
+        } else {
+            if (prop_len != -FDT_ERR_NOTFOUND) {
+                /* optional property not returned although property exists */
+                error_report_err(err);
+            } else {
+                error_free(err);
+            }
+        }
+    }
+}
+
+/* clock properties whose values are copied/pasted from host */
+static HostProperty clock_copied_properties[] = {
+    {"compatible", false},
+    {"#clock-cells", false},
+    {"clock-frequency", true},
+    {"clock-output-names", true},
+};
+
+/**
+ * fdt_build_clock_node
+ *
+ * Build a guest clock node, used as a dependency from a passthrough'ed
+ * device. Most information are retrieved from the host clock node.
+ * Also check the host clock is a fixed one.
+ *
+ * @host_fdt: host device tree blob from which info are retrieved
+ * @guest_fdt: guest device tree blob where the clock node is added
+ * @host_phandle: phandle of the clock in host device tree
+ * @guest_phandle: phandle to assign to the guest node
+ */
+static void fdt_build_clock_node(void *host_fdt, void *guest_fdt,
+                                uint32_t host_phandle,
+                                uint32_t guest_phandle)
+{
+    char *node_path = NULL;
+    char *nodename;
+    const void *r;
+    int ret, node_offset, prop_len, path_len = 16;
+
+    node_offset = fdt_node_offset_by_phandle(host_fdt, host_phandle);
+    if (node_offset <= 0) {
+        error_setg(&error_fatal,
+                   "not able to locate clock handle %d in host device tree",
+                   host_phandle);
+    }
+    node_path = g_malloc(path_len);
+    while ((ret = fdt_get_path(host_fdt, node_offset, node_path, path_len))
+            == -FDT_ERR_NOSPACE) {
+        path_len += 16;
+        node_path = g_realloc(node_path, path_len);
+    }
+    if (ret < 0) {
+        error_setg(&error_fatal,
+                   "not able to retrieve node path for clock handle %d",
+                   host_phandle);
+    }
+
+    r = qemu_fdt_getprop(host_fdt, node_path, "compatible", &prop_len,
+                         &error_fatal);
+    if (strcmp(r, "fixed-clock")) {
+        error_setg(&error_fatal,
+                   "clock handle %d is not a fixed clock", host_phandle);
+    }
+
+    nodename = strrchr(node_path, '/');
+    qemu_fdt_add_subnode(guest_fdt, nodename);
+
+    copy_properties_from_host(clock_copied_properties,
+                              ARRAY_SIZE(clock_copied_properties),
+                              host_fdt, guest_fdt,
+                              node_path, nodename);
+
+    qemu_fdt_setprop_cell(guest_fdt, nodename, "phandle", guest_phandle);
+
+    g_free(node_path);
+}
+
+/**
+ * sysfs_to_dt_name: convert the name found in sysfs into the node name
+ * for instance e0900000.xgmac is converted into xgmac@e0900000
+ * @sysfs_name: directory name in sysfs
+ *
+ * returns the device tree name upon success or NULL in case the sysfs name
+ * does not match the expected format
+ */
+static char *sysfs_to_dt_name(const char *sysfs_name)
+{
+    gchar **substrings =  g_strsplit(sysfs_name, ".", 2);
+    char *dt_name = NULL;
+
+    if (!substrings || !substrings[0] || !substrings[1]) {
+        goto out;
+    }
+    dt_name = g_strdup_printf("%s@%s", substrings[1], substrings[0]);
+out:
+    g_strfreev(substrings);
+    return dt_name;
+}
+
 /* Device Specific Code */
 
 /**
@@ -71,7 +217,7 @@ static int add_calxeda_midway_xgmac_fdt_node(SysBusDevice *sbdev, void *opaque)
     PlatformBusDevice *pbus = data->pbus;
     void *fdt = data->fdt;
     const char *parent_node = data->pbus_node_name;
-    int compat_str_len, i, ret = -1;
+    int compat_str_len, i;
     char *nodename;
     uint32_t *irq_attr, *reg_attr;
     uint64_t mmio_base, irq_number;
@@ -96,12 +242,8 @@ static int add_calxeda_midway_xgmac_fdt_node(SysBusDevice *sbdev, void *opaque)
         reg_attr[2 * i + 1] = cpu_to_be32(
                                 memory_region_size(&vdev->regions[i]->mem));
     }
-    ret = qemu_fdt_setprop(fdt, nodename, "reg", reg_attr,
-                           vbasedev->num_regions * 2 * sizeof(uint32_t));
-    if (ret) {
-        error_report("could not set reg property of node %s", nodename);
-        goto fail_reg;
-    }
+    qemu_fdt_setprop(fdt, nodename, "reg", reg_attr,
+                     vbasedev->num_regions * 2 * sizeof(uint32_t));
 
     irq_attr = g_new(uint32_t, vbasedev->num_irqs * 3);
     for (i = 0; i < vbasedev->num_irqs; i++) {
@@ -111,22 +253,173 @@ static int add_calxeda_midway_xgmac_fdt_node(SysBusDevice *sbdev, void *opaque)
         irq_attr[3 * i + 1] = cpu_to_be32(irq_number);
         irq_attr[3 * i + 2] = cpu_to_be32(GIC_FDT_IRQ_FLAGS_LEVEL_HI);
     }
-    ret = qemu_fdt_setprop(fdt, nodename, "interrupts",
+    qemu_fdt_setprop(fdt, nodename, "interrupts",
                      irq_attr, vbasedev->num_irqs * 3 * sizeof(uint32_t));
-    if (ret) {
-        error_report("could not set interrupts property of node %s",
-                     nodename);
+    g_free(irq_attr);
+    g_free(reg_attr);
+    g_free(nodename);
+    return 0;
+}
+
+/* AMD xgbe properties whose values are copied/pasted from host */
+static HostProperty amd_xgbe_copied_properties[] = {
+    {"compatible", false},
+    {"dma-coherent", true},
+    {"amd,per-channel-interrupt", true},
+    {"phy-mode", false},
+    {"mac-address", true},
+    {"amd,speed-set", false},
+    {"amd,serdes-blwc", true},
+    {"amd,serdes-cdr-rate", true},
+    {"amd,serdes-pq-skew", true},
+    {"amd,serdes-tx-amp", true},
+    {"amd,serdes-dfe-tap-config", true},
+    {"amd,serdes-dfe-tap-enable", true},
+    {"clock-names", false},
+};
+
+/**
+ * add_amd_xgbe_fdt_node
+ *
+ * Generates the combined xgbe/phy node following kernel >=4.2
+ * binding documentation:
+ * Documentation/devicetree/bindings/net/amd-xgbe.txt:
+ * Also 2 clock nodes are created (dma and ptp)
+ *
+ * Asserts in case of error
+ */
+static int add_amd_xgbe_fdt_node(SysBusDevice *sbdev, void *opaque)
+{
+    PlatformBusFDTData *data = opaque;
+    PlatformBusDevice *pbus = data->pbus;
+    VFIOPlatformDevice *vdev = VFIO_PLATFORM_DEVICE(sbdev);
+    VFIODevice *vbasedev = &vdev->vbasedev;
+    VFIOINTp *intp;
+    const char *parent_node = data->pbus_node_name;
+    char **node_path, *nodename, *dt_name;
+    void *guest_fdt = data->fdt, *host_fdt;
+    const void *r;
+    int i, prop_len;
+    uint32_t *irq_attr, *reg_attr, *host_clock_phandles;
+    uint64_t mmio_base, irq_number;
+    uint32_t guest_clock_phandles[2];
+
+    host_fdt = load_device_tree_from_sysfs();
+
+    dt_name = sysfs_to_dt_name(vbasedev->name);
+    if (!dt_name) {
+        error_setg(&error_fatal, "%s incorrect sysfs device name %s",
+                    __func__, vbasedev->name);
+    }
+    node_path = qemu_fdt_node_path(host_fdt, dt_name, vdev->compat,
+                                   &error_fatal);
+    if (!node_path || !node_path[0]) {
+        error_setg(&error_fatal, "%s unable to retrieve node path for %s/%s",
+                   __func__, dt_name, vdev->compat);
     }
+
+    if (node_path[1]) {
+        error_setg(&error_fatal, "%s more than one node matching %s/%s!",
+                   __func__, dt_name, vdev->compat);
+    }
+
+    g_free(dt_name);
+
+    if (vbasedev->num_regions != 5) {
+        error_setg(&error_fatal, "%s Does the host dt node combine XGBE/PHY?",
+                   __func__);
+    }
+
+    /* generate nodes for DMA_CLK and PTP_CLK */
+    r = qemu_fdt_getprop(host_fdt, node_path[0], "clocks",
+                         &prop_len, &error_fatal);
+    if (prop_len != 8) {
+        error_setg(&error_fatal, "%s clocks property should contain 2 handles",
+                   __func__);
+    }
+    host_clock_phandles = (uint32_t *)r;
+    guest_clock_phandles[0] = qemu_fdt_alloc_phandle(guest_fdt);
+    guest_clock_phandles[1] = qemu_fdt_alloc_phandle(guest_fdt);
+
+    /**
+     * clock handles fetched from host dt are in be32 layout whereas
+     * rest of the code uses cpu layout. Also guest clock handles are
+     * in cpu layout.
+     */
+    fdt_build_clock_node(host_fdt, guest_fdt,
+                         be32_to_cpu(host_clock_phandles[0]),
+                         guest_clock_phandles[0]);
+
+    fdt_build_clock_node(host_fdt, guest_fdt,
+                         be32_to_cpu(host_clock_phandles[1]),
+                         guest_clock_phandles[1]);
+
+    /* combined XGBE/PHY node */
+    mmio_base = platform_bus_get_mmio_addr(pbus, sbdev, 0);
+    nodename = g_strdup_printf("%s/%s@%" PRIx64, parent_node,
+                               vbasedev->name, mmio_base);
+    qemu_fdt_add_subnode(guest_fdt, nodename);
+
+    copy_properties_from_host(amd_xgbe_copied_properties,
+                       ARRAY_SIZE(amd_xgbe_copied_properties),
+                       host_fdt, guest_fdt,
+                       node_path[0], nodename);
+
+    qemu_fdt_setprop_cells(guest_fdt, nodename, "clocks",
+                           guest_clock_phandles[0],
+                           guest_clock_phandles[1]);
+
+    reg_attr = g_new(uint32_t, vbasedev->num_regions * 2);
+    for (i = 0; i < vbasedev->num_regions; i++) {
+        mmio_base = platform_bus_get_mmio_addr(pbus, sbdev, i);
+        reg_attr[2 * i] = cpu_to_be32(mmio_base);
+        reg_attr[2 * i + 1] = cpu_to_be32(
+                                memory_region_size(&vdev->regions[i]->mem));
+    }
+    qemu_fdt_setprop(guest_fdt, nodename, "reg", reg_attr,
+                     vbasedev->num_regions * 2 * sizeof(uint32_t));
+
+    irq_attr = g_new(uint32_t, vbasedev->num_irqs * 3);
+    for (i = 0; i < vbasedev->num_irqs; i++) {
+        irq_number = platform_bus_get_irqn(pbus, sbdev , i)
+                         + data->irq_start;
+        irq_attr[3 * i] = cpu_to_be32(GIC_FDT_IRQ_TYPE_SPI);
+        irq_attr[3 * i + 1] = cpu_to_be32(irq_number);
+        /*
+          * General device interrupt and PCS auto-negotiation interrupts are
+          * level-sensitive while the 4 per-channel interrupts are edge
+          * sensitive
+          */
+        QLIST_FOREACH(intp, &vdev->intp_list, next) {
+            if (intp->pin == i) {
+                break;
+            }
+        }
+        if (intp->flags & VFIO_IRQ_INFO_AUTOMASKED) {
+            irq_attr[3 * i + 2] = cpu_to_be32(GIC_FDT_IRQ_FLAGS_LEVEL_HI);
+        } else {
+            irq_attr[3 * i + 2] = cpu_to_be32(GIC_FDT_IRQ_FLAGS_EDGE_LO_HI);
+        }
+    }
+    qemu_fdt_setprop(guest_fdt, nodename, "interrupts",
+                     irq_attr, vbasedev->num_irqs * 3 * sizeof(uint32_t));
+
+    g_free(host_fdt);
+    g_strfreev(node_path);
     g_free(irq_attr);
-fail_reg:
     g_free(reg_attr);
     g_free(nodename);
-    return ret;
+    return 0;
 }
 
+#endif /* CONFIG_LINUX */
+
 /* list of supported dynamic sysbus devices */
 static const NodeCreationPair add_fdt_node_functions[] = {
+#ifdef CONFIG_LINUX
     {TYPE_VFIO_CALXEDA_XGMAC, add_calxeda_midway_xgmac_fdt_node},
+    {TYPE_VFIO_AMD_XGBE, add_amd_xgbe_fdt_node},
+#endif
     {"", NULL}, /* last element */
 };
 
diff --git a/hw/arm/vexpress.c b/hw/arm/vexpress.c
index 3154aeaa95..726c4e0c55 100644
--- a/hw/arm/vexpress.c
+++ b/hw/arm/vexpress.c
@@ -478,8 +478,10 @@ static void vexpress_modify_dtb(const struct arm_boot_info *info, void *fdt)
     uint32_t acells, scells, intc;
     const VEDBoardInfo *daughterboard = (const VEDBoardInfo *)info;
 
-    acells = qemu_fdt_getprop_cell(fdt, "/", "#address-cells");
-    scells = qemu_fdt_getprop_cell(fdt, "/", "#size-cells");
+    acells = qemu_fdt_getprop_cell(fdt, "/", "#address-cells",
+                                   NULL, &error_fatal);
+    scells = qemu_fdt_getprop_cell(fdt, "/", "#size-cells",
+                                   NULL, &error_fatal);
     intc = find_int_controller(fdt);
     if (!intc) {
         /* Not fatal, we just won't provide virtio. This will
diff --git a/hw/pci-bridge/ioh3420.c b/hw/pci-bridge/ioh3420.c
index 9e048ebe35..0937fa34be 100644
--- a/hw/pci-bridge/ioh3420.c
+++ b/hw/pci-bridge/ioh3420.c
@@ -126,7 +126,7 @@ static int ioh3420_initfn(PCIDevice *d)
         goto err_pcie_cap;
     }
     pcie_cap_root_init(d);
-    rc = pcie_aer_init(d, IOH_EP_AER_OFFSET);
+    rc = pcie_aer_init(d, IOH_EP_AER_OFFSET, PCI_ERR_SIZEOF);
     if (rc < 0) {
         goto err;
     }
diff --git a/hw/pci-bridge/xio3130_downstream.c b/hw/pci-bridge/xio3130_downstream.c
index c32f2712c8..cf1ee63aba 100644
--- a/hw/pci-bridge/xio3130_downstream.c
+++ b/hw/pci-bridge/xio3130_downstream.c
@@ -89,7 +89,7 @@ static int xio3130_downstream_initfn(PCIDevice *d)
         goto err_pcie_cap;
     }
     pcie_cap_arifwd_init(d);
-    rc = pcie_aer_init(d, XIO3130_AER_OFFSET);
+    rc = pcie_aer_init(d, XIO3130_AER_OFFSET, PCI_ERR_SIZEOF);
     if (rc < 0) {
         goto err;
     }
diff --git a/hw/pci-bridge/xio3130_upstream.c b/hw/pci-bridge/xio3130_upstream.c
index 19798c09a8..164ef58c46 100644
--- a/hw/pci-bridge/xio3130_upstream.c
+++ b/hw/pci-bridge/xio3130_upstream.c
@@ -78,7 +78,7 @@ static int xio3130_upstream_initfn(PCIDevice *d)
     }
     pcie_cap_flr_init(d);
     pcie_cap_deverr_init(d);
-    rc = pcie_aer_init(d, XIO3130_AER_OFFSET);
+    rc = pcie_aer_init(d, XIO3130_AER_OFFSET, PCI_ERR_SIZEOF);
     if (rc < 0) {
         goto err;
     }
diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c
index 435a6cfd57..4aca0c5912 100644
--- a/hw/pci/pcie.c
+++ b/hw/pci/pcie.c
@@ -608,7 +608,7 @@ void pcie_add_capability(PCIDevice *dev,
 
     assert(offset >= PCI_CONFIG_SPACE_SIZE);
     assert(offset < offset + size);
-    assert(offset + size < PCIE_CONFIG_SPACE_SIZE);
+    assert(offset + size <= PCIE_CONFIG_SPACE_SIZE);
     assert(size >= 8);
     assert(pci_is_express(dev));
 
diff --git a/hw/pci/pcie_aer.c b/hw/pci/pcie_aer.c
index a9d9d06208..e2d4e68ba3 100644
--- a/hw/pci/pcie_aer.c
+++ b/hw/pci/pcie_aer.c
@@ -95,12 +95,12 @@ static void aer_log_clear_all_err(PCIEAERLog *aer_log)
     aer_log->log_num = 0;
 }
 
-int pcie_aer_init(PCIDevice *dev, uint16_t offset)
+int pcie_aer_init(PCIDevice *dev, uint16_t offset, uint16_t size)
 {
     PCIExpressDevice *exp;
 
     pcie_add_capability(dev, PCI_EXT_CAP_ID_ERR, PCI_ERR_VER,
-                        offset, PCI_ERR_SIZEOF);
+                        offset, size);
     exp = &dev->exp;
     exp->aer_cap = offset;
 
@@ -371,7 +371,7 @@ static void pcie_aer_msg_root_port(PCIDevice *dev, const PCIEAERMsg *msg)
  *
  * Walk up the bus tree from the device, propagate the error message.
  */
-static void pcie_aer_msg(PCIDevice *dev, const PCIEAERMsg *msg)
+void pcie_aer_msg(PCIDevice *dev, const PCIEAERMsg *msg)
 {
     uint8_t type;
 
diff --git a/hw/vfio/Makefile.objs b/hw/vfio/Makefile.objs
index d3248633c1..ceddbb8f99 100644
--- a/hw/vfio/Makefile.objs
+++ b/hw/vfio/Makefile.objs
@@ -3,4 +3,5 @@ obj-$(CONFIG_SOFTMMU) += common.o
 obj-$(CONFIG_PCI) += pci.o pci-quirks.o
 obj-$(CONFIG_SOFTMMU) += platform.o
 obj-$(CONFIG_SOFTMMU) += calxeda-xgmac.o
+obj-$(CONFIG_SOFTMMU) += amd-xgbe.o
 endif
diff --git a/hw/vfio/amd-xgbe.c b/hw/vfio/amd-xgbe.c
new file mode 100644
index 0000000000..53451eb22d
--- /dev/null
+++ b/hw/vfio/amd-xgbe.c
@@ -0,0 +1,55 @@
+/*
+ * AMD XGBE VFIO device
+ *
+ * Copyright Linaro Limited, 2015
+ *
+ * Authors:
+ *  Eric Auger <eric.auger@linaro.org>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include "hw/vfio/vfio-amd-xgbe.h"
+
+static void amd_xgbe_realize(DeviceState *dev, Error **errp)
+{
+    VFIOPlatformDevice *vdev = VFIO_PLATFORM_DEVICE(dev);
+    VFIOAmdXgbeDeviceClass *k = VFIO_AMD_XGBE_DEVICE_GET_CLASS(dev);
+
+    vdev->compat = g_strdup("amd,xgbe-seattle-v1a");
+
+    k->parent_realize(dev, errp);
+}
+
+static const VMStateDescription vfio_platform_amd_xgbe_vmstate = {
+    .name = TYPE_VFIO_AMD_XGBE,
+    .unmigratable = 1,
+};
+
+static void vfio_amd_xgbe_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    VFIOAmdXgbeDeviceClass *vcxc =
+        VFIO_AMD_XGBE_DEVICE_CLASS(klass);
+    vcxc->parent_realize = dc->realize;
+    dc->realize = amd_xgbe_realize;
+    dc->desc = "VFIO AMD XGBE";
+    dc->vmsd = &vfio_platform_amd_xgbe_vmstate;
+}
+
+static const TypeInfo vfio_amd_xgbe_dev_info = {
+    .name = TYPE_VFIO_AMD_XGBE,
+    .parent = TYPE_VFIO_PLATFORM,
+    .instance_size = sizeof(VFIOAmdXgbeDevice),
+    .class_init = vfio_amd_xgbe_class_init,
+    .class_size = sizeof(VFIOAmdXgbeDeviceClass),
+};
+
+static void register_amd_xgbe_dev_type(void)
+{
+    type_register_static(&vfio_amd_xgbe_dev_info);
+}
+
+type_init(register_amd_xgbe_dev_type)
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 49f3d2d239..20b505f4ec 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -1207,7 +1207,7 @@ static int vfio_msix_early_setup(VFIOPCIDevice *vdev)
     }
 
     if (pread(fd, &ctrl, sizeof(ctrl),
-              vdev->config_offset + pos + PCI_CAP_FLAGS) != sizeof(ctrl)) {
+              vdev->config_offset + pos + PCI_MSIX_FLAGS) != sizeof(ctrl)) {
         return -errno;
     }
 
@@ -1505,10 +1505,11 @@ static void vfio_unmap_bars(VFIOPCIDevice *vdev)
  */
 static uint8_t vfio_std_cap_max_size(PCIDevice *pdev, uint8_t pos)
 {
-    uint8_t tmp, next = 0xff;
+    uint8_t tmp;
+    uint16_t next = PCI_CONFIG_SPACE_SIZE;
 
     for (tmp = pdev->config[PCI_CAPABILITY_LIST]; tmp;
-         tmp = pdev->config[tmp + 1]) {
+         tmp = pdev->config[tmp + PCI_CAP_LIST_NEXT]) {
         if (tmp > pos && tmp < next) {
             next = tmp;
         }
@@ -1697,7 +1698,7 @@ static int vfio_add_std_cap(VFIOPCIDevice *vdev, uint8_t pos)
     int ret;
 
     cap_id = pdev->config[pos];
-    next = pdev->config[pos + 1];
+    next = pdev->config[pos + PCI_CAP_LIST_NEXT];
 
     /*
      * If it becomes important to configure capabilities to their actual
@@ -1711,7 +1712,7 @@ static int vfio_add_std_cap(VFIOPCIDevice *vdev, uint8_t pos)
      * pci_add_capability always inserts the new capability at the head
      * of the chain.  Therefore to end up with a chain that matches the
      * physical device, we insert from the end by making this recursive.
-     * This is also why we pre-caclulate size above as cached config space
+     * This is also why we pre-calculate size above as cached config space
      * will be changed as we unwind the stack.
      */
     if (next) {
@@ -1727,7 +1728,7 @@ static int vfio_add_std_cap(VFIOPCIDevice *vdev, uint8_t pos)
     }
 
     /* Use emulated next pointer to allow dropping caps */
-    pci_set_byte(vdev->emulated_config_bits + pos + 1, 0xff);
+    pci_set_byte(vdev->emulated_config_bits + pos + PCI_CAP_LIST_NEXT, 0xff);
 
     switch (cap_id) {
     case PCI_CAP_ID_MSI:
diff --git a/include/hw/pci/pcie_aer.h b/include/hw/pci/pcie_aer.h
index 2fb83882be..c2ee4e2bdb 100644
--- a/include/hw/pci/pcie_aer.h
+++ b/include/hw/pci/pcie_aer.h
@@ -87,7 +87,7 @@ struct PCIEAERErr {
 
 extern const VMStateDescription vmstate_pcie_aer_log;
 
-int pcie_aer_init(PCIDevice *dev, uint16_t offset);
+int pcie_aer_init(PCIDevice *dev, uint16_t offset, uint16_t size);
 void pcie_aer_exit(PCIDevice *dev);
 void pcie_aer_write_config(PCIDevice *dev,
                            uint32_t addr, uint32_t val, int len);
@@ -102,5 +102,6 @@ void pcie_aer_root_write_config(PCIDevice *dev,
 
 /* error injection */
 int pcie_aer_inject_error(PCIDevice *dev, const PCIEAERErr *err);
+void pcie_aer_msg(PCIDevice *dev, const PCIEAERMsg *msg);
 
 #endif /* QEMU_PCIE_AER_H */
diff --git a/include/hw/vfio/vfio-amd-xgbe.h b/include/hw/vfio/vfio-amd-xgbe.h
new file mode 100644
index 0000000000..9fff65e99d
--- /dev/null
+++ b/include/hw/vfio/vfio-amd-xgbe.h
@@ -0,0 +1,51 @@
+/*
+ * VFIO AMD XGBE device
+ *
+ * Copyright Linaro Limited, 2015
+ *
+ * Authors:
+ *  Eric Auger <eric.auger@linaro.org>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef HW_VFIO_VFIO_AMD_XGBE_H
+#define HW_VFIO_VFIO_AMD_XGBE_H
+
+#include "hw/vfio/vfio-platform.h"
+
+#define TYPE_VFIO_AMD_XGBE "vfio-amd-xgbe"
+
+/**
+ * This device exposes:
+ * - 5 MMIO regions: MAC, PCS, SerDes Rx/Tx regs,
+     SerDes Integration Registers 1/2 & 2/2
+ * - 2 level sensitive IRQs and optional DMA channel IRQs
+ */
+struct VFIOAmdXgbeDevice {
+    VFIOPlatformDevice vdev;
+};
+
+typedef struct VFIOAmdXgbeDevice VFIOAmdXgbeDevice;
+
+struct VFIOAmdXgbeDeviceClass {
+    /*< private >*/
+    VFIOPlatformDeviceClass parent_class;
+    /*< public >*/
+    DeviceRealize parent_realize;
+};
+
+typedef struct VFIOAmdXgbeDeviceClass VFIOAmdXgbeDeviceClass;
+
+#define VFIO_AMD_XGBE_DEVICE(obj) \
+     OBJECT_CHECK(VFIOAmdXgbeDevice, (obj), TYPE_VFIO_AMD_XGBE)
+#define VFIO_AMD_XGBE_DEVICE_CLASS(klass) \
+     OBJECT_CLASS_CHECK(VFIOAmdXgbeDeviceClass, (klass), \
+                        TYPE_VFIO_AMD_XGBE)
+#define VFIO_AMD_XGBE_DEVICE_GET_CLASS(obj) \
+     OBJECT_GET_CLASS(VFIOAmdXgbeDeviceClass, (obj), \
+                      TYPE_VFIO_AMD_XGBE)
+
+#endif
diff --git a/include/sysemu/device_tree.h b/include/sysemu/device_tree.h
index 359e14304f..705650aad4 100644
--- a/include/sysemu/device_tree.h
+++ b/include/sysemu/device_tree.h
@@ -16,6 +16,32 @@
 
 void *create_device_tree(int *sizep);
 void *load_device_tree(const char *filename_path, int *sizep);
+#ifdef CONFIG_LINUX
+/**
+ * load_device_tree_from_sysfs: reads the device tree information in the
+ * /proc/device-tree directory and return the corresponding binary blob
+ * buffer pointer. Asserts in case of error.
+ */
+void *load_device_tree_from_sysfs(void);
+#endif
+
+/**
+ * qemu_fdt_node_path: return the paths of nodes matching a given
+ * name and compat string
+ * @fdt: pointer to the dt blob
+ * @name: node name
+ * @compat: compatibility string
+ * @errp: handle to an error object
+ *
+ * returns a newly allocated NULL-terminated array of node paths.
+ * Use g_strfreev() to free it. If one or more nodes were found, the
+ * array contains the path of each node and the last element equals to
+ * NULL. If there is no error but no matching node was found, the
+ * returned array contains a single element equal to NULL. If an error
+ * was encountered when parsing the blob, the function returns NULL
+ */
+char **qemu_fdt_node_path(void *fdt, const char *name, char *compat,
+                          Error **errp);
 
 int qemu_fdt_setprop(void *fdt, const char *node_path,
                      const char *property, const void *val, int size);
@@ -28,10 +54,33 @@ int qemu_fdt_setprop_string(void *fdt, const char *node_path,
 int qemu_fdt_setprop_phandle(void *fdt, const char *node_path,
                              const char *property,
                              const char *target_node_path);
+/**
+ * qemu_fdt_getprop: retrieve the value of a given property
+ * @fdt: pointer to the device tree blob
+ * @node_path: node path
+ * @property: name of the property to find
+ * @lenp: fdt error if any or length of the property on success
+ * @errp: handle to an error object
+ *
+ * returns a pointer to the property on success and NULL on failure
+ */
 const void *qemu_fdt_getprop(void *fdt, const char *node_path,
-                             const char *property, int *lenp);
+                             const char *property, int *lenp,
+                             Error **errp);
+/**
+ * qemu_fdt_getprop_cell: retrieve the value of a given 4 byte property
+ * @fdt: pointer to the device tree blob
+ * @node_path: node path
+ * @property: name of the property to find
+ * @lenp: fdt error if any or -EINVAL if the property size is different from
+ *        4 bytes, or 4 (expected length of the property) upon success.
+ * @errp: handle to an error object
+ *
+ * returns the property value on success
+ */
 uint32_t qemu_fdt_getprop_cell(void *fdt, const char *node_path,
-                               const char *property);
+                               const char *property, int *lenp,
+                               Error **errp);
 uint32_t qemu_fdt_get_phandle(void *fdt, const char *path);
 uint32_t qemu_fdt_alloc_phandle(void *fdt);
 int qemu_fdt_nop_node(void *fdt, const char *node_path);