summary refs log tree commit diff stats
path: root/hw
diff options
context:
space:
mode:
Diffstat (limited to 'hw')
-rw-r--r--hw/9pfs/9p-local.c1031
-rw-r--r--hw/9pfs/9p-local.h20
-rw-r--r--hw/9pfs/9p-posix-acl.c44
-rw-r--r--hw/9pfs/9p-util.c69
-rw-r--r--hw/9pfs/9p-util.h54
-rw-r--r--hw/9pfs/9p-xattr-user.c24
-rw-r--r--hw/9pfs/9p-xattr.c166
-rw-r--r--hw/9pfs/9p-xattr.h87
-rw-r--r--hw/9pfs/9p.c19
-rw-r--r--hw/9pfs/Makefile.objs2
-rw-r--r--hw/9pfs/cofile.c2
-rw-r--r--hw/acpi/tco.c1
-rw-r--r--hw/arm/armv7m.c379
-rw-r--r--hw/arm/bcm2835_peripherals.c58
-rw-r--r--hw/arm/exynos4210.c18
-rw-r--r--hw/arm/netduino2.c7
-rw-r--r--hw/arm/stm32f205_soc.c28
-rw-r--r--hw/arm/virt.c32
-rw-r--r--hw/block/block.c24
-rw-r--r--hw/block/fdc.c28
-rw-r--r--hw/block/m25p80.c8
-rw-r--r--hw/block/nand.c7
-rw-r--r--hw/block/nvme.c8
-rw-r--r--hw/block/onenand.c7
-rw-r--r--hw/block/pflash_cfi01.c18
-rw-r--r--hw/block/pflash_cfi02.c19
-rw-r--r--hw/block/virtio-blk.c8
-rw-r--r--hw/core/loader.c17
-rw-r--r--hw/core/or-irq.c3
-rw-r--r--hw/core/qdev-properties-system.c9
-rw-r--r--hw/core/qdev.c14
-rw-r--r--hw/core/register.c30
-rw-r--r--hw/display/milkymist-tmu2.c2
-rw-r--r--hw/gpio/Makefile.objs1
-rw-r--r--hw/gpio/bcm2835_gpio.c353
-rw-r--r--hw/ide/core.c2
-rw-r--r--hw/ide/qdev.c9
-rw-r--r--hw/intc/Makefile.objs2
-rw-r--r--hw/intc/arm_gic.c31
-rw-r--r--hw/intc/arm_gic_common.c23
-rw-r--r--hw/intc/arm_gicv3_common.c38
-rw-r--r--hw/intc/arm_gicv3_cpuif.c8
-rw-r--r--hw/intc/arm_gicv3_kvm.c629
-rw-r--r--hw/intc/armv7m_nvic.c965
-rw-r--r--hw/intc/gic_internal.h7
-rw-r--r--hw/intc/gicv3_internal.h3
-rw-r--r--hw/intc/trace-events15
-rw-r--r--hw/misc/Makefile.objs3
-rw-r--r--hw/misc/bcm2835_rng.c149
-rw-r--r--hw/misc/exynos4210_clk.c164
-rw-r--r--hw/net/cadence_gem.c2
-rw-r--r--hw/nvram/spapr_nvram.c8
-rw-r--r--hw/s390x/ipl.c90
-rw-r--r--hw/s390x/ipl.h5
-rw-r--r--hw/s390x/s390-virtio-ccw.c3
-rw-r--r--hw/s390x/s390-virtio.c2
-rw-r--r--hw/s390x/s390-virtio.h1
-rw-r--r--hw/scsi/scsi-disk.c12
-rw-r--r--hw/sd/Makefile.objs1
-rw-r--r--hw/sd/bcm2835_sdhost.c429
-rw-r--r--hw/sd/core.c27
-rw-r--r--hw/sd/sd.c8
-rw-r--r--hw/sd/sdhci.c25
-rw-r--r--hw/timer/Makefile.objs1
-rw-r--r--hw/timer/armv7m_systick.c240
-rw-r--r--hw/timer/imx_gpt.c33
-rw-r--r--hw/timer/trace-events6
-rw-r--r--hw/usb/dev-storage.c6
68 files changed, 4386 insertions, 1158 deletions
diff --git a/hw/9pfs/9p-local.c b/hw/9pfs/9p-local.c
index 7de07e1ba6..f22a3c3654 100644
--- a/hw/9pfs/9p-local.c
+++ b/hw/9pfs/9p-local.c
@@ -13,7 +13,9 @@
 
 #include "qemu/osdep.h"
 #include "9p.h"
+#include "9p-local.h"
 #include "9p-xattr.h"
+#include "9p-util.h"
 #include "fsdev/qemu-fsdev.h"   /* local_ops */
 #include <arpa/inet.h>
 #include <pwd.h>
@@ -43,40 +45,62 @@
 #define BTRFS_SUPER_MAGIC 0x9123683E
 #endif
 
-#define VIRTFS_META_DIR ".virtfs_metadata"
+typedef struct {
+    int mountfd;
+} LocalData;
 
-static char *local_mapped_attr_path(FsContext *ctx, const char *path)
+int local_open_nofollow(FsContext *fs_ctx, const char *path, int flags,
+                        mode_t mode)
 {
-    int dirlen;
-    const char *name = strrchr(path, '/');
-    if (name) {
-        dirlen = name - path;
-        ++name;
-    } else {
-        name = path;
-        dirlen = 0;
+    LocalData *data = fs_ctx->private;
+
+    /* All paths are relative to the path data->mountfd points to */
+    while (*path == '/') {
+        path++;
     }
-    return g_strdup_printf("%s/%.*s/%s/%s", ctx->fs_root,
-                           dirlen, path, VIRTFS_META_DIR, name);
+
+    return relative_openat_nofollow(data->mountfd, path, flags, mode);
+}
+
+int local_opendir_nofollow(FsContext *fs_ctx, const char *path)
+{
+    return local_open_nofollow(fs_ctx, path, O_DIRECTORY | O_RDONLY, 0);
+}
+
+static void renameat_preserve_errno(int odirfd, const char *opath, int ndirfd,
+                                    const char *npath)
+{
+    int serrno = errno;
+    renameat(odirfd, opath, ndirfd, npath);
+    errno = serrno;
 }
 
-static FILE *local_fopen(const char *path, const char *mode)
+static void unlinkat_preserve_errno(int dirfd, const char *path, int flags)
+{
+    int serrno = errno;
+    unlinkat(dirfd, path, flags);
+    errno = serrno;
+}
+
+#define VIRTFS_META_DIR ".virtfs_metadata"
+
+static FILE *local_fopenat(int dirfd, const char *name, const char *mode)
 {
     int fd, o_mode = 0;
     FILE *fp;
-    int flags = O_NOFOLLOW;
+    int flags;
     /*
      * only supports two modes
      */
     if (mode[0] == 'r') {
-        flags |= O_RDONLY;
+        flags = O_RDONLY;
     } else if (mode[0] == 'w') {
-        flags |= O_WRONLY | O_TRUNC | O_CREAT;
+        flags = O_WRONLY | O_TRUNC | O_CREAT;
         o_mode = S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH;
     } else {
         return NULL;
     }
-    fd = open(path, flags, o_mode);
+    fd = openat_file(dirfd, name, flags, o_mode);
     if (fd == -1) {
         return NULL;
     }
@@ -88,16 +112,20 @@ static FILE *local_fopen(const char *path, const char *mode)
 }
 
 #define ATTR_MAX 100
-static void local_mapped_file_attr(FsContext *ctx, const char *path,
+static void local_mapped_file_attr(int dirfd, const char *name,
                                    struct stat *stbuf)
 {
     FILE *fp;
     char buf[ATTR_MAX];
-    char *attr_path;
+    int map_dirfd;
 
-    attr_path = local_mapped_attr_path(ctx, path);
-    fp = local_fopen(attr_path, "r");
-    g_free(attr_path);
+    map_dirfd = openat_dir(dirfd, VIRTFS_META_DIR);
+    if (map_dirfd == -1) {
+        return;
+    }
+
+    fp = local_fopenat(map_dirfd, name, "r");
+    close_preserve_errno(map_dirfd);
     if (!fp) {
         return;
     }
@@ -119,12 +147,17 @@ static void local_mapped_file_attr(FsContext *ctx, const char *path,
 
 static int local_lstat(FsContext *fs_ctx, V9fsPath *fs_path, struct stat *stbuf)
 {
-    int err;
-    char *buffer;
-    char *path = fs_path->data;
+    int err = -1;
+    char *dirpath = g_path_get_dirname(fs_path->data);
+    char *name = g_path_get_basename(fs_path->data);
+    int dirfd;
 
-    buffer = rpath(fs_ctx, path);
-    err =  lstat(buffer, stbuf);
+    dirfd = local_opendir_nofollow(fs_ctx, dirpath);
+    if (dirfd == -1) {
+        goto out;
+    }
+
+    err = fstatat(dirfd, name, stbuf, AT_SYMLINK_NOFOLLOW);
     if (err) {
         goto err_out;
     }
@@ -134,87 +167,83 @@ static int local_lstat(FsContext *fs_ctx, V9fsPath *fs_path, struct stat *stbuf)
         gid_t tmp_gid;
         mode_t tmp_mode;
         dev_t tmp_dev;
-        if (getxattr(buffer, "user.virtfs.uid", &tmp_uid, sizeof(uid_t)) > 0) {
+
+        if (fgetxattrat_nofollow(dirfd, name, "user.virtfs.uid", &tmp_uid,
+                                 sizeof(uid_t)) > 0) {
             stbuf->st_uid = le32_to_cpu(tmp_uid);
         }
-        if (getxattr(buffer, "user.virtfs.gid", &tmp_gid, sizeof(gid_t)) > 0) {
+        if (fgetxattrat_nofollow(dirfd, name, "user.virtfs.gid", &tmp_gid,
+                                 sizeof(gid_t)) > 0) {
             stbuf->st_gid = le32_to_cpu(tmp_gid);
         }
-        if (getxattr(buffer, "user.virtfs.mode",
-                    &tmp_mode, sizeof(mode_t)) > 0) {
+        if (fgetxattrat_nofollow(dirfd, name, "user.virtfs.mode", &tmp_mode,
+                                 sizeof(mode_t)) > 0) {
             stbuf->st_mode = le32_to_cpu(tmp_mode);
         }
-        if (getxattr(buffer, "user.virtfs.rdev", &tmp_dev, sizeof(dev_t)) > 0) {
+        if (fgetxattrat_nofollow(dirfd, name, "user.virtfs.rdev", &tmp_dev,
+                                 sizeof(dev_t)) > 0) {
             stbuf->st_rdev = le64_to_cpu(tmp_dev);
         }
     } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
-        local_mapped_file_attr(fs_ctx, path, stbuf);
+        local_mapped_file_attr(dirfd, name, stbuf);
     }
 
 err_out:
-    g_free(buffer);
-    return err;
-}
-
-static int local_create_mapped_attr_dir(FsContext *ctx, const char *path)
-{
-    int err;
-    char *attr_dir;
-    char *tmp_path = g_strdup(path);
-
-    attr_dir = g_strdup_printf("%s/%s/%s",
-             ctx->fs_root, dirname(tmp_path), VIRTFS_META_DIR);
-
-    err = mkdir(attr_dir, 0700);
-    if (err < 0 && errno == EEXIST) {
-        err = 0;
-    }
-    g_free(attr_dir);
-    g_free(tmp_path);
+    close_preserve_errno(dirfd);
+out:
+    g_free(name);
+    g_free(dirpath);
     return err;
 }
 
-static int local_set_mapped_file_attr(FsContext *ctx,
-                                      const char *path, FsCred *credp)
+static int local_set_mapped_file_attrat(int dirfd, const char *name,
+                                        FsCred *credp)
 {
     FILE *fp;
-    int ret = 0;
+    int ret;
     char buf[ATTR_MAX];
-    char *attr_path;
     int uid = -1, gid = -1, mode = -1, rdev = -1;
+    int map_dirfd;
+
+    ret = mkdirat(dirfd, VIRTFS_META_DIR, 0700);
+    if (ret < 0 && errno != EEXIST) {
+        return -1;
+    }
 
-    attr_path = local_mapped_attr_path(ctx, path);
-    fp = local_fopen(attr_path, "r");
+    map_dirfd = openat_dir(dirfd, VIRTFS_META_DIR);
+    if (map_dirfd == -1) {
+        return -1;
+    }
+
+    fp = local_fopenat(map_dirfd, name, "r");
     if (!fp) {
-        goto create_map_file;
+        if (errno == ENOENT) {
+            goto update_map_file;
+        } else {
+            close_preserve_errno(map_dirfd);
+            return -1;
+        }
     }
     memset(buf, 0, ATTR_MAX);
     while (fgets(buf, ATTR_MAX, fp)) {
         if (!strncmp(buf, "virtfs.uid", 10)) {
-            uid = atoi(buf+11);
+            uid = atoi(buf + 11);
         } else if (!strncmp(buf, "virtfs.gid", 10)) {
-            gid = atoi(buf+11);
+            gid = atoi(buf + 11);
         } else if (!strncmp(buf, "virtfs.mode", 11)) {
-            mode = atoi(buf+12);
+            mode = atoi(buf + 12);
         } else if (!strncmp(buf, "virtfs.rdev", 11)) {
-            rdev = atoi(buf+12);
+            rdev = atoi(buf + 12);
         }
         memset(buf, 0, ATTR_MAX);
     }
     fclose(fp);
-    goto update_map_file;
-
-create_map_file:
-    ret = local_create_mapped_attr_dir(ctx, path);
-    if (ret < 0) {
-        goto err_out;
-    }
 
 update_map_file:
-    fp = local_fopen(attr_path, "w");
+    fp = local_fopenat(map_dirfd, name, "w");
+    close_preserve_errno(map_dirfd);
     if (!fp) {
-        ret = -1;
-        goto err_out;
+        return -1;
     }
 
     if (credp->fc_uid != -1) {
@@ -230,7 +259,6 @@ update_map_file:
         rdev = credp->fc_rdev;
     }
 
-
     if (uid != -1) {
         fprintf(fp, "virtfs.uid=%d\n", uid);
     }
@@ -245,39 +273,71 @@ update_map_file:
     }
     fclose(fp);
 
-err_out:
-    g_free(attr_path);
+    return 0;
+}
+
+static int fchmodat_nofollow(int dirfd, const char *name, mode_t mode)
+{
+    int fd, ret;
+
+    /* FIXME: this should be handled with fchmodat(AT_SYMLINK_NOFOLLOW).
+     * Unfortunately, the linux kernel doesn't implement it yet. As an
+     * alternative, let's open the file and use fchmod() instead. This
+     * may fail depending on the permissions of the file, but it is the
+     * best we can do to avoid TOCTTOU. We first try to open read-only
+     * in case name points to a directory. If that fails, we try write-only
+     * in case name doesn't point to a directory.
+     */
+    fd = openat_file(dirfd, name, O_RDONLY, 0);
+    if (fd == -1) {
+        /* In case the file is writable-only and isn't a directory. */
+        if (errno == EACCES) {
+            fd = openat_file(dirfd, name, O_WRONLY, 0);
+        }
+        if (fd == -1 && errno == EISDIR) {
+            errno = EACCES;
+        }
+    }
+    if (fd == -1) {
+        return -1;
+    }
+    ret = fchmod(fd, mode);
+    close_preserve_errno(fd);
     return ret;
 }
 
-static int local_set_xattr(const char *path, FsCred *credp)
+static int local_set_xattrat(int dirfd, const char *path, FsCred *credp)
 {
     int err;
 
     if (credp->fc_uid != -1) {
         uint32_t tmp_uid = cpu_to_le32(credp->fc_uid);
-        err = setxattr(path, "user.virtfs.uid", &tmp_uid, sizeof(uid_t), 0);
+        err = fsetxattrat_nofollow(dirfd, path, "user.virtfs.uid", &tmp_uid,
+                                   sizeof(uid_t), 0);
         if (err) {
             return err;
         }
     }
     if (credp->fc_gid != -1) {
         uint32_t tmp_gid = cpu_to_le32(credp->fc_gid);
-        err = setxattr(path, "user.virtfs.gid", &tmp_gid, sizeof(gid_t), 0);
+        err = fsetxattrat_nofollow(dirfd, path, "user.virtfs.gid", &tmp_gid,
+                                   sizeof(gid_t), 0);
         if (err) {
             return err;
         }
     }
     if (credp->fc_mode != -1) {
         uint32_t tmp_mode = cpu_to_le32(credp->fc_mode);
-        err = setxattr(path, "user.virtfs.mode", &tmp_mode, sizeof(mode_t), 0);
+        err = fsetxattrat_nofollow(dirfd, path, "user.virtfs.mode", &tmp_mode,
+                                   sizeof(mode_t), 0);
         if (err) {
             return err;
         }
     }
     if (credp->fc_rdev != -1) {
         uint64_t tmp_rdev = cpu_to_le64(credp->fc_rdev);
-        err = setxattr(path, "user.virtfs.rdev", &tmp_rdev, sizeof(dev_t), 0);
+        err = fsetxattrat_nofollow(dirfd, path, "user.virtfs.rdev", &tmp_rdev,
+                                   sizeof(dev_t), 0);
         if (err) {
             return err;
         }
@@ -285,58 +345,56 @@ static int local_set_xattr(const char *path, FsCred *credp)
     return 0;
 }
 
-static int local_post_create_passthrough(FsContext *fs_ctx, const char *path,
-                                         FsCred *credp)
+static int local_set_cred_passthrough(FsContext *fs_ctx, int dirfd,
+                                      const char *name, FsCred *credp)
 {
-    char *buffer;
-
-    buffer = rpath(fs_ctx, path);
-    if (lchown(buffer, credp->fc_uid, credp->fc_gid) < 0) {
+    if (fchownat(dirfd, name, credp->fc_uid, credp->fc_gid,
+                 AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH) < 0) {
         /*
          * If we fail to change ownership and if we are
          * using security model none. Ignore the error
          */
         if ((fs_ctx->export_flags & V9FS_SEC_MASK) != V9FS_SM_NONE) {
-            goto err;
+            return -1;
         }
     }
 
-    if (chmod(buffer, credp->fc_mode & 07777) < 0) {
-        goto err;
-    }
-
-    g_free(buffer);
-    return 0;
-err:
-    g_free(buffer);
-    return -1;
+    return fchmodat_nofollow(dirfd, name, credp->fc_mode & 07777);
 }
 
 static ssize_t local_readlink(FsContext *fs_ctx, V9fsPath *fs_path,
                               char *buf, size_t bufsz)
 {
     ssize_t tsize = -1;
-    char *buffer;
-    char *path = fs_path->data;
 
     if ((fs_ctx->export_flags & V9FS_SM_MAPPED) ||
         (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE)) {
         int fd;
-        buffer = rpath(fs_ctx, path);
-        fd = open(buffer, O_RDONLY | O_NOFOLLOW);
-        g_free(buffer);
+
+        fd = local_open_nofollow(fs_ctx, fs_path->data, O_RDONLY, 0);
         if (fd == -1) {
             return -1;
         }
         do {
             tsize = read(fd, (void *)buf, bufsz);
         } while (tsize == -1 && errno == EINTR);
-        close(fd);
+        close_preserve_errno(fd);
     } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) ||
                (fs_ctx->export_flags & V9FS_SM_NONE)) {
-        buffer = rpath(fs_ctx, path);
-        tsize = readlink(buffer, buf, bufsz);
-        g_free(buffer);
+        char *dirpath = g_path_get_dirname(fs_path->data);
+        char *name = g_path_get_basename(fs_path->data);
+        int dirfd;
+
+        dirfd = local_opendir_nofollow(fs_ctx, dirpath);
+        if (dirfd == -1) {
+            goto out;
+        }
+
+        tsize = readlinkat(dirfd, name, buf, bufsz);
+        close_preserve_errno(dirfd);
+    out:
+        g_free(name);
+        g_free(dirpath);
     }
     return tsize;
 }
@@ -354,27 +412,32 @@ static int local_closedir(FsContext *ctx, V9fsFidOpenState *fs)
 static int local_open(FsContext *ctx, V9fsPath *fs_path,
                       int flags, V9fsFidOpenState *fs)
 {
-    char *buffer;
-    char *path = fs_path->data;
+    int fd;
 
-    buffer = rpath(ctx, path);
-    fs->fd = open(buffer, flags | O_NOFOLLOW);
-    g_free(buffer);
+    fd = local_open_nofollow(ctx, fs_path->data, flags, 0);
+    if (fd == -1) {
+        return -1;
+    }
+    fs->fd = fd;
     return fs->fd;
 }
 
 static int local_opendir(FsContext *ctx,
                          V9fsPath *fs_path, V9fsFidOpenState *fs)
 {
-    char *buffer;
-    char *path = fs_path->data;
+    int dirfd;
+    DIR *stream;
+
+    dirfd = local_opendir_nofollow(ctx, fs_path->data);
+    if (dirfd == -1) {
+        return -1;
+    }
 
-    buffer = rpath(ctx, path);
-    fs->dir.stream = opendir(buffer);
-    g_free(buffer);
-    if (!fs->dir.stream) {
+    stream = fdopendir(dirfd);
+    if (!stream) {
         return -1;
     }
+    fs->dir.stream = stream;
     return 0;
 }
 
@@ -463,145 +526,122 @@ static ssize_t local_pwritev(FsContext *ctx, V9fsFidOpenState *fs,
 
 static int local_chmod(FsContext *fs_ctx, V9fsPath *fs_path, FsCred *credp)
 {
-    char *buffer;
+    char *dirpath = g_path_get_dirname(fs_path->data);
+    char *name = g_path_get_basename(fs_path->data);
     int ret = -1;
-    char *path = fs_path->data;
+    int dirfd;
+
+    dirfd = local_opendir_nofollow(fs_ctx, dirpath);
+    if (dirfd == -1) {
+        goto out;
+    }
 
     if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
-        buffer = rpath(fs_ctx, path);
-        ret = local_set_xattr(buffer, credp);
-        g_free(buffer);
+        ret = local_set_xattrat(dirfd, name, credp);
     } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
-        return local_set_mapped_file_attr(fs_ctx, path, credp);
-    } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) ||
-               (fs_ctx->export_flags & V9FS_SM_NONE)) {
-        buffer = rpath(fs_ctx, path);
-        ret = chmod(buffer, credp->fc_mode);
-        g_free(buffer);
+        ret = local_set_mapped_file_attrat(dirfd, name, credp);
+    } else if (fs_ctx->export_flags & V9FS_SM_PASSTHROUGH ||
+               fs_ctx->export_flags & V9FS_SM_NONE) {
+        ret = fchmodat_nofollow(dirfd, name, credp->fc_mode);
     }
+    close_preserve_errno(dirfd);
+
+out:
+    g_free(dirpath);
+    g_free(name);
     return ret;
 }
 
 static int local_mknod(FsContext *fs_ctx, V9fsPath *dir_path,
                        const char *name, FsCred *credp)
 {
-    char *path;
     int err = -1;
-    int serrno = 0;
-    V9fsString fullname;
-    char *buffer = NULL;
+    int dirfd;
 
-    v9fs_string_init(&fullname);
-    v9fs_string_sprintf(&fullname, "%s/%s", dir_path->data, name);
-    path = fullname.data;
+    dirfd = local_opendir_nofollow(fs_ctx, dir_path->data);
+    if (dirfd == -1) {
+        return -1;
+    }
 
-    /* Determine the security model */
-    if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
-        buffer = rpath(fs_ctx, path);
-        err = mknod(buffer, SM_LOCAL_MODE_BITS|S_IFREG, 0);
+    if (fs_ctx->export_flags & V9FS_SM_MAPPED ||
+        fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
+        err = mknodat(dirfd, name, SM_LOCAL_MODE_BITS | S_IFREG, 0);
         if (err == -1) {
             goto out;
         }
-        err = local_set_xattr(buffer, credp);
-        if (err == -1) {
-            serrno = errno;
-            goto err_end;
-        }
-    } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
 
-        buffer = rpath(fs_ctx, path);
-        err = mknod(buffer, SM_LOCAL_MODE_BITS|S_IFREG, 0);
-        if (err == -1) {
-            goto out;
+        if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
+            err = local_set_xattrat(dirfd, name, credp);
+        } else {
+            err = local_set_mapped_file_attrat(dirfd, name, credp);
         }
-        err = local_set_mapped_file_attr(fs_ctx, path, credp);
         if (err == -1) {
-            serrno = errno;
             goto err_end;
         }
-    } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) ||
-               (fs_ctx->export_flags & V9FS_SM_NONE)) {
-        buffer = rpath(fs_ctx, path);
-        err = mknod(buffer, credp->fc_mode, credp->fc_rdev);
+    } else if (fs_ctx->export_flags & V9FS_SM_PASSTHROUGH ||
+               fs_ctx->export_flags & V9FS_SM_NONE) {
+        err = mknodat(dirfd, name, credp->fc_mode, credp->fc_rdev);
         if (err == -1) {
             goto out;
         }
-        err = local_post_create_passthrough(fs_ctx, path, credp);
+        err = local_set_cred_passthrough(fs_ctx, dirfd, name, credp);
         if (err == -1) {
-            serrno = errno;
             goto err_end;
         }
     }
     goto out;
 
 err_end:
-    remove(buffer);
-    errno = serrno;
+    unlinkat_preserve_errno(dirfd, name, 0);
 out:
-    g_free(buffer);
-    v9fs_string_free(&fullname);
+    close_preserve_errno(dirfd);
     return err;
 }
 
 static int local_mkdir(FsContext *fs_ctx, V9fsPath *dir_path,
                        const char *name, FsCred *credp)
 {
-    char *path;
     int err = -1;
-    int serrno = 0;
-    V9fsString fullname;
-    char *buffer = NULL;
+    int dirfd;
 
-    v9fs_string_init(&fullname);
-    v9fs_string_sprintf(&fullname, "%s/%s", dir_path->data, name);
-    path = fullname.data;
+    dirfd = local_opendir_nofollow(fs_ctx, dir_path->data);
+    if (dirfd == -1) {
+        return -1;
+    }
 
-    /* Determine the security model */
-    if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
-        buffer = rpath(fs_ctx, path);
-        err = mkdir(buffer, SM_LOCAL_DIR_MODE_BITS);
+    if (fs_ctx->export_flags & V9FS_SM_MAPPED ||
+        fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
+        err = mkdirat(dirfd, name, SM_LOCAL_DIR_MODE_BITS);
         if (err == -1) {
             goto out;
         }
-        credp->fc_mode = credp->fc_mode|S_IFDIR;
-        err = local_set_xattr(buffer, credp);
-        if (err == -1) {
-            serrno = errno;
-            goto err_end;
-        }
-    } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
-        buffer = rpath(fs_ctx, path);
-        err = mkdir(buffer, SM_LOCAL_DIR_MODE_BITS);
-        if (err == -1) {
-            goto out;
+        credp->fc_mode = credp->fc_mode | S_IFDIR;
+
+        if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
+            err = local_set_xattrat(dirfd, name, credp);
+        } else {
+            err = local_set_mapped_file_attrat(dirfd, name, credp);
         }
-        credp->fc_mode = credp->fc_mode|S_IFDIR;
-        err = local_set_mapped_file_attr(fs_ctx, path, credp);
         if (err == -1) {
-            serrno = errno;
             goto err_end;
         }
-    } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) ||
-               (fs_ctx->export_flags & V9FS_SM_NONE)) {
-        buffer = rpath(fs_ctx, path);
-        err = mkdir(buffer, credp->fc_mode);
+    } else if (fs_ctx->export_flags & V9FS_SM_PASSTHROUGH ||
+               fs_ctx->export_flags & V9FS_SM_NONE) {
+        err = mkdirat(dirfd, name, credp->fc_mode);
         if (err == -1) {
             goto out;
         }
-        err = local_post_create_passthrough(fs_ctx, path, credp);
+        err = local_set_cred_passthrough(fs_ctx, dirfd, name, credp);
         if (err == -1) {
-            serrno = errno;
             goto err_end;
         }
     }
     goto out;
 
 err_end:
-    remove(buffer);
-    errno = serrno;
+    unlinkat_preserve_errno(dirfd, name, AT_REMOVEDIR);
 out:
-    g_free(buffer);
-    v9fs_string_free(&fullname);
+    close_preserve_errno(dirfd);
     return err;
 }
 
@@ -649,62 +689,45 @@ static int local_fstat(FsContext *fs_ctx, int fid_type,
 static int local_open2(FsContext *fs_ctx, V9fsPath *dir_path, const char *name,
                        int flags, FsCred *credp, V9fsFidOpenState *fs)
 {
-    char *path;
     int fd = -1;
     int err = -1;
-    int serrno = 0;
-    V9fsString fullname;
-    char *buffer = NULL;
+    int dirfd;
 
     /*
      * Mark all the open to not follow symlinks
      */
     flags |= O_NOFOLLOW;
 
-    v9fs_string_init(&fullname);
-    v9fs_string_sprintf(&fullname, "%s/%s", dir_path->data, name);
-    path = fullname.data;
+    dirfd = local_opendir_nofollow(fs_ctx, dir_path->data);
+    if (dirfd == -1) {
+        return -1;
+    }
 
     /* Determine the security model */
-    if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
-        buffer = rpath(fs_ctx, path);
-        fd = open(buffer, flags, SM_LOCAL_MODE_BITS);
+    if (fs_ctx->export_flags & V9FS_SM_MAPPED ||
+        fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
+        fd = openat_file(dirfd, name, flags, SM_LOCAL_MODE_BITS);
         if (fd == -1) {
-            err = fd;
             goto out;
         }
         credp->fc_mode = credp->fc_mode|S_IFREG;
-        /* Set cleint credentials in xattr */
-        err = local_set_xattr(buffer, credp);
-        if (err == -1) {
-            serrno = errno;
-            goto err_end;
+        if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
+            /* Set cleint credentials in xattr */
+            err = local_set_xattrat(dirfd, name, credp);
+        } else {
+            err = local_set_mapped_file_attrat(dirfd, name, credp);
         }
-    } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
-        buffer = rpath(fs_ctx, path);
-        fd = open(buffer, flags, SM_LOCAL_MODE_BITS);
-        if (fd == -1) {
-            err = fd;
-            goto out;
-        }
-        credp->fc_mode = credp->fc_mode|S_IFREG;
-        /* Set client credentials in .virtfs_metadata directory files */
-        err = local_set_mapped_file_attr(fs_ctx, path, credp);
         if (err == -1) {
-            serrno = errno;
             goto err_end;
         }
     } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) ||
                (fs_ctx->export_flags & V9FS_SM_NONE)) {
-        buffer = rpath(fs_ctx, path);
-        fd = open(buffer, flags, credp->fc_mode);
+        fd = openat_file(dirfd, name, flags, credp->fc_mode);
         if (fd == -1) {
-            err = fd;
             goto out;
         }
-        err = local_post_create_passthrough(fs_ctx, path, credp);
+        err = local_set_cred_passthrough(fs_ctx, dirfd, name, credp);
         if (err == -1) {
-            serrno = errno;
             goto err_end;
         }
     }
@@ -713,12 +736,11 @@ static int local_open2(FsContext *fs_ctx, V9fsPath *dir_path, const char *name,
     goto out;
 
 err_end:
-    close(fd);
-    remove(buffer);
-    errno = serrno;
+    unlinkat_preserve_errno(dirfd, name,
+                            flags & O_DIRECTORY ? AT_REMOVEDIR : 0);
+    close_preserve_errno(fd);
 out:
-    g_free(buffer);
-    v9fs_string_free(&fullname);
+    close_preserve_errno(dirfd);
     return err;
 }
 
@@ -727,23 +749,22 @@ static int local_symlink(FsContext *fs_ctx, const char *oldpath,
                          V9fsPath *dir_path, const char *name, FsCred *credp)
 {
     int err = -1;
-    int serrno = 0;
-    char *newpath;
-    V9fsString fullname;
-    char *buffer = NULL;
+    int dirfd;
 
-    v9fs_string_init(&fullname);
-    v9fs_string_sprintf(&fullname, "%s/%s", dir_path->data, name);
-    newpath = fullname.data;
+    dirfd = local_opendir_nofollow(fs_ctx, dir_path->data);
+    if (dirfd == -1) {
+        return -1;
+    }
 
     /* Determine the security model */
-    if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
+    if (fs_ctx->export_flags & V9FS_SM_MAPPED ||
+        fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
         int fd;
         ssize_t oldpath_size, write_size;
-        buffer = rpath(fs_ctx, newpath);
-        fd = open(buffer, O_CREAT|O_EXCL|O_RDWR|O_NOFOLLOW, SM_LOCAL_MODE_BITS);
+
+        fd = openat_file(dirfd, name, O_CREAT | O_EXCL | O_RDWR,
+                         SM_LOCAL_MODE_BITS);
         if (fd == -1) {
-            err = fd;
             goto out;
         }
         /* Write the oldpath (target) to the file. */
@@ -751,218 +772,204 @@ static int local_symlink(FsContext *fs_ctx, const char *oldpath,
         do {
             write_size = write(fd, (void *)oldpath, oldpath_size);
         } while (write_size == -1 && errno == EINTR);
+        close_preserve_errno(fd);
 
         if (write_size != oldpath_size) {
-            serrno = errno;
-            close(fd);
-            err = -1;
             goto err_end;
         }
-        close(fd);
         /* Set cleint credentials in symlink's xattr */
-        credp->fc_mode = credp->fc_mode|S_IFLNK;
-        err = local_set_xattr(buffer, credp);
-        if (err == -1) {
-            serrno = errno;
-            goto err_end;
-        }
-    } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
-        int fd;
-        ssize_t oldpath_size, write_size;
-        buffer = rpath(fs_ctx, newpath);
-        fd = open(buffer, O_CREAT|O_EXCL|O_RDWR|O_NOFOLLOW, SM_LOCAL_MODE_BITS);
-        if (fd == -1) {
-            err = fd;
-            goto out;
-        }
-        /* Write the oldpath (target) to the file. */
-        oldpath_size = strlen(oldpath);
-        do {
-            write_size = write(fd, (void *)oldpath, oldpath_size);
-        } while (write_size == -1 && errno == EINTR);
+        credp->fc_mode = credp->fc_mode | S_IFLNK;
 
-        if (write_size != oldpath_size) {
-            serrno = errno;
-            close(fd);
-            err = -1;
-            goto err_end;
+        if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
+            err = local_set_xattrat(dirfd, name, credp);
+        } else {
+            err = local_set_mapped_file_attrat(dirfd, name, credp);
         }
-        close(fd);
-        /* Set cleint credentials in symlink's xattr */
-        credp->fc_mode = credp->fc_mode|S_IFLNK;
-        err = local_set_mapped_file_attr(fs_ctx, newpath, credp);
         if (err == -1) {
-            serrno = errno;
             goto err_end;
         }
-    } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) ||
-               (fs_ctx->export_flags & V9FS_SM_NONE)) {
-        buffer = rpath(fs_ctx, newpath);
-        err = symlink(oldpath, buffer);
+    } else if (fs_ctx->export_flags & V9FS_SM_PASSTHROUGH ||
+               fs_ctx->export_flags & V9FS_SM_NONE) {
+        err = symlinkat(oldpath, dirfd, name);
         if (err) {
             goto out;
         }
-        err = lchown(buffer, credp->fc_uid, credp->fc_gid);
+        err = fchownat(dirfd, name, credp->fc_uid, credp->fc_gid,
+                       AT_SYMLINK_NOFOLLOW);
         if (err == -1) {
             /*
              * If we fail to change ownership and if we are
              * using security model none. Ignore the error
              */
             if ((fs_ctx->export_flags & V9FS_SEC_MASK) != V9FS_SM_NONE) {
-                serrno = errno;
                 goto err_end;
-            } else
+            } else {
                 err = 0;
+            }
         }
     }
     goto out;
 
 err_end:
-    remove(buffer);
-    errno = serrno;
+    unlinkat_preserve_errno(dirfd, name, 0);
 out:
-    g_free(buffer);
-    v9fs_string_free(&fullname);
+    close_preserve_errno(dirfd);
     return err;
 }
 
 static int local_link(FsContext *ctx, V9fsPath *oldpath,
                       V9fsPath *dirpath, const char *name)
 {
-    int ret;
-    V9fsString newpath;
-    char *buffer, *buffer1;
+    char *odirpath = g_path_get_dirname(oldpath->data);
+    char *oname = g_path_get_basename(oldpath->data);
+    int ret = -1;
+    int odirfd, ndirfd;
 
-    v9fs_string_init(&newpath);
-    v9fs_string_sprintf(&newpath, "%s/%s", dirpath->data, name);
+    odirfd = local_opendir_nofollow(ctx, odirpath);
+    if (odirfd == -1) {
+        goto out;
+    }
+
+    ndirfd = local_opendir_nofollow(ctx, dirpath->data);
+    if (ndirfd == -1) {
+        close_preserve_errno(odirfd);
+        goto out;
+    }
 
-    buffer = rpath(ctx, oldpath->data);
-    buffer1 = rpath(ctx, newpath.data);
-    ret = link(buffer, buffer1);
-    g_free(buffer);
-    g_free(buffer1);
+    ret = linkat(odirfd, oname, ndirfd, name, 0);
+    if (ret < 0) {
+        goto out_close;
+    }
 
     /* now link the virtfs_metadata files */
-    if (!ret && (ctx->export_flags & V9FS_SM_MAPPED_FILE)) {
-        /* Link the .virtfs_metadata files. Create the metada directory */
-        ret = local_create_mapped_attr_dir(ctx, newpath.data);
-        if (ret < 0) {
-            goto err_out;
+    if (ctx->export_flags & V9FS_SM_MAPPED_FILE) {
+        int omap_dirfd, nmap_dirfd;
+
+        ret = mkdirat(ndirfd, VIRTFS_META_DIR, 0700);
+        if (ret < 0 && errno != EEXIST) {
+            goto err_undo_link;
+        }
+
+        omap_dirfd = openat_dir(odirfd, VIRTFS_META_DIR);
+        if (omap_dirfd == -1) {
+            goto err;
+        }
+
+        nmap_dirfd = openat_dir(ndirfd, VIRTFS_META_DIR);
+        if (nmap_dirfd == -1) {
+            close_preserve_errno(omap_dirfd);
+            goto err;
         }
-        buffer = local_mapped_attr_path(ctx, oldpath->data);
-        buffer1 = local_mapped_attr_path(ctx, newpath.data);
-        ret = link(buffer, buffer1);
-        g_free(buffer);
-        g_free(buffer1);
+
+        ret = linkat(omap_dirfd, oname, nmap_dirfd, name, 0);
+        close_preserve_errno(nmap_dirfd);
+        close_preserve_errno(omap_dirfd);
         if (ret < 0 && errno != ENOENT) {
-            goto err_out;
+            goto err_undo_link;
         }
-    }
-err_out:
-    v9fs_string_free(&newpath);
-    return ret;
-}
 
-static int local_truncate(FsContext *ctx, V9fsPath *fs_path, off_t size)
-{
-    char *buffer;
-    int ret;
-    char *path = fs_path->data;
+        ret = 0;
+    }
+    goto out_close;
 
-    buffer = rpath(ctx, path);
-    ret = truncate(buffer, size);
-    g_free(buffer);
+err:
+    ret = -1;
+err_undo_link:
+    unlinkat_preserve_errno(ndirfd, name, 0);
+out_close:
+    close_preserve_errno(ndirfd);
+    close_preserve_errno(odirfd);
+out:
+    g_free(oname);
+    g_free(odirpath);
     return ret;
 }
 
-static int local_rename(FsContext *ctx, const char *oldpath,
-                        const char *newpath)
+static int local_truncate(FsContext *ctx, V9fsPath *fs_path, off_t size)
 {
-    int err;
-    char *buffer, *buffer1;
+    int fd, ret;
 
-    if (ctx->export_flags & V9FS_SM_MAPPED_FILE) {
-        err = local_create_mapped_attr_dir(ctx, newpath);
-        if (err < 0) {
-            return err;
-        }
-        /* rename the .virtfs_metadata files */
-        buffer = local_mapped_attr_path(ctx, oldpath);
-        buffer1 = local_mapped_attr_path(ctx, newpath);
-        err = rename(buffer, buffer1);
-        g_free(buffer);
-        g_free(buffer1);
-        if (err < 0 && errno != ENOENT) {
-            return err;
-        }
+    fd = local_open_nofollow(ctx, fs_path->data, O_WRONLY, 0);
+    if (fd == -1) {
+        return -1;
     }
-
-    buffer = rpath(ctx, oldpath);
-    buffer1 = rpath(ctx, newpath);
-    err = rename(buffer, buffer1);
-    g_free(buffer);
-    g_free(buffer1);
-    return err;
+    ret = ftruncate(fd, size);
+    close_preserve_errno(fd);
+    return ret;
 }
 
 static int local_chown(FsContext *fs_ctx, V9fsPath *fs_path, FsCred *credp)
 {
-    char *buffer;
+    char *dirpath = g_path_get_dirname(fs_path->data);
+    char *name = g_path_get_basename(fs_path->data);
     int ret = -1;
-    char *path = fs_path->data;
+    int dirfd;
+
+    dirfd = local_opendir_nofollow(fs_ctx, dirpath);
+    if (dirfd == -1) {
+        goto out;
+    }
 
     if ((credp->fc_uid == -1 && credp->fc_gid == -1) ||
         (fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) ||
         (fs_ctx->export_flags & V9FS_SM_NONE)) {
-        buffer = rpath(fs_ctx, path);
-        ret = lchown(buffer, credp->fc_uid, credp->fc_gid);
-        g_free(buffer);
+        ret = fchownat(dirfd, name, credp->fc_uid, credp->fc_gid,
+                       AT_SYMLINK_NOFOLLOW);
     } else if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
-        buffer = rpath(fs_ctx, path);
-        ret = local_set_xattr(buffer, credp);
-        g_free(buffer);
+        ret = local_set_xattrat(dirfd, name, credp);
     } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
-        return local_set_mapped_file_attr(fs_ctx, path, credp);
+        ret = local_set_mapped_file_attrat(dirfd, name, credp);
     }
+
+    close_preserve_errno(dirfd);
+out:
+    g_free(name);
+    g_free(dirpath);
     return ret;
 }
 
 static int local_utimensat(FsContext *s, V9fsPath *fs_path,
                            const struct timespec *buf)
 {
-    char *buffer;
-    int ret;
-    char *path = fs_path->data;
+    char *dirpath = g_path_get_dirname(fs_path->data);
+    char *name = g_path_get_basename(fs_path->data);
+    int dirfd, ret = -1;
+
+    dirfd = local_opendir_nofollow(s, dirpath);
+    if (dirfd == -1) {
+        goto out;
+    }
 
-    buffer = rpath(s, path);
-    ret = qemu_utimens(buffer, buf);
-    g_free(buffer);
+    ret = utimensat(dirfd, name, buf, AT_SYMLINK_NOFOLLOW);
+    close_preserve_errno(dirfd);
+out:
+    g_free(dirpath);
+    g_free(name);
     return ret;
 }
 
-static int local_remove(FsContext *ctx, const char *path)
+static int local_unlinkat_common(FsContext *ctx, int dirfd, const char *name,
+                                 int flags)
 {
-    int err;
-    struct stat stbuf;
-    char *buffer;
+    int ret = -1;
 
     if (ctx->export_flags & V9FS_SM_MAPPED_FILE) {
-        buffer = rpath(ctx, path);
-        err =  lstat(buffer, &stbuf);
-        g_free(buffer);
-        if (err) {
-            goto err_out;
-        }
-        /*
-         * If directory remove .virtfs_metadata contained in the
-         * directory
-         */
-        if (S_ISDIR(stbuf.st_mode)) {
-            buffer = g_strdup_printf("%s/%s/%s", ctx->fs_root,
-                                     path, VIRTFS_META_DIR);
-            err = remove(buffer);
-            g_free(buffer);
-            if (err < 0 && errno != ENOENT) {
+        int map_dirfd;
+
+        if (flags == AT_REMOVEDIR) {
+            int fd;
+
+            fd = openat(dirfd, name, O_RDONLY | O_DIRECTORY | O_PATH);
+            if (fd == -1) {
+                goto err_out;
+            }
+            /*
+             * If directory remove .virtfs_metadata contained in the
+             * directory
+             */
+            ret = unlinkat(fd, VIRTFS_META_DIR, AT_REMOVEDIR);
+            close_preserve_errno(fd);
+            if (ret < 0 && errno != ENOENT) {
                 /*
                  * We didn't had the .virtfs_metadata file. May be file created
                  * in non-mapped mode ?. Ignore ENOENT.
@@ -972,12 +979,12 @@ static int local_remove(FsContext *ctx, const char *path)
         }
         /*
          * Now remove the name from parent directory
-         * .virtfs_metadata directory
+         * .virtfs_metadata directory.
          */
-        buffer = local_mapped_attr_path(ctx, path);
-        err = remove(buffer);
-        g_free(buffer);
-        if (err < 0 && errno != ENOENT) {
+        map_dirfd = openat_dir(dirfd, VIRTFS_META_DIR);
+        ret = unlinkat(map_dirfd, name, 0);
+        close_preserve_errno(map_dirfd);
+        if (ret < 0 && errno != ENOENT) {
             /*
              * We didn't had the .virtfs_metadata file. May be file created
              * in non-mapped mode ?. Ignore ENOENT.
@@ -986,10 +993,39 @@ static int local_remove(FsContext *ctx, const char *path)
         }
     }
 
-    buffer = rpath(ctx, path);
-    err = remove(buffer);
-    g_free(buffer);
+    ret = unlinkat(dirfd, name, flags);
+err_out:
+    return ret;
+}
+
+static int local_remove(FsContext *ctx, const char *path)
+{
+    struct stat stbuf;
+    char *dirpath = g_path_get_dirname(path);
+    char *name = g_path_get_basename(path);
+    int flags = 0;
+    int dirfd;
+    int err = -1;
+
+    dirfd = local_opendir_nofollow(ctx, dirpath);
+    if (dirfd) {
+        goto out;
+    }
+
+    if (fstatat(dirfd, path, &stbuf, AT_SYMLINK_NOFOLLOW) < 0) {
+        goto err_out;
+    }
+
+    if (S_ISDIR(stbuf.st_mode)) {
+        flags |= AT_REMOVEDIR;
+    }
+
+    err = local_unlinkat_common(ctx, dirfd, name, flags);
 err_out:
+    close_preserve_errno(dirfd);
+out:
+    g_free(name);
+    g_free(dirpath);
     return err;
 }
 
@@ -1013,13 +1049,11 @@ static int local_fsync(FsContext *ctx, int fid_type,
 
 static int local_statfs(FsContext *s, V9fsPath *fs_path, struct statfs *stbuf)
 {
-    char *buffer;
-    int ret;
-    char *path = fs_path->data;
+    int fd, ret;
 
-    buffer = rpath(s, path);
-    ret = statfs(buffer, stbuf);
-    g_free(buffer);
+    fd = local_open_nofollow(s, fs_path->data, O_RDONLY, 0);
+    ret = fstatfs(fd, stbuf);
+    close_preserve_errno(fd);
     return ret;
 }
 
@@ -1071,70 +1105,105 @@ static int local_renameat(FsContext *ctx, V9fsPath *olddir,
                           const char *new_name)
 {
     int ret;
-    V9fsString old_full_name, new_full_name;
+    int odirfd, ndirfd;
+
+    odirfd = local_opendir_nofollow(ctx, olddir->data);
+    if (odirfd == -1) {
+        return -1;
+    }
+
+    ndirfd = local_opendir_nofollow(ctx, newdir->data);
+    if (ndirfd == -1) {
+        close_preserve_errno(odirfd);
+        return -1;
+    }
+
+    ret = renameat(odirfd, old_name, ndirfd, new_name);
+    if (ret < 0) {
+        goto out;
+    }
+
+    if (ctx->export_flags & V9FS_SM_MAPPED_FILE) {
+        int omap_dirfd, nmap_dirfd;
 
-    v9fs_string_init(&old_full_name);
-    v9fs_string_init(&new_full_name);
+        ret = mkdirat(ndirfd, VIRTFS_META_DIR, 0700);
+        if (ret < 0 && errno != EEXIST) {
+            goto err_undo_rename;
+        }
+
+        omap_dirfd = openat_dir(odirfd, VIRTFS_META_DIR);
+        if (omap_dirfd == -1) {
+            goto err;
+        }
+
+        nmap_dirfd = openat_dir(ndirfd, VIRTFS_META_DIR);
+        if (nmap_dirfd == -1) {
+            close_preserve_errno(omap_dirfd);
+            goto err;
+        }
 
-    v9fs_string_sprintf(&old_full_name, "%s/%s", olddir->data, old_name);
-    v9fs_string_sprintf(&new_full_name, "%s/%s", newdir->data, new_name);
+        /* rename the .virtfs_metadata files */
+        ret = renameat(omap_dirfd, old_name, nmap_dirfd, new_name);
+        close_preserve_errno(nmap_dirfd);
+        close_preserve_errno(omap_dirfd);
+        if (ret < 0 && errno != ENOENT) {
+            goto err_undo_rename;
+        }
 
-    ret = local_rename(ctx, old_full_name.data, new_full_name.data);
-    v9fs_string_free(&old_full_name);
-    v9fs_string_free(&new_full_name);
+        ret = 0;
+    }
+    goto out;
+
+err:
+    ret = -1;
+err_undo_rename:
+    renameat_preserve_errno(ndirfd, new_name, odirfd, old_name);
+out:
+    close_preserve_errno(ndirfd);
+    close_preserve_errno(odirfd);
     return ret;
 }
 
+static void v9fs_path_init_dirname(V9fsPath *path, const char *str)
+{
+    path->data = g_path_get_dirname(str);
+    path->size = strlen(path->data) + 1;
+}
+
+static int local_rename(FsContext *ctx, const char *oldpath,
+                        const char *newpath)
+{
+    int err;
+    char *oname = g_path_get_basename(oldpath);
+    char *nname = g_path_get_basename(newpath);
+    V9fsPath olddir, newdir;
+
+    v9fs_path_init_dirname(&olddir, oldpath);
+    v9fs_path_init_dirname(&newdir, newpath);
+
+    err = local_renameat(ctx, &olddir, oname, &newdir, nname);
+
+    v9fs_path_free(&newdir);
+    v9fs_path_free(&olddir);
+    g_free(nname);
+    g_free(oname);
+
+    return err;
+}
+
 static int local_unlinkat(FsContext *ctx, V9fsPath *dir,
                           const char *name, int flags)
 {
     int ret;
-    V9fsString fullname;
-    char *buffer;
+    int dirfd;
 
-    v9fs_string_init(&fullname);
-
-    v9fs_string_sprintf(&fullname, "%s/%s", dir->data, name);
-    if (ctx->export_flags & V9FS_SM_MAPPED_FILE) {
-        if (flags == AT_REMOVEDIR) {
-            /*
-             * If directory remove .virtfs_metadata contained in the
-             * directory
-             */
-            buffer = g_strdup_printf("%s/%s/%s", ctx->fs_root,
-                                     fullname.data, VIRTFS_META_DIR);
-            ret = remove(buffer);
-            g_free(buffer);
-            if (ret < 0 && errno != ENOENT) {
-                /*
-                 * We didn't had the .virtfs_metadata file. May be file created
-                 * in non-mapped mode ?. Ignore ENOENT.
-                 */
-                goto err_out;
-            }
-        }
-        /*
-         * Now remove the name from parent directory
-         * .virtfs_metadata directory.
-         */
-        buffer = local_mapped_attr_path(ctx, fullname.data);
-        ret = remove(buffer);
-        g_free(buffer);
-        if (ret < 0 && errno != ENOENT) {
-            /*
-             * We didn't had the .virtfs_metadata file. May be file created
-             * in non-mapped mode ?. Ignore ENOENT.
-             */
-            goto err_out;
-        }
+    dirfd = local_opendir_nofollow(ctx, dir->data);
+    if (dirfd == -1) {
+        return -1;
     }
-    /* Remove the name finally */
-    buffer = rpath(ctx, fullname.data);
-    ret = remove(buffer);
-    g_free(buffer);
 
-err_out:
-    v9fs_string_free(&fullname);
+    ret = local_unlinkat_common(ctx, dirfd, name, flags);
+    close_preserve_errno(dirfd);
     return ret;
 }
 
@@ -1168,8 +1237,31 @@ static int local_ioc_getversion(FsContext *ctx, V9fsPath *path,
 
 static int local_init(FsContext *ctx)
 {
-    int err = 0;
     struct statfs stbuf;
+    LocalData *data = g_malloc(sizeof(*data));
+
+    data->mountfd = open(ctx->fs_root, O_DIRECTORY | O_RDONLY);
+    if (data->mountfd == -1) {
+        goto err;
+    }
+
+#ifdef FS_IOC_GETVERSION
+    /*
+     * use ioc_getversion only if the ioctl is definied
+     */
+    if (fstatfs(data->mountfd, &stbuf) < 0) {
+        close_preserve_errno(data->mountfd);
+        goto err;
+    }
+    switch (stbuf.f_type) {
+    case EXT2_SUPER_MAGIC:
+    case BTRFS_SUPER_MAGIC:
+    case REISERFS_SUPER_MAGIC:
+    case XFS_SUPER_MAGIC:
+        ctx->exops.get_st_gen = local_ioc_getversion;
+        break;
+    }
+#endif
 
     if (ctx->export_flags & V9FS_SM_PASSTHROUGH) {
         ctx->xops = passthrough_xattr_ops;
@@ -1185,29 +1277,28 @@ static int local_init(FsContext *ctx)
         ctx->xops = passthrough_xattr_ops;
     }
     ctx->export_flags |= V9FS_PATHNAME_FSCONTEXT;
-#ifdef FS_IOC_GETVERSION
-    /*
-     * use ioc_getversion only if the iocl is definied
-     */
-    err = statfs(ctx->fs_root, &stbuf);
-    if (!err) {
-        switch (stbuf.f_type) {
-        case EXT2_SUPER_MAGIC:
-        case BTRFS_SUPER_MAGIC:
-        case REISERFS_SUPER_MAGIC:
-        case XFS_SUPER_MAGIC:
-            ctx->exops.get_st_gen = local_ioc_getversion;
-            break;
-        }
-    }
-#endif
-    return err;
+
+    ctx->private = data;
+    return 0;
+
+err:
+    g_free(data);
+    return -1;
+}
+
+static void local_cleanup(FsContext *ctx)
+{
+    LocalData *data = ctx->private;
+
+    close(data->mountfd);
+    g_free(data);
 }
 
 static int local_parse_opts(QemuOpts *opts, struct FsDriverEntry *fse)
 {
     const char *sec_model = qemu_opt_get(opts, "security_model");
     const char *path = qemu_opt_get(opts, "path");
+    Error *err = NULL;
 
     if (!sec_model) {
         error_report("Security model not specified, local fs needs security model");
@@ -1236,6 +1327,13 @@ static int local_parse_opts(QemuOpts *opts, struct FsDriverEntry *fse)
         error_report("fsdev: No path specified");
         return -1;
     }
+
+    fsdev_throttle_parse_opts(opts, &fse->fst, &err);
+    if (err) {
+        error_reportf_err(err, "Throttle configuration is not valid: ");
+        return -1;
+    }
+
     fse->path = g_strdup(path);
 
     return 0;
@@ -1244,6 +1342,7 @@ static int local_parse_opts(QemuOpts *opts, struct FsDriverEntry *fse)
 FileOperations local_ops = {
     .parse_opts = local_parse_opts,
     .init  = local_init,
+    .cleanup = local_cleanup,
     .lstat = local_lstat,
     .readlink = local_readlink,
     .close = local_close,
diff --git a/hw/9pfs/9p-local.h b/hw/9pfs/9p-local.h
new file mode 100644
index 0000000000..32c72749d9
--- /dev/null
+++ b/hw/9pfs/9p-local.h
@@ -0,0 +1,20 @@
+/*
+ * 9p local backend utilities
+ *
+ * Copyright IBM, Corp. 2017
+ *
+ * Authors:
+ *  Greg Kurz <groug@kaod.org>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#ifndef QEMU_9P_LOCAL_H
+#define QEMU_9P_LOCAL_H
+
+int local_open_nofollow(FsContext *fs_ctx, const char *path, int flags,
+                        mode_t mode);
+int local_opendir_nofollow(FsContext *fs_ctx, const char *path);
+
+#endif
diff --git a/hw/9pfs/9p-posix-acl.c b/hw/9pfs/9p-posix-acl.c
index ec003181cd..bbf89064f7 100644
--- a/hw/9pfs/9p-posix-acl.c
+++ b/hw/9pfs/9p-posix-acl.c
@@ -25,13 +25,7 @@
 static ssize_t mp_pacl_getxattr(FsContext *ctx, const char *path,
                                 const char *name, void *value, size_t size)
 {
-    char *buffer;
-    ssize_t ret;
-
-    buffer = rpath(ctx, path);
-    ret = lgetxattr(buffer, MAP_ACL_ACCESS, value, size);
-    g_free(buffer);
-    return ret;
+    return local_getxattr_nofollow(ctx, path, MAP_ACL_ACCESS, value, size);
 }
 
 static ssize_t mp_pacl_listxattr(FsContext *ctx, const char *path,
@@ -56,23 +50,16 @@ static ssize_t mp_pacl_listxattr(FsContext *ctx, const char *path,
 static int mp_pacl_setxattr(FsContext *ctx, const char *path, const char *name,
                             void *value, size_t size, int flags)
 {
-    char *buffer;
-    int ret;
-
-    buffer = rpath(ctx, path);
-    ret = lsetxattr(buffer, MAP_ACL_ACCESS, value, size, flags);
-    g_free(buffer);
-    return ret;
+    return local_setxattr_nofollow(ctx, path, MAP_ACL_ACCESS, value, size,
+                                   flags);
 }
 
 static int mp_pacl_removexattr(FsContext *ctx,
                                const char *path, const char *name)
 {
     int ret;
-    char *buffer;
 
-    buffer = rpath(ctx, path);
-    ret  = lremovexattr(buffer, MAP_ACL_ACCESS);
+    ret = local_removexattr_nofollow(ctx, path, MAP_ACL_ACCESS);
     if (ret == -1 && errno == ENODATA) {
         /*
          * We don't get ENODATA error when trying to remove a
@@ -82,20 +69,13 @@ static int mp_pacl_removexattr(FsContext *ctx,
         errno = 0;
         ret = 0;
     }
-    g_free(buffer);
     return ret;
 }
 
 static ssize_t mp_dacl_getxattr(FsContext *ctx, const char *path,
                                 const char *name, void *value, size_t size)
 {
-    char *buffer;
-    ssize_t ret;
-
-    buffer = rpath(ctx, path);
-    ret = lgetxattr(buffer, MAP_ACL_DEFAULT, value, size);
-    g_free(buffer);
-    return ret;
+    return local_getxattr_nofollow(ctx, path, MAP_ACL_DEFAULT, value, size);
 }
 
 static ssize_t mp_dacl_listxattr(FsContext *ctx, const char *path,
@@ -120,23 +100,16 @@ static ssize_t mp_dacl_listxattr(FsContext *ctx, const char *path,
 static int mp_dacl_setxattr(FsContext *ctx, const char *path, const char *name,
                             void *value, size_t size, int flags)
 {
-    char *buffer;
-    int ret;
-
-    buffer = rpath(ctx, path);
-    ret = lsetxattr(buffer, MAP_ACL_DEFAULT, value, size, flags);
-    g_free(buffer);
-    return ret;
+    return local_setxattr_nofollow(ctx, path, MAP_ACL_DEFAULT, value, size,
+                                   flags);
 }
 
 static int mp_dacl_removexattr(FsContext *ctx,
                                const char *path, const char *name)
 {
     int ret;
-    char *buffer;
 
-    buffer = rpath(ctx, path);
-    ret  = lremovexattr(buffer, MAP_ACL_DEFAULT);
+    ret = local_removexattr_nofollow(ctx, path, MAP_ACL_DEFAULT);
     if (ret == -1 && errno == ENODATA) {
         /*
          * We don't get ENODATA error when trying to remove a
@@ -146,7 +119,6 @@ static int mp_dacl_removexattr(FsContext *ctx,
         errno = 0;
         ret = 0;
     }
-    g_free(buffer);
     return ret;
 }
 
diff --git a/hw/9pfs/9p-util.c b/hw/9pfs/9p-util.c
new file mode 100644
index 0000000000..fdb4d57376
--- /dev/null
+++ b/hw/9pfs/9p-util.c
@@ -0,0 +1,69 @@
+/*
+ * 9p utilities
+ *
+ * Copyright IBM, Corp. 2017
+ *
+ * Authors:
+ *  Greg Kurz <groug@kaod.org>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/xattr.h"
+#include "9p-util.h"
+
+int relative_openat_nofollow(int dirfd, const char *path, int flags,
+                             mode_t mode)
+{
+    int fd;
+
+    fd = dup(dirfd);
+    if (fd == -1) {
+        return -1;
+    }
+
+    while (*path) {
+        const char *c;
+        int next_fd;
+        char *head;
+
+        /* Only relative paths without consecutive slashes */
+        assert(path[0] != '/');
+
+        head = g_strdup(path);
+        c = strchr(path, '/');
+        if (c) {
+            head[c - path] = 0;
+            next_fd = openat_dir(fd, head);
+        } else {
+            next_fd = openat_file(fd, head, flags, mode);
+        }
+        g_free(head);
+        if (next_fd == -1) {
+            close_preserve_errno(fd);
+            return -1;
+        }
+        close(fd);
+        fd = next_fd;
+
+        if (!c) {
+            break;
+        }
+        path = c + 1;
+    }
+
+    return fd;
+}
+
+ssize_t fgetxattrat_nofollow(int dirfd, const char *filename, const char *name,
+                             void *value, size_t size)
+{
+    char *proc_path = g_strdup_printf("/proc/self/fd/%d/%s", dirfd, filename);
+    int ret;
+
+    ret = lgetxattr(proc_path, name, value, size);
+    g_free(proc_path);
+    return ret;
+}
diff --git a/hw/9pfs/9p-util.h b/hw/9pfs/9p-util.h
new file mode 100644
index 0000000000..091f3ce88e
--- /dev/null
+++ b/hw/9pfs/9p-util.h
@@ -0,0 +1,54 @@
+/*
+ * 9p utilities
+ *
+ * Copyright IBM, Corp. 2017
+ *
+ * Authors:
+ *  Greg Kurz <groug@kaod.org>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#ifndef QEMU_9P_UTIL_H
+#define QEMU_9P_UTIL_H
+
+static inline void close_preserve_errno(int fd)
+{
+    int serrno = errno;
+    close(fd);
+    errno = serrno;
+}
+
+static inline int openat_dir(int dirfd, const char *name)
+{
+    return openat(dirfd, name, O_DIRECTORY | O_RDONLY | O_PATH);
+}
+
+static inline int openat_file(int dirfd, const char *name, int flags,
+                              mode_t mode)
+{
+    int fd, serrno, ret;
+
+    fd = openat(dirfd, name, flags | O_NOFOLLOW | O_NOCTTY | O_NONBLOCK,
+                mode);
+    if (fd == -1) {
+        return -1;
+    }
+
+    serrno = errno;
+    /* O_NONBLOCK was only needed to open the file. Let's drop it. */
+    ret = fcntl(fd, F_SETFL, flags);
+    assert(!ret);
+    errno = serrno;
+    return fd;
+}
+
+int relative_openat_nofollow(int dirfd, const char *path, int flags,
+                             mode_t mode);
+ssize_t fgetxattrat_nofollow(int dirfd, const char *path, const char *name,
+                             void *value, size_t size);
+int fsetxattrat_nofollow(int dirfd, const char *path, const char *name,
+                         void *value, size_t size, int flags);
+
+#endif
diff --git a/hw/9pfs/9p-xattr-user.c b/hw/9pfs/9p-xattr-user.c
index f87530c8b5..2c90817b75 100644
--- a/hw/9pfs/9p-xattr-user.c
+++ b/hw/9pfs/9p-xattr-user.c
@@ -20,9 +20,6 @@
 static ssize_t mp_user_getxattr(FsContext *ctx, const char *path,
                                 const char *name, void *value, size_t size)
 {
-    char *buffer;
-    ssize_t ret;
-
     if (strncmp(name, "user.virtfs.", 12) == 0) {
         /*
          * Don't allow fetch of user.virtfs namesapce
@@ -31,10 +28,7 @@ static ssize_t mp_user_getxattr(FsContext *ctx, const char *path,
         errno = ENOATTR;
         return -1;
     }
-    buffer = rpath(ctx, path);
-    ret = lgetxattr(buffer, name, value, size);
-    g_free(buffer);
-    return ret;
+    return local_getxattr_nofollow(ctx, path, name, value, size);
 }
 
 static ssize_t mp_user_listxattr(FsContext *ctx, const char *path,
@@ -73,9 +67,6 @@ static ssize_t mp_user_listxattr(FsContext *ctx, const char *path,
 static int mp_user_setxattr(FsContext *ctx, const char *path, const char *name,
                             void *value, size_t size, int flags)
 {
-    char *buffer;
-    int ret;
-
     if (strncmp(name, "user.virtfs.", 12) == 0) {
         /*
          * Don't allow fetch of user.virtfs namesapce
@@ -84,18 +75,12 @@ static int mp_user_setxattr(FsContext *ctx, const char *path, const char *name,
         errno = EACCES;
         return -1;
     }
-    buffer = rpath(ctx, path);
-    ret = lsetxattr(buffer, name, value, size, flags);
-    g_free(buffer);
-    return ret;
+    return local_setxattr_nofollow(ctx, path, name, value, size, flags);
 }
 
 static int mp_user_removexattr(FsContext *ctx,
                                const char *path, const char *name)
 {
-    char *buffer;
-    int ret;
-
     if (strncmp(name, "user.virtfs.", 12) == 0) {
         /*
          * Don't allow fetch of user.virtfs namesapce
@@ -104,10 +89,7 @@ static int mp_user_removexattr(FsContext *ctx,
         errno = EACCES;
         return -1;
     }
-    buffer = rpath(ctx, path);
-    ret = lremovexattr(buffer, name);
-    g_free(buffer);
-    return ret;
+    return local_removexattr_nofollow(ctx, path, name);
 }
 
 XattrOperations mapped_user_xattr = {
diff --git a/hw/9pfs/9p-xattr.c b/hw/9pfs/9p-xattr.c
index 5d8595ed93..eec160b3c2 100644
--- a/hw/9pfs/9p-xattr.c
+++ b/hw/9pfs/9p-xattr.c
@@ -15,6 +15,8 @@
 #include "9p.h"
 #include "fsdev/file-op-9p.h"
 #include "9p-xattr.h"
+#include "9p-util.h"
+#include "9p-local.h"
 
 
 static XattrOperations *get_xattr_operations(XattrOperations **h,
@@ -58,6 +60,16 @@ ssize_t pt_listxattr(FsContext *ctx, const char *path,
     return name_size;
 }
 
+static ssize_t flistxattrat_nofollow(int dirfd, const char *filename,
+                                     char *list, size_t size)
+{
+    char *proc_path = g_strdup_printf("/proc/self/fd/%d/%s", dirfd, filename);
+    int ret;
+
+    ret = llistxattr(proc_path, list, size);
+    g_free(proc_path);
+    return ret;
+}
 
 /*
  * Get the list and pass to each layer to find out whether
@@ -67,24 +79,37 @@ ssize_t v9fs_list_xattr(FsContext *ctx, const char *path,
                         void *value, size_t vsize)
 {
     ssize_t size = 0;
-    char *buffer;
     void *ovalue = value;
     XattrOperations *xops;
     char *orig_value, *orig_value_start;
     ssize_t xattr_len, parsed_len = 0, attr_len;
+    char *dirpath, *name;
+    int dirfd;
 
     /* Get the actual len */
-    buffer = rpath(ctx, path);
-    xattr_len = llistxattr(buffer, value, 0);
+    dirpath = g_path_get_dirname(path);
+    dirfd = local_opendir_nofollow(ctx, dirpath);
+    g_free(dirpath);
+    if (dirfd == -1) {
+        return -1;
+    }
+
+    name = g_path_get_basename(path);
+    xattr_len = flistxattrat_nofollow(dirfd, name, value, 0);
     if (xattr_len <= 0) {
-        g_free(buffer);
+        g_free(name);
+        close_preserve_errno(dirfd);
         return xattr_len;
     }
 
     /* Now fetch the xattr and find the actual size */
     orig_value = g_malloc(xattr_len);
-    xattr_len = llistxattr(buffer, orig_value, xattr_len);
-    g_free(buffer);
+    xattr_len = flistxattrat_nofollow(dirfd, name, orig_value, xattr_len);
+    g_free(name);
+    close_preserve_errno(dirfd);
+    if (xattr_len < 0) {
+        return -1;
+    }
 
     /* store the orig pointer */
     orig_value_start = orig_value;
@@ -143,6 +168,135 @@ int v9fs_remove_xattr(FsContext *ctx,
 
 }
 
+ssize_t local_getxattr_nofollow(FsContext *ctx, const char *path,
+                                const char *name, void *value, size_t size)
+{
+    char *dirpath = g_path_get_dirname(path);
+    char *filename = g_path_get_basename(path);
+    int dirfd;
+    ssize_t ret = -1;
+
+    dirfd = local_opendir_nofollow(ctx, dirpath);
+    if (dirfd == -1) {
+        goto out;
+    }
+
+    ret = fgetxattrat_nofollow(dirfd, filename, name, value, size);
+    close_preserve_errno(dirfd);
+out:
+    g_free(dirpath);
+    g_free(filename);
+    return ret;
+}
+
+ssize_t pt_getxattr(FsContext *ctx, const char *path, const char *name,
+                    void *value, size_t size)
+{
+    return local_getxattr_nofollow(ctx, path, name, value, size);
+}
+
+int fsetxattrat_nofollow(int dirfd, const char *filename, const char *name,
+                         void *value, size_t size, int flags)
+{
+    char *proc_path = g_strdup_printf("/proc/self/fd/%d/%s", dirfd, filename);
+    int ret;
+
+    ret = lsetxattr(proc_path, name, value, size, flags);
+    g_free(proc_path);
+    return ret;
+}
+
+ssize_t local_setxattr_nofollow(FsContext *ctx, const char *path,
+                                const char *name, void *value, size_t size,
+                                int flags)
+{
+    char *dirpath = g_path_get_dirname(path);
+    char *filename = g_path_get_basename(path);
+    int dirfd;
+    ssize_t ret = -1;
+
+    dirfd = local_opendir_nofollow(ctx, dirpath);
+    if (dirfd == -1) {
+        goto out;
+    }
+
+    ret = fsetxattrat_nofollow(dirfd, filename, name, value, size, flags);
+    close_preserve_errno(dirfd);
+out:
+    g_free(dirpath);
+    g_free(filename);
+    return ret;
+}
+
+int pt_setxattr(FsContext *ctx, const char *path, const char *name, void *value,
+                size_t size, int flags)
+{
+    return local_setxattr_nofollow(ctx, path, name, value, size, flags);
+}
+
+static ssize_t fremovexattrat_nofollow(int dirfd, const char *filename,
+                                       const char *name)
+{
+    char *proc_path = g_strdup_printf("/proc/self/fd/%d/%s", dirfd, filename);
+    int ret;
+
+    ret = lremovexattr(proc_path, name);
+    g_free(proc_path);
+    return ret;
+}
+
+ssize_t local_removexattr_nofollow(FsContext *ctx, const char *path,
+                                   const char *name)
+{
+    char *dirpath = g_path_get_dirname(path);
+    char *filename = g_path_get_basename(path);
+    int dirfd;
+    ssize_t ret = -1;
+
+    dirfd = local_opendir_nofollow(ctx, dirpath);
+    if (dirfd == -1) {
+        goto out;
+    }
+
+    ret = fremovexattrat_nofollow(dirfd, filename, name);
+    close_preserve_errno(dirfd);
+out:
+    g_free(dirpath);
+    g_free(filename);
+    return ret;
+}
+
+int pt_removexattr(FsContext *ctx, const char *path, const char *name)
+{
+    return local_removexattr_nofollow(ctx, path, name);
+}
+
+ssize_t notsup_getxattr(FsContext *ctx, const char *path, const char *name,
+                        void *value, size_t size)
+{
+    errno = ENOTSUP;
+    return -1;
+}
+
+int notsup_setxattr(FsContext *ctx, const char *path, const char *name,
+                    void *value, size_t size, int flags)
+{
+    errno = ENOTSUP;
+    return -1;
+}
+
+ssize_t notsup_listxattr(FsContext *ctx, const char *path, char *name,
+                         void *value, size_t size)
+{
+    return 0;
+}
+
+int notsup_removexattr(FsContext *ctx, const char *path, const char *name)
+{
+    errno = ENOTSUP;
+    return -1;
+}
+
 XattrOperations *mapped_xattr_ops[] = {
     &mapped_user_xattr,
     &mapped_pacl_xattr,
diff --git a/hw/9pfs/9p-xattr.h b/hw/9pfs/9p-xattr.h
index a853ea641c..0d83996575 100644
--- a/hw/9pfs/9p-xattr.h
+++ b/hw/9pfs/9p-xattr.h
@@ -29,6 +29,13 @@ typedef struct xattr_operations
                        const char *path, const char *name);
 } XattrOperations;
 
+ssize_t local_getxattr_nofollow(FsContext *ctx, const char *path,
+                                const char *name, void *value, size_t size);
+ssize_t local_setxattr_nofollow(FsContext *ctx, const char *path,
+                                const char *name, void *value, size_t size,
+                                int flags);
+ssize_t local_removexattr_nofollow(FsContext *ctx, const char *path,
+                                   const char *name);
 
 extern XattrOperations mapped_user_xattr;
 extern XattrOperations passthrough_user_xattr;
@@ -49,73 +56,21 @@ ssize_t v9fs_list_xattr(FsContext *ctx, const char *path, void *value,
 int v9fs_set_xattr(FsContext *ctx, const char *path, const char *name,
                           void *value, size_t size, int flags);
 int v9fs_remove_xattr(FsContext *ctx, const char *path, const char *name);
+
 ssize_t pt_listxattr(FsContext *ctx, const char *path, char *name, void *value,
                      size_t size);
-
-static inline ssize_t pt_getxattr(FsContext *ctx, const char *path,
-                                  const char *name, void *value, size_t size)
-{
-    char *buffer;
-    ssize_t ret;
-
-    buffer = rpath(ctx, path);
-    ret = lgetxattr(buffer, name, value, size);
-    g_free(buffer);
-    return ret;
-}
-
-static inline int pt_setxattr(FsContext *ctx, const char *path,
-                              const char *name, void *value,
-                              size_t size, int flags)
-{
-    char *buffer;
-    int ret;
-
-    buffer = rpath(ctx, path);
-    ret = lsetxattr(buffer, name, value, size, flags);
-    g_free(buffer);
-    return ret;
-}
-
-static inline int pt_removexattr(FsContext *ctx,
-                                 const char *path, const char *name)
-{
-    char *buffer;
-    int ret;
-
-    buffer = rpath(ctx, path);
-    ret = lremovexattr(path, name);
-    g_free(buffer);
-    return ret;
-}
-
-static inline ssize_t notsup_getxattr(FsContext *ctx, const char *path,
-                                      const char *name, void *value,
-                                      size_t size)
-{
-    errno = ENOTSUP;
-    return -1;
-}
-
-static inline int notsup_setxattr(FsContext *ctx, const char *path,
-                                  const char *name, void *value,
-                                  size_t size, int flags)
-{
-    errno = ENOTSUP;
-    return -1;
-}
-
-static inline ssize_t notsup_listxattr(FsContext *ctx, const char *path,
-                                       char *name, void *value, size_t size)
-{
-    return 0;
-}
-
-static inline int notsup_removexattr(FsContext *ctx,
-                                     const char *path, const char *name)
-{
-    errno = ENOTSUP;
-    return -1;
-}
+ssize_t pt_getxattr(FsContext *ctx, const char *path, const char *name,
+                    void *value, size_t size);
+int pt_setxattr(FsContext *ctx, const char *path, const char *name, void *value,
+                size_t size, int flags);
+int pt_removexattr(FsContext *ctx, const char *path, const char *name);
+
+ssize_t notsup_getxattr(FsContext *ctx, const char *path, const char *name,
+                        void *value, size_t size);
+int notsup_setxattr(FsContext *ctx, const char *path, const char *name,
+                    void *value, size_t size, int flags);
+ssize_t notsup_listxattr(FsContext *ctx, const char *path, char *name,
+                         void *value, size_t size);
+int notsup_removexattr(FsContext *ctx, const char *path, const char *name);
 
 #endif
diff --git a/hw/9pfs/9p.c b/hw/9pfs/9p.c
index 3af1c93dc8..76c9247c77 100644
--- a/hw/9pfs/9p.c
+++ b/hw/9pfs/9p.c
@@ -3010,7 +3010,6 @@ out_nofid:
  */
 static void coroutine_fn v9fs_lock(void *opaque)
 {
-    int8_t status;
     V9fsFlock flock;
     size_t offset = 7;
     struct stat stbuf;
@@ -3018,7 +3017,6 @@ static void coroutine_fn v9fs_lock(void *opaque)
     int32_t fid, err = 0;
     V9fsPDU *pdu = opaque;
 
-    status = P9_LOCK_ERROR;
     v9fs_string_init(&flock.client_id);
     err = pdu_unmarshal(pdu, offset, "dbdqqds", &fid, &flock.type,
                         &flock.flags, &flock.start, &flock.length,
@@ -3044,15 +3042,15 @@ static void coroutine_fn v9fs_lock(void *opaque)
     if (err < 0) {
         goto out;
     }
-    status = P9_LOCK_SUCCESS;
+    err = pdu_marshal(pdu, offset, "b", P9_LOCK_SUCCESS);
+    if (err < 0) {
+        goto out;
+    }
+    err += offset;
+    trace_v9fs_lock_return(pdu->tag, pdu->id, P9_LOCK_SUCCESS);
 out:
     put_fid(pdu, fidp);
 out_nofid:
-    err = pdu_marshal(pdu, offset, "b", status);
-    if (err > 0) {
-        err += offset;
-    }
-    trace_v9fs_lock_return(pdu->tag, pdu->id, status);
     pdu_complete(pdu, err);
     v9fs_string_free(&flock.client_id);
 }
@@ -3531,6 +3529,10 @@ int v9fs_device_realize_common(V9fsState *s, Error **errp)
         error_setg(errp, "share path %s is not a directory", fse->path);
         goto out;
     }
+
+    s->ctx.fst = &fse->fst;
+    fsdev_throttle_init(s->ctx.fst);
+
     v9fs_path_free(&path);
 
     rc = 0;
@@ -3551,6 +3553,7 @@ void v9fs_device_unrealize_common(V9fsState *s, Error **errp)
     if (s->ops->cleanup) {
         s->ops->cleanup(&s->ctx);
     }
+    fsdev_throttle_cleanup(s->ctx.fst);
     g_free(s->tag);
     g_free(s->ctx.fs_root);
 }
diff --git a/hw/9pfs/Makefile.objs b/hw/9pfs/Makefile.objs
index da0ae0cfdb..32197e6671 100644
--- a/hw/9pfs/Makefile.objs
+++ b/hw/9pfs/Makefile.objs
@@ -1,4 +1,4 @@
-common-obj-y  = 9p.o
+common-obj-y  = 9p.o 9p-util.o
 common-obj-y += 9p-local.o 9p-xattr.o
 common-obj-y += 9p-xattr-user.o 9p-posix-acl.o
 common-obj-y += coth.o cofs.o codir.o cofile.o
diff --git a/hw/9pfs/cofile.c b/hw/9pfs/cofile.c
index 120e267108..88791bc327 100644
--- a/hw/9pfs/cofile.c
+++ b/hw/9pfs/cofile.c
@@ -247,6 +247,7 @@ int coroutine_fn v9fs_co_pwritev(V9fsPDU *pdu, V9fsFidState *fidp,
     if (v9fs_request_cancelled(pdu)) {
         return -EINTR;
     }
+    fsdev_co_throttle_request(s->ctx.fst, true, iov, iovcnt);
     v9fs_co_run_in_worker(
         {
             err = s->ops->pwritev(&s->ctx, &fidp->fs, iov, iovcnt, offset);
@@ -266,6 +267,7 @@ int coroutine_fn v9fs_co_preadv(V9fsPDU *pdu, V9fsFidState *fidp,
     if (v9fs_request_cancelled(pdu)) {
         return -EINTR;
     }
+    fsdev_co_throttle_request(s->ctx.fst, false, iov, iovcnt);
     v9fs_co_run_in_worker(
         {
             err = s->ops->preadv(&s->ctx, &fidp->fs, iov, iovcnt, offset);
diff --git a/hw/acpi/tco.c b/hw/acpi/tco.c
index 8ce7daf23a..b4adac88cd 100644
--- a/hw/acpi/tco.c
+++ b/hw/acpi/tco.c
@@ -49,6 +49,7 @@ static inline void tco_timer_reload(TCOIORegs *tr)
 static inline void tco_timer_stop(TCOIORegs *tr)
 {
     tr->expire_time = -1;
+    timer_del(tr->tco_timer);
 }
 
 static void tco_timer_expired(void *opaque)
diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c
index 0c9ca7bfa0..c8a11f2b53 100644
--- a/hw/arm/armv7m.c
+++ b/hw/arm/armv7m.c
@@ -8,6 +8,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "hw/arm/armv7m.h"
 #include "qapi/error.h"
 #include "qemu-common.h"
 #include "cpu.h"
@@ -17,147 +18,260 @@
 #include "elf.h"
 #include "sysemu/qtest.h"
 #include "qemu/error-report.h"
+#include "exec/address-spaces.h"
 
 /* Bitbanded IO.  Each word corresponds to a single bit.  */
 
 /* Get the byte address of the real memory for a bitband access.  */
-static inline uint32_t bitband_addr(void * opaque, uint32_t addr)
+static inline hwaddr bitband_addr(BitBandState *s, hwaddr offset)
 {
-    uint32_t res;
-
-    res = *(uint32_t *)opaque;
-    res |= (addr & 0x1ffffff) >> 5;
-    return res;
-
+    return s->base | (offset & 0x1ffffff) >> 5;
 }
 
-static uint32_t bitband_readb(void *opaque, hwaddr offset)
+static MemTxResult bitband_read(void *opaque, hwaddr offset,
+                                uint64_t *data, unsigned size, MemTxAttrs attrs)
 {
-    uint8_t v;
-    cpu_physical_memory_read(bitband_addr(opaque, offset), &v, 1);
-    return (v & (1 << ((offset >> 2) & 7))) != 0;
+    BitBandState *s = opaque;
+    uint8_t buf[4];
+    MemTxResult res;
+    int bitpos, bit;
+    hwaddr addr;
+
+    assert(size <= 4);
+
+    /* Find address in underlying memory and round down to multiple of size */
+    addr = bitband_addr(s, offset) & (-size);
+    res = address_space_read(s->source_as, addr, attrs, buf, size);
+    if (res) {
+        return res;
+    }
+    /* Bit position in the N bytes read... */
+    bitpos = (offset >> 2) & ((size * 8) - 1);
+    /* ...converted to byte in buffer and bit in byte */
+    bit = (buf[bitpos >> 3] >> (bitpos & 7)) & 1;
+    *data = bit;
+    return MEMTX_OK;
 }
 
-static void bitband_writeb(void *opaque, hwaddr offset,
-                           uint32_t value)
+static MemTxResult bitband_write(void *opaque, hwaddr offset, uint64_t value,
+                                 unsigned size, MemTxAttrs attrs)
 {
-    uint32_t addr;
-    uint8_t mask;
-    uint8_t v;
-    addr = bitband_addr(opaque, offset);
-    mask = (1 << ((offset >> 2) & 7));
-    cpu_physical_memory_read(addr, &v, 1);
-    if (value & 1)
-        v |= mask;
-    else
-        v &= ~mask;
-    cpu_physical_memory_write(addr, &v, 1);
+    BitBandState *s = opaque;
+    uint8_t buf[4];
+    MemTxResult res;
+    int bitpos, bit;
+    hwaddr addr;
+
+    assert(size <= 4);
+
+    /* Find address in underlying memory and round down to multiple of size */
+    addr = bitband_addr(s, offset) & (-size);
+    res = address_space_read(s->source_as, addr, attrs, buf, size);
+    if (res) {
+        return res;
+    }
+    /* Bit position in the N bytes read... */
+    bitpos = (offset >> 2) & ((size * 8) - 1);
+    /* ...converted to byte in buffer and bit in byte */
+    bit = 1 << (bitpos & 7);
+    if (value & 1) {
+        buf[bitpos >> 3] |= bit;
+    } else {
+        buf[bitpos >> 3] &= ~bit;
+    }
+    return address_space_write(s->source_as, addr, attrs, buf, size);
 }
 
-static uint32_t bitband_readw(void *opaque, hwaddr offset)
+static const MemoryRegionOps bitband_ops = {
+    .read_with_attrs = bitband_read,
+    .write_with_attrs = bitband_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+    .impl.min_access_size = 1,
+    .impl.max_access_size = 4,
+    .valid.min_access_size = 1,
+    .valid.max_access_size = 4,
+};
+
+static void bitband_init(Object *obj)
 {
-    uint32_t addr;
-    uint16_t mask;
-    uint16_t v;
-    addr = bitband_addr(opaque, offset) & ~1;
-    mask = (1 << ((offset >> 2) & 15));
-    mask = tswap16(mask);
-    cpu_physical_memory_read(addr, &v, 2);
-    return (v & mask) != 0;
+    BitBandState *s = BITBAND(obj);
+    SysBusDevice *dev = SYS_BUS_DEVICE(obj);
+
+    object_property_add_link(obj, "source-memory",
+                             TYPE_MEMORY_REGION,
+                             (Object **)&s->source_memory,
+                             qdev_prop_allow_set_link_before_realize,
+                             OBJ_PROP_LINK_UNREF_ON_RELEASE,
+                             &error_abort);
+    memory_region_init_io(&s->iomem, obj, &bitband_ops, s,
+                          "bitband", 0x02000000);
+    sysbus_init_mmio(dev, &s->iomem);
 }
 
-static void bitband_writew(void *opaque, hwaddr offset,
-                           uint32_t value)
+static void bitband_realize(DeviceState *dev, Error **errp)
 {
-    uint32_t addr;
-    uint16_t mask;
-    uint16_t v;
-    addr = bitband_addr(opaque, offset) & ~1;
-    mask = (1 << ((offset >> 2) & 15));
-    mask = tswap16(mask);
-    cpu_physical_memory_read(addr, &v, 2);
-    if (value & 1)
-        v |= mask;
-    else
-        v &= ~mask;
-    cpu_physical_memory_write(addr, &v, 2);
+    BitBandState *s = BITBAND(dev);
+
+    if (!s->source_memory) {
+        error_setg(errp, "source-memory property not set");
+        return;
+    }
+
+    s->source_as = address_space_init_shareable(s->source_memory,
+                                                "bitband-source");
 }
 
-static uint32_t bitband_readl(void *opaque, hwaddr offset)
+/* Board init.  */
+
+static const hwaddr bitband_input_addr[ARMV7M_NUM_BITBANDS] = {
+    0x20000000, 0x40000000
+};
+
+static const hwaddr bitband_output_addr[ARMV7M_NUM_BITBANDS] = {
+    0x22000000, 0x42000000
+};
+
+static void armv7m_instance_init(Object *obj)
 {
-    uint32_t addr;
-    uint32_t mask;
-    uint32_t v;
-    addr = bitband_addr(opaque, offset) & ~3;
-    mask = (1 << ((offset >> 2) & 31));
-    mask = tswap32(mask);
-    cpu_physical_memory_read(addr, &v, 4);
-    return (v & mask) != 0;
+    ARMv7MState *s = ARMV7M(obj);
+    int i;
+
+    /* Can't init the cpu here, we don't yet know which model to use */
+
+    object_property_add_link(obj, "memory",
+                             TYPE_MEMORY_REGION,
+                             (Object **)&s->board_memory,
+                             qdev_prop_allow_set_link_before_realize,
+                             OBJ_PROP_LINK_UNREF_ON_RELEASE,
+                             &error_abort);
+    memory_region_init(&s->container, obj, "armv7m-container", UINT64_MAX);
+
+    object_initialize(&s->nvic, sizeof(s->nvic), "armv7m_nvic");
+    qdev_set_parent_bus(DEVICE(&s->nvic), sysbus_get_default());
+    object_property_add_alias(obj, "num-irq",
+                              OBJECT(&s->nvic), "num-irq", &error_abort);
+
+    for (i = 0; i < ARRAY_SIZE(s->bitband); i++) {
+        object_initialize(&s->bitband[i], sizeof(s->bitband[i]), TYPE_BITBAND);
+        qdev_set_parent_bus(DEVICE(&s->bitband[i]), sysbus_get_default());
+    }
 }
 
-static void bitband_writel(void *opaque, hwaddr offset,
-                           uint32_t value)
+static void armv7m_realize(DeviceState *dev, Error **errp)
 {
-    uint32_t addr;
-    uint32_t mask;
-    uint32_t v;
-    addr = bitband_addr(opaque, offset) & ~3;
-    mask = (1 << ((offset >> 2) & 31));
-    mask = tswap32(mask);
-    cpu_physical_memory_read(addr, &v, 4);
-    if (value & 1)
-        v |= mask;
-    else
-        v &= ~mask;
-    cpu_physical_memory_write(addr, &v, 4);
-}
+    ARMv7MState *s = ARMV7M(dev);
+    SysBusDevice *sbd;
+    Error *err = NULL;
+    int i;
+    char **cpustr;
+    ObjectClass *oc;
+    const char *typename;
+    CPUClass *cc;
+
+    if (!s->board_memory) {
+        error_setg(errp, "memory property was not set");
+        return;
+    }
 
-static const MemoryRegionOps bitband_ops = {
-    .old_mmio = {
-        .read = { bitband_readb, bitband_readw, bitband_readl, },
-        .write = { bitband_writeb, bitband_writew, bitband_writel, },
-    },
-    .endianness = DEVICE_NATIVE_ENDIAN,
-};
+    memory_region_add_subregion_overlap(&s->container, 0, s->board_memory, -1);
 
-#define TYPE_BITBAND "ARM,bitband-memory"
-#define BITBAND(obj) OBJECT_CHECK(BitBandState, (obj), TYPE_BITBAND)
+    cpustr = g_strsplit(s->cpu_model, ",", 2);
 
-typedef struct {
-    /*< private >*/
-    SysBusDevice parent_obj;
-    /*< public >*/
+    oc = cpu_class_by_name(TYPE_ARM_CPU, cpustr[0]);
+    if (!oc) {
+        error_setg(errp, "Unknown CPU model %s", cpustr[0]);
+        g_strfreev(cpustr);
+        return;
+    }
 
-    MemoryRegion iomem;
-    uint32_t base;
-} BitBandState;
+    cc = CPU_CLASS(oc);
+    typename = object_class_get_name(oc);
+    cc->parse_features(typename, cpustr[1], &err);
+    g_strfreev(cpustr);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
 
-static void bitband_init(Object *obj)
-{
-    BitBandState *s = BITBAND(obj);
-    SysBusDevice *dev = SYS_BUS_DEVICE(obj);
+    s->cpu = ARM_CPU(object_new(typename));
+    if (!s->cpu) {
+        error_setg(errp, "Unknown CPU model %s", s->cpu_model);
+        return;
+    }
 
-    memory_region_init_io(&s->iomem, obj, &bitband_ops, &s->base,
-                          "bitband", 0x02000000);
-    sysbus_init_mmio(dev, &s->iomem);
+    object_property_set_link(OBJECT(s->cpu), OBJECT(&s->container), "memory",
+                             &error_abort);
+    object_property_set_bool(OBJECT(s->cpu), true, "realized", &err);
+    if (err != NULL) {
+        error_propagate(errp, err);
+        return;
+    }
+
+    /* Note that we must realize the NVIC after the CPU */
+    object_property_set_bool(OBJECT(&s->nvic), true, "realized", &err);
+    if (err != NULL) {
+        error_propagate(errp, err);
+        return;
+    }
+
+    /* Alias the NVIC's input and output GPIOs as our own so the board
+     * code can wire them up. (We do this in realize because the
+     * NVIC doesn't create the input GPIO array until realize.)
+     */
+    qdev_pass_gpios(DEVICE(&s->nvic), dev, NULL);
+    qdev_pass_gpios(DEVICE(&s->nvic), dev, "SYSRESETREQ");
+
+    /* Wire the NVIC up to the CPU */
+    sbd = SYS_BUS_DEVICE(&s->nvic);
+    sysbus_connect_irq(sbd, 0,
+                       qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_IRQ));
+    s->cpu->env.nvic = &s->nvic;
+
+    memory_region_add_subregion(&s->container, 0xe000e000,
+                                sysbus_mmio_get_region(sbd, 0));
+
+    for (i = 0; i < ARRAY_SIZE(s->bitband); i++) {
+        Object *obj = OBJECT(&s->bitband[i]);
+        SysBusDevice *sbd = SYS_BUS_DEVICE(&s->bitband[i]);
+
+        object_property_set_int(obj, bitband_input_addr[i], "base", &err);
+        if (err != NULL) {
+            error_propagate(errp, err);
+            return;
+        }
+        object_property_set_link(obj, OBJECT(s->board_memory),
+                                 "source-memory", &error_abort);
+        object_property_set_bool(obj, true, "realized", &err);
+        if (err != NULL) {
+            error_propagate(errp, err);
+            return;
+        }
+
+        memory_region_add_subregion(&s->container, bitband_output_addr[i],
+                                    sysbus_mmio_get_region(sbd, 0));
+    }
 }
 
-static void armv7m_bitband_init(void)
-{
-    DeviceState *dev;
+static Property armv7m_properties[] = {
+    DEFINE_PROP_STRING("cpu-model", ARMv7MState, cpu_model),
+    DEFINE_PROP_END_OF_LIST(),
+};
 
-    dev = qdev_create(NULL, TYPE_BITBAND);
-    qdev_prop_set_uint32(dev, "base", 0x20000000);
-    qdev_init_nofail(dev);
-    sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, 0x22000000);
+static void armv7m_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dev = qdev_create(NULL, TYPE_BITBAND);
-    qdev_prop_set_uint32(dev, "base", 0x40000000);
-    qdev_init_nofail(dev);
-    sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, 0x42000000);
+    dc->realize = armv7m_realize;
+    dc->props = armv7m_properties;
 }
 
-/* Board init.  */
+static const TypeInfo armv7m_info = {
+    .name = TYPE_ARMV7M,
+    .parent = TYPE_SYS_BUS_DEVICE,
+    .instance_size = sizeof(ARMv7MState),
+    .instance_init = armv7m_instance_init,
+    .class_init = armv7m_class_init,
+};
 
 static void armv7m_reset(void *opaque)
 {
@@ -168,37 +282,35 @@ static void armv7m_reset(void *opaque)
 
 /* Init CPU and memory for a v7-M based board.
    mem_size is in bytes.
-   Returns the NVIC array.  */
+   Returns the ARMv7M device.  */
 
 DeviceState *armv7m_init(MemoryRegion *system_memory, int mem_size, int num_irq,
                       const char *kernel_filename, const char *cpu_model)
 {
-    ARMCPU *cpu;
-    CPUARMState *env;
-    DeviceState *nvic;
-    int image_size;
-    uint64_t entry;
-    uint64_t lowaddr;
-    int big_endian;
+    DeviceState *armv7m;
 
     if (cpu_model == NULL) {
-	cpu_model = "cortex-m3";
-    }
-    cpu = cpu_arm_init(cpu_model);
-    if (cpu == NULL) {
-        fprintf(stderr, "Unable to find CPU definition\n");
-        exit(1);
+        cpu_model = "cortex-m3";
     }
-    env = &cpu->env;
 
-    armv7m_bitband_init();
+    armv7m = qdev_create(NULL, "armv7m");
+    qdev_prop_set_uint32(armv7m, "num-irq", num_irq);
+    qdev_prop_set_string(armv7m, "cpu-model", cpu_model);
+    object_property_set_link(OBJECT(armv7m), OBJECT(get_system_memory()),
+                                     "memory", &error_abort);
+    /* This will exit with an error if the user passed us a bad cpu_model */
+    qdev_init_nofail(armv7m);
+
+    armv7m_load_kernel(ARM_CPU(first_cpu), kernel_filename, mem_size);
+    return armv7m;
+}
 
-    nvic = qdev_create(NULL, "armv7m_nvic");
-    qdev_prop_set_uint32(nvic, "num-irq", num_irq);
-    env->nvic = nvic;
-    qdev_init_nofail(nvic);
-    sysbus_connect_irq(SYS_BUS_DEVICE(nvic), 0,
-                       qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ));
+void armv7m_load_kernel(ARMCPU *cpu, const char *kernel_filename, int mem_size)
+{
+    int image_size;
+    uint64_t entry;
+    uint64_t lowaddr;
+    int big_endian;
 
 #ifdef TARGET_WORDS_BIGENDIAN
     big_endian = 1;
@@ -224,8 +336,15 @@ DeviceState *armv7m_init(MemoryRegion *system_memory, int mem_size, int num_irq,
         }
     }
 
+    /* CPU objects (unlike devices) are not automatically reset on system
+     * reset, so we must always register a handler to do so. Unlike
+     * A-profile CPUs, we don't need to do anything special in the
+     * handler to arrange that it starts correctly.
+     * This is arguably the wrong place to do this, but it matches the
+     * way A-profile does it. Note that this means that every M profile
+     * board must call this function!
+     */
     qemu_register_reset(armv7m_reset, cpu);
-    return nvic;
 }
 
 static Property bitband_properties[] = {
@@ -237,6 +356,7 @@ static void bitband_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
+    dc->realize = bitband_realize;
     dc->props = bitband_properties;
 }
 
@@ -251,6 +371,7 @@ static const TypeInfo bitband_info = {
 static void armv7m_register_types(void)
 {
     type_register_static(&bitband_info);
+    type_register_static(&armv7m_info);
 }
 
 type_init(armv7m_register_types)
diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c
index 2e641a3989..369ef1e3bd 100644
--- a/hw/arm/bcm2835_peripherals.c
+++ b/hw/arm/bcm2835_peripherals.c
@@ -86,11 +86,21 @@ static void bcm2835_peripherals_init(Object *obj)
     object_property_add_const_link(OBJECT(&s->property), "dma-mr",
                                    OBJECT(&s->gpu_bus_mr), &error_abort);
 
+    /* Random Number Generator */
+    object_initialize(&s->rng, sizeof(s->rng), TYPE_BCM2835_RNG);
+    object_property_add_child(obj, "rng", OBJECT(&s->rng), NULL);
+    qdev_set_parent_bus(DEVICE(&s->rng), sysbus_get_default());
+
     /* Extended Mass Media Controller */
     object_initialize(&s->sdhci, sizeof(s->sdhci), TYPE_SYSBUS_SDHCI);
     object_property_add_child(obj, "sdhci", OBJECT(&s->sdhci), NULL);
     qdev_set_parent_bus(DEVICE(&s->sdhci), sysbus_get_default());
 
+    /* SDHOST */
+    object_initialize(&s->sdhost, sizeof(s->sdhost), TYPE_BCM2835_SDHOST);
+    object_property_add_child(obj, "sdhost", OBJECT(&s->sdhost), NULL);
+    qdev_set_parent_bus(DEVICE(&s->sdhost), sysbus_get_default());
+
     /* DMA Channels */
     object_initialize(&s->dma, sizeof(s->dma), TYPE_BCM2835_DMA);
     object_property_add_child(obj, "dma", OBJECT(&s->dma), NULL);
@@ -98,6 +108,16 @@ static void bcm2835_peripherals_init(Object *obj)
 
     object_property_add_const_link(OBJECT(&s->dma), "dma-mr",
                                    OBJECT(&s->gpu_bus_mr), &error_abort);
+
+    /* GPIO */
+    object_initialize(&s->gpio, sizeof(s->gpio), TYPE_BCM2835_GPIO);
+    object_property_add_child(obj, "gpio", OBJECT(&s->gpio), NULL);
+    qdev_set_parent_bus(DEVICE(&s->gpio), sysbus_get_default());
+
+    object_property_add_const_link(OBJECT(&s->gpio), "sdbus-sdhci",
+                                   OBJECT(&s->sdhci.sdbus), &error_abort);
+    object_property_add_const_link(OBJECT(&s->gpio), "sdbus-sdhost",
+                                   OBJECT(&s->sdhost.sdbus), &error_abort);
 }
 
 static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp)
@@ -226,6 +246,16 @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp)
     sysbus_connect_irq(SYS_BUS_DEVICE(&s->property), 0,
                       qdev_get_gpio_in(DEVICE(&s->mboxes), MBOX_CHAN_PROPERTY));
 
+    /* Random Number Generator */
+    object_property_set_bool(OBJECT(&s->rng), true, "realized", &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
+
+    memory_region_add_subregion(&s->peri_mr, RNG_OFFSET,
+                sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->rng), 0));
+
     /* Extended Mass Media Controller */
     object_property_set_int(OBJECT(&s->sdhci), BCM2835_SDHC_CAPAREG, "capareg",
                             &err);
@@ -252,13 +282,20 @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp)
     sysbus_connect_irq(SYS_BUS_DEVICE(&s->sdhci), 0,
         qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ,
                                INTERRUPT_ARASANSDIO));
-    object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->sdhci), "sd-bus",
-                              &err);
+
+    /* SDHOST */
+    object_property_set_bool(OBJECT(&s->sdhost), true, "realized", &err);
     if (err) {
         error_propagate(errp, err);
         return;
     }
 
+    memory_region_add_subregion(&s->peri_mr, MMCI0_OFFSET,
+                sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->sdhost), 0));
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->sdhost), 0,
+        qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ,
+                               INTERRUPT_SDIO));
+
     /* DMA Channels */
     object_property_set_bool(OBJECT(&s->dma), true, "realized", &err);
     if (err) {
@@ -277,6 +314,23 @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp)
                                                   BCM2835_IC_GPU_IRQ,
                                                   INTERRUPT_DMA0 + n));
     }
+
+    /* GPIO */
+    object_property_set_bool(OBJECT(&s->gpio), true, "realized", &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
+
+    memory_region_add_subregion(&s->peri_mr, GPIO_OFFSET,
+                sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->gpio), 0));
+
+    object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->gpio), "sd-bus",
+                              &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
 }
 
 static void bcm2835_peripherals_class_init(ObjectClass *oc, void *data)
diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c
index be3c96d21e..1d2b50cc4e 100644
--- a/hw/arm/exynos4210.c
+++ b/hw/arm/exynos4210.c
@@ -24,6 +24,7 @@
 #include "qemu/osdep.h"
 #include "qapi/error.h"
 #include "qemu-common.h"
+#include "qemu/log.h"
 #include "cpu.h"
 #include "hw/boards.h"
 #include "sysemu/sysemu.h"
@@ -74,6 +75,9 @@
 /* PMU SFR base address */
 #define EXYNOS4210_PMU_BASE_ADDR            0x10020000
 
+/* Clock controller SFR base address */
+#define EXYNOS4210_CLK_BASE_ADDR            0x10030000
+
 /* Display controllers (FIMD) */
 #define EXYNOS4210_FIMD0_BASE_ADDR          0x11C00000
 
@@ -138,6 +142,16 @@ void exynos4210_write_secondary(ARMCPU *cpu,
                        info->smp_loader_start);
 }
 
+static uint64_t exynos4210_calc_affinity(int cpu)
+{
+    uint64_t mp_affinity;
+
+    /* Exynos4210 has 0x9 as cluster ID */
+    mp_affinity = (0x9 << ARM_AFF1_SHIFT) | cpu;
+
+    return mp_affinity;
+}
+
 Exynos4210State *exynos4210_init(MemoryRegion *system_mem,
         unsigned long ram_size)
 {
@@ -163,6 +177,8 @@ Exynos4210State *exynos4210_init(MemoryRegion *system_mem,
         }
 
         s->cpu[n] = ARM_CPU(cpuobj);
+        object_property_set_int(cpuobj, exynos4210_calc_affinity(n),
+                                "mp-affinity", &error_abort);
         object_property_set_int(cpuobj, EXYNOS4210_SMP_PRIVATE_BASE_ADDR,
                                 "reset-cbar", &error_abort);
         object_property_set_bool(cpuobj, true, "realized", &error_fatal);
@@ -297,6 +313,8 @@ Exynos4210State *exynos4210_init(MemoryRegion *system_mem,
     */
     sysbus_create_simple("exynos4210.pmu", EXYNOS4210_PMU_BASE_ADDR, NULL);
 
+    sysbus_create_simple("exynos4210.clk", EXYNOS4210_CLK_BASE_ADDR, NULL);
+
     /* PWM */
     sysbus_create_varargs("exynos4210.pwm", EXYNOS4210_PWM_BASE_ADDR,
                           s->irq_table[exynos4210_get_irq(22, 0)],
diff --git a/hw/arm/netduino2.c b/hw/arm/netduino2.c
index 23d792837f..3cfe332dd1 100644
--- a/hw/arm/netduino2.c
+++ b/hw/arm/netduino2.c
@@ -27,17 +27,18 @@
 #include "hw/boards.h"
 #include "qemu/error-report.h"
 #include "hw/arm/stm32f205_soc.h"
+#include "hw/arm/arm.h"
 
 static void netduino2_init(MachineState *machine)
 {
     DeviceState *dev;
 
     dev = qdev_create(NULL, TYPE_STM32F205_SOC);
-    if (machine->kernel_filename) {
-        qdev_prop_set_string(dev, "kernel-filename", machine->kernel_filename);
-    }
     qdev_prop_set_string(dev, "cpu-model", "cortex-m3");
     object_property_set_bool(OBJECT(dev), true, "realized", &error_fatal);
+
+    armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename,
+                       FLASH_SIZE);
 }
 
 static void netduino2_machine_init(MachineClass *mc)
diff --git a/hw/arm/stm32f205_soc.c b/hw/arm/stm32f205_soc.c
index 38425bda6c..6e1260d2ed 100644
--- a/hw/arm/stm32f205_soc.c
+++ b/hw/arm/stm32f205_soc.c
@@ -49,6 +49,9 @@ static void stm32f205_soc_initfn(Object *obj)
     STM32F205State *s = STM32F205_SOC(obj);
     int i;
 
+    object_initialize(&s->armv7m, sizeof(s->armv7m), TYPE_ARMV7M);
+    qdev_set_parent_bus(DEVICE(&s->armv7m), sysbus_get_default());
+
     object_initialize(&s->syscfg, sizeof(s->syscfg), TYPE_STM32F2XX_SYSCFG);
     qdev_set_parent_bus(DEVICE(&s->syscfg), sysbus_get_default());
 
@@ -82,7 +85,7 @@ static void stm32f205_soc_initfn(Object *obj)
 static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp)
 {
     STM32F205State *s = STM32F205_SOC(dev_soc);
-    DeviceState *dev, *nvic;
+    DeviceState *dev, *armv7m;
     SysBusDevice *busdev;
     Error *err = NULL;
     int i;
@@ -110,8 +113,16 @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp)
     vmstate_register_ram_global(sram);
     memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, sram);
 
-    nvic = armv7m_init(get_system_memory(), FLASH_SIZE, 96,
-                       s->kernel_filename, s->cpu_model);
+    armv7m = DEVICE(&s->armv7m);
+    qdev_prop_set_uint32(armv7m, "num-irq", 96);
+    qdev_prop_set_string(armv7m, "cpu-model", s->cpu_model);
+    object_property_set_link(OBJECT(&s->armv7m), OBJECT(get_system_memory()),
+                                     "memory", &error_abort);
+    object_property_set_bool(OBJECT(&s->armv7m), true, "realized", &err);
+    if (err != NULL) {
+        error_propagate(errp, err);
+        return;
+    }
 
     /* System configuration controller */
     dev = DEVICE(&s->syscfg);
@@ -122,7 +133,7 @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp)
     }
     busdev = SYS_BUS_DEVICE(dev);
     sysbus_mmio_map(busdev, 0, 0x40013800);
-    sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(nvic, 71));
+    sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, 71));
 
     /* Attach UART (uses USART registers) and USART controllers */
     for (i = 0; i < STM_NUM_USARTS; i++) {
@@ -136,7 +147,7 @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp)
         }
         busdev = SYS_BUS_DEVICE(dev);
         sysbus_mmio_map(busdev, 0, usart_addr[i]);
-        sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(nvic, usart_irq[i]));
+        sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, usart_irq[i]));
     }
 
     /* Timer 2 to 5 */
@@ -150,7 +161,7 @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp)
         }
         busdev = SYS_BUS_DEVICE(dev);
         sysbus_mmio_map(busdev, 0, timer_addr[i]);
-        sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(nvic, timer_irq[i]));
+        sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, timer_irq[i]));
     }
 
     /* ADC 1 to 3 */
@@ -162,7 +173,7 @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp)
         return;
     }
     qdev_connect_gpio_out(DEVICE(s->adc_irqs), 0,
-                          qdev_get_gpio_in(nvic, ADC_IRQ));
+                          qdev_get_gpio_in(armv7m, ADC_IRQ));
 
     for (i = 0; i < STM_NUM_ADCS; i++) {
         dev = DEVICE(&(s->adc[i]));
@@ -187,12 +198,11 @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp)
         }
         busdev = SYS_BUS_DEVICE(dev);
         sysbus_mmio_map(busdev, 0, spi_addr[i]);
-        sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(nvic, spi_irq[i]));
+        sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, spi_irq[i]));
     }
 }
 
 static Property stm32f205_soc_properties[] = {
-    DEFINE_PROP_STRING("kernel-filename", STM32F205State, kernel_filename),
     DEFINE_PROP_STRING("cpu-model", STM32F205State, cpu_model),
     DEFINE_PROP_END_OF_LIST(),
 };
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index f3440f2ccb..5f62a0321e 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -535,7 +535,6 @@ static void create_v2m(VirtMachineState *vms, qemu_irq *pic)
 static void create_gic(VirtMachineState *vms, qemu_irq *pic)
 {
     /* We create a standalone GIC */
-    VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms);
     DeviceState *gicdev;
     SysBusDevice *gicbusdev;
     const char *gictype;
@@ -605,7 +604,7 @@ static void create_gic(VirtMachineState *vms, qemu_irq *pic)
 
     fdt_add_gic_node(vms);
 
-    if (type == 3 && !vmc->no_its) {
+    if (type == 3 && vms->its) {
         create_its(vms, gicdev);
     } else if (type == 2) {
         create_v2m(vms, pic);
@@ -1378,6 +1377,7 @@ static void machvirt_init(MachineState *machine)
         }
 
         object_property_set_bool(cpuobj, true, "realized", NULL);
+        object_unref(cpuobj);
     }
     fdt_add_timer_nodes(vms);
     fdt_add_cpu_nodes(vms);
@@ -1480,6 +1480,20 @@ static void virt_set_highmem(Object *obj, bool value, Error **errp)
     vms->highmem = value;
 }
 
+static bool virt_get_its(Object *obj, Error **errp)
+{
+    VirtMachineState *vms = VIRT_MACHINE(obj);
+
+    return vms->its;
+}
+
+static void virt_set_its(Object *obj, bool value, Error **errp)
+{
+    VirtMachineState *vms = VIRT_MACHINE(obj);
+
+    vms->its = value;
+}
+
 static char *virt_get_gic_version(Object *obj, Error **errp)
 {
     VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -1540,6 +1554,7 @@ type_init(machvirt_machine_init);
 static void virt_2_9_instance_init(Object *obj)
 {
     VirtMachineState *vms = VIRT_MACHINE(obj);
+    VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms);
 
     /* EL3 is disabled by default on virt: this makes us consistent
      * between KVM and TCG for this board, and it also allows us to
@@ -1579,6 +1594,19 @@ static void virt_2_9_instance_init(Object *obj)
                                     "Set GIC version. "
                                     "Valid values are 2, 3 and host", NULL);
 
+    if (vmc->no_its) {
+        vms->its = false;
+    } else {
+        /* Default allows ITS instantiation */
+        vms->its = true;
+        object_property_add_bool(obj, "its", virt_get_its,
+                                 virt_set_its, NULL);
+        object_property_set_description(obj, "its",
+                                        "Set on/off to enable/disable "
+                                        "ITS instantiation",
+                                        NULL);
+    }
+
     vms->memmap = a15memmap;
     vms->irqmap = a15irqmap;
 }
diff --git a/hw/block/block.c b/hw/block/block.c
index 8dc9d84a39..27878d0087 100644
--- a/hw/block/block.c
+++ b/hw/block/block.c
@@ -51,11 +51,33 @@ void blkconf_blocksizes(BlockConf *conf)
     }
 }
 
-void blkconf_apply_backend_options(BlockConf *conf)
+void blkconf_apply_backend_options(BlockConf *conf, bool readonly,
+                                   bool resizable, Error **errp)
 {
     BlockBackend *blk = conf->blk;
     BlockdevOnError rerror, werror;
+    uint64_t perm, shared_perm;
     bool wce;
+    int ret;
+
+    perm = BLK_PERM_CONSISTENT_READ;
+    if (!readonly) {
+        perm |= BLK_PERM_WRITE;
+    }
+
+    shared_perm = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
+                  BLK_PERM_GRAPH_MOD;
+    if (resizable) {
+        shared_perm |= BLK_PERM_RESIZE;
+    }
+    if (conf->share_rw) {
+        shared_perm |= BLK_PERM_WRITE;
+    }
+
+    ret = blk_set_perm(blk, perm, shared_perm, errp);
+    if (ret < 0) {
+        return;
+    }
 
     switch (conf->wce) {
     case ON_OFF_AUTO_ON:    wce = true; break;
diff --git a/hw/block/fdc.c b/hw/block/fdc.c
index 17d29e7bc5..a328693d15 100644
--- a/hw/block/fdc.c
+++ b/hw/block/fdc.c
@@ -186,6 +186,7 @@ typedef enum FDiskFlags {
 struct FDrive {
     FDCtrl *fdctrl;
     BlockBackend *blk;
+    BlockConf *conf;
     /* Drive status */
     FloppyDriveType drive;    /* CMOS drive type        */
     uint8_t perpendicular;    /* 2.88 MB access mode    */
@@ -469,9 +470,22 @@ static void fd_revalidate(FDrive *drv)
     }
 }
 
-static void fd_change_cb(void *opaque, bool load)
+static void fd_change_cb(void *opaque, bool load, Error **errp)
 {
     FDrive *drive = opaque;
+    Error *local_err = NULL;
+
+    if (!load) {
+        blk_set_perm(drive->blk, 0, BLK_PERM_ALL, &error_abort);
+    } else {
+        blkconf_apply_backend_options(drive->conf,
+                                      blk_is_read_only(drive->blk), false,
+                                      &local_err);
+        if (local_err) {
+            error_propagate(errp, local_err);
+            return;
+        }
+    }
 
     drive->media_changed = 1;
     drive->media_validated = false;
@@ -508,6 +522,7 @@ static int floppy_drive_init(DeviceState *qdev)
     FloppyDrive *dev = FLOPPY_DRIVE(qdev);
     FloppyBus *bus = FLOPPY_BUS(qdev->parent_bus);
     FDrive *drive;
+    Error *local_err = NULL;
     int ret;
 
     if (dev->unit == -1) {
@@ -533,7 +548,7 @@ static int floppy_drive_init(DeviceState *qdev)
 
     if (!dev->conf.blk) {
         /* Anonymous BlockBackend for an empty drive */
-        dev->conf.blk = blk_new();
+        dev->conf.blk = blk_new(0, BLK_PERM_ALL);
         ret = blk_attach_dev(dev->conf.blk, qdev);
         assert(ret == 0);
     }
@@ -551,7 +566,13 @@ static int floppy_drive_init(DeviceState *qdev)
      * blkconf_apply_backend_options(). */
     dev->conf.rerror = BLOCKDEV_ON_ERROR_AUTO;
     dev->conf.werror = BLOCKDEV_ON_ERROR_AUTO;
-    blkconf_apply_backend_options(&dev->conf);
+
+    blkconf_apply_backend_options(&dev->conf, blk_is_read_only(dev->conf.blk),
+                                  false, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+        return -1;
+    }
 
     /* 'enospc' is the default for -drive, 'report' is what blk_new() gives us
      * for empty drives. */
@@ -565,6 +586,7 @@ static int floppy_drive_init(DeviceState *qdev)
         return -1;
     }
 
+    drive->conf = &dev->conf;
     drive->blk = dev->conf.blk;
     drive->fdctrl = bus->fdc;
 
diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c
index 2d6eb46a04..190573cefa 100644
--- a/hw/block/m25p80.c
+++ b/hw/block/m25p80.c
@@ -1215,6 +1215,7 @@ static void m25p80_realize(SSISlave *ss, Error **errp)
 {
     Flash *s = M25P80(ss);
     M25P80Class *mc = M25P80_GET_CLASS(s);
+    int ret;
 
     s->pi = mc->pi;
 
@@ -1222,6 +1223,13 @@ static void m25p80_realize(SSISlave *ss, Error **errp)
     s->dirty_page = -1;
 
     if (s->blk) {
+        uint64_t perm = BLK_PERM_CONSISTENT_READ |
+                        (blk_is_read_only(s->blk) ? 0 : BLK_PERM_WRITE);
+        ret = blk_set_perm(s->blk, perm, BLK_PERM_ALL, errp);
+        if (ret < 0) {
+            return;
+        }
+
         DB_PRINT_L(0, "Binding to IF_MTD drive\n");
         s->storage = blk_blockalign(s->blk, s->size);
 
diff --git a/hw/block/nand.c b/hw/block/nand.c
index c69e6755d9..0d33ac281f 100644
--- a/hw/block/nand.c
+++ b/hw/block/nand.c
@@ -373,6 +373,8 @@ static void nand_realize(DeviceState *dev, Error **errp)
 {
     int pagesize;
     NANDFlashState *s = NAND(dev);
+    int ret;
+
 
     s->buswidth = nand_flash_ids[s->chip_id].width >> 3;
     s->size = nand_flash_ids[s->chip_id].size << 20;
@@ -407,6 +409,11 @@ static void nand_realize(DeviceState *dev, Error **errp)
             error_setg(errp, "Can't use a read-only drive");
             return;
         }
+        ret = blk_set_perm(s->blk, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE,
+                           BLK_PERM_ALL, errp);
+        if (ret < 0) {
+            return;
+        }
         if (blk_getlength(s->blk) >=
                 (s->pages << s->page_shift) + (s->pages << s->oob_shift)) {
             pagesize = 0;
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index ae91a18f17..ae303d44e5 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -835,6 +835,7 @@ static int nvme_init(PCIDevice *pci_dev)
     int i;
     int64_t bs_size;
     uint8_t *pci_conf;
+    Error *local_err = NULL;
 
     if (!n->conf.blk) {
         return -1;
@@ -850,7 +851,12 @@ static int nvme_init(PCIDevice *pci_dev)
         return -1;
     }
     blkconf_blocksizes(&n->conf);
-    blkconf_apply_backend_options(&n->conf);
+    blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk),
+                                  false, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+        return -1;
+    }
 
     pci_conf = pci_dev->config;
     pci_conf[PCI_INTERRUPT_PIN] = 1;
diff --git a/hw/block/onenand.c b/hw/block/onenand.c
index 8d8422739e..ddf5492426 100644
--- a/hw/block/onenand.c
+++ b/hw/block/onenand.c
@@ -778,6 +778,7 @@ static int onenand_initfn(SysBusDevice *sbd)
     OneNANDState *s = ONE_NAND(dev);
     uint32_t size = 1 << (24 + ((s->id.dev >> 4) & 7));
     void *ram;
+    Error *local_err = NULL;
 
     s->base = (hwaddr)-1;
     s->rdy = NULL;
@@ -796,6 +797,12 @@ static int onenand_initfn(SysBusDevice *sbd)
             error_report("Can't use a read-only drive");
             return -1;
         }
+        blk_set_perm(s->blk, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE,
+                     BLK_PERM_ALL, &local_err);
+        if (local_err) {
+            error_report_err(local_err);
+            return -1;
+        }
         s->blk_cur = s->blk;
     }
     s->otp = memset(g_malloc((64 + 2) << PAGE_SHIFT),
diff --git a/hw/block/pflash_cfi01.c b/hw/block/pflash_cfi01.c
index 71b98a3eef..594d4cf6fe 100644
--- a/hw/block/pflash_cfi01.c
+++ b/hw/block/pflash_cfi01.c
@@ -758,6 +758,18 @@ static void pflash_cfi01_realize(DeviceState *dev, Error **errp)
     sysbus_init_mmio(SYS_BUS_DEVICE(dev), &pfl->mem);
 
     if (pfl->blk) {
+        uint64_t perm;
+        pfl->ro = blk_is_read_only(pfl->blk);
+        perm = BLK_PERM_CONSISTENT_READ | (pfl->ro ? 0 : BLK_PERM_WRITE);
+        ret = blk_set_perm(pfl->blk, perm, BLK_PERM_ALL, errp);
+        if (ret < 0) {
+            return;
+        }
+    } else {
+        pfl->ro = 0;
+    }
+
+    if (pfl->blk) {
         /* read the initial flash content */
         ret = blk_pread(pfl->blk, 0, pfl->storage, total_len);
 
@@ -768,12 +780,6 @@ static void pflash_cfi01_realize(DeviceState *dev, Error **errp)
         }
     }
 
-    if (pfl->blk) {
-        pfl->ro = blk_is_read_only(pfl->blk);
-    } else {
-        pfl->ro = 0;
-    }
-
     /* Default to devices being used at their maximum device width. This was
      * assumed before the device_width support was added.
      */
diff --git a/hw/block/pflash_cfi02.c b/hw/block/pflash_cfi02.c
index ef71322759..e6c5c6c25d 100644
--- a/hw/block/pflash_cfi02.c
+++ b/hw/block/pflash_cfi02.c
@@ -632,6 +632,19 @@ static void pflash_cfi02_realize(DeviceState *dev, Error **errp)
     vmstate_register_ram(&pfl->orig_mem, DEVICE(pfl));
     pfl->storage = memory_region_get_ram_ptr(&pfl->orig_mem);
     pfl->chip_len = chip_len;
+
+    if (pfl->blk) {
+        uint64_t perm;
+        pfl->ro = blk_is_read_only(pfl->blk);
+        perm = BLK_PERM_CONSISTENT_READ | (pfl->ro ? 0 : BLK_PERM_WRITE);
+        ret = blk_set_perm(pfl->blk, perm, BLK_PERM_ALL, errp);
+        if (ret < 0) {
+            return;
+        }
+    } else {
+        pfl->ro = 0;
+    }
+
     if (pfl->blk) {
         /* read the initial flash content */
         ret = blk_pread(pfl->blk, 0, pfl->storage, chip_len);
@@ -646,12 +659,6 @@ static void pflash_cfi02_realize(DeviceState *dev, Error **errp)
     pfl->rom_mode = 1;
     sysbus_init_mmio(SYS_BUS_DEVICE(dev), &pfl->mem);
 
-    if (pfl->blk) {
-        pfl->ro = blk_is_read_only(pfl->blk);
-    } else {
-        pfl->ro = 0;
-    }
-
     pfl->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, pflash_timer, pfl);
     pfl->wcycle = 0;
     pfl->cmd = 0;
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index 843bd2fa73..98c16a7a9a 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -928,7 +928,13 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
     }
 
     blkconf_serial(&conf->conf, &conf->serial);
-    blkconf_apply_backend_options(&conf->conf);
+    blkconf_apply_backend_options(&conf->conf,
+                                  blk_is_read_only(conf->conf.blk), true,
+                                  &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
     s->original_wce = blk_enable_write_cache(conf->conf.blk);
     blkconf_geometry(&conf->conf, NULL, 65535, 255, 255, &err);
     if (err) {
diff --git a/hw/core/loader.c b/hw/core/loader.c
index 8b980e91fb..bf17b42cbe 100644
--- a/hw/core/loader.c
+++ b/hw/core/loader.c
@@ -435,6 +435,19 @@ int load_elf_as(const char *filename,
                 uint64_t *highaddr, int big_endian, int elf_machine,
                 int clear_lsb, int data_swab, AddressSpace *as)
 {
+    return load_elf_ram(filename, translate_fn, translate_opaque,
+                        pentry, lowaddr, highaddr, big_endian, elf_machine,
+                        clear_lsb, data_swab, as, true);
+}
+
+/* return < 0 if error, otherwise the number of bytes loaded in memory */
+int load_elf_ram(const char *filename,
+                 uint64_t (*translate_fn)(void *, uint64_t),
+                 void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr,
+                 uint64_t *highaddr, int big_endian, int elf_machine,
+                 int clear_lsb, int data_swab, AddressSpace *as,
+                 bool load_rom)
+{
     int fd, data_order, target_data_order, must_swab, ret = ELF_LOAD_FAILED;
     uint8_t e_ident[EI_NIDENT];
 
@@ -473,11 +486,11 @@ int load_elf_as(const char *filename,
     if (e_ident[EI_CLASS] == ELFCLASS64) {
         ret = load_elf64(filename, fd, translate_fn, translate_opaque, must_swab,
                          pentry, lowaddr, highaddr, elf_machine, clear_lsb,
-                         data_swab, as);
+                         data_swab, as, load_rom);
     } else {
         ret = load_elf32(filename, fd, translate_fn, translate_opaque, must_swab,
                          pentry, lowaddr, highaddr, elf_machine, clear_lsb,
-                         data_swab, as);
+                         data_swab, as, load_rom);
     }
 
  fail:
diff --git a/hw/core/or-irq.c b/hw/core/or-irq.c
index 1ac090d1a4..1485d5b285 100644
--- a/hw/core/or-irq.c
+++ b/hw/core/or-irq.c
@@ -89,6 +89,9 @@ static void or_irq_class_init(ObjectClass *klass, void *data)
     dc->props = or_irq_properties;
     dc->realize = or_irq_realize;
     dc->vmsd = &vmstate_or_irq;
+
+    /* Reason: Needs to be wired up to work, e.g. see stm32f205_soc.c */
+    dc->cannot_instantiate_with_device_add_yet = true;
 }
 
 static const TypeInfo or_irq_type_info = {
diff --git a/hw/core/qdev-properties-system.c b/hw/core/qdev-properties-system.c
index 94f4d8bde4..c34be1c1ba 100644
--- a/hw/core/qdev-properties-system.c
+++ b/hw/core/qdev-properties-system.c
@@ -73,14 +73,19 @@ static void parse_drive(DeviceState *dev, const char *str, void **ptr,
 {
     BlockBackend *blk;
     bool blk_created = false;
+    int ret;
 
     blk = blk_by_name(str);
     if (!blk) {
         BlockDriverState *bs = bdrv_lookup_bs(NULL, str, NULL);
         if (bs) {
-            blk = blk_new();
-            blk_insert_bs(blk, bs);
+            blk = blk_new(0, BLK_PERM_ALL);
             blk_created = true;
+
+            ret = blk_insert_bs(blk, bs, errp);
+            if (ret < 0) {
+                goto fail;
+            }
         }
     }
     if (!blk) {
diff --git a/hw/core/qdev.c b/hw/core/qdev.c
index 06ba02e2a3..923e626333 100644
--- a/hw/core/qdev.c
+++ b/hw/core/qdev.c
@@ -102,9 +102,23 @@ static void bus_add_child(BusState *bus, DeviceState *child)
 
 void qdev_set_parent_bus(DeviceState *dev, BusState *bus)
 {
+    bool replugging = dev->parent_bus != NULL;
+
+    if (replugging) {
+        /* Keep a reference to the device while it's not plugged into
+         * any bus, to avoid it potentially evaporating when it is
+         * dereffed in bus_remove_child().
+         */
+        object_ref(OBJECT(dev));
+        bus_remove_child(dev->parent_bus, dev);
+        object_unref(OBJECT(dev->parent_bus));
+    }
     dev->parent_bus = bus;
     object_ref(OBJECT(bus));
     bus_add_child(bus, dev);
+    if (replugging) {
+        object_unref(OBJECT(dev));
+    }
 }
 
 /* Create a new device.  This only initializes the device state
diff --git a/hw/core/register.c b/hw/core/register.c
index 4bfbc508de..dc335a79a9 100644
--- a/hw/core/register.c
+++ b/hw/core/register.c
@@ -59,6 +59,15 @@ static inline uint64_t register_read_val(RegisterInfo *reg)
     return 0; /* unreachable */
 }
 
+static inline uint64_t register_enabled_mask(int data_size, unsigned size)
+{
+    if (data_size < size) {
+        size = data_size;
+    }
+
+    return MAKE_64BIT_MASK(0, size * 8);
+}
+
 void register_write(RegisterInfo *reg, uint64_t val, uint64_t we,
                     const char *prefix, bool debug)
 {
@@ -192,11 +201,7 @@ void register_write_memory(void *opaque, hwaddr addr,
     }
 
     /* Generate appropriate write enable mask */
-    if (reg->data_size < size) {
-        we = MAKE_64BIT_MASK(0, reg->data_size * 8);
-    } else {
-        we = MAKE_64BIT_MASK(0, size * 8);
-    }
+    we = register_enabled_mask(reg->data_size, size);
 
     register_write(reg, value, we, reg_array->prefix,
                    reg_array->debug);
@@ -208,6 +213,7 @@ uint64_t register_read_memory(void *opaque, hwaddr addr,
     RegisterInfoArray *reg_array = opaque;
     RegisterInfo *reg = NULL;
     uint64_t read_val;
+    uint64_t re;
     int i;
 
     for (i = 0; i < reg_array->num_elements; i++) {
@@ -223,7 +229,10 @@ uint64_t register_read_memory(void *opaque, hwaddr addr,
         return 0;
     }
 
-    read_val = register_read(reg, size * 8, reg_array->prefix,
+    /* Generate appropriate read enable mask */
+    re = register_enabled_mask(reg->data_size, size);
+
+    read_val = register_read(reg, re, reg_array->prefix,
                              reg_array->debug);
 
     return extract64(read_val, 0, size * 8);
@@ -274,9 +283,18 @@ void register_finalize_block(RegisterInfoArray *r_array)
     g_free(r_array);
 }
 
+static void register_class_init(ObjectClass *oc, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(oc);
+
+    /* Reason: needs to be wired up to work */
+    dc->cannot_instantiate_with_device_add_yet = true;
+}
+
 static const TypeInfo register_info = {
     .name  = TYPE_REGISTER,
     .parent = TYPE_DEVICE,
+    .class_init = register_class_init,
 };
 
 static void register_register_types(void)
diff --git a/hw/display/milkymist-tmu2.c b/hw/display/milkymist-tmu2.c
index 7528665510..59120ddb67 100644
--- a/hw/display/milkymist-tmu2.c
+++ b/hw/display/milkymist-tmu2.c
@@ -293,7 +293,7 @@ static void tmu2_start(MilkymistTMU2State *s)
     cpu_physical_memory_unmap(mesh, mesh_len, 0, mesh_len);
 
     /* Write back the OpenGL framebuffer to the QEMU framebuffer */
-    fb_len = 2 * s->regs[R_DSTHRES] * s->regs[R_DSTVRES];
+    fb_len = 2ULL * s->regs[R_DSTHRES] * s->regs[R_DSTVRES];
     fb = cpu_physical_memory_map(s->regs[R_DSTFBUF], &fb_len, 1);
     if (fb == NULL) {
         glDeleteTextures(1, &texture);
diff --git a/hw/gpio/Makefile.objs b/hw/gpio/Makefile.objs
index a43c7cf442..fa0a72e6d0 100644
--- a/hw/gpio/Makefile.objs
+++ b/hw/gpio/Makefile.objs
@@ -7,3 +7,4 @@ common-obj-$(CONFIG_GPIO_KEY) += gpio_key.o
 
 obj-$(CONFIG_OMAP) += omap_gpio.o
 obj-$(CONFIG_IMX) += imx_gpio.o
+obj-$(CONFIG_RASPI) += bcm2835_gpio.o
diff --git a/hw/gpio/bcm2835_gpio.c b/hw/gpio/bcm2835_gpio.c
new file mode 100644
index 0000000000..acc2e3cf9e
--- /dev/null
+++ b/hw/gpio/bcm2835_gpio.c
@@ -0,0 +1,353 @@
+/*
+ * Raspberry Pi (BCM2835) GPIO Controller
+ *
+ * Copyright (c) 2017 Antfield SAS
+ *
+ * Authors:
+ *  Clement Deschamps <clement.deschamps@antfield.fr>
+ *  Luc Michel <luc.michel@antfield.fr>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/log.h"
+#include "qemu/timer.h"
+#include "qapi/error.h"
+#include "hw/sysbus.h"
+#include "hw/sd/sd.h"
+#include "hw/gpio/bcm2835_gpio.h"
+
+#define GPFSEL0   0x00
+#define GPFSEL1   0x04
+#define GPFSEL2   0x08
+#define GPFSEL3   0x0C
+#define GPFSEL4   0x10
+#define GPFSEL5   0x14
+#define GPSET0    0x1C
+#define GPSET1    0x20
+#define GPCLR0    0x28
+#define GPCLR1    0x2C
+#define GPLEV0    0x34
+#define GPLEV1    0x38
+#define GPEDS0    0x40
+#define GPEDS1    0x44
+#define GPREN0    0x4C
+#define GPREN1    0x50
+#define GPFEN0    0x58
+#define GPFEN1    0x5C
+#define GPHEN0    0x64
+#define GPHEN1    0x68
+#define GPLEN0    0x70
+#define GPLEN1    0x74
+#define GPAREN0   0x7C
+#define GPAREN1   0x80
+#define GPAFEN0   0x88
+#define GPAFEN1   0x8C
+#define GPPUD     0x94
+#define GPPUDCLK0 0x98
+#define GPPUDCLK1 0x9C
+
+static uint32_t gpfsel_get(BCM2835GpioState *s, uint8_t reg)
+{
+    int i;
+    uint32_t value = 0;
+    for (i = 0; i < 10; i++) {
+        uint32_t index = 10 * reg + i;
+        if (index < sizeof(s->fsel)) {
+            value |= (s->fsel[index] & 0x7) << (3 * i);
+        }
+    }
+    return value;
+}
+
+static void gpfsel_set(BCM2835GpioState *s, uint8_t reg, uint32_t value)
+{
+    int i;
+    for (i = 0; i < 10; i++) {
+        uint32_t index = 10 * reg + i;
+        if (index < sizeof(s->fsel)) {
+            int fsel = (value >> (3 * i)) & 0x7;
+            s->fsel[index] = fsel;
+        }
+    }
+
+    /* SD controller selection (48-53) */
+    if (s->sd_fsel != 0
+            && (s->fsel[48] == 0) /* SD_CLK_R */
+            && (s->fsel[49] == 0) /* SD_CMD_R */
+            && (s->fsel[50] == 0) /* SD_DATA0_R */
+            && (s->fsel[51] == 0) /* SD_DATA1_R */
+            && (s->fsel[52] == 0) /* SD_DATA2_R */
+            && (s->fsel[53] == 0) /* SD_DATA3_R */
+            ) {
+        /* SDHCI controller selected */
+        sdbus_reparent_card(s->sdbus_sdhost, s->sdbus_sdhci);
+        s->sd_fsel = 0;
+    } else if (s->sd_fsel != 4
+            && (s->fsel[48] == 4) /* SD_CLK_R */
+            && (s->fsel[49] == 4) /* SD_CMD_R */
+            && (s->fsel[50] == 4) /* SD_DATA0_R */
+            && (s->fsel[51] == 4) /* SD_DATA1_R */
+            && (s->fsel[52] == 4) /* SD_DATA2_R */
+            && (s->fsel[53] == 4) /* SD_DATA3_R */
+            ) {
+        /* SDHost controller selected */
+        sdbus_reparent_card(s->sdbus_sdhci, s->sdbus_sdhost);
+        s->sd_fsel = 4;
+    }
+}
+
+static int gpfsel_is_out(BCM2835GpioState *s, int index)
+{
+    if (index >= 0 && index < 54) {
+        return s->fsel[index] == 1;
+    }
+    return 0;
+}
+
+static void gpset(BCM2835GpioState *s,
+        uint32_t val, uint8_t start, uint8_t count, uint32_t *lev)
+{
+    uint32_t changes = val & ~*lev;
+    uint32_t cur = 1;
+
+    int i;
+    for (i = 0; i < count; i++) {
+        if ((changes & cur) && (gpfsel_is_out(s, start + i))) {
+            qemu_set_irq(s->out[start + i], 1);
+        }
+        cur <<= 1;
+    }
+
+    *lev |= val;
+}
+
+static void gpclr(BCM2835GpioState *s,
+        uint32_t val, uint8_t start, uint8_t count, uint32_t *lev)
+{
+    uint32_t changes = val & *lev;
+    uint32_t cur = 1;
+
+    int i;
+    for (i = 0; i < count; i++) {
+        if ((changes & cur) && (gpfsel_is_out(s, start + i))) {
+            qemu_set_irq(s->out[start + i], 0);
+        }
+        cur <<= 1;
+    }
+
+    *lev &= ~val;
+}
+
+static uint64_t bcm2835_gpio_read(void *opaque, hwaddr offset,
+        unsigned size)
+{
+    BCM2835GpioState *s = (BCM2835GpioState *)opaque;
+
+    switch (offset) {
+    case GPFSEL0:
+    case GPFSEL1:
+    case GPFSEL2:
+    case GPFSEL3:
+    case GPFSEL4:
+    case GPFSEL5:
+        return gpfsel_get(s, offset / 4);
+    case GPSET0:
+    case GPSET1:
+        /* Write Only */
+        return 0;
+    case GPCLR0:
+    case GPCLR1:
+        /* Write Only */
+        return 0;
+    case GPLEV0:
+        return s->lev0;
+    case GPLEV1:
+        return s->lev1;
+    case GPEDS0:
+    case GPEDS1:
+    case GPREN0:
+    case GPREN1:
+    case GPFEN0:
+    case GPFEN1:
+    case GPHEN0:
+    case GPHEN1:
+    case GPLEN0:
+    case GPLEN1:
+    case GPAREN0:
+    case GPAREN1:
+    case GPAFEN0:
+    case GPAFEN1:
+    case GPPUD:
+    case GPPUDCLK0:
+    case GPPUDCLK1:
+        /* Not implemented */
+        return 0;
+    default:
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset %"HWADDR_PRIx"\n",
+                __func__, offset);
+        break;
+    }
+
+    return 0;
+}
+
+static void bcm2835_gpio_write(void *opaque, hwaddr offset,
+        uint64_t value, unsigned size)
+{
+    BCM2835GpioState *s = (BCM2835GpioState *)opaque;
+
+    switch (offset) {
+    case GPFSEL0:
+    case GPFSEL1:
+    case GPFSEL2:
+    case GPFSEL3:
+    case GPFSEL4:
+    case GPFSEL5:
+        gpfsel_set(s, offset / 4, value);
+        break;
+    case GPSET0:
+        gpset(s, value, 0, 32, &s->lev0);
+        break;
+    case GPSET1:
+        gpset(s, value, 32, 22, &s->lev1);
+        break;
+    case GPCLR0:
+        gpclr(s, value, 0, 32, &s->lev0);
+        break;
+    case GPCLR1:
+        gpclr(s, value, 32, 22, &s->lev1);
+        break;
+    case GPLEV0:
+    case GPLEV1:
+        /* Read Only */
+        break;
+    case GPEDS0:
+    case GPEDS1:
+    case GPREN0:
+    case GPREN1:
+    case GPFEN0:
+    case GPFEN1:
+    case GPHEN0:
+    case GPHEN1:
+    case GPLEN0:
+    case GPLEN1:
+    case GPAREN0:
+    case GPAREN1:
+    case GPAFEN0:
+    case GPAFEN1:
+    case GPPUD:
+    case GPPUDCLK0:
+    case GPPUDCLK1:
+        /* Not implemented */
+        break;
+    default:
+        goto err_out;
+    }
+    return;
+
+err_out:
+    qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset %"HWADDR_PRIx"\n",
+            __func__, offset);
+}
+
+static void bcm2835_gpio_reset(DeviceState *dev)
+{
+    BCM2835GpioState *s = BCM2835_GPIO(dev);
+
+    int i;
+    for (i = 0; i < 6; i++) {
+        gpfsel_set(s, i, 0);
+    }
+
+    s->sd_fsel = 0;
+
+    /* SDHCI is selected by default */
+    sdbus_reparent_card(&s->sdbus, s->sdbus_sdhci);
+
+    s->lev0 = 0;
+    s->lev1 = 0;
+}
+
+static const MemoryRegionOps bcm2835_gpio_ops = {
+    .read = bcm2835_gpio_read,
+    .write = bcm2835_gpio_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+};
+
+static const VMStateDescription vmstate_bcm2835_gpio = {
+    .name = "bcm2835_gpio",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT8_ARRAY(fsel, BCM2835GpioState, 54),
+        VMSTATE_UINT32(lev0, BCM2835GpioState),
+        VMSTATE_UINT32(lev1, BCM2835GpioState),
+        VMSTATE_UINT8(sd_fsel, BCM2835GpioState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static void bcm2835_gpio_init(Object *obj)
+{
+    BCM2835GpioState *s = BCM2835_GPIO(obj);
+    DeviceState *dev = DEVICE(obj);
+    SysBusDevice *sbd = SYS_BUS_DEVICE(obj);
+
+    qbus_create_inplace(&s->sdbus, sizeof(s->sdbus),
+                        TYPE_SD_BUS, DEVICE(s), "sd-bus");
+
+    memory_region_init_io(&s->iomem, obj,
+            &bcm2835_gpio_ops, s, "bcm2835_gpio", 0x1000);
+    sysbus_init_mmio(sbd, &s->iomem);
+    qdev_init_gpio_out(dev, s->out, 54);
+}
+
+static void bcm2835_gpio_realize(DeviceState *dev, Error **errp)
+{
+    BCM2835GpioState *s = BCM2835_GPIO(dev);
+    Object *obj;
+    Error *err = NULL;
+
+    obj = object_property_get_link(OBJECT(dev), "sdbus-sdhci", &err);
+    if (obj == NULL) {
+        error_setg(errp, "%s: required sdhci link not found: %s",
+                __func__, error_get_pretty(err));
+        return;
+    }
+    s->sdbus_sdhci = SD_BUS(obj);
+
+    obj = object_property_get_link(OBJECT(dev), "sdbus-sdhost", &err);
+    if (obj == NULL) {
+        error_setg(errp, "%s: required sdhost link not found: %s",
+                __func__, error_get_pretty(err));
+        return;
+    }
+    s->sdbus_sdhost = SD_BUS(obj);
+}
+
+static void bcm2835_gpio_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+
+    dc->vmsd = &vmstate_bcm2835_gpio;
+    dc->realize = &bcm2835_gpio_realize;
+    dc->reset = &bcm2835_gpio_reset;
+}
+
+static const TypeInfo bcm2835_gpio_info = {
+    .name          = TYPE_BCM2835_GPIO,
+    .parent        = TYPE_SYS_BUS_DEVICE,
+    .instance_size = sizeof(BCM2835GpioState),
+    .instance_init = bcm2835_gpio_init,
+    .class_init    = bcm2835_gpio_class_init,
+};
+
+static void bcm2835_gpio_register_types(void)
+{
+    type_register_static(&bcm2835_gpio_info);
+}
+
+type_init(bcm2835_gpio_register_types)
diff --git a/hw/ide/core.c b/hw/ide/core.c
index cfa5de6ebf..db509b3e15 100644
--- a/hw/ide/core.c
+++ b/hw/ide/core.c
@@ -1120,7 +1120,7 @@ static void ide_cfata_metadata_write(IDEState *s)
 }
 
 /* called when the inserted state of the media has changed */
-static void ide_cd_change_cb(void *opaque, bool load)
+static void ide_cd_change_cb(void *opaque, bool load, Error **errp)
 {
     IDEState *s = opaque;
     uint64_t nb_sectors;
diff --git a/hw/ide/qdev.c b/hw/ide/qdev.c
index dbaa75cf59..4383cd111d 100644
--- a/hw/ide/qdev.c
+++ b/hw/ide/qdev.c
@@ -170,7 +170,7 @@ static int ide_dev_initfn(IDEDevice *dev, IDEDriveKind kind)
             return -1;
         } else {
             /* Anonymous BlockBackend for an empty drive */
-            dev->conf.blk = blk_new();
+            dev->conf.blk = blk_new(0, BLK_PERM_ALL);
         }
     }
 
@@ -196,7 +196,12 @@ static int ide_dev_initfn(IDEDevice *dev, IDEDriveKind kind)
             return -1;
         }
     }
-    blkconf_apply_backend_options(&dev->conf);
+    blkconf_apply_backend_options(&dev->conf, kind == IDE_CD, kind != IDE_CD,
+                                  &err);
+    if (err) {
+        error_report_err(err);
+        return -1;
+    }
 
     if (ide_init_drive(s, dev->conf.blk, kind,
                        dev->version, dev->serial, dev->model, dev->wwn,
diff --git a/hw/intc/Makefile.objs b/hw/intc/Makefile.objs
index 8948106ac4..adedd0da5f 100644
--- a/hw/intc/Makefile.objs
+++ b/hw/intc/Makefile.objs
@@ -24,7 +24,7 @@ obj-$(CONFIG_APIC) += apic.o apic_common.o
 obj-$(CONFIG_ARM_GIC_KVM) += arm_gic_kvm.o
 obj-$(call land,$(CONFIG_ARM_GIC_KVM),$(TARGET_AARCH64)) += arm_gicv3_kvm.o
 obj-$(call land,$(CONFIG_ARM_GIC_KVM),$(TARGET_AARCH64)) += arm_gicv3_its_kvm.o
-obj-$(CONFIG_STELLARIS) += armv7m_nvic.o
+obj-$(CONFIG_ARM_V7M) += armv7m_nvic.o
 obj-$(CONFIG_EXYNOS4) += exynos4210_gic.o exynos4210_combiner.o
 obj-$(CONFIG_GRLIB) += grlib_irqmp.o
 obj-$(CONFIG_IOAPIC) += ioapic.o
diff --git a/hw/intc/arm_gic.c b/hw/intc/arm_gic.c
index 521aac3cc6..8e5a9d8a3e 100644
--- a/hw/intc/arm_gic.c
+++ b/hw/intc/arm_gic.c
@@ -156,17 +156,6 @@ static void gic_set_irq_11mpcore(GICState *s, int irq, int level,
     }
 }
 
-static void gic_set_irq_nvic(GICState *s, int irq, int level,
-                                 int cm, int target)
-{
-    if (level) {
-        GIC_SET_LEVEL(irq, cm);
-        GIC_SET_PENDING(irq, target);
-    } else {
-        GIC_CLEAR_LEVEL(irq, cm);
-    }
-}
-
 static void gic_set_irq_generic(GICState *s, int irq, int level,
                                 int cm, int target)
 {
@@ -214,8 +203,6 @@ static void gic_set_irq(void *opaque, int irq, int level)
 
     if (s->revision == REV_11MPCORE) {
         gic_set_irq_11mpcore(s, irq, level, cm, target);
-    } else if (s->revision == REV_NVIC) {
-        gic_set_irq_nvic(s, irq, level, cm, target);
     } else {
         gic_set_irq_generic(s, irq, level, cm, target);
     }
@@ -367,7 +354,7 @@ uint32_t gic_acknowledge_irq(GICState *s, int cpu, MemTxAttrs attrs)
         return 1023;
     }
 
-    if (s->revision == REV_11MPCORE || s->revision == REV_NVIC) {
+    if (s->revision == REV_11MPCORE) {
         /* Clear pending flags for both level and edge triggered interrupts.
          * Level triggered IRQs will be reasserted once they become inactive.
          */
@@ -589,11 +576,6 @@ void gic_complete_irq(GICState *s, int cpu, int irq, MemTxAttrs attrs)
             DPRINTF("Set %d pending mask %x\n", irq, cm);
             GIC_SET_PENDING(irq, cm);
         }
-    } else if (s->revision == REV_NVIC) {
-        if (GIC_TEST_LEVEL(irq, cm)) {
-            DPRINTF("Set nvic %d pending mask %x\n", irq, cm);
-            GIC_SET_PENDING(irq, cm);
-        }
     }
 
     group = gic_has_groups(s) && GIC_TEST_GROUP(irq, cm);
@@ -768,7 +750,7 @@ static uint32_t gic_dist_readb(void *opaque, hwaddr offset, MemTxAttrs attrs)
     } else if (offset < 0xf10) {
         goto bad_reg;
     } else if (offset < 0xf30) {
-        if (s->revision == REV_11MPCORE || s->revision == REV_NVIC) {
+        if (s->revision == REV_11MPCORE) {
             goto bad_reg;
         }
 
@@ -802,9 +784,6 @@ static uint32_t gic_dist_readb(void *opaque, hwaddr offset, MemTxAttrs attrs)
             case 2:
                 res = gic_id_gicv2[(offset - 0xfd0) >> 2];
                 break;
-            case REV_NVIC:
-                /* Shouldn't be able to get here */
-                abort();
             default:
                 res = 0;
             }
@@ -1028,7 +1007,7 @@ static void gic_dist_writeb(void *opaque, hwaddr offset,
                 continue; /* Ignore Non-secure access of Group0 IRQ */
             }
 
-            if (s->revision == REV_11MPCORE || s->revision == REV_NVIC) {
+            if (s->revision == REV_11MPCORE) {
                 if (value & (1 << (i * 2))) {
                     GIC_SET_MODEL(irq + i);
                 } else {
@@ -1046,7 +1025,7 @@ static void gic_dist_writeb(void *opaque, hwaddr offset,
         goto bad_reg;
     } else if (offset < 0xf20) {
         /* GICD_CPENDSGIRn */
-        if (s->revision == REV_11MPCORE || s->revision == REV_NVIC) {
+        if (s->revision == REV_11MPCORE) {
             goto bad_reg;
         }
         irq = (offset - 0xf10);
@@ -1060,7 +1039,7 @@ static void gic_dist_writeb(void *opaque, hwaddr offset,
         }
     } else if (offset < 0xf30) {
         /* GICD_SPENDSGIRn */
-        if (s->revision == REV_11MPCORE || s->revision == REV_NVIC) {
+        if (s->revision == REV_11MPCORE) {
             goto bad_reg;
         }
         irq = (offset - 0xf20);
diff --git a/hw/intc/arm_gic_common.c b/hw/intc/arm_gic_common.c
index 4a8df44fb1..70f1134823 100644
--- a/hw/intc/arm_gic_common.c
+++ b/hw/intc/arm_gic_common.c
@@ -99,9 +99,7 @@ void gic_init_irqs_and_mmio(GICState *s, qemu_irq_handler handler,
      *  [N+32..N+63] PPIs for CPU 1
      *   ...
      */
-    if (s->revision != REV_NVIC) {
-        i += (GIC_INTERNAL * s->num_cpu);
-    }
+    i += (GIC_INTERNAL * s->num_cpu);
     qdev_init_gpio_in(DEVICE(s), handler, i);
 
     for (i = 0; i < s->num_cpu; i++) {
@@ -121,16 +119,12 @@ void gic_init_irqs_and_mmio(GICState *s, qemu_irq_handler handler,
     memory_region_init_io(&s->iomem, OBJECT(s), ops, s, "gic_dist", 0x1000);
     sysbus_init_mmio(sbd, &s->iomem);
 
-    if (s->revision != REV_NVIC) {
-        /* This is the main CPU interface "for this core". It is always
-         * present because it is required by both software emulation and KVM.
-         * NVIC is not handled here because its CPU interface is different,
-         * neither it can use KVM.
-         */
-        memory_region_init_io(&s->cpuiomem[0], OBJECT(s), ops ? &ops[1] : NULL,
-                              s, "gic_cpu", s->revision == 2 ? 0x2000 : 0x100);
-        sysbus_init_mmio(sbd, &s->cpuiomem[0]);
-    }
+    /* This is the main CPU interface "for this core". It is always
+     * present because it is required by both software emulation and KVM.
+     */
+    memory_region_init_io(&s->cpuiomem[0], OBJECT(s), ops ? &ops[1] : NULL,
+                          s, "gic_cpu", s->revision == 2 ? 0x2000 : 0x100);
+    sysbus_init_mmio(sbd, &s->cpuiomem[0]);
 }
 
 static void arm_gic_common_realize(DeviceState *dev, Error **errp)
@@ -162,7 +156,7 @@ static void arm_gic_common_realize(DeviceState *dev, Error **errp)
     }
 
     if (s->security_extn &&
-        (s->revision == REV_11MPCORE || s->revision == REV_NVIC)) {
+        (s->revision == REV_11MPCORE)) {
         error_setg(errp, "this GIC revision does not implement "
                    "the security extensions");
         return;
@@ -255,7 +249,6 @@ static Property arm_gic_common_properties[] = {
     DEFINE_PROP_UINT32("num-irq", GICState, num_irq, 32),
     /* Revision can be 1 or 2 for GIC architecture specification
      * versions 1 or 2, or 0 to indicate the legacy 11MPCore GIC.
-     * (Internally, 0xffffffff also indicates "not a GIC but an NVIC".)
      */
     DEFINE_PROP_UINT32("revision", GICState, revision, 1),
     /* True if the GIC should implement the security extensions */
diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c
index 16b9b0f7eb..c6493d6c07 100644
--- a/hw/intc/arm_gicv3_common.c
+++ b/hw/intc/arm_gicv3_common.c
@@ -70,6 +70,38 @@ static const VMStateDescription vmstate_gicv3_cpu_virt = {
     }
 };
 
+static int icc_sre_el1_reg_pre_load(void *opaque)
+{
+    GICv3CPUState *cs = opaque;
+
+   /*
+    * If the sre_el1 subsection is not transferred this
+    * means SRE_EL1 is 0x7 (which might not be the same as
+    * our reset value).
+    */
+    cs->icc_sre_el1 = 0x7;
+    return 0;
+}
+
+static bool icc_sre_el1_reg_needed(void *opaque)
+{
+    GICv3CPUState *cs = opaque;
+
+    return cs->icc_sre_el1 != 7;
+}
+
+const VMStateDescription vmstate_gicv3_cpu_sre_el1 = {
+    .name = "arm_gicv3_cpu/sre_el1",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .pre_load = icc_sre_el1_reg_pre_load,
+    .needed = icc_sre_el1_reg_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT64(icc_sre_el1, GICv3CPUState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static const VMStateDescription vmstate_gicv3_cpu = {
     .name = "arm_gicv3_cpu",
     .version_id = 1,
@@ -100,6 +132,10 @@ static const VMStateDescription vmstate_gicv3_cpu = {
     .subsections = (const VMStateDescription * []) {
         &vmstate_gicv3_cpu_virt,
         NULL
+    },
+    .subsections = (const VMStateDescription * []) {
+        &vmstate_gicv3_cpu_sre_el1,
+        NULL
     }
 };
 
@@ -216,6 +252,8 @@ static void arm_gicv3_common_realize(DeviceState *dev, Error **errp)
 
         s->cpu[i].cpu = cpu;
         s->cpu[i].gic = s;
+        /* Store GICv3CPUState in CPUARMState gicv3state pointer */
+        gicv3_set_gicv3state(cpu, &s->cpu[i]);
 
         /* Pre-construct the GICR_TYPER:
          * For our implementation:
diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c
index f775aba507..0b208560bd 100644
--- a/hw/intc/arm_gicv3_cpuif.c
+++ b/hw/intc/arm_gicv3_cpuif.c
@@ -19,6 +19,14 @@
 #include "gicv3_internal.h"
 #include "cpu.h"
 
+void gicv3_set_gicv3state(CPUState *cpu, GICv3CPUState *s)
+{
+    ARMCPU *arm_cpu = ARM_CPU(cpu);
+    CPUARMState *env = &arm_cpu->env;
+
+    env->gicv3state = (void *)s;
+};
+
 static GICv3CPUState *icc_cs_from_env(CPUARMState *env)
 {
     /* Given the CPU, find the right GICv3CPUState struct.
diff --git a/hw/intc/arm_gicv3_kvm.c b/hw/intc/arm_gicv3_kvm.c
index d69dc47370..81f0403117 100644
--- a/hw/intc/arm_gicv3_kvm.c
+++ b/hw/intc/arm_gicv3_kvm.c
@@ -23,8 +23,10 @@
 #include "qapi/error.h"
 #include "hw/intc/arm_gicv3_common.h"
 #include "hw/sysbus.h"
+#include "qemu/error-report.h"
 #include "sysemu/kvm.h"
 #include "kvm_arm.h"
+#include "gicv3_internal.h"
 #include "vgic_common.h"
 #include "migration/migration.h"
 
@@ -44,6 +46,32 @@
 #define KVM_ARM_GICV3_GET_CLASS(obj) \
      OBJECT_GET_CLASS(KVMARMGICv3Class, (obj), TYPE_KVM_ARM_GICV3)
 
+#define   KVM_DEV_ARM_VGIC_SYSREG(op0, op1, crn, crm, op2)         \
+                             (ARM64_SYS_REG_SHIFT_MASK(op0, OP0) | \
+                              ARM64_SYS_REG_SHIFT_MASK(op1, OP1) | \
+                              ARM64_SYS_REG_SHIFT_MASK(crn, CRN) | \
+                              ARM64_SYS_REG_SHIFT_MASK(crm, CRM) | \
+                              ARM64_SYS_REG_SHIFT_MASK(op2, OP2))
+
+#define ICC_PMR_EL1     \
+    KVM_DEV_ARM_VGIC_SYSREG(3, 0, 4, 6, 0)
+#define ICC_BPR0_EL1    \
+    KVM_DEV_ARM_VGIC_SYSREG(3, 0, 12, 8, 3)
+#define ICC_AP0R_EL1(n) \
+    KVM_DEV_ARM_VGIC_SYSREG(3, 0, 12, 8, 4 | n)
+#define ICC_AP1R_EL1(n) \
+    KVM_DEV_ARM_VGIC_SYSREG(3, 0, 12, 9, n)
+#define ICC_BPR1_EL1    \
+    KVM_DEV_ARM_VGIC_SYSREG(3, 0, 12, 12, 3)
+#define ICC_CTLR_EL1    \
+    KVM_DEV_ARM_VGIC_SYSREG(3, 0, 12, 12, 4)
+#define ICC_SRE_EL1 \
+    KVM_DEV_ARM_VGIC_SYSREG(3, 0, 12, 12, 5)
+#define ICC_IGRPEN0_EL1 \
+    KVM_DEV_ARM_VGIC_SYSREG(3, 0, 12, 12, 6)
+#define ICC_IGRPEN1_EL1 \
+    KVM_DEV_ARM_VGIC_SYSREG(3, 0, 12, 12, 7)
+
 typedef struct KVMARMGICv3Class {
     ARMGICv3CommonClass parent_class;
     DeviceRealize parent_realize;
@@ -57,16 +85,549 @@ static void kvm_arm_gicv3_set_irq(void *opaque, int irq, int level)
     kvm_arm_gic_set_irq(s->num_irq, irq, level);
 }
 
+#define KVM_VGIC_ATTR(reg, typer) \
+    ((typer & KVM_DEV_ARM_VGIC_V3_MPIDR_MASK) | (reg))
+
+static inline void kvm_gicd_access(GICv3State *s, int offset,
+                                   uint32_t *val, bool write)
+{
+    kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_DIST_REGS,
+                      KVM_VGIC_ATTR(offset, 0),
+                      val, write);
+}
+
+static inline void kvm_gicr_access(GICv3State *s, int offset, int cpu,
+                                   uint32_t *val, bool write)
+{
+    kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_REDIST_REGS,
+                      KVM_VGIC_ATTR(offset, s->cpu[cpu].gicr_typer),
+                      val, write);
+}
+
+static inline void kvm_gicc_access(GICv3State *s, uint64_t reg, int cpu,
+                                   uint64_t *val, bool write)
+{
+    kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS,
+                      KVM_VGIC_ATTR(reg, s->cpu[cpu].gicr_typer),
+                      val, write);
+}
+
+static inline void kvm_gic_line_level_access(GICv3State *s, int irq, int cpu,
+                                             uint32_t *val, bool write)
+{
+    kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO,
+                      KVM_VGIC_ATTR(irq, s->cpu[cpu].gicr_typer) |
+                      (VGIC_LEVEL_INFO_LINE_LEVEL <<
+                       KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT),
+                      val, write);
+}
+
+/* Loop through each distributor IRQ related register; since bits
+ * corresponding to SPIs and PPIs are RAZ/WI when affinity routing
+ * is enabled, we skip those.
+ */
+#define for_each_dist_irq_reg(_irq, _max, _field_width) \
+    for (_irq = GIC_INTERNAL; _irq < _max; _irq += (32 / _field_width))
+
+static void kvm_dist_get_priority(GICv3State *s, uint32_t offset, uint8_t *bmp)
+{
+    uint32_t reg, *field;
+    int irq;
+
+    field = (uint32_t *)bmp;
+    for_each_dist_irq_reg(irq, s->num_irq, 8) {
+        kvm_gicd_access(s, offset, &reg, false);
+        *field = reg;
+        offset += 4;
+        field++;
+    }
+}
+
+static void kvm_dist_put_priority(GICv3State *s, uint32_t offset, uint8_t *bmp)
+{
+    uint32_t reg, *field;
+    int irq;
+
+    field = (uint32_t *)bmp;
+    for_each_dist_irq_reg(irq, s->num_irq, 8) {
+        reg = *field;
+        kvm_gicd_access(s, offset, &reg, true);
+        offset += 4;
+        field++;
+    }
+}
+
+static void kvm_dist_get_edge_trigger(GICv3State *s, uint32_t offset,
+                                      uint32_t *bmp)
+{
+    uint32_t reg;
+    int irq;
+
+    for_each_dist_irq_reg(irq, s->num_irq, 2) {
+        kvm_gicd_access(s, offset, &reg, false);
+        reg = half_unshuffle32(reg >> 1);
+        if (irq % 32 != 0) {
+            reg = (reg << 16);
+        }
+        *gic_bmp_ptr32(bmp, irq) |=  reg;
+        offset += 4;
+    }
+}
+
+static void kvm_dist_put_edge_trigger(GICv3State *s, uint32_t offset,
+                                      uint32_t *bmp)
+{
+    uint32_t reg;
+    int irq;
+
+    for_each_dist_irq_reg(irq, s->num_irq, 2) {
+        reg = *gic_bmp_ptr32(bmp, irq);
+        if (irq % 32 != 0) {
+            reg = (reg & 0xffff0000) >> 16;
+        } else {
+            reg = reg & 0xffff;
+        }
+        reg = half_shuffle32(reg) << 1;
+        kvm_gicd_access(s, offset, &reg, true);
+        offset += 4;
+    }
+}
+
+static void kvm_gic_get_line_level_bmp(GICv3State *s, uint32_t *bmp)
+{
+    uint32_t reg;
+    int irq;
+
+    for_each_dist_irq_reg(irq, s->num_irq, 1) {
+        kvm_gic_line_level_access(s, irq, 0, &reg, false);
+        *gic_bmp_ptr32(bmp, irq) = reg;
+    }
+}
+
+static void kvm_gic_put_line_level_bmp(GICv3State *s, uint32_t *bmp)
+{
+    uint32_t reg;
+    int irq;
+
+    for_each_dist_irq_reg(irq, s->num_irq, 1) {
+        reg = *gic_bmp_ptr32(bmp, irq);
+        kvm_gic_line_level_access(s, irq, 0, &reg, true);
+    }
+}
+
+/* Read a bitmap register group from the kernel VGIC. */
+static void kvm_dist_getbmp(GICv3State *s, uint32_t offset, uint32_t *bmp)
+{
+    uint32_t reg;
+    int irq;
+
+    for_each_dist_irq_reg(irq, s->num_irq, 1) {
+        kvm_gicd_access(s, offset, &reg, false);
+        *gic_bmp_ptr32(bmp, irq) = reg;
+        offset += 4;
+    }
+}
+
+static void kvm_dist_putbmp(GICv3State *s, uint32_t offset,
+                            uint32_t clroffset, uint32_t *bmp)
+{
+    uint32_t reg;
+    int irq;
+
+    for_each_dist_irq_reg(irq, s->num_irq, 1) {
+        /* If this bitmap is a set/clear register pair, first write to the
+         * clear-reg to clear all bits before using the set-reg to write
+         * the 1 bits.
+         */
+        if (clroffset != 0) {
+            reg = 0;
+            kvm_gicd_access(s, clroffset, &reg, true);
+        }
+        reg = *gic_bmp_ptr32(bmp, irq);
+        kvm_gicd_access(s, offset, &reg, true);
+        offset += 4;
+    }
+}
+
+static void kvm_arm_gicv3_check(GICv3State *s)
+{
+    uint32_t reg;
+    uint32_t num_irq;
+
+    /* Sanity checking s->num_irq */
+    kvm_gicd_access(s, GICD_TYPER, &reg, false);
+    num_irq = ((reg & 0x1f) + 1) * 32;
+
+    if (num_irq < s->num_irq) {
+        error_report("Model requests %u IRQs, but kernel supports max %u",
+                     s->num_irq, num_irq);
+        abort();
+    }
+}
+
 static void kvm_arm_gicv3_put(GICv3State *s)
 {
-    /* TODO */
-    DPRINTF("Cannot put kernel gic state, no kernel interface\n");
+    uint32_t regl, regh, reg;
+    uint64_t reg64, redist_typer;
+    int ncpu, i;
+
+    kvm_arm_gicv3_check(s);
+
+    kvm_gicr_access(s, GICR_TYPER, 0, &regl, false);
+    kvm_gicr_access(s, GICR_TYPER + 4, 0, &regh, false);
+    redist_typer = ((uint64_t)regh << 32) | regl;
+
+    reg = s->gicd_ctlr;
+    kvm_gicd_access(s, GICD_CTLR, &reg, true);
+
+    if (redist_typer & GICR_TYPER_PLPIS) {
+        /* Set base addresses before LPIs are enabled by GICR_CTLR write */
+        for (ncpu = 0; ncpu < s->num_cpu; ncpu++) {
+            GICv3CPUState *c = &s->cpu[ncpu];
+
+            reg64 = c->gicr_propbaser;
+            regl = (uint32_t)reg64;
+            kvm_gicr_access(s, GICR_PROPBASER, ncpu, &regl, true);
+            regh = (uint32_t)(reg64 >> 32);
+            kvm_gicr_access(s, GICR_PROPBASER + 4, ncpu, &regh, true);
+
+            reg64 = c->gicr_pendbaser;
+            if (!c->gicr_ctlr & GICR_CTLR_ENABLE_LPIS) {
+                /* Setting PTZ is advised if LPIs are disabled, to reduce
+                 * GIC initialization time.
+                 */
+                reg64 |= GICR_PENDBASER_PTZ;
+            }
+            regl = (uint32_t)reg64;
+            kvm_gicr_access(s, GICR_PENDBASER, ncpu, &regl, true);
+            regh = (uint32_t)(reg64 >> 32);
+            kvm_gicr_access(s, GICR_PENDBASER + 4, ncpu, &regh, true);
+        }
+    }
+
+    /* Redistributor state (one per CPU) */
+
+    for (ncpu = 0; ncpu < s->num_cpu; ncpu++) {
+        GICv3CPUState *c = &s->cpu[ncpu];
+
+        reg = c->gicr_ctlr;
+        kvm_gicr_access(s, GICR_CTLR, ncpu, &reg, true);
+
+        reg = c->gicr_statusr[GICV3_NS];
+        kvm_gicr_access(s, GICR_STATUSR, ncpu, &reg, true);
+
+        reg = c->gicr_waker;
+        kvm_gicr_access(s, GICR_WAKER, ncpu, &reg, true);
+
+        reg = c->gicr_igroupr0;
+        kvm_gicr_access(s, GICR_IGROUPR0, ncpu, &reg, true);
+
+        reg = ~0;
+        kvm_gicr_access(s, GICR_ICENABLER0, ncpu, &reg, true);
+        reg = c->gicr_ienabler0;
+        kvm_gicr_access(s, GICR_ISENABLER0, ncpu, &reg, true);
+
+        /* Restore config before pending so we treat level/edge correctly */
+        reg = half_shuffle32(c->edge_trigger >> 16) << 1;
+        kvm_gicr_access(s, GICR_ICFGR1, ncpu, &reg, true);
+
+        reg = c->level;
+        kvm_gic_line_level_access(s, 0, ncpu, &reg, true);
+
+        reg = ~0;
+        kvm_gicr_access(s, GICR_ICPENDR0, ncpu, &reg, true);
+        reg = c->gicr_ipendr0;
+        kvm_gicr_access(s, GICR_ISPENDR0, ncpu, &reg, true);
+
+        reg = ~0;
+        kvm_gicr_access(s, GICR_ICACTIVER0, ncpu, &reg, true);
+        reg = c->gicr_iactiver0;
+        kvm_gicr_access(s, GICR_ISACTIVER0, ncpu, &reg, true);
+
+        for (i = 0; i < GIC_INTERNAL; i += 4) {
+            reg = c->gicr_ipriorityr[i] |
+                (c->gicr_ipriorityr[i + 1] << 8) |
+                (c->gicr_ipriorityr[i + 2] << 16) |
+                (c->gicr_ipriorityr[i + 3] << 24);
+            kvm_gicr_access(s, GICR_IPRIORITYR + i, ncpu, &reg, true);
+        }
+    }
+
+    /* Distributor state (shared between all CPUs */
+    reg = s->gicd_statusr[GICV3_NS];
+    kvm_gicd_access(s, GICD_STATUSR, &reg, true);
+
+    /* s->enable bitmap -> GICD_ISENABLERn */
+    kvm_dist_putbmp(s, GICD_ISENABLER, GICD_ICENABLER, s->enabled);
+
+    /* s->group bitmap -> GICD_IGROUPRn */
+    kvm_dist_putbmp(s, GICD_IGROUPR, 0, s->group);
+
+    /* Restore targets before pending to ensure the pending state is set on
+     * the appropriate CPU interfaces in the kernel
+     */
+
+    /* s->gicd_irouter[irq] -> GICD_IROUTERn
+     * We can't use kvm_dist_put() here because the registers are 64-bit
+     */
+    for (i = GIC_INTERNAL; i < s->num_irq; i++) {
+        uint32_t offset;
+
+        offset = GICD_IROUTER + (sizeof(uint32_t) * i);
+        reg = (uint32_t)s->gicd_irouter[i];
+        kvm_gicd_access(s, offset, &reg, true);
+
+        offset = GICD_IROUTER + (sizeof(uint32_t) * i) + 4;
+        reg = (uint32_t)(s->gicd_irouter[i] >> 32);
+        kvm_gicd_access(s, offset, &reg, true);
+    }
+
+    /* s->trigger bitmap -> GICD_ICFGRn
+     * (restore configuration registers before pending IRQs so we treat
+     * level/edge correctly)
+     */
+    kvm_dist_put_edge_trigger(s, GICD_ICFGR, s->edge_trigger);
+
+    /* s->level bitmap ->  line_level */
+    kvm_gic_put_line_level_bmp(s, s->level);
+
+    /* s->pending bitmap -> GICD_ISPENDRn */
+    kvm_dist_putbmp(s, GICD_ISPENDR, GICD_ICPENDR, s->pending);
+
+    /* s->active bitmap -> GICD_ISACTIVERn */
+    kvm_dist_putbmp(s, GICD_ISACTIVER, GICD_ICACTIVER, s->active);
+
+    /* s->gicd_ipriority[] -> GICD_IPRIORITYRn */
+    kvm_dist_put_priority(s, GICD_IPRIORITYR, s->gicd_ipriority);
+
+    /* CPU Interface state (one per CPU) */
+
+    for (ncpu = 0; ncpu < s->num_cpu; ncpu++) {
+        GICv3CPUState *c = &s->cpu[ncpu];
+        int num_pri_bits;
+
+        kvm_gicc_access(s, ICC_SRE_EL1, ncpu, &c->icc_sre_el1, true);
+        kvm_gicc_access(s, ICC_CTLR_EL1, ncpu,
+                        &c->icc_ctlr_el1[GICV3_NS], true);
+        kvm_gicc_access(s, ICC_IGRPEN0_EL1, ncpu,
+                        &c->icc_igrpen[GICV3_G0], true);
+        kvm_gicc_access(s, ICC_IGRPEN1_EL1, ncpu,
+                        &c->icc_igrpen[GICV3_G1NS], true);
+        kvm_gicc_access(s, ICC_PMR_EL1, ncpu, &c->icc_pmr_el1, true);
+        kvm_gicc_access(s, ICC_BPR0_EL1, ncpu, &c->icc_bpr[GICV3_G0], true);
+        kvm_gicc_access(s, ICC_BPR1_EL1, ncpu, &c->icc_bpr[GICV3_G1NS], true);
+
+        num_pri_bits = ((c->icc_ctlr_el1[GICV3_NS] &
+                        ICC_CTLR_EL1_PRIBITS_MASK) >>
+                        ICC_CTLR_EL1_PRIBITS_SHIFT) + 1;
+
+        switch (num_pri_bits) {
+        case 7:
+            reg64 = c->icc_apr[GICV3_G0][3];
+            kvm_gicc_access(s, ICC_AP0R_EL1(3), ncpu, &reg64, true);
+            reg64 = c->icc_apr[GICV3_G0][2];
+            kvm_gicc_access(s, ICC_AP0R_EL1(2), ncpu, &reg64, true);
+        case 6:
+            reg64 = c->icc_apr[GICV3_G0][1];
+            kvm_gicc_access(s, ICC_AP0R_EL1(1), ncpu, &reg64, true);
+        default:
+            reg64 = c->icc_apr[GICV3_G0][0];
+            kvm_gicc_access(s, ICC_AP0R_EL1(0), ncpu, &reg64, true);
+        }
+
+        switch (num_pri_bits) {
+        case 7:
+            reg64 = c->icc_apr[GICV3_G1NS][3];
+            kvm_gicc_access(s, ICC_AP1R_EL1(3), ncpu, &reg64, true);
+            reg64 = c->icc_apr[GICV3_G1NS][2];
+            kvm_gicc_access(s, ICC_AP1R_EL1(2), ncpu, &reg64, true);
+        case 6:
+            reg64 = c->icc_apr[GICV3_G1NS][1];
+            kvm_gicc_access(s, ICC_AP1R_EL1(1), ncpu, &reg64, true);
+        default:
+            reg64 = c->icc_apr[GICV3_G1NS][0];
+            kvm_gicc_access(s, ICC_AP1R_EL1(0), ncpu, &reg64, true);
+        }
+    }
 }
 
 static void kvm_arm_gicv3_get(GICv3State *s)
 {
-    /* TODO */
-    DPRINTF("Cannot get kernel gic state, no kernel interface\n");
+    uint32_t regl, regh, reg;
+    uint64_t reg64, redist_typer;
+    int ncpu, i;
+
+    kvm_arm_gicv3_check(s);
+
+    kvm_gicr_access(s, GICR_TYPER, 0, &regl, false);
+    kvm_gicr_access(s, GICR_TYPER + 4, 0, &regh, false);
+    redist_typer = ((uint64_t)regh << 32) | regl;
+
+    kvm_gicd_access(s, GICD_CTLR, &reg, false);
+    s->gicd_ctlr = reg;
+
+    /* Redistributor state (one per CPU) */
+
+    for (ncpu = 0; ncpu < s->num_cpu; ncpu++) {
+        GICv3CPUState *c = &s->cpu[ncpu];
+
+        kvm_gicr_access(s, GICR_CTLR, ncpu, &reg, false);
+        c->gicr_ctlr = reg;
+
+        kvm_gicr_access(s, GICR_STATUSR, ncpu, &reg, false);
+        c->gicr_statusr[GICV3_NS] = reg;
+
+        kvm_gicr_access(s, GICR_WAKER, ncpu, &reg, false);
+        c->gicr_waker = reg;
+
+        kvm_gicr_access(s, GICR_IGROUPR0, ncpu, &reg, false);
+        c->gicr_igroupr0 = reg;
+        kvm_gicr_access(s, GICR_ISENABLER0, ncpu, &reg, false);
+        c->gicr_ienabler0 = reg;
+        kvm_gicr_access(s, GICR_ICFGR1, ncpu, &reg, false);
+        c->edge_trigger = half_unshuffle32(reg >> 1) << 16;
+        kvm_gic_line_level_access(s, 0, ncpu, &reg, false);
+        c->level = reg;
+        kvm_gicr_access(s, GICR_ISPENDR0, ncpu, &reg, false);
+        c->gicr_ipendr0 = reg;
+        kvm_gicr_access(s, GICR_ISACTIVER0, ncpu, &reg, false);
+        c->gicr_iactiver0 = reg;
+
+        for (i = 0; i < GIC_INTERNAL; i += 4) {
+            kvm_gicr_access(s, GICR_IPRIORITYR + i, ncpu, &reg, false);
+            c->gicr_ipriorityr[i] = extract32(reg, 0, 8);
+            c->gicr_ipriorityr[i + 1] = extract32(reg, 8, 8);
+            c->gicr_ipriorityr[i + 2] = extract32(reg, 16, 8);
+            c->gicr_ipriorityr[i + 3] = extract32(reg, 24, 8);
+        }
+    }
+
+    if (redist_typer & GICR_TYPER_PLPIS) {
+        for (ncpu = 0; ncpu < s->num_cpu; ncpu++) {
+            GICv3CPUState *c = &s->cpu[ncpu];
+
+            kvm_gicr_access(s, GICR_PROPBASER, ncpu, &regl, false);
+            kvm_gicr_access(s, GICR_PROPBASER + 4, ncpu, &regh, false);
+            c->gicr_propbaser = ((uint64_t)regh << 32) | regl;
+
+            kvm_gicr_access(s, GICR_PENDBASER, ncpu, &regl, false);
+            kvm_gicr_access(s, GICR_PENDBASER + 4, ncpu, &regh, false);
+            c->gicr_pendbaser = ((uint64_t)regh << 32) | regl;
+        }
+    }
+
+    /* Distributor state (shared between all CPUs */
+
+    kvm_gicd_access(s, GICD_STATUSR, &reg, false);
+    s->gicd_statusr[GICV3_NS] = reg;
+
+    /* GICD_IGROUPRn -> s->group bitmap */
+    kvm_dist_getbmp(s, GICD_IGROUPR, s->group);
+
+    /* GICD_ISENABLERn -> s->enabled bitmap */
+    kvm_dist_getbmp(s, GICD_ISENABLER, s->enabled);
+
+    /* Line level of irq */
+    kvm_gic_get_line_level_bmp(s, s->level);
+    /* GICD_ISPENDRn -> s->pending bitmap */
+    kvm_dist_getbmp(s, GICD_ISPENDR, s->pending);
+
+    /* GICD_ISACTIVERn -> s->active bitmap */
+    kvm_dist_getbmp(s, GICD_ISACTIVER, s->active);
+
+    /* GICD_ICFGRn -> s->trigger bitmap */
+    kvm_dist_get_edge_trigger(s, GICD_ICFGR, s->edge_trigger);
+
+    /* GICD_IPRIORITYRn -> s->gicd_ipriority[] */
+    kvm_dist_get_priority(s, GICD_IPRIORITYR, s->gicd_ipriority);
+
+    /* GICD_IROUTERn -> s->gicd_irouter[irq] */
+    for (i = GIC_INTERNAL; i < s->num_irq; i++) {
+        uint32_t offset;
+
+        offset = GICD_IROUTER + (sizeof(uint32_t) * i);
+        kvm_gicd_access(s, offset, &regl, false);
+        offset = GICD_IROUTER + (sizeof(uint32_t) * i) + 4;
+        kvm_gicd_access(s, offset, &regh, false);
+        s->gicd_irouter[i] = ((uint64_t)regh << 32) | regl;
+    }
+
+    /*****************************************************************
+     * CPU Interface(s) State
+     */
+
+    for (ncpu = 0; ncpu < s->num_cpu; ncpu++) {
+        GICv3CPUState *c = &s->cpu[ncpu];
+        int num_pri_bits;
+
+        kvm_gicc_access(s, ICC_SRE_EL1, ncpu, &c->icc_sre_el1, false);
+        kvm_gicc_access(s, ICC_CTLR_EL1, ncpu,
+                        &c->icc_ctlr_el1[GICV3_NS], false);
+        kvm_gicc_access(s, ICC_IGRPEN0_EL1, ncpu,
+                        &c->icc_igrpen[GICV3_G0], false);
+        kvm_gicc_access(s, ICC_IGRPEN1_EL1, ncpu,
+                        &c->icc_igrpen[GICV3_G1NS], false);
+        kvm_gicc_access(s, ICC_PMR_EL1, ncpu, &c->icc_pmr_el1, false);
+        kvm_gicc_access(s, ICC_BPR0_EL1, ncpu, &c->icc_bpr[GICV3_G0], false);
+        kvm_gicc_access(s, ICC_BPR1_EL1, ncpu, &c->icc_bpr[GICV3_G1NS], false);
+        num_pri_bits = ((c->icc_ctlr_el1[GICV3_NS] &
+                        ICC_CTLR_EL1_PRIBITS_MASK) >>
+                        ICC_CTLR_EL1_PRIBITS_SHIFT) + 1;
+
+        switch (num_pri_bits) {
+        case 7:
+            kvm_gicc_access(s, ICC_AP0R_EL1(3), ncpu, &reg64, false);
+            c->icc_apr[GICV3_G0][3] = reg64;
+            kvm_gicc_access(s, ICC_AP0R_EL1(2), ncpu, &reg64, false);
+            c->icc_apr[GICV3_G0][2] = reg64;
+        case 6:
+            kvm_gicc_access(s, ICC_AP0R_EL1(1), ncpu, &reg64, false);
+            c->icc_apr[GICV3_G0][1] = reg64;
+        default:
+            kvm_gicc_access(s, ICC_AP0R_EL1(0), ncpu, &reg64, false);
+            c->icc_apr[GICV3_G0][0] = reg64;
+        }
+
+        switch (num_pri_bits) {
+        case 7:
+            kvm_gicc_access(s, ICC_AP1R_EL1(3), ncpu, &reg64, false);
+            c->icc_apr[GICV3_G1NS][3] = reg64;
+            kvm_gicc_access(s, ICC_AP1R_EL1(2), ncpu, &reg64, false);
+            c->icc_apr[GICV3_G1NS][2] = reg64;
+        case 6:
+            kvm_gicc_access(s, ICC_AP1R_EL1(1), ncpu, &reg64, false);
+            c->icc_apr[GICV3_G1NS][1] = reg64;
+        default:
+            kvm_gicc_access(s, ICC_AP1R_EL1(0), ncpu, &reg64, false);
+            c->icc_apr[GICV3_G1NS][0] = reg64;
+        }
+    }
+}
+
+static void arm_gicv3_icc_reset(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    ARMCPU *cpu;
+    GICv3State *s;
+    GICv3CPUState *c;
+
+    c = (GICv3CPUState *)env->gicv3state;
+    s = c->gic;
+    cpu = ARM_CPU(c->cpu);
+
+    /* Initialize to actual HW supported configuration */
+    kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS,
+                      KVM_VGIC_ATTR(ICC_CTLR_EL1, cpu->mp_affinity),
+                      &c->icc_ctlr_el1[GICV3_NS], false);
+
+    c->icc_ctlr_el1[GICV3_S] = c->icc_ctlr_el1[GICV3_NS];
+    c->icc_pmr_el1 = 0;
+    c->icc_bpr[GICV3_G0] = GIC_MIN_BPR;
+    c->icc_bpr[GICV3_G1] = GIC_MIN_BPR;
+    c->icc_bpr[GICV3_G1NS] = GIC_MIN_BPR;
+
+    c->icc_sre_el1 = 0x7;
+    memset(c->icc_apr, 0, sizeof(c->icc_apr));
+    memset(c->icc_igrpen, 0, sizeof(c->icc_igrpen));
 }
 
 static void kvm_arm_gicv3_reset(DeviceState *dev)
@@ -77,9 +638,43 @@ static void kvm_arm_gicv3_reset(DeviceState *dev)
     DPRINTF("Reset\n");
 
     kgc->parent_reset(dev);
+
+    if (s->migration_blocker) {
+        DPRINTF("Cannot put kernel gic state, no kernel interface\n");
+        return;
+    }
+
     kvm_arm_gicv3_put(s);
 }
 
+/*
+ * CPU interface registers of GIC needs to be reset on CPU reset.
+ * For the calling arm_gicv3_icc_reset() on CPU reset, we register
+ * below ARMCPRegInfo. As we reset the whole cpu interface under single
+ * register reset, we define only one register of CPU interface instead
+ * of defining all the registers.
+ */
+static const ARMCPRegInfo gicv3_cpuif_reginfo[] = {
+    { .name = "ICC_CTLR_EL1", .state = ARM_CP_STATE_BOTH,
+      .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 12, .opc2 = 4,
+      /*
+       * If ARM_CP_NOP is used, resetfn is not called,
+       * So ARM_CP_NO_RAW is appropriate type.
+       */
+      .type = ARM_CP_NO_RAW,
+      .access = PL1_RW,
+      .readfn = arm_cp_read_zero,
+      .writefn = arm_cp_write_ignore,
+      /*
+       * We hang the whole cpu interface reset routine off here
+       * rather than parcelling it out into one little function
+       * per register
+       */
+      .resetfn = arm_gicv3_icc_reset,
+    },
+    REGINFO_SENTINEL
+};
+
 static void kvm_arm_gicv3_realize(DeviceState *dev, Error **errp)
 {
     GICv3State *s = KVM_ARM_GICV3(dev);
@@ -103,16 +698,10 @@ static void kvm_arm_gicv3_realize(DeviceState *dev, Error **errp)
 
     gicv3_init_irqs_and_mmio(s, kvm_arm_gicv3_set_irq, NULL);
 
-    /* Block migration of a KVM GICv3 device: the API for saving and restoring
-     * the state in the kernel is not yet finalised in the kernel or
-     * implemented in QEMU.
-     */
-    error_setg(&s->migration_blocker, "vGICv3 migration is not implemented");
-    migrate_add_blocker(s->migration_blocker, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        error_free(s->migration_blocker);
-        return;
+    for (i = 0; i < s->num_cpu; i++) {
+        ARMCPU *cpu = ARM_CPU(qemu_get_cpu(i));
+
+        define_arm_cp_regs(cpu, gicv3_cpuif_reginfo);
     }
 
     /* Try to create the device via the device control API */
@@ -145,6 +734,18 @@ static void kvm_arm_gicv3_realize(DeviceState *dev, Error **errp)
 
         kvm_irqchip_commit_routes(kvm_state);
     }
+
+    if (!kvm_device_check_attr(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_DIST_REGS,
+                               GICD_CTLR)) {
+        error_setg(&s->migration_blocker, "This operating system kernel does "
+                                          "not support vGICv3 migration");
+        migrate_add_blocker(s->migration_blocker, &local_err);
+        if (local_err) {
+            error_propagate(errp, local_err);
+            error_free(s->migration_blocker);
+            return;
+        }
+    }
 }
 
 static void kvm_arm_gicv3_class_init(ObjectClass *klass, void *data)
diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c
index fe5c303de9..32ffa0bf35 100644
--- a/hw/intc/armv7m_nvic.c
+++ b/hw/intc/armv7m_nvic.c
@@ -17,213 +17,425 @@
 #include "hw/sysbus.h"
 #include "qemu/timer.h"
 #include "hw/arm/arm.h"
-#include "exec/address-spaces.h"
-#include "gic_internal.h"
+#include "hw/arm/armv7m_nvic.h"
+#include "target/arm/cpu.h"
 #include "qemu/log.h"
+#include "trace.h"
 
-typedef struct {
-    GICState gic;
-    ARMCPU *cpu;
-    struct {
-        uint32_t control;
-        uint32_t reload;
-        int64_t tick;
-        QEMUTimer *timer;
-    } systick;
-    MemoryRegion sysregmem;
-    MemoryRegion gic_iomem_alias;
-    MemoryRegion container;
-    uint32_t num_irq;
-    qemu_irq sysresetreq;
-} nvic_state;
-
-#define TYPE_NVIC "armv7m_nvic"
-/**
- * NVICClass:
- * @parent_reset: the parent class' reset handler.
+/* IRQ number counting:
  *
- * A model of the v7M NVIC and System Controller
+ * the num-irq property counts the number of external IRQ lines
+ *
+ * NVICState::num_irq counts the total number of exceptions
+ * (external IRQs, the 15 internal exceptions including reset,
+ * and one for the unused exception number 0).
+ *
+ * NVIC_MAX_IRQ is the highest permitted number of external IRQ lines.
+ *
+ * NVIC_MAX_VECTORS is the highest permitted number of exceptions.
+ *
+ * Iterating through all exceptions should typically be done with
+ * for (i = 1; i < s->num_irq; i++) to avoid the unused slot 0.
+ *
+ * The external qemu_irq lines are the NVIC's external IRQ lines,
+ * so line 0 is exception 16.
+ *
+ * In the terminology of the architecture manual, "interrupts" are
+ * a subcategory of exception referring to the external interrupts
+ * (which are exception numbers NVIC_FIRST_IRQ and upward).
+ * For historical reasons QEMU tends to use "interrupt" and
+ * "exception" more or less interchangeably.
+ */
+#define NVIC_FIRST_IRQ 16
+#define NVIC_MAX_IRQ (NVIC_MAX_VECTORS - NVIC_FIRST_IRQ)
+
+/* Effective running priority of the CPU when no exception is active
+ * (higher than the highest possible priority value)
  */
-typedef struct NVICClass {
-    /*< private >*/
-    ARMGICClass parent_class;
-    /*< public >*/
-    DeviceRealize parent_realize;
-    void (*parent_reset)(DeviceState *dev);
-} NVICClass;
-
-#define NVIC_CLASS(klass) \
-    OBJECT_CLASS_CHECK(NVICClass, (klass), TYPE_NVIC)
-#define NVIC_GET_CLASS(obj) \
-    OBJECT_GET_CLASS(NVICClass, (obj), TYPE_NVIC)
-#define NVIC(obj) \
-    OBJECT_CHECK(nvic_state, (obj), TYPE_NVIC)
+#define NVIC_NOEXC_PRIO 0x100
 
 static const uint8_t nvic_id[] = {
     0x00, 0xb0, 0x1b, 0x00, 0x0d, 0xe0, 0x05, 0xb1
 };
 
-/* qemu timers run at 1GHz.   We want something closer to 1MHz.  */
-#define SYSTICK_SCALE 1000ULL
+static int nvic_pending_prio(NVICState *s)
+{
+    /* return the priority of the current pending interrupt,
+     * or NVIC_NOEXC_PRIO if no interrupt is pending
+     */
+    return s->vectpending ? s->vectors[s->vectpending].prio : NVIC_NOEXC_PRIO;
+}
 
-#define SYSTICK_ENABLE    (1 << 0)
-#define SYSTICK_TICKINT   (1 << 1)
-#define SYSTICK_CLKSOURCE (1 << 2)
-#define SYSTICK_COUNTFLAG (1 << 16)
+/* Return the value of the ISCR RETTOBASE bit:
+ * 1 if there is exactly one active exception
+ * 0 if there is more than one active exception
+ * UNKNOWN if there are no active exceptions (we choose 1,
+ * which matches the choice Cortex-M3 is documented as making).
+ *
+ * NB: some versions of the documentation talk about this
+ * counting "active exceptions other than the one shown by IPSR";
+ * this is only different in the obscure corner case where guest
+ * code has manually deactivated an exception and is about
+ * to fail an exception-return integrity check. The definition
+ * above is the one from the v8M ARM ARM and is also in line
+ * with the behaviour documented for the Cortex-M3.
+ */
+static bool nvic_rettobase(NVICState *s)
+{
+    int irq, nhand = 0;
 
-int system_clock_scale;
+    for (irq = ARMV7M_EXCP_RESET; irq < s->num_irq; irq++) {
+        if (s->vectors[irq].active) {
+            nhand++;
+            if (nhand == 2) {
+                return 0;
+            }
+        }
+    }
 
-/* Conversion factor from qemu timer to SysTick frequencies.  */
-static inline int64_t systick_scale(nvic_state *s)
-{
-    if (s->systick.control & SYSTICK_CLKSOURCE)
-        return system_clock_scale;
-    else
-        return 1000;
+    return 1;
 }
 
-static void systick_reload(nvic_state *s, int reset)
+/* Return the value of the ISCR ISRPENDING bit:
+ * 1 if an external interrupt is pending
+ * 0 if no external interrupt is pending
+ */
+static bool nvic_isrpending(NVICState *s)
 {
-    /* The Cortex-M3 Devices Generic User Guide says that "When the
-     * ENABLE bit is set to 1, the counter loads the RELOAD value from the
-     * SYST RVR register and then counts down". So, we need to check the
-     * ENABLE bit before reloading the value.
+    int irq;
+
+    /* We can shortcut if the highest priority pending interrupt
+     * happens to be external or if there is nothing pending.
      */
-    if ((s->systick.control & SYSTICK_ENABLE) == 0) {
-        return;
+    if (s->vectpending > NVIC_FIRST_IRQ) {
+        return true;
+    }
+    if (s->vectpending == 0) {
+        return false;
+    }
+
+    for (irq = NVIC_FIRST_IRQ; irq < s->num_irq; irq++) {
+        if (s->vectors[irq].pending) {
+            return true;
+        }
     }
+    return false;
+}
 
-    if (reset)
-        s->systick.tick = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
-    s->systick.tick += (s->systick.reload + 1) * systick_scale(s);
-    timer_mod(s->systick.timer, s->systick.tick);
+/* Return a mask word which clears the subpriority bits from
+ * a priority value for an M-profile exception, leaving only
+ * the group priority.
+ */
+static inline uint32_t nvic_gprio_mask(NVICState *s)
+{
+    return ~0U << (s->prigroup + 1);
 }
 
-static void systick_timer_tick(void * opaque)
+/* Recompute vectpending and exception_prio */
+static void nvic_recompute_state(NVICState *s)
 {
-    nvic_state *s = (nvic_state *)opaque;
-    s->systick.control |= SYSTICK_COUNTFLAG;
-    if (s->systick.control & SYSTICK_TICKINT) {
-        /* Trigger the interrupt.  */
-        armv7m_nvic_set_pending(s, ARMV7M_EXCP_SYSTICK);
+    int i;
+    int pend_prio = NVIC_NOEXC_PRIO;
+    int active_prio = NVIC_NOEXC_PRIO;
+    int pend_irq = 0;
+
+    for (i = 1; i < s->num_irq; i++) {
+        VecInfo *vec = &s->vectors[i];
+
+        if (vec->enabled && vec->pending && vec->prio < pend_prio) {
+            pend_prio = vec->prio;
+            pend_irq = i;
+        }
+        if (vec->active && vec->prio < active_prio) {
+            active_prio = vec->prio;
+        }
     }
-    if (s->systick.reload == 0) {
-        s->systick.control &= ~SYSTICK_ENABLE;
+
+    s->vectpending = pend_irq;
+    s->exception_prio = active_prio & nvic_gprio_mask(s);
+
+    trace_nvic_recompute_state(s->vectpending, s->exception_prio);
+}
+
+/* Return the current execution priority of the CPU
+ * (equivalent to the pseudocode ExecutionPriority function).
+ * This is a value between -2 (NMI priority) and NVIC_NOEXC_PRIO.
+ */
+static inline int nvic_exec_prio(NVICState *s)
+{
+    CPUARMState *env = &s->cpu->env;
+    int running;
+
+    if (env->daif & PSTATE_F) { /* FAULTMASK */
+        running = -1;
+    } else if (env->daif & PSTATE_I) { /* PRIMASK */
+        running = 0;
+    } else if (env->v7m.basepri > 0) {
+        running = env->v7m.basepri & nvic_gprio_mask(s);
     } else {
-        systick_reload(s, 0);
+        running = NVIC_NOEXC_PRIO; /* lower than any possible priority */
     }
+    /* consider priority of active handler */
+    return MIN(running, s->exception_prio);
 }
 
-static void systick_reset(nvic_state *s)
+bool armv7m_nvic_can_take_pending_exception(void *opaque)
 {
-    s->systick.control = 0;
-    s->systick.reload = 0;
-    s->systick.tick = 0;
-    timer_del(s->systick.timer);
+    NVICState *s = opaque;
+
+    return nvic_exec_prio(s) > nvic_pending_prio(s);
+}
+
+/* caller must call nvic_irq_update() after this */
+static void set_prio(NVICState *s, unsigned irq, uint8_t prio)
+{
+    assert(irq > ARMV7M_EXCP_NMI); /* only use for configurable prios */
+    assert(irq < s->num_irq);
+
+    s->vectors[irq].prio = prio;
+
+    trace_nvic_set_prio(irq, prio);
+}
+
+/* Recompute state and assert irq line accordingly.
+ * Must be called after changes to:
+ *  vec->active, vec->enabled, vec->pending or vec->prio for any vector
+ *  prigroup
+ */
+static void nvic_irq_update(NVICState *s)
+{
+    int lvl;
+    int pend_prio;
+
+    nvic_recompute_state(s);
+    pend_prio = nvic_pending_prio(s);
+
+    /* Raise NVIC output if this IRQ would be taken, except that we
+     * ignore the effects of the BASEPRI, FAULTMASK and PRIMASK (which
+     * will be checked for in arm_v7m_cpu_exec_interrupt()); changes
+     * to those CPU registers don't cause us to recalculate the NVIC
+     * pending info.
+     */
+    lvl = (pend_prio < s->exception_prio);
+    trace_nvic_irq_update(s->vectpending, pend_prio, s->exception_prio, lvl);
+    qemu_set_irq(s->excpout, lvl);
+}
+
+static void armv7m_nvic_clear_pending(void *opaque, int irq)
+{
+    NVICState *s = (NVICState *)opaque;
+    VecInfo *vec;
+
+    assert(irq > ARMV7M_EXCP_RESET && irq < s->num_irq);
+
+    vec = &s->vectors[irq];
+    trace_nvic_clear_pending(irq, vec->enabled, vec->prio);
+    if (vec->pending) {
+        vec->pending = 0;
+        nvic_irq_update(s);
+    }
 }
 
-/* The external routines use the hardware vector numbering, ie. the first
-   IRQ is #16.  The internal GIC routines use #32 as the first IRQ.  */
 void armv7m_nvic_set_pending(void *opaque, int irq)
 {
-    nvic_state *s = (nvic_state *)opaque;
-    if (irq >= 16)
-        irq += 16;
-    gic_set_pending_private(&s->gic, 0, irq);
+    NVICState *s = (NVICState *)opaque;
+    VecInfo *vec;
+
+    assert(irq > ARMV7M_EXCP_RESET && irq < s->num_irq);
+
+    vec = &s->vectors[irq];
+    trace_nvic_set_pending(irq, vec->enabled, vec->prio);
+
+
+    if (irq >= ARMV7M_EXCP_HARD && irq < ARMV7M_EXCP_PENDSV) {
+        /* If a synchronous exception is pending then it may be
+         * escalated to HardFault if:
+         *  * it is equal or lower priority to current execution
+         *  * it is disabled
+         * (ie we need to take it immediately but we can't do so).
+         * Asynchronous exceptions (and interrupts) simply remain pending.
+         *
+         * For QEMU, we don't have any imprecise (asynchronous) faults,
+         * so we can assume that PREFETCH_ABORT and DATA_ABORT are always
+         * synchronous.
+         * Debug exceptions are awkward because only Debug exceptions
+         * resulting from the BKPT instruction should be escalated,
+         * but we don't currently implement any Debug exceptions other
+         * than those that result from BKPT, so we treat all debug exceptions
+         * as needing escalation.
+         *
+         * This all means we can identify whether to escalate based only on
+         * the exception number and don't (yet) need the caller to explicitly
+         * tell us whether this exception is synchronous or not.
+         */
+        int running = nvic_exec_prio(s);
+        bool escalate = false;
+
+        if (vec->prio >= running) {
+            trace_nvic_escalate_prio(irq, vec->prio, running);
+            escalate = true;
+        } else if (!vec->enabled) {
+            trace_nvic_escalate_disabled(irq);
+            escalate = true;
+        }
+
+        if (escalate) {
+            if (running < 0) {
+                /* We want to escalate to HardFault but we can't take a
+                 * synchronous HardFault at this point either. This is a
+                 * Lockup condition due to a guest bug. We don't model
+                 * Lockup, so report via cpu_abort() instead.
+                 */
+                cpu_abort(&s->cpu->parent_obj,
+                          "Lockup: can't escalate %d to HardFault "
+                          "(current priority %d)\n", irq, running);
+            }
+
+            /* We can do the escalation, so we take HardFault instead */
+            irq = ARMV7M_EXCP_HARD;
+            vec = &s->vectors[irq];
+            s->cpu->env.v7m.hfsr |= R_V7M_HFSR_FORCED_MASK;
+        }
+    }
+
+    if (!vec->pending) {
+        vec->pending = 1;
+        nvic_irq_update(s);
+    }
 }
 
 /* Make pending IRQ active.  */
-int armv7m_nvic_acknowledge_irq(void *opaque)
+void armv7m_nvic_acknowledge_irq(void *opaque)
 {
-    nvic_state *s = (nvic_state *)opaque;
-    uint32_t irq;
-
-    irq = gic_acknowledge_irq(&s->gic, 0, MEMTXATTRS_UNSPECIFIED);
-    if (irq == 1023)
-        hw_error("Interrupt but no vector\n");
-    if (irq >= 32)
-        irq -= 16;
-    return irq;
+    NVICState *s = (NVICState *)opaque;
+    CPUARMState *env = &s->cpu->env;
+    const int pending = s->vectpending;
+    const int running = nvic_exec_prio(s);
+    int pendgroupprio;
+    VecInfo *vec;
+
+    assert(pending > ARMV7M_EXCP_RESET && pending < s->num_irq);
+
+    vec = &s->vectors[pending];
+
+    assert(vec->enabled);
+    assert(vec->pending);
+
+    pendgroupprio = vec->prio & nvic_gprio_mask(s);
+    assert(pendgroupprio < running);
+
+    trace_nvic_acknowledge_irq(pending, vec->prio);
+
+    vec->active = 1;
+    vec->pending = 0;
+
+    env->v7m.exception = s->vectpending;
+
+    nvic_irq_update(s);
 }
 
-void armv7m_nvic_complete_irq(void *opaque, int irq)
+int armv7m_nvic_complete_irq(void *opaque, int irq)
 {
-    nvic_state *s = (nvic_state *)opaque;
-    if (irq >= 16)
-        irq += 16;
-    gic_complete_irq(&s->gic, 0, irq, MEMTXATTRS_UNSPECIFIED);
+    NVICState *s = (NVICState *)opaque;
+    VecInfo *vec;
+    int ret;
+
+    assert(irq > ARMV7M_EXCP_RESET && irq < s->num_irq);
+
+    vec = &s->vectors[irq];
+
+    trace_nvic_complete_irq(irq);
+
+    if (!vec->active) {
+        /* Tell the caller this was an illegal exception return */
+        return -1;
+    }
+
+    ret = nvic_rettobase(s);
+
+    vec->active = 0;
+    if (vec->level) {
+        /* Re-pend the exception if it's still held high; only
+         * happens for extenal IRQs
+         */
+        assert(irq >= NVIC_FIRST_IRQ);
+        vec->pending = 1;
+    }
+
+    nvic_irq_update(s);
+
+    return ret;
+}
+
+/* callback when external interrupt line is changed */
+static void set_irq_level(void *opaque, int n, int level)
+{
+    NVICState *s = opaque;
+    VecInfo *vec;
+
+    n += NVIC_FIRST_IRQ;
+
+    assert(n >= NVIC_FIRST_IRQ && n < s->num_irq);
+
+    trace_nvic_set_irq_level(n, level);
+
+    /* The pending status of an external interrupt is
+     * latched on rising edge and exception handler return.
+     *
+     * Pulsing the IRQ will always run the handler
+     * once, and the handler will re-run until the
+     * level is low when the handler completes.
+     */
+    vec = &s->vectors[n];
+    if (level != vec->level) {
+        vec->level = level;
+        if (level) {
+            armv7m_nvic_set_pending(s, n);
+        }
+    }
 }
 
-static uint32_t nvic_readl(nvic_state *s, uint32_t offset)
+static uint32_t nvic_readl(NVICState *s, uint32_t offset)
 {
     ARMCPU *cpu = s->cpu;
     uint32_t val;
-    int irq;
 
     switch (offset) {
     case 4: /* Interrupt Control Type.  */
-        return (s->num_irq / 32) - 1;
-    case 0x10: /* SysTick Control and Status.  */
-        val = s->systick.control;
-        s->systick.control &= ~SYSTICK_COUNTFLAG;
-        return val;
-    case 0x14: /* SysTick Reload Value.  */
-        return s->systick.reload;
-    case 0x18: /* SysTick Current Value.  */
-        {
-            int64_t t;
-            if ((s->systick.control & SYSTICK_ENABLE) == 0)
-                return 0;
-            t = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
-            if (t >= s->systick.tick)
-                return 0;
-            val = ((s->systick.tick - (t + 1)) / systick_scale(s)) + 1;
-            /* The interrupt in triggered when the timer reaches zero.
-               However the counter is not reloaded until the next clock
-               tick.  This is a hack to return zero during the first tick.  */
-            if (val > s->systick.reload)
-                val = 0;
-            return val;
-        }
-    case 0x1c: /* SysTick Calibration Value.  */
-        return 10000;
+        return ((s->num_irq - NVIC_FIRST_IRQ) / 32) - 1;
     case 0xd00: /* CPUID Base.  */
         return cpu->midr;
     case 0xd04: /* Interrupt Control State.  */
         /* VECTACTIVE */
         val = cpu->env.v7m.exception;
-        if (val == 1023) {
-            val = 0;
-        } else if (val >= 32) {
-            val -= 16;
-        }
         /* VECTPENDING */
-        if (s->gic.current_pending[0] != 1023)
-            val |= (s->gic.current_pending[0] << 12);
-        /* ISRPENDING and RETTOBASE */
-        for (irq = 32; irq < s->num_irq; irq++) {
-            if (s->gic.irq_state[irq].pending) {
-                val |= (1 << 22);
-                break;
-            }
-            if (irq != cpu->env.v7m.exception && s->gic.irq_state[irq].active) {
-                val |= (1 << 11);
-            }
+        val |= (s->vectpending & 0xff) << 12;
+        /* ISRPENDING - set if any external IRQ is pending */
+        if (nvic_isrpending(s)) {
+            val |= (1 << 22);
+        }
+        /* RETTOBASE - set if only one handler is active */
+        if (nvic_rettobase(s)) {
+            val |= (1 << 11);
         }
         /* PENDSTSET */
-        if (s->gic.irq_state[ARMV7M_EXCP_SYSTICK].pending)
+        if (s->vectors[ARMV7M_EXCP_SYSTICK].pending) {
             val |= (1 << 26);
+        }
         /* PENDSVSET */
-        if (s->gic.irq_state[ARMV7M_EXCP_PENDSV].pending)
+        if (s->vectors[ARMV7M_EXCP_PENDSV].pending) {
             val |= (1 << 28);
+        }
         /* NMIPENDSET */
-        if (s->gic.irq_state[ARMV7M_EXCP_NMI].pending)
+        if (s->vectors[ARMV7M_EXCP_NMI].pending) {
             val |= (1 << 31);
+        }
+        /* ISRPREEMPT not implemented */
         return val;
     case 0xd08: /* Vector Table Offset.  */
         return cpu->env.v7m.vecbase;
     case 0xd0c: /* Application Interrupt/Reset Control.  */
-        return 0xfa050000;
+        return 0xfa050000 | (s->prigroup << 8);
     case 0xd10: /* System Control.  */
         /* TODO: Implement SLEEPONEXIT.  */
         return 0;
@@ -231,20 +443,48 @@ static uint32_t nvic_readl(nvic_state *s, uint32_t offset)
         return cpu->env.v7m.ccr;
     case 0xd24: /* System Handler Status.  */
         val = 0;
-        if (s->gic.irq_state[ARMV7M_EXCP_MEM].active) val |= (1 << 0);
-        if (s->gic.irq_state[ARMV7M_EXCP_BUS].active) val |= (1 << 1);
-        if (s->gic.irq_state[ARMV7M_EXCP_USAGE].active) val |= (1 << 3);
-        if (s->gic.irq_state[ARMV7M_EXCP_SVC].active) val |= (1 << 7);
-        if (s->gic.irq_state[ARMV7M_EXCP_DEBUG].active) val |= (1 << 8);
-        if (s->gic.irq_state[ARMV7M_EXCP_PENDSV].active) val |= (1 << 10);
-        if (s->gic.irq_state[ARMV7M_EXCP_SYSTICK].active) val |= (1 << 11);
-        if (s->gic.irq_state[ARMV7M_EXCP_USAGE].pending) val |= (1 << 12);
-        if (s->gic.irq_state[ARMV7M_EXCP_MEM].pending) val |= (1 << 13);
-        if (s->gic.irq_state[ARMV7M_EXCP_BUS].pending) val |= (1 << 14);
-        if (s->gic.irq_state[ARMV7M_EXCP_SVC].pending) val |= (1 << 15);
-        if (s->gic.irq_state[ARMV7M_EXCP_MEM].enabled) val |= (1 << 16);
-        if (s->gic.irq_state[ARMV7M_EXCP_BUS].enabled) val |= (1 << 17);
-        if (s->gic.irq_state[ARMV7M_EXCP_USAGE].enabled) val |= (1 << 18);
+        if (s->vectors[ARMV7M_EXCP_MEM].active) {
+            val |= (1 << 0);
+        }
+        if (s->vectors[ARMV7M_EXCP_BUS].active) {
+            val |= (1 << 1);
+        }
+        if (s->vectors[ARMV7M_EXCP_USAGE].active) {
+            val |= (1 << 3);
+        }
+        if (s->vectors[ARMV7M_EXCP_SVC].active) {
+            val |= (1 << 7);
+        }
+        if (s->vectors[ARMV7M_EXCP_DEBUG].active) {
+            val |= (1 << 8);
+        }
+        if (s->vectors[ARMV7M_EXCP_PENDSV].active) {
+            val |= (1 << 10);
+        }
+        if (s->vectors[ARMV7M_EXCP_SYSTICK].active) {
+            val |= (1 << 11);
+        }
+        if (s->vectors[ARMV7M_EXCP_USAGE].pending) {
+            val |= (1 << 12);
+        }
+        if (s->vectors[ARMV7M_EXCP_MEM].pending) {
+            val |= (1 << 13);
+        }
+        if (s->vectors[ARMV7M_EXCP_BUS].pending) {
+            val |= (1 << 14);
+        }
+        if (s->vectors[ARMV7M_EXCP_SVC].pending) {
+            val |= (1 << 15);
+        }
+        if (s->vectors[ARMV7M_EXCP_MEM].enabled) {
+            val |= (1 << 16);
+        }
+        if (s->vectors[ARMV7M_EXCP_BUS].enabled) {
+            val |= (1 << 17);
+        }
+        if (s->vectors[ARMV7M_EXCP_USAGE].enabled) {
+            val |= (1 << 18);
+        }
         return val;
     case 0xd28: /* Configurable Fault Status.  */
         return cpu->env.v7m.cfsr;
@@ -294,43 +534,11 @@ static uint32_t nvic_readl(nvic_state *s, uint32_t offset)
     }
 }
 
-static void nvic_writel(nvic_state *s, uint32_t offset, uint32_t value)
+static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value)
 {
     ARMCPU *cpu = s->cpu;
-    uint32_t oldval;
+
     switch (offset) {
-    case 0x10: /* SysTick Control and Status.  */
-        oldval = s->systick.control;
-        s->systick.control &= 0xfffffff8;
-        s->systick.control |= value & 7;
-        if ((oldval ^ value) & SYSTICK_ENABLE) {
-            int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
-            if (value & SYSTICK_ENABLE) {
-                if (s->systick.tick) {
-                    s->systick.tick += now;
-                    timer_mod(s->systick.timer, s->systick.tick);
-                } else {
-                    systick_reload(s, 1);
-                }
-            } else {
-                timer_del(s->systick.timer);
-                s->systick.tick -= now;
-                if (s->systick.tick < 0)
-                  s->systick.tick = 0;
-            }
-        } else if ((oldval ^ value) & SYSTICK_CLKSOURCE) {
-            /* This is a hack. Force the timer to be reloaded
-               when the reference clock is changed.  */
-            systick_reload(s, 1);
-        }
-        break;
-    case 0x14: /* SysTick Reload Value.  */
-        s->systick.reload = value;
-        break;
-    case 0x18: /* SysTick Current Value.  Writes reload the timer.  */
-        systick_reload(s, 1);
-        s->systick.control &= ~SYSTICK_COUNTFLAG;
-        break;
     case 0xd04: /* Interrupt Control State.  */
         if (value & (1 << 31)) {
             armv7m_nvic_set_pending(s, ARMV7M_EXCP_NMI);
@@ -338,14 +546,12 @@ static void nvic_writel(nvic_state *s, uint32_t offset, uint32_t value)
         if (value & (1 << 28)) {
             armv7m_nvic_set_pending(s, ARMV7M_EXCP_PENDSV);
         } else if (value & (1 << 27)) {
-            s->gic.irq_state[ARMV7M_EXCP_PENDSV].pending = 0;
-            gic_update(&s->gic);
+            armv7m_nvic_clear_pending(s, ARMV7M_EXCP_PENDSV);
         }
         if (value & (1 << 26)) {
             armv7m_nvic_set_pending(s, ARMV7M_EXCP_SYSTICK);
         } else if (value & (1 << 25)) {
-            s->gic.irq_state[ARMV7M_EXCP_SYSTICK].pending = 0;
-            gic_update(&s->gic);
+            armv7m_nvic_clear_pending(s, ARMV7M_EXCP_SYSTICK);
         }
         break;
     case 0xd08: /* Vector Table Offset.  */
@@ -357,14 +563,17 @@ static void nvic_writel(nvic_state *s, uint32_t offset, uint32_t value)
                 qemu_irq_pulse(s->sysresetreq);
             }
             if (value & 2) {
-                qemu_log_mask(LOG_UNIMP, "VECTCLRACTIVE unimplemented\n");
+                qemu_log_mask(LOG_GUEST_ERROR,
+                              "Setting VECTCLRACTIVE when not in DEBUG mode "
+                              "is UNPREDICTABLE\n");
             }
             if (value & 1) {
-                qemu_log_mask(LOG_UNIMP, "AIRCR system reset unimplemented\n");
-            }
-            if (value & 0x700) {
-                qemu_log_mask(LOG_UNIMP, "PRIGROUP unimplemented\n");
+                qemu_log_mask(LOG_GUEST_ERROR,
+                              "Setting VECTRESET when not in DEBUG mode "
+                              "is UNPREDICTABLE\n");
             }
+            s->prigroup = extract32(value, 8, 3);
+            nvic_irq_update(s);
         }
         break;
     case 0xd10: /* System Control.  */
@@ -383,11 +592,21 @@ static void nvic_writel(nvic_state *s, uint32_t offset, uint32_t value)
         cpu->env.v7m.ccr = value;
         break;
     case 0xd24: /* System Handler Control.  */
-        /* TODO: Real hardware allows you to set/clear the active bits
-           under some circumstances.  We don't implement this.  */
-        s->gic.irq_state[ARMV7M_EXCP_MEM].enabled = (value & (1 << 16)) != 0;
-        s->gic.irq_state[ARMV7M_EXCP_BUS].enabled = (value & (1 << 17)) != 0;
-        s->gic.irq_state[ARMV7M_EXCP_USAGE].enabled = (value & (1 << 18)) != 0;
+        s->vectors[ARMV7M_EXCP_MEM].active = (value & (1 << 0)) != 0;
+        s->vectors[ARMV7M_EXCP_BUS].active = (value & (1 << 1)) != 0;
+        s->vectors[ARMV7M_EXCP_USAGE].active = (value & (1 << 3)) != 0;
+        s->vectors[ARMV7M_EXCP_SVC].active = (value & (1 << 7)) != 0;
+        s->vectors[ARMV7M_EXCP_DEBUG].active = (value & (1 << 8)) != 0;
+        s->vectors[ARMV7M_EXCP_PENDSV].active = (value & (1 << 10)) != 0;
+        s->vectors[ARMV7M_EXCP_SYSTICK].active = (value & (1 << 11)) != 0;
+        s->vectors[ARMV7M_EXCP_USAGE].pending = (value & (1 << 12)) != 0;
+        s->vectors[ARMV7M_EXCP_MEM].pending = (value & (1 << 13)) != 0;
+        s->vectors[ARMV7M_EXCP_BUS].pending = (value & (1 << 14)) != 0;
+        s->vectors[ARMV7M_EXCP_SVC].pending = (value & (1 << 15)) != 0;
+        s->vectors[ARMV7M_EXCP_MEM].enabled = (value & (1 << 16)) != 0;
+        s->vectors[ARMV7M_EXCP_BUS].enabled = (value & (1 << 17)) != 0;
+        s->vectors[ARMV7M_EXCP_USAGE].enabled = (value & (1 << 18)) != 0;
+        nvic_irq_update(s);
         break;
     case 0xd28: /* Configurable Fault Status.  */
         cpu->env.v7m.cfsr &= ~value; /* W1C */
@@ -409,13 +628,16 @@ static void nvic_writel(nvic_state *s, uint32_t offset, uint32_t value)
                       "NVIC: Aux fault status registers unimplemented\n");
         break;
     case 0xf00: /* Software Triggered Interrupt Register */
+    {
         /* user mode can only write to STIR if CCR.USERSETMPEND permits it */
-        if ((value & 0x1ff) < s->num_irq &&
+        int excnum = (value & 0x1ff) + NVIC_FIRST_IRQ;
+        if (excnum < s->num_irq &&
             (arm_current_el(&cpu->env) ||
              (cpu->env.v7m.ccr & R_V7M_CCR_USERSETMPEND_MASK))) {
-            gic_set_pending_private(&s->gic, 0, value & 0x1ff);
+            armv7m_nvic_set_pending(s, excnum);
         }
         break;
+    }
     default:
         qemu_log_mask(LOG_GUEST_ERROR,
                       "NVIC: Bad write offset 0x%x\n", offset);
@@ -425,46 +647,142 @@ static void nvic_writel(nvic_state *s, uint32_t offset, uint32_t value)
 static uint64_t nvic_sysreg_read(void *opaque, hwaddr addr,
                                  unsigned size)
 {
-    nvic_state *s = (nvic_state *)opaque;
+    NVICState *s = (NVICState *)opaque;
     uint32_t offset = addr;
-    int i;
+    unsigned i, startvec, end;
     uint32_t val;
 
     switch (offset) {
+    /* reads of set and clear both return the status */
+    case 0x100 ... 0x13f: /* NVIC Set enable */
+        offset += 0x80;
+        /* fall through */
+    case 0x180 ... 0x1bf: /* NVIC Clear enable */
+        val = 0;
+        startvec = offset - 0x180 + NVIC_FIRST_IRQ; /* vector # */
+
+        for (i = 0, end = size * 8; i < end && startvec + i < s->num_irq; i++) {
+            if (s->vectors[startvec + i].enabled) {
+                val |= (1 << i);
+            }
+        }
+        break;
+    case 0x200 ... 0x23f: /* NVIC Set pend */
+        offset += 0x80;
+        /* fall through */
+    case 0x280 ... 0x2bf: /* NVIC Clear pend */
+        val = 0;
+        startvec = offset - 0x280 + NVIC_FIRST_IRQ; /* vector # */
+        for (i = 0, end = size * 8; i < end && startvec + i < s->num_irq; i++) {
+            if (s->vectors[startvec + i].pending) {
+                val |= (1 << i);
+            }
+        }
+        break;
+    case 0x300 ... 0x33f: /* NVIC Active */
+        val = 0;
+        startvec = offset - 0x300 + NVIC_FIRST_IRQ; /* vector # */
+
+        for (i = 0, end = size * 8; i < end && startvec + i < s->num_irq; i++) {
+            if (s->vectors[startvec + i].active) {
+                val |= (1 << i);
+            }
+        }
+        break;
+    case 0x400 ... 0x5ef: /* NVIC Priority */
+        val = 0;
+        startvec = offset - 0x400 + NVIC_FIRST_IRQ; /* vector # */
+
+        for (i = 0; i < size && startvec + i < s->num_irq; i++) {
+            val |= s->vectors[startvec + i].prio << (8 * i);
+        }
+        break;
     case 0xd18 ... 0xd23: /* System Handler Priority.  */
         val = 0;
         for (i = 0; i < size; i++) {
-            val |= s->gic.priority1[(offset - 0xd14) + i][0] << (i * 8);
+            val |= s->vectors[(offset - 0xd14) + i].prio << (i * 8);
         }
-        return val;
+        break;
     case 0xfe0 ... 0xfff: /* ID.  */
         if (offset & 3) {
-            return 0;
+            val = 0;
+        } else {
+            val = nvic_id[(offset - 0xfe0) >> 2];
+        }
+        break;
+    default:
+        if (size == 4) {
+            val = nvic_readl(s, offset);
+        } else {
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "NVIC: Bad read of size %d at offset 0x%x\n",
+                          size, offset);
+            val = 0;
         }
-        return nvic_id[(offset - 0xfe0) >> 2];
-    }
-    if (size == 4) {
-        return nvic_readl(s, offset);
     }
-    qemu_log_mask(LOG_GUEST_ERROR,
-                  "NVIC: Bad read of size %d at offset 0x%x\n", size, offset);
-    return 0;
+
+    trace_nvic_sysreg_read(addr, val, size);
+    return val;
 }
 
 static void nvic_sysreg_write(void *opaque, hwaddr addr,
                               uint64_t value, unsigned size)
 {
-    nvic_state *s = (nvic_state *)opaque;
+    NVICState *s = (NVICState *)opaque;
     uint32_t offset = addr;
-    int i;
+    unsigned i, startvec, end;
+    unsigned setval = 0;
+
+    trace_nvic_sysreg_write(addr, value, size);
 
     switch (offset) {
+    case 0x100 ... 0x13f: /* NVIC Set enable */
+        offset += 0x80;
+        setval = 1;
+        /* fall through */
+    case 0x180 ... 0x1bf: /* NVIC Clear enable */
+        startvec = 8 * (offset - 0x180) + NVIC_FIRST_IRQ;
+
+        for (i = 0, end = size * 8; i < end && startvec + i < s->num_irq; i++) {
+            if (value & (1 << i)) {
+                s->vectors[startvec + i].enabled = setval;
+            }
+        }
+        nvic_irq_update(s);
+        return;
+    case 0x200 ... 0x23f: /* NVIC Set pend */
+        /* the special logic in armv7m_nvic_set_pending()
+         * is not needed since IRQs are never escalated
+         */
+        offset += 0x80;
+        setval = 1;
+        /* fall through */
+    case 0x280 ... 0x2bf: /* NVIC Clear pend */
+        startvec = 8 * (offset - 0x280) + NVIC_FIRST_IRQ; /* vector # */
+
+        for (i = 0, end = size * 8; i < end && startvec + i < s->num_irq; i++) {
+            if (value & (1 << i)) {
+                s->vectors[startvec + i].pending = setval;
+            }
+        }
+        nvic_irq_update(s);
+        return;
+    case 0x300 ... 0x33f: /* NVIC Active */
+        return; /* R/O */
+    case 0x400 ... 0x5ef: /* NVIC Priority */
+        startvec = 8 * (offset - 0x400) + NVIC_FIRST_IRQ; /* vector # */
+
+        for (i = 0; i < size && startvec + i < s->num_irq; i++) {
+            set_prio(s, startvec + i, (value >> (i * 8)) & 0xff);
+        }
+        nvic_irq_update(s);
+        return;
     case 0xd18 ... 0xd23: /* System Handler Priority.  */
         for (i = 0; i < size; i++) {
-            s->gic.priority1[(offset - 0xd14) + i][0] =
-                (value >> (i * 8)) & 0xff;
+            unsigned hdlidx = (offset - 0xd14) + i;
+            set_prio(s, hdlidx, (value >> (i * 8)) & 0xff);
         }
-        gic_update(&s->gic);
+        nvic_irq_update(s);
         return;
     }
     if (size == 4) {
@@ -481,61 +799,143 @@ static const MemoryRegionOps nvic_sysreg_ops = {
     .endianness = DEVICE_NATIVE_ENDIAN,
 };
 
-static const VMStateDescription vmstate_nvic = {
-    .name = "armv7m_nvic",
+static int nvic_post_load(void *opaque, int version_id)
+{
+    NVICState *s = opaque;
+    unsigned i;
+
+    /* Check for out of range priority settings */
+    if (s->vectors[ARMV7M_EXCP_RESET].prio != -3 ||
+        s->vectors[ARMV7M_EXCP_NMI].prio != -2 ||
+        s->vectors[ARMV7M_EXCP_HARD].prio != -1) {
+        return 1;
+    }
+    for (i = ARMV7M_EXCP_MEM; i < s->num_irq; i++) {
+        if (s->vectors[i].prio & ~0xff) {
+            return 1;
+        }
+    }
+
+    nvic_recompute_state(s);
+
+    return 0;
+}
+
+static const VMStateDescription vmstate_VecInfo = {
+    .name = "armv7m_nvic_info",
     .version_id = 1,
     .minimum_version_id = 1,
     .fields = (VMStateField[]) {
-        VMSTATE_UINT32(systick.control, nvic_state),
-        VMSTATE_UINT32(systick.reload, nvic_state),
-        VMSTATE_INT64(systick.tick, nvic_state),
-        VMSTATE_TIMER_PTR(systick.timer, nvic_state),
+        VMSTATE_INT16(prio, VecInfo),
+        VMSTATE_UINT8(enabled, VecInfo),
+        VMSTATE_UINT8(pending, VecInfo),
+        VMSTATE_UINT8(active, VecInfo),
+        VMSTATE_UINT8(level, VecInfo),
         VMSTATE_END_OF_LIST()
     }
 };
 
+static const VMStateDescription vmstate_nvic = {
+    .name = "armv7m_nvic",
+    .version_id = 4,
+    .minimum_version_id = 4,
+    .post_load = &nvic_post_load,
+    .fields = (VMStateField[]) {
+        VMSTATE_STRUCT_ARRAY(vectors, NVICState, NVIC_MAX_VECTORS, 1,
+                             vmstate_VecInfo, VecInfo),
+        VMSTATE_UINT32(prigroup, NVICState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static Property props_nvic[] = {
+    /* Number of external IRQ lines (so excluding the 16 internal exceptions) */
+    DEFINE_PROP_UINT32("num-irq", NVICState, num_irq, 64),
+    DEFINE_PROP_END_OF_LIST()
+};
+
 static void armv7m_nvic_reset(DeviceState *dev)
 {
-    nvic_state *s = NVIC(dev);
-    NVICClass *nc = NVIC_GET_CLASS(s);
-    nc->parent_reset(dev);
-    /* Common GIC reset resets to disabled; the NVIC doesn't have
-     * per-CPU interfaces so mark our non-existent CPU interface
-     * as enabled by default, and with a priority mask which allows
-     * all interrupts through.
+    NVICState *s = NVIC(dev);
+
+    s->vectors[ARMV7M_EXCP_NMI].enabled = 1;
+    s->vectors[ARMV7M_EXCP_HARD].enabled = 1;
+    /* MEM, BUS, and USAGE are enabled through
+     * the System Handler Control register
+     */
+    s->vectors[ARMV7M_EXCP_SVC].enabled = 1;
+    s->vectors[ARMV7M_EXCP_DEBUG].enabled = 1;
+    s->vectors[ARMV7M_EXCP_PENDSV].enabled = 1;
+    s->vectors[ARMV7M_EXCP_SYSTICK].enabled = 1;
+
+    s->vectors[ARMV7M_EXCP_RESET].prio = -3;
+    s->vectors[ARMV7M_EXCP_NMI].prio = -2;
+    s->vectors[ARMV7M_EXCP_HARD].prio = -1;
+
+    /* Strictly speaking the reset handler should be enabled.
+     * However, we don't simulate soft resets through the NVIC,
+     * and the reset vector should never be pended.
+     * So we leave it disabled to catch logic errors.
      */
-    s->gic.cpu_ctlr[0] = GICC_CTLR_EN_GRP0;
-    s->gic.priority_mask[0] = 0x100;
-    /* The NVIC as a whole is always enabled. */
-    s->gic.ctlr = 1;
-    systick_reset(s);
+
+    s->exception_prio = NVIC_NOEXC_PRIO;
+    s->vectpending = 0;
+}
+
+static void nvic_systick_trigger(void *opaque, int n, int level)
+{
+    NVICState *s = opaque;
+
+    if (level) {
+        /* SysTick just asked us to pend its exception.
+         * (This is different from an external interrupt line's
+         * behaviour.)
+         */
+        armv7m_nvic_set_pending(s, ARMV7M_EXCP_SYSTICK);
+    }
 }
 
 static void armv7m_nvic_realize(DeviceState *dev, Error **errp)
 {
-    nvic_state *s = NVIC(dev);
-    NVICClass *nc = NVIC_GET_CLASS(s);
-    Error *local_err = NULL;
+    NVICState *s = NVIC(dev);
+    SysBusDevice *systick_sbd;
+    Error *err = NULL;
 
     s->cpu = ARM_CPU(qemu_get_cpu(0));
     assert(s->cpu);
-    /* The NVIC always has only one CPU */
-    s->gic.num_cpu = 1;
-    /* Tell the common code we're an NVIC */
-    s->gic.revision = 0xffffffff;
-    s->num_irq = s->gic.num_irq;
-    nc->parent_realize(dev, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
+
+    if (s->num_irq > NVIC_MAX_IRQ) {
+        error_setg(errp, "num-irq %d exceeds NVIC maximum", s->num_irq);
+        return;
+    }
+
+    qdev_init_gpio_in(dev, set_irq_level, s->num_irq);
+
+    /* include space for internal exception vectors */
+    s->num_irq += NVIC_FIRST_IRQ;
+
+    object_property_set_bool(OBJECT(&s->systick), true, "realized", &err);
+    if (err != NULL) {
+        error_propagate(errp, err);
         return;
     }
-    gic_init_irqs_and_distributor(&s->gic);
-    /* The NVIC and system controller register area looks like this:
-     *  0..0xff : system control registers, including systick
-     *  0x100..0xcff : GIC-like registers
-     *  0xd00..0xfff : system control registers
-     * We use overlaying to put the GIC like registers
-     * over the top of the system control register region.
+    systick_sbd = SYS_BUS_DEVICE(&s->systick);
+    sysbus_connect_irq(systick_sbd, 0,
+                       qdev_get_gpio_in_named(dev, "systick-trigger", 0));
+
+    /* The NVIC and System Control Space (SCS) starts at 0xe000e000
+     * and looks like this:
+     *  0x004 - ICTR
+     *  0x010 - 0xff - systick
+     *  0x100..0x7ec - NVIC
+     *  0x7f0..0xcff - Reserved
+     *  0xd00..0xd3c - SCS registers
+     *  0xd40..0xeff - Reserved or Not implemented
+     *  0xf00 - STIR
+     *
+     * At the moment there is only one thing in the container region,
+     * but we leave it in place to allow us to pull systick out into
+     * its own device object later.
      */
     memory_region_init(&s->container, OBJECT(s), "nvic", 0x1000);
     /* The system register region goes at the bottom of the priority
@@ -544,19 +944,11 @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp)
     memory_region_init_io(&s->sysregmem, OBJECT(s), &nvic_sysreg_ops, s,
                           "nvic_sysregs", 0x1000);
     memory_region_add_subregion(&s->container, 0, &s->sysregmem);
-    /* Alias the GIC region so we can get only the section of it
-     * we need, and layer it on top of the system register region.
-     */
-    memory_region_init_alias(&s->gic_iomem_alias, OBJECT(s),
-                             "nvic-gic", &s->gic.iomem,
-                             0x100, 0xc00);
-    memory_region_add_subregion_overlap(&s->container, 0x100,
-                                        &s->gic_iomem_alias, 1);
-    /* Map the whole thing into system memory at the location required
-     * by the v7M architecture.
-     */
-    memory_region_add_subregion(get_system_memory(), 0xe000e000, &s->container);
-    s->systick.timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, systick_timer_tick, s);
+    memory_region_add_subregion_overlap(&s->container, 0x10,
+                                        sysbus_mmio_get_region(systick_sbd, 0),
+                                        1);
+
+    sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->container);
 }
 
 static void armv7m_nvic_instance_init(Object *obj)
@@ -567,36 +959,35 @@ static void armv7m_nvic_instance_init(Object *obj)
      * any user-specified property setting, so just modify the
      * value in the GICState struct.
      */
-    GICState *s = ARM_GIC_COMMON(obj);
     DeviceState *dev = DEVICE(obj);
-    nvic_state *nvic = NVIC(obj);
-    /* The ARM v7m may have anything from 0 to 496 external interrupt
-     * IRQ lines. We default to 64. Other boards may differ and should
-     * set the num-irq property appropriately.
-     */
-    s->num_irq = 64;
+    NVICState *nvic = NVIC(obj);
+    SysBusDevice *sbd = SYS_BUS_DEVICE(obj);
+
+    object_initialize(&nvic->systick, sizeof(nvic->systick), TYPE_SYSTICK);
+    qdev_set_parent_bus(DEVICE(&nvic->systick), sysbus_get_default());
+
+    sysbus_init_irq(sbd, &nvic->excpout);
     qdev_init_gpio_out_named(dev, &nvic->sysresetreq, "SYSRESETREQ", 1);
+    qdev_init_gpio_in_named(dev, nvic_systick_trigger, "systick-trigger", 1);
 }
 
 static void armv7m_nvic_class_init(ObjectClass *klass, void *data)
 {
-    NVICClass *nc = NVIC_CLASS(klass);
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    nc->parent_reset = dc->reset;
-    nc->parent_realize = dc->realize;
     dc->vmsd  = &vmstate_nvic;
+    dc->props = props_nvic;
     dc->reset = armv7m_nvic_reset;
     dc->realize = armv7m_nvic_realize;
 }
 
 static const TypeInfo armv7m_nvic_info = {
     .name          = TYPE_NVIC,
-    .parent        = TYPE_ARM_GIC_COMMON,
+    .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_init = armv7m_nvic_instance_init,
-    .instance_size = sizeof(nvic_state),
+    .instance_size = sizeof(NVICState),
     .class_init    = armv7m_nvic_class_init,
-    .class_size    = sizeof(NVICClass),
+    .class_size    = sizeof(SysBusDeviceClass),
 };
 
 static void armv7m_nvic_register_types(void)
diff --git a/hw/intc/gic_internal.h b/hw/intc/gic_internal.h
index 3f311740da..7fe87b13de 100644
--- a/hw/intc/gic_internal.h
+++ b/hw/intc/gic_internal.h
@@ -25,9 +25,7 @@
 
 #define ALL_CPU_MASK ((unsigned)(((1 << GIC_NCPU) - 1)))
 
-/* The NVIC has 16 internal vectors.  However these are not exposed
-   through the normal GIC interface.  */
-#define GIC_BASE_IRQ ((s->revision == REV_NVIC) ? 32 : 0)
+#define GIC_BASE_IRQ 0
 
 #define GIC_SET_ENABLED(irq, cm) s->irq_state[irq].enabled |= (cm)
 #define GIC_CLEAR_ENABLED(irq, cm) s->irq_state[irq].enabled &= ~(cm)
@@ -75,7 +73,6 @@
 
 /* The special cases for the revision property: */
 #define REV_11MPCORE 0
-#define REV_NVIC 0xffffffff
 
 void gic_set_pending_private(GICState *s, int cpu, int irq);
 uint32_t gic_acknowledge_irq(GICState *s, int cpu, MemTxAttrs attrs);
@@ -87,7 +84,7 @@ void gic_set_priority(GICState *s, int cpu, int irq, uint8_t val,
 
 static inline bool gic_test_pending(GICState *s, int irq, int cm)
 {
-    if (s->revision == REV_NVIC || s->revision == REV_11MPCORE) {
+    if (s->revision == REV_11MPCORE) {
         return s->irq_state[irq].pending & cm;
     } else {
         /* Edge-triggered interrupts are marked pending on a rising edge, but
diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h
index aeb801d133..05303a55c8 100644
--- a/hw/intc/gicv3_internal.h
+++ b/hw/intc/gicv3_internal.h
@@ -138,6 +138,7 @@
 #define ICC_CTLR_EL1_EOIMODE        (1U << 1)
 #define ICC_CTLR_EL1_PMHE           (1U << 6)
 #define ICC_CTLR_EL1_PRIBITS_SHIFT 8
+#define ICC_CTLR_EL1_PRIBITS_MASK   (7U << ICC_CTLR_EL1_PRIBITS_SHIFT)
 #define ICC_CTLR_EL1_IDBITS_SHIFT 11
 #define ICC_CTLR_EL1_SEIS           (1U << 14)
 #define ICC_CTLR_EL1_A3V            (1U << 15)
@@ -407,4 +408,6 @@ static inline void gicv3_cache_all_target_cpustates(GICv3State *s)
     }
 }
 
+void gicv3_set_gicv3state(CPUState *cpu, GICv3CPUState *s);
+
 #endif /* QEMU_ARM_GICV3_INTERNAL_H */
diff --git a/hw/intc/trace-events b/hw/intc/trace-events
index 39a538d048..729c1288f1 100644
--- a/hw/intc/trace-events
+++ b/hw/intc/trace-events
@@ -161,3 +161,18 @@ gicv3_redist_write(uint32_t cpu, uint64_t offset, uint64_t data, unsigned size,
 gicv3_redist_badwrite(uint32_t cpu, uint64_t offset, uint64_t data, unsigned size, bool secure) "GICv3 redistributor %x write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u secure %d: error"
 gicv3_redist_set_irq(uint32_t cpu, int irq, int level) "GICv3 redistributor %x interrupt %d level changed to %d"
 gicv3_redist_send_sgi(uint32_t cpu, int irq) "GICv3 redistributor %x pending SGI %d"
+
+# hw/intc/armv7m_nvic.c
+nvic_recompute_state(int vectpending, int exception_prio) "NVIC state recomputed: vectpending %d exception_prio %d"
+nvic_set_prio(int irq, uint8_t prio) "NVIC set irq %d priority %d"
+nvic_irq_update(int vectpending, int pendprio, int exception_prio, int level) "NVIC vectpending %d pending prio %d exception_prio %d: setting irq line to %d"
+nvic_escalate_prio(int irq, int irqprio, int runprio) "NVIC escalating irq %d to HardFault: insufficient priority %d >= %d"
+nvic_escalate_disabled(int irq) "NVIC escalating irq %d to HardFault: disabled"
+nvic_set_pending(int irq, int en, int prio) "NVIC set pending irq %d (enabled: %d priority %d)"
+nvic_clear_pending(int irq, int en, int prio) "NVIC clear pending irq %d (enabled: %d priority %d)"
+nvic_set_pending_level(int irq) "NVIC set pending: irq %d higher prio than vectpending: setting irq line to 1"
+nvic_acknowledge_irq(int irq, int prio) "NVIC acknowledge IRQ: %d now active (prio %d)"
+nvic_complete_irq(int irq) "NVIC complete IRQ %d"
+nvic_set_irq_level(int irq, int level) "NVIC external irq %d level set to %d"
+nvic_sysreg_read(uint64_t addr, uint32_t value, unsigned size) "NVIC sysreg read addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u"
+nvic_sysreg_write(uint64_t addr, uint32_t value, unsigned size) "NVIC sysreg write addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u"
diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs
index 898e4ccfb1..c8b489390f 100644
--- a/hw/misc/Makefile.objs
+++ b/hw/misc/Makefile.objs
@@ -26,7 +26,7 @@ obj-$(CONFIG_IVSHMEM) += ivshmem.o
 obj-$(CONFIG_REALVIEW) += arm_sysctl.o
 obj-$(CONFIG_NSERIES) += cbus.o
 obj-$(CONFIG_ECCMEMCTL) += eccmemctl.o
-obj-$(CONFIG_EXYNOS4) += exynos4210_pmu.o
+obj-$(CONFIG_EXYNOS4) += exynos4210_pmu.o exynos4210_clk.o
 obj-$(CONFIG_IMX) += imx_ccm.o
 obj-$(CONFIG_IMX) += imx31_ccm.o
 obj-$(CONFIG_IMX) += imx25_ccm.o
@@ -42,6 +42,7 @@ obj-$(CONFIG_OMAP) += omap_sdrc.o
 obj-$(CONFIG_OMAP) += omap_tap.o
 obj-$(CONFIG_RASPI) += bcm2835_mbox.o
 obj-$(CONFIG_RASPI) += bcm2835_property.o
+obj-$(CONFIG_RASPI) += bcm2835_rng.o
 obj-$(CONFIG_SLAVIO) += slavio_misc.o
 obj-$(CONFIG_ZYNQ) += zynq_slcr.o
 obj-$(CONFIG_ZYNQ) += zynq-xadc.o
diff --git a/hw/misc/bcm2835_rng.c b/hw/misc/bcm2835_rng.c
new file mode 100644
index 0000000000..4d62143b24
--- /dev/null
+++ b/hw/misc/bcm2835_rng.c
@@ -0,0 +1,149 @@
+/*
+ * BCM2835 Random Number Generator emulation
+ *
+ * Copyright (C) 2017 Marcin Chojnacki <marcinch7@gmail.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/log.h"
+#include "qapi/error.h"
+#include "crypto/random.h"
+#include "hw/misc/bcm2835_rng.h"
+
+static uint32_t get_random_bytes(void)
+{
+    uint32_t res;
+    Error *err = NULL;
+
+    if (qcrypto_random_bytes((uint8_t *)&res, sizeof(res), &err) < 0) {
+        /* On failure we don't want to return the guest a non-random
+         * value in case they're really using it for cryptographic
+         * purposes, so the best we can do is die here.
+         * This shouldn't happen unless something's broken.
+         * In theory we could implement this device's full FIFO
+         * and interrupt semantics and then just stop filling the
+         * FIFO. That's a lot of work, though, so we assume any
+         * errors are systematic problems and trust that if we didn't
+         * fail as the guest inited then we won't fail later on
+         * mid-run.
+         */
+        error_report_err(err);
+        exit(1);
+    }
+    return res;
+}
+
+static uint64_t bcm2835_rng_read(void *opaque, hwaddr offset,
+                                 unsigned size)
+{
+    BCM2835RngState *s = (BCM2835RngState *)opaque;
+    uint32_t res = 0;
+
+    assert(size == 4);
+
+    switch (offset) {
+    case 0x0:    /* rng_ctrl */
+        res = s->rng_ctrl;
+        break;
+    case 0x4:    /* rng_status */
+        res = s->rng_status | (1 << 24);
+        break;
+    case 0x8:    /* rng_data */
+        res = get_random_bytes();
+        break;
+
+    default:
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "bcm2835_rng_read: Bad offset %x\n",
+                      (int)offset);
+        res = 0;
+        break;
+    }
+
+    return res;
+}
+
+static void bcm2835_rng_write(void *opaque, hwaddr offset,
+                              uint64_t value, unsigned size)
+{
+    BCM2835RngState *s = (BCM2835RngState *)opaque;
+
+    assert(size == 4);
+
+    switch (offset) {
+    case 0x0:    /* rng_ctrl */
+        s->rng_ctrl = value;
+        break;
+    case 0x4:    /* rng_status */
+        /* we shouldn't let the guest write to bits [31..20] */
+        s->rng_status &= ~0xFFFFF;        /* clear 20 lower bits */
+        s->rng_status |= value & 0xFFFFF; /* set them to new value */
+        break;
+
+    default:
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "bcm2835_rng_write: Bad offset %x\n",
+                      (int)offset);
+        break;
+    }
+}
+
+static const MemoryRegionOps bcm2835_rng_ops = {
+    .read = bcm2835_rng_read,
+    .write = bcm2835_rng_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+};
+
+static const VMStateDescription vmstate_bcm2835_rng = {
+    .name = TYPE_BCM2835_RNG,
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT32(rng_ctrl, BCM2835RngState),
+        VMSTATE_UINT32(rng_status, BCM2835RngState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static void bcm2835_rng_init(Object *obj)
+{
+    BCM2835RngState *s = BCM2835_RNG(obj);
+
+    memory_region_init_io(&s->iomem, obj, &bcm2835_rng_ops, s,
+                          TYPE_BCM2835_RNG, 0x10);
+    sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem);
+}
+
+static void bcm2835_rng_reset(DeviceState *dev)
+{
+    BCM2835RngState *s = BCM2835_RNG(dev);
+
+    s->rng_ctrl = 0;
+    s->rng_status = 0;
+}
+
+static void bcm2835_rng_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+
+    dc->reset = bcm2835_rng_reset;
+    dc->vmsd = &vmstate_bcm2835_rng;
+}
+
+static TypeInfo bcm2835_rng_info = {
+    .name          = TYPE_BCM2835_RNG,
+    .parent        = TYPE_SYS_BUS_DEVICE,
+    .instance_size = sizeof(BCM2835RngState),
+    .class_init    = bcm2835_rng_class_init,
+    .instance_init = bcm2835_rng_init,
+};
+
+static void bcm2835_rng_register_types(void)
+{
+    type_register_static(&bcm2835_rng_info);
+}
+
+type_init(bcm2835_rng_register_types)
diff --git a/hw/misc/exynos4210_clk.c b/hw/misc/exynos4210_clk.c
new file mode 100644
index 0000000000..81862c0ada
--- /dev/null
+++ b/hw/misc/exynos4210_clk.c
@@ -0,0 +1,164 @@
+/*
+ *  Exynos4210 Clock Controller Emulation
+ *
+ *  Copyright (c) 2017 Krzysztof Kozlowski <krzk@kernel.org>
+ *
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under the terms of the GNU General Public License as published by the
+ *  Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful, but WITHOUT
+ *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *  FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ *  for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "qemu/osdep.h"
+#include "hw/sysbus.h"
+#include "qemu/log.h"
+
+#define TYPE_EXYNOS4210_CLK             "exynos4210.clk"
+#define EXYNOS4210_CLK(obj) \
+    OBJECT_CHECK(Exynos4210ClkState, (obj), TYPE_EXYNOS4210_CLK)
+
+#define CLK_PLL_LOCKED                  BIT(29)
+
+#define EXYNOS4210_CLK_REGS_MEM_SIZE    0x15104
+
+typedef struct Exynos4210Reg {
+    const char   *name; /* for debug only */
+    uint32_t     offset;
+    uint32_t     reset_value;
+} Exynos4210Reg;
+
+/* Clock controller register base: 0x10030000 */
+static const Exynos4210Reg exynos4210_clk_regs[] = {
+    {"EPLL_LOCK",                     0xc010, 0x00000fff},
+    {"VPLL_LOCK",                     0xc020, 0x00000fff},
+    {"EPLL_CON0",                     0xc110, 0x00300301 | CLK_PLL_LOCKED},
+    {"EPLL_CON1",                     0xc114, 0x00000000},
+    {"VPLL_CON0",                     0xc120, 0x00240201 | CLK_PLL_LOCKED},
+    {"VPLL_CON1",                     0xc124, 0x66010464},
+    {"APLL_LOCK",                    0x14000, 0x00000fff},
+    {"MPLL_LOCK",                    0x14004, 0x00000fff},
+    {"APLL_CON0",                    0x14100, 0x00c80601 | CLK_PLL_LOCKED},
+    {"APLL_CON1",                    0x14104, 0x0000001c},
+    {"MPLL_CON0",                    0x14108, 0x00c80601 | CLK_PLL_LOCKED},
+    {"MPLL_CON1",                    0x1410c, 0x0000001c},
+};
+
+#define EXYNOS4210_REGS_NUM       ARRAY_SIZE(exynos4210_clk_regs)
+
+typedef struct Exynos4210ClkState {
+    SysBusDevice parent_obj;
+
+    MemoryRegion iomem;
+    uint32_t reg[EXYNOS4210_REGS_NUM];
+} Exynos4210ClkState;
+
+static uint64_t exynos4210_clk_read(void *opaque, hwaddr offset,
+                                    unsigned size)
+{
+    const Exynos4210ClkState *s = (Exynos4210ClkState *)opaque;
+    const Exynos4210Reg *regs = exynos4210_clk_regs;
+    unsigned int i;
+
+    for (i = 0; i < EXYNOS4210_REGS_NUM; i++) {
+        if (regs->offset == offset) {
+            return s->reg[i];
+        }
+        regs++;
+    }
+    qemu_log_mask(LOG_GUEST_ERROR, "%s: bad read offset 0x%04x\n",
+                  __func__, (uint32_t)offset);
+    return 0;
+}
+
+static void exynos4210_clk_write(void *opaque, hwaddr offset,
+                                 uint64_t val, unsigned size)
+{
+    Exynos4210ClkState *s = (Exynos4210ClkState *)opaque;
+    const Exynos4210Reg *regs = exynos4210_clk_regs;
+    unsigned int i;
+
+    for (i = 0; i < EXYNOS4210_REGS_NUM; i++) {
+        if (regs->offset == offset) {
+            s->reg[i] = val;
+            return;
+        }
+        regs++;
+    }
+    qemu_log_mask(LOG_GUEST_ERROR, "%s: bad write offset 0x%04x\n",
+                  __func__, (uint32_t)offset);
+}
+
+static const MemoryRegionOps exynos4210_clk_ops = {
+    .read = exynos4210_clk_read,
+    .write = exynos4210_clk_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+    .valid = {
+        .min_access_size = 4,
+        .max_access_size = 4,
+        .unaligned = false
+    }
+};
+
+static void exynos4210_clk_reset(DeviceState *dev)
+{
+    Exynos4210ClkState *s = EXYNOS4210_CLK(dev);
+    unsigned int i;
+
+    /* Set default values for registers */
+    for (i = 0; i < EXYNOS4210_REGS_NUM; i++) {
+        s->reg[i] = exynos4210_clk_regs[i].reset_value;
+    }
+}
+
+static void exynos4210_clk_init(Object *obj)
+{
+    Exynos4210ClkState *s = EXYNOS4210_CLK(obj);
+    SysBusDevice *dev = SYS_BUS_DEVICE(obj);
+
+    /* memory mapping */
+    memory_region_init_io(&s->iomem, obj, &exynos4210_clk_ops, s,
+                          TYPE_EXYNOS4210_CLK, EXYNOS4210_CLK_REGS_MEM_SIZE);
+    sysbus_init_mmio(dev, &s->iomem);
+}
+
+static const VMStateDescription exynos4210_clk_vmstate = {
+    .name = TYPE_EXYNOS4210_CLK,
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT32_ARRAY(reg, Exynos4210ClkState, EXYNOS4210_REGS_NUM),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static void exynos4210_clk_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+
+    dc->reset = exynos4210_clk_reset;
+    dc->vmsd = &exynos4210_clk_vmstate;
+}
+
+static const TypeInfo exynos4210_clk_info = {
+    .name          = TYPE_EXYNOS4210_CLK,
+    .parent        = TYPE_SYS_BUS_DEVICE,
+    .instance_size = sizeof(Exynos4210ClkState),
+    .instance_init = exynos4210_clk_init,
+    .class_init    = exynos4210_clk_class_init,
+};
+
+static void exynos4210_clk_register(void)
+{
+    qemu_log_mask(LOG_GUEST_ERROR, "Clock init\n");
+    type_register_static(&exynos4210_clk_info);
+}
+
+type_init(exynos4210_clk_register)
diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c
index e99d4544a2..d4de8ad9f1 100644
--- a/hw/net/cadence_gem.c
+++ b/hw/net/cadence_gem.c
@@ -508,7 +508,7 @@ static void gem_update_int_status(CadenceGEMState *s)
 
     if ((s->num_priority_queues == 1) && s->regs[GEM_ISR]) {
         /* No priority queues, just trigger the interrupt */
-        DB_PRINT("asserting int.\n", i);
+        DB_PRINT("asserting int.\n");
         qemu_set_irq(s->irq[0], 1);
         return;
     }
diff --git a/hw/nvram/spapr_nvram.c b/hw/nvram/spapr_nvram.c
index 65ba188555..aa5d2c1f5f 100644
--- a/hw/nvram/spapr_nvram.c
+++ b/hw/nvram/spapr_nvram.c
@@ -141,9 +141,17 @@ static void rtas_nvram_store(PowerPCCPU *cpu, sPAPRMachineState *spapr,
 static void spapr_nvram_realize(VIOsPAPRDevice *dev, Error **errp)
 {
     sPAPRNVRAM *nvram = VIO_SPAPR_NVRAM(dev);
+    int ret;
 
     if (nvram->blk) {
         nvram->size = blk_getlength(nvram->blk);
+
+        ret = blk_set_perm(nvram->blk,
+                           BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE,
+                           BLK_PERM_ALL, errp);
+        if (ret < 0) {
+            return;
+        }
     } else {
         nvram->size = DEFAULT_NVRAM_SIZE;
     }
diff --git a/hw/s390x/ipl.c b/hw/s390x/ipl.c
index 2e2664f22e..7978c7d52a 100644
--- a/hw/s390x/ipl.c
+++ b/hw/s390x/ipl.c
@@ -20,6 +20,7 @@
 #include "hw/s390x/virtio-ccw.h"
 #include "hw/s390x/css.h"
 #include "ipl.h"
+#include "qemu/error-report.h"
 
 #define KERN_IMAGE_START                0x010000UL
 #define KERN_PARM_AREA                  0x010480UL
@@ -209,6 +210,7 @@ static Property s390_ipl_properties[] = {
     DEFINE_PROP_STRING("initrd", S390IPLState, initrd),
     DEFINE_PROP_STRING("cmdline", S390IPLState, cmdline),
     DEFINE_PROP_STRING("firmware", S390IPLState, firmware),
+    DEFINE_PROP_STRING("netboot_fw", S390IPLState, netboot_fw),
     DEFINE_PROP_BOOL("enforce_bios", S390IPLState, enforce_bios, false),
     DEFINE_PROP_BOOL("iplbext_migration", S390IPLState, iplbext_migration,
                      true),
@@ -226,6 +228,12 @@ static bool s390_gen_initial_iplb(S390IPLState *ipl)
                 TYPE_VIRTIO_CCW_DEVICE);
         SCSIDevice *sd = (SCSIDevice *) object_dynamic_cast(OBJECT(dev_st),
                                                             TYPE_SCSI_DEVICE);
+        VirtIONet *vn = (VirtIONet *) object_dynamic_cast(OBJECT(dev_st),
+                                                          TYPE_VIRTIO_NET);
+
+        if (vn) {
+            ipl->netboot = true;
+        }
         if (virtio_ccw_dev) {
             CcwDevice *ccw_dev = CCW_DEVICE(virtio_ccw_dev);
 
@@ -258,12 +266,86 @@ static bool s390_gen_initial_iplb(S390IPLState *ipl)
     return false;
 }
 
+static int load_netboot_image(Error **errp)
+{
+    S390IPLState *ipl = get_ipl_device();
+    char *netboot_filename;
+    MemoryRegion *sysmem =  get_system_memory();
+    MemoryRegion *mr = NULL;
+    void *ram_ptr = NULL;
+    int img_size = -1;
+
+    mr = memory_region_find(sysmem, 0, 1).mr;
+    if (!mr) {
+        error_setg(errp, "Failed to find memory region at address 0");
+        return -1;
+    }
+
+    ram_ptr = memory_region_get_ram_ptr(mr);
+    if (!ram_ptr) {
+        error_setg(errp, "No RAM found");
+        goto unref_mr;
+    }
+
+    netboot_filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, ipl->netboot_fw);
+    if (netboot_filename == NULL) {
+        error_setg(errp, "Could not find network bootloader");
+        goto unref_mr;
+    }
+
+    img_size = load_elf_ram(netboot_filename, NULL, NULL, &ipl->start_addr,
+                            NULL, NULL, 1, EM_S390, 0, 0, NULL, false);
+
+    if (img_size < 0) {
+        img_size = load_image_size(netboot_filename, ram_ptr, ram_size);
+        ipl->start_addr = KERN_IMAGE_START;
+    }
+
+    if (img_size < 0) {
+        error_setg(errp, "Failed to load network bootloader");
+    }
+
+    g_free(netboot_filename);
+
+unref_mr:
+    memory_region_unref(mr);
+    return img_size;
+}
+
+static bool is_virtio_net_device(IplParameterBlock *iplb)
+{
+    uint8_t cssid;
+    uint8_t ssid;
+    uint16_t devno;
+    uint16_t schid;
+    SubchDev *sch = NULL;
+
+    if (iplb->pbt != S390_IPL_TYPE_CCW) {
+        return false;
+    }
+
+    devno = be16_to_cpu(iplb->ccw.devno);
+    ssid = iplb->ccw.ssid & 3;
+
+    for (schid = 0; schid < MAX_SCHID; schid++) {
+        for (cssid = 0; cssid < MAX_CSSID; cssid++) {
+            sch = css_find_subch(1, cssid, ssid, schid);
+
+            if (sch && sch->devno == devno) {
+                return sch->id.cu_model == VIRTIO_ID_NET;
+            }
+        }
+    }
+    return false;
+}
+
 void s390_ipl_update_diag308(IplParameterBlock *iplb)
 {
     S390IPLState *ipl = get_ipl_device();
 
     ipl->iplb = *iplb;
     ipl->iplb_valid = true;
+    ipl->netboot = is_virtio_net_device(iplb);
 }
 
 IplParameterBlock *s390_ipl_get_iplb(void)
@@ -287,6 +369,7 @@ void s390_reipl_request(void)
 void s390_ipl_prepare_cpu(S390CPU *cpu)
 {
     S390IPLState *ipl = get_ipl_device();
+    Error *err = NULL;
 
     cpu->env.psw.addr = ipl->start_addr;
     cpu->env.psw.mask = IPL_PSW_MASK;
@@ -297,6 +380,13 @@ void s390_ipl_prepare_cpu(S390CPU *cpu)
             ipl->iplb_valid = s390_gen_initial_iplb(ipl);
         }
     }
+    if (ipl->netboot) {
+        if (load_netboot_image(&err) < 0) {
+            error_report_err(err);
+            vm_stop(RUN_STATE_INTERNAL_ERROR);
+        }
+        ipl->iplb.ccw.netboot_start_addr = ipl->start_addr;
+    }
 }
 
 static void s390_ipl_reset(DeviceState *dev)
diff --git a/hw/s390x/ipl.h b/hw/s390x/ipl.h
index c89109585a..46930e4c64 100644
--- a/hw/s390x/ipl.h
+++ b/hw/s390x/ipl.h
@@ -16,7 +16,8 @@
 #include "cpu.h"
 
 struct IplBlockCcw {
-    uint8_t  reserved0[85];
+    uint64_t netboot_start_addr;
+    uint8_t  reserved0[77];
     uint8_t  ssid;
     uint16_t devno;
     uint8_t  vm_flags;
@@ -100,12 +101,14 @@ struct S390IPLState {
     IplParameterBlock iplb;
     bool iplb_valid;
     bool reipl_requested;
+    bool netboot;
 
     /*< public >*/
     char *kernel;
     char *initrd;
     char *cmdline;
     char *firmware;
+    char *netboot_fw;
     uint8_t cssid;
     uint8_t ssid;
     uint16_t devno;
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 4f0d62b2d8..40914fde6f 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -116,7 +116,8 @@ static void ccw_init(MachineState *machine)
     /* get a BUS */
     css_bus = virtual_css_bus_init();
     s390_init_ipl_dev(machine->kernel_filename, machine->kernel_cmdline,
-                      machine->initrd_filename, "s390-ccw.img", true);
+                      machine->initrd_filename, "s390-ccw.img",
+                      "s390-netboot.img", true);
     s390_flic_init();
 
     dev = qdev_create(NULL, TYPE_S390_PCI_HOST_BRIDGE);
diff --git a/hw/s390x/s390-virtio.c b/hw/s390x/s390-virtio.c
index 9cfb09057e..afa4148e6b 100644
--- a/hw/s390x/s390-virtio.c
+++ b/hw/s390x/s390-virtio.c
@@ -65,6 +65,7 @@ void s390_init_ipl_dev(const char *kernel_filename,
                        const char *kernel_cmdline,
                        const char *initrd_filename,
                        const char *firmware,
+                       const char *netboot_fw,
                        bool enforce_bios)
 {
     Object *new = object_new(TYPE_S390_IPL);
@@ -78,6 +79,7 @@ void s390_init_ipl_dev(const char *kernel_filename,
     }
     qdev_prop_set_string(dev, "cmdline", kernel_cmdline);
     qdev_prop_set_string(dev, "firmware", firmware);
+    qdev_prop_set_string(dev, "netboot_fw", netboot_fw);
     qdev_prop_set_bit(dev, "enforce_bios", enforce_bios);
     object_property_add_child(qdev_get_machine(), TYPE_S390_IPL,
                               new, NULL);
diff --git a/hw/s390x/s390-virtio.h b/hw/s390x/s390-virtio.h
index f588b80a6e..f2377a3e0e 100644
--- a/hw/s390x/s390-virtio.h
+++ b/hw/s390x/s390-virtio.h
@@ -24,6 +24,7 @@ void s390_init_ipl_dev(const char *kernel_filename,
                        const char *kernel_cmdline,
                        const char *initrd_filename,
                        const char *firmware,
+                       const char *netboot_fw,
                        bool enforce_bios);
 void s390_create_virtio_net(BusState *bus, const char *name);
 void s390_nmi(NMIState *n, int cpu_index, Error **errp);
diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c
index bbfb5dc289..a53f058621 100644
--- a/hw/scsi/scsi-disk.c
+++ b/hw/scsi/scsi-disk.c
@@ -2240,7 +2240,7 @@ static void scsi_disk_resize_cb(void *opaque)
     }
 }
 
-static void scsi_cd_change_media_cb(void *opaque, bool load)
+static void scsi_cd_change_media_cb(void *opaque, bool load, Error **errp)
 {
     SCSIDiskState *s = opaque;
 
@@ -2328,7 +2328,13 @@ static void scsi_realize(SCSIDevice *dev, Error **errp)
             return;
         }
     }
-    blkconf_apply_backend_options(&dev->conf);
+    blkconf_apply_backend_options(&dev->conf,
+                                  blk_is_read_only(s->qdev.conf.blk),
+                                  dev->type == TYPE_DISK, &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
 
     if (s->qdev.conf.discard_granularity == -1) {
         s->qdev.conf.discard_granularity =
@@ -2380,7 +2386,7 @@ static void scsi_cd_realize(SCSIDevice *dev, Error **errp)
     SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, dev);
 
     if (!dev->conf.blk) {
-        dev->conf.blk = blk_new();
+        dev->conf.blk = blk_new(0, BLK_PERM_ALL);
     }
 
     s->qdev.blocksize = 2048;
diff --git a/hw/sd/Makefile.objs b/hw/sd/Makefile.objs
index 31c83308f2..c2b7664264 100644
--- a/hw/sd/Makefile.objs
+++ b/hw/sd/Makefile.objs
@@ -6,3 +6,4 @@ common-obj-$(CONFIG_SDHCI) += sdhci.o
 obj-$(CONFIG_MILKYMIST) += milkymist-memcard.o
 obj-$(CONFIG_OMAP) += omap_mmc.o
 obj-$(CONFIG_PXA2XX) += pxa2xx_mmci.o
+obj-$(CONFIG_RASPI) += bcm2835_sdhost.o
diff --git a/hw/sd/bcm2835_sdhost.c b/hw/sd/bcm2835_sdhost.c
new file mode 100644
index 0000000000..f7f4e656df
--- /dev/null
+++ b/hw/sd/bcm2835_sdhost.c
@@ -0,0 +1,429 @@
+/*
+ * Raspberry Pi (BCM2835) SD Host Controller
+ *
+ * Copyright (c) 2017 Antfield SAS
+ *
+ * Authors:
+ *  Clement Deschamps <clement.deschamps@antfield.fr>
+ *  Luc Michel <luc.michel@antfield.fr>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/log.h"
+#include "sysemu/blockdev.h"
+#include "hw/sd/bcm2835_sdhost.h"
+
+#define TYPE_BCM2835_SDHOST_BUS "bcm2835-sdhost-bus"
+#define BCM2835_SDHOST_BUS(obj) \
+    OBJECT_CHECK(SDBus, (obj), TYPE_BCM2835_SDHOST_BUS)
+
+#define SDCMD  0x00 /* Command to SD card              - 16 R/W */
+#define SDARG  0x04 /* Argument to SD card             - 32 R/W */
+#define SDTOUT 0x08 /* Start value for timeout counter - 32 R/W */
+#define SDCDIV 0x0c /* Start value for clock divider   - 11 R/W */
+#define SDRSP0 0x10 /* SD card rsp (31:0)         - 32 R   */
+#define SDRSP1 0x14 /* SD card rsp (63:32)        - 32 R   */
+#define SDRSP2 0x18 /* SD card rsp (95:64)        - 32 R   */
+#define SDRSP3 0x1c /* SD card rsp (127:96)       - 32 R   */
+#define SDHSTS 0x20 /* SD host status                  - 11 R   */
+#define SDVDD  0x30 /* SD card power control           -  1 R/W */
+#define SDEDM  0x34 /* Emergency Debug Mode            - 13 R/W */
+#define SDHCFG 0x38 /* Host configuration              -  2 R/W */
+#define SDHBCT 0x3c /* Host byte count (debug)         - 32 R/W */
+#define SDDATA 0x40 /* Data to/from SD card            - 32 R/W */
+#define SDHBLC 0x50 /* Host block count (SDIO/SDHC)    -  9 R/W */
+
+#define SDCMD_NEW_FLAG                  0x8000
+#define SDCMD_FAIL_FLAG                 0x4000
+#define SDCMD_BUSYWAIT                  0x800
+#define SDCMD_NO_RESPONSE               0x400
+#define SDCMD_LONG_RESPONSE             0x200
+#define SDCMD_WRITE_CMD                 0x80
+#define SDCMD_READ_CMD                  0x40
+#define SDCMD_CMD_MASK                  0x3f
+
+#define SDCDIV_MAX_CDIV                 0x7ff
+
+#define SDHSTS_BUSY_IRPT                0x400
+#define SDHSTS_BLOCK_IRPT               0x200
+#define SDHSTS_SDIO_IRPT                0x100
+#define SDHSTS_REW_TIME_OUT             0x80
+#define SDHSTS_CMD_TIME_OUT             0x40
+#define SDHSTS_CRC16_ERROR              0x20
+#define SDHSTS_CRC7_ERROR               0x10
+#define SDHSTS_FIFO_ERROR               0x08
+/* Reserved */
+/* Reserved */
+#define SDHSTS_DATA_FLAG                0x01
+
+#define SDHCFG_BUSY_IRPT_EN     (1 << 10)
+#define SDHCFG_BLOCK_IRPT_EN    (1 << 8)
+#define SDHCFG_SDIO_IRPT_EN     (1 << 5)
+#define SDHCFG_DATA_IRPT_EN     (1 << 4)
+#define SDHCFG_SLOW_CARD        (1 << 3)
+#define SDHCFG_WIDE_EXT_BUS     (1 << 2)
+#define SDHCFG_WIDE_INT_BUS     (1 << 1)
+#define SDHCFG_REL_CMD_LINE     (1 << 0)
+
+#define SDEDM_FORCE_DATA_MODE   (1 << 19)
+#define SDEDM_CLOCK_PULSE       (1 << 20)
+#define SDEDM_BYPASS            (1 << 21)
+
+#define SDEDM_WRITE_THRESHOLD_SHIFT 9
+#define SDEDM_READ_THRESHOLD_SHIFT 14
+#define SDEDM_THRESHOLD_MASK     0x1f
+
+#define SDEDM_FSM_MASK           0xf
+#define SDEDM_FSM_IDENTMODE      0x0
+#define SDEDM_FSM_DATAMODE       0x1
+#define SDEDM_FSM_READDATA       0x2
+#define SDEDM_FSM_WRITEDATA      0x3
+#define SDEDM_FSM_READWAIT       0x4
+#define SDEDM_FSM_READCRC        0x5
+#define SDEDM_FSM_WRITECRC       0x6
+#define SDEDM_FSM_WRITEWAIT1     0x7
+#define SDEDM_FSM_POWERDOWN      0x8
+#define SDEDM_FSM_POWERUP        0x9
+#define SDEDM_FSM_WRITESTART1    0xa
+#define SDEDM_FSM_WRITESTART2    0xb
+#define SDEDM_FSM_GENPULSES      0xc
+#define SDEDM_FSM_WRITEWAIT2     0xd
+#define SDEDM_FSM_STARTPOWDOWN   0xf
+
+#define SDDATA_FIFO_WORDS        16
+
+static void bcm2835_sdhost_update_irq(BCM2835SDHostState *s)
+{
+    uint32_t irq = s->status &
+        (SDHSTS_BUSY_IRPT | SDHSTS_BLOCK_IRPT | SDHSTS_SDIO_IRPT);
+    qemu_set_irq(s->irq, !!irq);
+}
+
+static void bcm2835_sdhost_send_command(BCM2835SDHostState *s)
+{
+    SDRequest request;
+    uint8_t rsp[16];
+    int rlen;
+
+    request.cmd = s->cmd & SDCMD_CMD_MASK;
+    request.arg = s->cmdarg;
+
+    rlen = sdbus_do_command(&s->sdbus, &request, rsp);
+    if (rlen < 0) {
+        goto error;
+    }
+    if (!(s->cmd & SDCMD_NO_RESPONSE)) {
+#define RWORD(n) (((uint32_t)rsp[n] << 24) | (rsp[n + 1] << 16) \
+                  | (rsp[n + 2] << 8) | rsp[n + 3])
+        if (rlen == 0 || (rlen == 4 && (s->cmd & SDCMD_LONG_RESPONSE))) {
+            goto error;
+        }
+        if (rlen != 4 && rlen != 16) {
+            goto error;
+        }
+        if (rlen == 4) {
+            s->rsp[0] = RWORD(0);
+            s->rsp[1] = s->rsp[2] = s->rsp[3] = 0;
+        } else {
+            s->rsp[0] = RWORD(12);
+            s->rsp[1] = RWORD(8);
+            s->rsp[2] = RWORD(4);
+            s->rsp[3] = RWORD(0);
+        }
+#undef RWORD
+    }
+    return;
+
+error:
+    s->cmd |= SDCMD_FAIL_FLAG;
+    s->status |= SDHSTS_CMD_TIME_OUT;
+}
+
+static void bcm2835_sdhost_fifo_push(BCM2835SDHostState *s, uint32_t value)
+{
+    int n;
+
+    if (s->fifo_len == BCM2835_SDHOST_FIFO_LEN) {
+        /* FIFO overflow */
+        return;
+    }
+    n = (s->fifo_pos + s->fifo_len) & (BCM2835_SDHOST_FIFO_LEN - 1);
+    s->fifo_len++;
+    s->fifo[n] = value;
+}
+
+static uint32_t bcm2835_sdhost_fifo_pop(BCM2835SDHostState *s)
+{
+    uint32_t value;
+
+    if (s->fifo_len == 0) {
+        /* FIFO underflow */
+        return 0;
+    }
+    value = s->fifo[s->fifo_pos];
+    s->fifo_len--;
+    s->fifo_pos = (s->fifo_pos + 1) & (BCM2835_SDHOST_FIFO_LEN - 1);
+    return value;
+}
+
+static void bcm2835_sdhost_fifo_run(BCM2835SDHostState *s)
+{
+    uint32_t value = 0;
+    int n;
+    int is_read;
+
+    is_read = (s->cmd & SDCMD_READ_CMD) != 0;
+    if (s->datacnt != 0 && (!is_read || sdbus_data_ready(&s->sdbus))) {
+        if (is_read) {
+            n = 0;
+            while (s->datacnt && s->fifo_len < BCM2835_SDHOST_FIFO_LEN) {
+                value |= (uint32_t)sdbus_read_data(&s->sdbus) << (n * 8);
+                s->datacnt--;
+                n++;
+                if (n == 4) {
+                    bcm2835_sdhost_fifo_push(s, value);
+                    n = 0;
+                    value = 0;
+                }
+            }
+            if (n != 0) {
+                bcm2835_sdhost_fifo_push(s, value);
+            }
+        } else { /* write */
+            n = 0;
+            while (s->datacnt > 0 && (s->fifo_len > 0 || n > 0)) {
+                if (n == 0) {
+                    value = bcm2835_sdhost_fifo_pop(s);
+                    n = 4;
+                }
+                n--;
+                s->datacnt--;
+                sdbus_write_data(&s->sdbus, value & 0xff);
+                value >>= 8;
+            }
+        }
+    }
+    if (s->datacnt == 0) {
+        s->status |= SDHSTS_DATA_FLAG;
+
+        s->edm &= ~0xf;
+        s->edm |= SDEDM_FSM_DATAMODE;
+
+        if (s->config & SDHCFG_DATA_IRPT_EN) {
+            s->status |= SDHSTS_SDIO_IRPT;
+        }
+
+        if ((s->cmd & SDCMD_BUSYWAIT) && (s->config & SDHCFG_BUSY_IRPT_EN)) {
+            s->status |= SDHSTS_BUSY_IRPT;
+        }
+
+        if ((s->cmd & SDCMD_WRITE_CMD) && (s->config & SDHCFG_BLOCK_IRPT_EN)) {
+            s->status |= SDHSTS_BLOCK_IRPT;
+        }
+
+        bcm2835_sdhost_update_irq(s);
+    }
+
+    s->edm &= ~(0x1f << 4);
+    s->edm |= ((s->fifo_len & 0x1f) << 4);
+}
+
+static uint64_t bcm2835_sdhost_read(void *opaque, hwaddr offset,
+    unsigned size)
+{
+    BCM2835SDHostState *s = (BCM2835SDHostState *)opaque;
+    uint32_t res = 0;
+
+    switch (offset) {
+    case SDCMD:
+        res = s->cmd;
+        break;
+    case SDHSTS:
+        res = s->status;
+        break;
+    case SDRSP0:
+        res = s->rsp[0];
+        break;
+    case SDRSP1:
+        res = s->rsp[1];
+        break;
+    case SDRSP2:
+        res = s->rsp[2];
+        break;
+    case SDRSP3:
+        res = s->rsp[3];
+        break;
+    case SDEDM:
+        res = s->edm;
+        break;
+    case SDVDD:
+        res = s->vdd;
+        break;
+    case SDDATA:
+        res = bcm2835_sdhost_fifo_pop(s);
+        bcm2835_sdhost_fifo_run(s);
+        break;
+    case SDHBCT:
+        res = s->hbct;
+        break;
+    case SDHBLC:
+        res = s->hblc;
+        break;
+
+    default:
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset %"HWADDR_PRIx"\n",
+                      __func__, offset);
+        res = 0;
+        break;
+    }
+
+    return res;
+}
+
+static void bcm2835_sdhost_write(void *opaque, hwaddr offset,
+    uint64_t value, unsigned size)
+{
+    BCM2835SDHostState *s = (BCM2835SDHostState *)opaque;
+
+    switch (offset) {
+    case SDCMD:
+        s->cmd = value;
+        if (value & SDCMD_NEW_FLAG) {
+            bcm2835_sdhost_send_command(s);
+            bcm2835_sdhost_fifo_run(s);
+            s->cmd &= ~SDCMD_NEW_FLAG;
+        }
+        break;
+    case SDTOUT:
+        break;
+    case SDCDIV:
+        break;
+    case SDHSTS:
+        s->status &= ~value;
+        bcm2835_sdhost_update_irq(s);
+        break;
+    case SDARG:
+        s->cmdarg = value;
+        break;
+    case SDEDM:
+        if ((value & 0xf) == 0xf) {
+            /* power down */
+            value &= ~0xf;
+        }
+        s->edm = value;
+        break;
+    case SDHCFG:
+        s->config = value;
+        bcm2835_sdhost_fifo_run(s);
+        break;
+    case SDVDD:
+        s->vdd = value;
+        break;
+    case SDDATA:
+        bcm2835_sdhost_fifo_push(s, value);
+        bcm2835_sdhost_fifo_run(s);
+        break;
+    case SDHBCT:
+        s->hbct = value;
+        break;
+    case SDHBLC:
+        s->hblc = value;
+        s->datacnt = s->hblc * s->hbct;
+        bcm2835_sdhost_fifo_run(s);
+        break;
+
+    default:
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset %"HWADDR_PRIx"\n",
+                      __func__, offset);
+        break;
+    }
+}
+
+static const MemoryRegionOps bcm2835_sdhost_ops = {
+    .read = bcm2835_sdhost_read,
+    .write = bcm2835_sdhost_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+};
+
+static const VMStateDescription vmstate_bcm2835_sdhost = {
+    .name = TYPE_BCM2835_SDHOST,
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT32(cmd, BCM2835SDHostState),
+        VMSTATE_UINT32(cmdarg, BCM2835SDHostState),
+        VMSTATE_UINT32(status, BCM2835SDHostState),
+        VMSTATE_UINT32_ARRAY(rsp, BCM2835SDHostState, 4),
+        VMSTATE_UINT32(config, BCM2835SDHostState),
+        VMSTATE_UINT32(edm, BCM2835SDHostState),
+        VMSTATE_UINT32(vdd, BCM2835SDHostState),
+        VMSTATE_UINT32(hbct, BCM2835SDHostState),
+        VMSTATE_UINT32(hblc, BCM2835SDHostState),
+        VMSTATE_INT32(fifo_pos, BCM2835SDHostState),
+        VMSTATE_INT32(fifo_len, BCM2835SDHostState),
+        VMSTATE_UINT32_ARRAY(fifo, BCM2835SDHostState, BCM2835_SDHOST_FIFO_LEN),
+        VMSTATE_UINT32(datacnt, BCM2835SDHostState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static void bcm2835_sdhost_init(Object *obj)
+{
+    BCM2835SDHostState *s = BCM2835_SDHOST(obj);
+
+    qbus_create_inplace(&s->sdbus, sizeof(s->sdbus),
+                        TYPE_BCM2835_SDHOST_BUS, DEVICE(s), "sd-bus");
+
+    memory_region_init_io(&s->iomem, obj, &bcm2835_sdhost_ops, s,
+                          TYPE_BCM2835_SDHOST, 0x1000);
+    sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem);
+    sysbus_init_irq(SYS_BUS_DEVICE(s), &s->irq);
+}
+
+static void bcm2835_sdhost_reset(DeviceState *dev)
+{
+    BCM2835SDHostState *s = BCM2835_SDHOST(dev);
+
+    s->cmd = 0;
+    s->cmdarg = 0;
+    s->edm = 0x0000c60f;
+    s->config = 0;
+    s->hbct = 0;
+    s->hblc = 0;
+    s->datacnt = 0;
+    s->fifo_pos = 0;
+    s->fifo_len = 0;
+}
+
+static void bcm2835_sdhost_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+
+    dc->reset = bcm2835_sdhost_reset;
+    dc->vmsd = &vmstate_bcm2835_sdhost;
+}
+
+static TypeInfo bcm2835_sdhost_info = {
+    .name          = TYPE_BCM2835_SDHOST,
+    .parent        = TYPE_SYS_BUS_DEVICE,
+    .instance_size = sizeof(BCM2835SDHostState),
+    .class_init    = bcm2835_sdhost_class_init,
+    .instance_init = bcm2835_sdhost_init,
+};
+
+static const TypeInfo bcm2835_sdhost_bus_info = {
+    .name = TYPE_BCM2835_SDHOST_BUS,
+    .parent = TYPE_SD_BUS,
+    .instance_size = sizeof(SDBus),
+};
+
+static void bcm2835_sdhost_register_types(void)
+{
+    type_register_static(&bcm2835_sdhost_info);
+    type_register_static(&bcm2835_sdhost_bus_info);
+}
+
+type_init(bcm2835_sdhost_register_types)
diff --git a/hw/sd/core.c b/hw/sd/core.c
index 14c2bdf27b..295dc44ab7 100644
--- a/hw/sd/core.c
+++ b/hw/sd/core.c
@@ -131,6 +131,33 @@ void sdbus_set_readonly(SDBus *sdbus, bool readonly)
     }
 }
 
+void sdbus_reparent_card(SDBus *from, SDBus *to)
+{
+    SDState *card = get_card(from);
+    SDCardClass *sc;
+    bool readonly;
+
+    /* We directly reparent the card object rather than implementing this
+     * as a hotpluggable connection because we don't want to expose SD cards
+     * to users as being hotpluggable, and we can get away with it in this
+     * limited use case. This could perhaps be implemented more cleanly in
+     * future by adding support to the hotplug infrastructure for "device
+     * can be hotplugged only via code, not by user".
+     */
+
+    if (!card) {
+        return;
+    }
+
+    sc = SD_CARD_GET_CLASS(card);
+    readonly = sc->get_readonly(card);
+
+    sdbus_set_inserted(from, false);
+    qdev_set_parent_bus(DEVICE(card), &to->qbus);
+    sdbus_set_inserted(to, true);
+    sdbus_set_readonly(to, readonly);
+}
+
 static const TypeInfo sd_bus_info = {
     .name = TYPE_SD_BUS,
     .parent = TYPE_BUS,
diff --git a/hw/sd/sd.c b/hw/sd/sd.c
index 8e88e8311a..ba47bff4db 100644
--- a/hw/sd/sd.c
+++ b/hw/sd/sd.c
@@ -458,7 +458,7 @@ static bool sd_get_readonly(SDState *sd)
     return sd->wp_switch;
 }
 
-static void sd_cardchange(void *opaque, bool load)
+static void sd_cardchange(void *opaque, bool load, Error **errp)
 {
     SDState *sd = opaque;
     DeviceState *dev = DEVICE(sd);
@@ -1887,6 +1887,7 @@ static void sd_instance_finalize(Object *obj)
 static void sd_realize(DeviceState *dev, Error **errp)
 {
     SDState *sd = SD_CARD(dev);
+    int ret;
 
     if (sd->blk && blk_is_read_only(sd->blk)) {
         error_setg(errp, "Cannot use read-only drive as SD card");
@@ -1894,6 +1895,11 @@ static void sd_realize(DeviceState *dev, Error **errp)
     }
 
     if (sd->blk) {
+        ret = blk_set_perm(sd->blk, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE,
+                           BLK_PERM_ALL, errp);
+        if (ret < 0) {
+            return;
+        }
         blk_set_dev_ops(sd->blk, &sd_block_ops, sd);
     }
 }
diff --git a/hw/sd/sdhci.c b/hw/sd/sdhci.c
index da32b5f709..6d6a791ee9 100644
--- a/hw/sd/sdhci.c
+++ b/hw/sd/sdhci.c
@@ -119,6 +119,7 @@
     (SDHC_CAPAB_BASECLKFREQ << 8) | (SDHC_CAPAB_TOUNIT << 7) | \
     (SDHC_CAPAB_TOCLKFREQ))
 
+#define MASK_TRNMOD     0x0037
 #define MASKED_WRITE(reg, mask, val)  (reg = (reg & (mask)) | (val))
 
 static uint8_t sdhci_slotint(SDHCIState *s)
@@ -486,6 +487,11 @@ static void sdhci_sdma_transfer_multi_blocks(SDHCIState *s)
     uint32_t boundary_chk = 1 << (((s->blksize & 0xf000) >> 12) + 12);
     uint32_t boundary_count = boundary_chk - (s->sdmasysad % boundary_chk);
 
+    if (!(s->trnmod & SDHC_TRNS_BLK_CNT_EN) || !s->blkcnt) {
+        qemu_log_mask(LOG_UNIMP, "infinite transfer is not supported\n");
+        return;
+    }
+
     /* XXX: Some sd/mmc drivers (for example, u-boot-slp) do not account for
      * possible stop at page boundary if initial address is not page aligned,
      * allow them to work properly */
@@ -564,7 +570,6 @@ static void sdhci_sdma_transfer_multi_blocks(SDHCIState *s)
 }
 
 /* single block SDMA transfer */
-
 static void sdhci_sdma_transfer_single_block(SDHCIState *s)
 {
     int n;
@@ -583,10 +588,7 @@ static void sdhci_sdma_transfer_single_block(SDHCIState *s)
             sdbus_write_data(&s->sdbus, s->fifo_buffer[n]);
         }
     }
-
-    if (s->trnmod & SDHC_TRNS_BLK_CNT_EN) {
-        s->blkcnt--;
-    }
+    s->blkcnt--;
 
     sdhci_end_transfer(s);
 }
@@ -797,11 +799,6 @@ static void sdhci_data_transfer(void *opaque)
     if (s->trnmod & SDHC_TRNS_DMA) {
         switch (SDHC_DMA_TYPE(s->hostctl)) {
         case SDHC_CTRL_SDMA:
-            if ((s->trnmod & SDHC_TRNS_MULTI) &&
-                    (!(s->trnmod & SDHC_TRNS_BLK_CNT_EN) || s->blkcnt == 0)) {
-                break;
-            }
-
             if ((s->blkcnt == 1) || !(s->trnmod & SDHC_TRNS_MULTI)) {
                 sdhci_sdma_transfer_single_block(s);
             } else {
@@ -1022,7 +1019,11 @@ sdhci_write(void *opaque, hwaddr offset, uint64_t val, unsigned size)
         /* Writing to last byte of sdmasysad might trigger transfer */
         if (!(mask & 0xFF000000) && TRANSFERRING_DATA(s->prnsts) && s->blkcnt &&
                 s->blksize && SDHC_DMA_TYPE(s->hostctl) == SDHC_CTRL_SDMA) {
-            sdhci_sdma_transfer_multi_blocks(s);
+            if (s->trnmod & SDHC_TRNS_MULTI) {
+                sdhci_sdma_transfer_multi_blocks(s);
+            } else {
+                sdhci_sdma_transfer_single_block(s);
+            }
         }
         break;
     case SDHC_BLKSIZE:
@@ -1050,7 +1051,7 @@ sdhci_write(void *opaque, hwaddr offset, uint64_t val, unsigned size)
         if (!(s->capareg & SDHC_CAN_DO_DMA)) {
             value &= ~SDHC_TRNS_DMA;
         }
-        MASKED_WRITE(s->trnmod, mask, value);
+        MASKED_WRITE(s->trnmod, mask, value & MASK_TRNMOD);
         MASKED_WRITE(s->cmdreg, mask >> 16, value >> 16);
 
         /* Writing to the upper byte of CMDREG triggers SD command generation */
diff --git a/hw/timer/Makefile.objs b/hw/timer/Makefile.objs
index fc9966880f..dd6f27e2a3 100644
--- a/hw/timer/Makefile.objs
+++ b/hw/timer/Makefile.objs
@@ -1,5 +1,6 @@
 common-obj-$(CONFIG_ARM_TIMER) += arm_timer.o
 common-obj-$(CONFIG_ARM_MPTIMER) += arm_mptimer.o
+common-obj-$(CONFIG_ARM_V7M) += armv7m_systick.o
 common-obj-$(CONFIG_A9_GTIMER) += a9gtimer.o
 common-obj-$(CONFIG_CADENCE) += cadence_ttc.o
 common-obj-$(CONFIG_DS1338) += ds1338.o
diff --git a/hw/timer/armv7m_systick.c b/hw/timer/armv7m_systick.c
new file mode 100644
index 0000000000..df8d2804b3
--- /dev/null
+++ b/hw/timer/armv7m_systick.c
@@ -0,0 +1,240 @@
+/*
+ * ARMv7M SysTick timer
+ *
+ * Copyright (c) 2006-2007 CodeSourcery.
+ * Written by Paul Brook
+ * Copyright (c) 2017 Linaro Ltd
+ * Written by Peter Maydell
+ *
+ * This code is licensed under the GPL (version 2 or later).
+ */
+
+#include "qemu/osdep.h"
+#include "hw/timer/armv7m_systick.h"
+#include "qemu-common.h"
+#include "hw/sysbus.h"
+#include "qemu/timer.h"
+#include "qemu/log.h"
+#include "trace.h"
+
+/* qemu timers run at 1GHz.   We want something closer to 1MHz.  */
+#define SYSTICK_SCALE 1000ULL
+
+#define SYSTICK_ENABLE    (1 << 0)
+#define SYSTICK_TICKINT   (1 << 1)
+#define SYSTICK_CLKSOURCE (1 << 2)
+#define SYSTICK_COUNTFLAG (1 << 16)
+
+int system_clock_scale;
+
+/* Conversion factor from qemu timer to SysTick frequencies.  */
+static inline int64_t systick_scale(SysTickState *s)
+{
+    if (s->control & SYSTICK_CLKSOURCE) {
+        return system_clock_scale;
+    } else {
+        return 1000;
+    }
+}
+
+static void systick_reload(SysTickState *s, int reset)
+{
+    /* The Cortex-M3 Devices Generic User Guide says that "When the
+     * ENABLE bit is set to 1, the counter loads the RELOAD value from the
+     * SYST RVR register and then counts down". So, we need to check the
+     * ENABLE bit before reloading the value.
+     */
+    trace_systick_reload();
+
+    if ((s->control & SYSTICK_ENABLE) == 0) {
+        return;
+    }
+
+    if (reset) {
+        s->tick = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+    }
+    s->tick += (s->reload + 1) * systick_scale(s);
+    timer_mod(s->timer, s->tick);
+}
+
+static void systick_timer_tick(void *opaque)
+{
+    SysTickState *s = (SysTickState *)opaque;
+
+    trace_systick_timer_tick();
+
+    s->control |= SYSTICK_COUNTFLAG;
+    if (s->control & SYSTICK_TICKINT) {
+        /* Tell the NVIC to pend the SysTick exception */
+        qemu_irq_pulse(s->irq);
+    }
+    if (s->reload == 0) {
+        s->control &= ~SYSTICK_ENABLE;
+    } else {
+        systick_reload(s, 0);
+    }
+}
+
+static uint64_t systick_read(void *opaque, hwaddr addr, unsigned size)
+{
+    SysTickState *s = opaque;
+    uint32_t val;
+
+    switch (addr) {
+    case 0x0: /* SysTick Control and Status.  */
+        val = s->control;
+        s->control &= ~SYSTICK_COUNTFLAG;
+        break;
+    case 0x4: /* SysTick Reload Value.  */
+        val = s->reload;
+        break;
+    case 0x8: /* SysTick Current Value.  */
+    {
+        int64_t t;
+
+        if ((s->control & SYSTICK_ENABLE) == 0) {
+            val = 0;
+            break;
+        }
+        t = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+        if (t >= s->tick) {
+            val = 0;
+            break;
+        }
+        val = ((s->tick - (t + 1)) / systick_scale(s)) + 1;
+        /* The interrupt in triggered when the timer reaches zero.
+           However the counter is not reloaded until the next clock
+           tick.  This is a hack to return zero during the first tick.  */
+        if (val > s->reload) {
+            val = 0;
+        }
+        break;
+    }
+    case 0xc: /* SysTick Calibration Value.  */
+        val = 10000;
+        break;
+    default:
+        val = 0;
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "SysTick: Bad read offset 0x%" HWADDR_PRIx "\n", addr);
+        break;
+    }
+
+    trace_systick_read(addr, val, size);
+    return val;
+}
+
+static void systick_write(void *opaque, hwaddr addr,
+                          uint64_t value, unsigned size)
+{
+    SysTickState *s = opaque;
+
+    trace_systick_write(addr, value, size);
+
+    switch (addr) {
+    case 0x0: /* SysTick Control and Status.  */
+    {
+        uint32_t oldval = s->control;
+
+        s->control &= 0xfffffff8;
+        s->control |= value & 7;
+        if ((oldval ^ value) & SYSTICK_ENABLE) {
+            int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+            if (value & SYSTICK_ENABLE) {
+                if (s->tick) {
+                    s->tick += now;
+                    timer_mod(s->timer, s->tick);
+                } else {
+                    systick_reload(s, 1);
+                }
+            } else {
+                timer_del(s->timer);
+                s->tick -= now;
+                if (s->tick < 0) {
+                    s->tick = 0;
+                }
+            }
+        } else if ((oldval ^ value) & SYSTICK_CLKSOURCE) {
+            /* This is a hack. Force the timer to be reloaded
+               when the reference clock is changed.  */
+            systick_reload(s, 1);
+        }
+        break;
+    }
+    case 0x4: /* SysTick Reload Value.  */
+        s->reload = value;
+        break;
+    case 0x8: /* SysTick Current Value.  Writes reload the timer.  */
+        systick_reload(s, 1);
+        s->control &= ~SYSTICK_COUNTFLAG;
+        break;
+    default:
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "SysTick: Bad write offset 0x%" HWADDR_PRIx "\n", addr);
+    }
+}
+
+static const MemoryRegionOps systick_ops = {
+    .read = systick_read,
+    .write = systick_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+    .valid.min_access_size = 4,
+    .valid.max_access_size = 4,
+};
+
+static void systick_reset(DeviceState *dev)
+{
+    SysTickState *s = SYSTICK(dev);
+
+    s->control = 0;
+    s->reload = 0;
+    s->tick = 0;
+    timer_del(s->timer);
+}
+
+static void systick_instance_init(Object *obj)
+{
+    SysBusDevice *sbd = SYS_BUS_DEVICE(obj);
+    SysTickState *s = SYSTICK(obj);
+
+    memory_region_init_io(&s->iomem, obj, &systick_ops, s, "systick", 0xe0);
+    sysbus_init_mmio(sbd, &s->iomem);
+    sysbus_init_irq(sbd, &s->irq);
+    s->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, systick_timer_tick, s);
+}
+
+static const VMStateDescription vmstate_systick = {
+    .name = "armv7m_systick",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT32(control, SysTickState),
+        VMSTATE_UINT32(reload, SysTickState),
+        VMSTATE_INT64(tick, SysTickState),
+        VMSTATE_TIMER_PTR(timer, SysTickState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static void systick_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+
+    dc->vmsd = &vmstate_systick;
+    dc->reset = systick_reset;
+}
+
+static const TypeInfo armv7m_systick_info = {
+    .name = TYPE_SYSTICK,
+    .parent = TYPE_SYS_BUS_DEVICE,
+    .instance_init = systick_instance_init,
+    .instance_size = sizeof(SysTickState),
+    .class_init = systick_class_init,
+};
+
+static void armv7m_systick_register_types(void)
+{
+    type_register_static(&armv7m_systick_info);
+}
+
+type_init(armv7m_systick_register_types)
diff --git a/hw/timer/imx_gpt.c b/hw/timer/imx_gpt.c
index 010ccbf207..4b9b54bf2e 100644
--- a/hw/timer/imx_gpt.c
+++ b/hw/timer/imx_gpt.c
@@ -296,18 +296,23 @@ static uint64_t imx_gpt_read(void *opaque, hwaddr offset, unsigned size)
     return reg_value;
 }
 
-static void imx_gpt_reset(DeviceState *dev)
-{
-    IMXGPTState *s = IMX_GPT(dev);
 
+static void imx_gpt_reset_common(IMXGPTState *s, bool is_soft_reset)
+{
     /* stop timer */
     ptimer_stop(s->timer);
 
-    /*
-     * Soft reset doesn't touch some bits; hard reset clears them
+    /* Soft reset and hard reset differ only in their handling of the CR
+     * register -- soft reset preserves the values of some bits there.
      */
-    s->cr &= ~(GPT_CR_EN|GPT_CR_ENMOD|GPT_CR_STOPEN|GPT_CR_DOZEN|
-               GPT_CR_WAITEN|GPT_CR_DBGEN);
+    if (is_soft_reset) {
+        /* Clear all CR bits except those that are preserved by soft reset. */
+        s->cr &= GPT_CR_EN | GPT_CR_ENMOD | GPT_CR_STOPEN | GPT_CR_DOZEN |
+            GPT_CR_WAITEN | GPT_CR_DBGEN |
+            (GPT_CR_CLKSRC_MASK << GPT_CR_CLKSRC_SHIFT);
+    } else {
+        s->cr = 0;
+    }
     s->sr = 0;
     s->pr = 0;
     s->ir = 0;
@@ -333,6 +338,18 @@ static void imx_gpt_reset(DeviceState *dev)
     }
 }
 
+static void imx_gpt_soft_reset(DeviceState *dev)
+{
+    IMXGPTState *s = IMX_GPT(dev);
+    imx_gpt_reset_common(s, true);
+}
+
+static void imx_gpt_reset(DeviceState *dev)
+{
+    IMXGPTState *s = IMX_GPT(dev);
+    imx_gpt_reset_common(s, false);
+}
+
 static void imx_gpt_write(void *opaque, hwaddr offset, uint64_t value,
                           unsigned size)
 {
@@ -348,7 +365,7 @@ static void imx_gpt_write(void *opaque, hwaddr offset, uint64_t value,
         s->cr = value & ~0x7c14;
         if (s->cr & GPT_CR_SWR) { /* force reset */
             /* handle the reset */
-            imx_gpt_reset(DEVICE(s));
+            imx_gpt_soft_reset(DEVICE(s));
         } else {
             /* set our freq, as the source might have changed */
             imx_gpt_set_freq(s);
diff --git a/hw/timer/trace-events b/hw/timer/trace-events
index 3495c41c18..d17cfe6b39 100644
--- a/hw/timer/trace-events
+++ b/hw/timer/trace-events
@@ -49,3 +49,9 @@ aspeed_timer_ctrl_pulse_enable(uint8_t i, bool enable) "Timer %" PRIu8 ": %d"
 aspeed_timer_set_ctrl2(uint32_t value) "Value: 0x%" PRIx32
 aspeed_timer_set_value(int timer, int reg, uint32_t value) "Timer %d register %d: 0x%" PRIx32
 aspeed_timer_read(uint64_t offset, unsigned size, uint64_t value) "From 0x%" PRIx64 ": of size %u: 0x%" PRIx64
+
+# hw/timer/armv7m_systick.c
+systick_reload(void) "systick reload"
+systick_timer_tick(void) "systick reload"
+systick_read(uint64_t addr, uint32_t value, unsigned size) "systick read addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u"
+systick_write(uint64_t addr, uint32_t value, unsigned size) "systick write addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u"
diff --git a/hw/usb/dev-storage.c b/hw/usb/dev-storage.c
index c607f7606d..a71b354fa6 100644
--- a/hw/usb/dev-storage.c
+++ b/hw/usb/dev-storage.c
@@ -603,7 +603,11 @@ static void usb_msd_realize_storage(USBDevice *dev, Error **errp)
 
     blkconf_serial(&s->conf, &dev->serial);
     blkconf_blocksizes(&s->conf);
-    blkconf_apply_backend_options(&s->conf);
+    blkconf_apply_backend_options(&s->conf, blk_is_read_only(blk), true, &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
 
     /*
      * Hack alert: this pretends to be a block device, but it's really