diff options
Diffstat (limited to 'hw')
34 files changed, 2685 insertions, 944 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/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 9ed22d5bc8..369ef1e3bd 100644 --- a/hw/arm/bcm2835_peripherals.c +++ b/hw/arm/bcm2835_peripherals.c @@ -96,6 +96,11 @@ static void bcm2835_peripherals_init(Object *obj) 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); @@ -103,6 +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) @@ -267,13 +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) { @@ -292,6 +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/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/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/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/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/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_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, ®, 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, ®, 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, ®, 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, ®, 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, ®, 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, ®, 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, ®, 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, ®, true); + } + reg = *gic_bmp_ptr32(bmp, irq); + kvm_gicd_access(s, offset, ®, 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, ®, 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, ®l, false); + kvm_gicr_access(s, GICR_TYPER + 4, 0, ®h, false); + redist_typer = ((uint64_t)regh << 32) | regl; + + reg = s->gicd_ctlr; + kvm_gicd_access(s, GICD_CTLR, ®, 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, ®l, true); + regh = (uint32_t)(reg64 >> 32); + kvm_gicr_access(s, GICR_PROPBASER + 4, ncpu, ®h, 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, ®l, true); + regh = (uint32_t)(reg64 >> 32); + kvm_gicr_access(s, GICR_PENDBASER + 4, ncpu, ®h, 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, ®, true); + + reg = c->gicr_statusr[GICV3_NS]; + kvm_gicr_access(s, GICR_STATUSR, ncpu, ®, true); + + reg = c->gicr_waker; + kvm_gicr_access(s, GICR_WAKER, ncpu, ®, true); + + reg = c->gicr_igroupr0; + kvm_gicr_access(s, GICR_IGROUPR0, ncpu, ®, true); + + reg = ~0; + kvm_gicr_access(s, GICR_ICENABLER0, ncpu, ®, true); + reg = c->gicr_ienabler0; + kvm_gicr_access(s, GICR_ISENABLER0, ncpu, ®, 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, ®, true); + + reg = c->level; + kvm_gic_line_level_access(s, 0, ncpu, ®, true); + + reg = ~0; + kvm_gicr_access(s, GICR_ICPENDR0, ncpu, ®, true); + reg = c->gicr_ipendr0; + kvm_gicr_access(s, GICR_ISPENDR0, ncpu, ®, true); + + reg = ~0; + kvm_gicr_access(s, GICR_ICACTIVER0, ncpu, ®, true); + reg = c->gicr_iactiver0; + kvm_gicr_access(s, GICR_ISACTIVER0, ncpu, ®, 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, ®, true); + } + } + + /* Distributor state (shared between all CPUs */ + reg = s->gicd_statusr[GICV3_NS]; + kvm_gicd_access(s, GICD_STATUSR, ®, 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, ®, true); + + offset = GICD_IROUTER + (sizeof(uint32_t) * i) + 4; + reg = (uint32_t)(s->gicd_irouter[i] >> 32); + kvm_gicd_access(s, offset, ®, 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, ®64, true); + reg64 = c->icc_apr[GICV3_G0][2]; + kvm_gicc_access(s, ICC_AP0R_EL1(2), ncpu, ®64, true); + case 6: + reg64 = c->icc_apr[GICV3_G0][1]; + kvm_gicc_access(s, ICC_AP0R_EL1(1), ncpu, ®64, true); + default: + reg64 = c->icc_apr[GICV3_G0][0]; + kvm_gicc_access(s, ICC_AP0R_EL1(0), ncpu, ®64, true); + } + + switch (num_pri_bits) { + case 7: + reg64 = c->icc_apr[GICV3_G1NS][3]; + kvm_gicc_access(s, ICC_AP1R_EL1(3), ncpu, ®64, true); + reg64 = c->icc_apr[GICV3_G1NS][2]; + kvm_gicc_access(s, ICC_AP1R_EL1(2), ncpu, ®64, true); + case 6: + reg64 = c->icc_apr[GICV3_G1NS][1]; + kvm_gicc_access(s, ICC_AP1R_EL1(1), ncpu, ®64, true); + default: + reg64 = c->icc_apr[GICV3_G1NS][0]; + kvm_gicc_access(s, ICC_AP1R_EL1(0), ncpu, ®64, 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, ®l, false); + kvm_gicr_access(s, GICR_TYPER + 4, 0, ®h, false); + redist_typer = ((uint64_t)regh << 32) | regl; + + kvm_gicd_access(s, GICD_CTLR, ®, 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, ®, false); + c->gicr_ctlr = reg; + + kvm_gicr_access(s, GICR_STATUSR, ncpu, ®, false); + c->gicr_statusr[GICV3_NS] = reg; + + kvm_gicr_access(s, GICR_WAKER, ncpu, ®, false); + c->gicr_waker = reg; + + kvm_gicr_access(s, GICR_IGROUPR0, ncpu, ®, false); + c->gicr_igroupr0 = reg; + kvm_gicr_access(s, GICR_ISENABLER0, ncpu, ®, false); + c->gicr_ienabler0 = reg; + kvm_gicr_access(s, GICR_ICFGR1, ncpu, ®, false); + c->edge_trigger = half_unshuffle32(reg >> 1) << 16; + kvm_gic_line_level_access(s, 0, ncpu, ®, false); + c->level = reg; + kvm_gicr_access(s, GICR_ISPENDR0, ncpu, ®, false); + c->gicr_ipendr0 = reg; + kvm_gicr_access(s, GICR_ISACTIVER0, ncpu, ®, false); + c->gicr_iactiver0 = reg; + + for (i = 0; i < GIC_INTERNAL; i += 4) { + kvm_gicr_access(s, GICR_IPRIORITYR + i, ncpu, ®, 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, ®l, false); + kvm_gicr_access(s, GICR_PROPBASER + 4, ncpu, ®h, false); + c->gicr_propbaser = ((uint64_t)regh << 32) | regl; + + kvm_gicr_access(s, GICR_PENDBASER, ncpu, ®l, false); + kvm_gicr_access(s, GICR_PENDBASER + 4, ncpu, ®h, false); + c->gicr_pendbaser = ((uint64_t)regh << 32) | regl; + } + } + + /* Distributor state (shared between all CPUs */ + + kvm_gicd_access(s, GICD_STATUSR, ®, 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, ®l, false); + offset = GICD_IROUTER + (sizeof(uint32_t) * i) + 4; + kvm_gicd_access(s, offset, ®h, 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, ®64, false); + c->icc_apr[GICV3_G0][3] = reg64; + kvm_gicc_access(s, ICC_AP0R_EL1(2), ncpu, ®64, false); + c->icc_apr[GICV3_G0][2] = reg64; + case 6: + kvm_gicc_access(s, ICC_AP0R_EL1(1), ncpu, ®64, false); + c->icc_apr[GICV3_G0][1] = reg64; + default: + kvm_gicc_access(s, ICC_AP0R_EL1(0), ncpu, ®64, false); + c->icc_apr[GICV3_G0][0] = reg64; + } + + switch (num_pri_bits) { + case 7: + kvm_gicc_access(s, ICC_AP1R_EL1(3), ncpu, ®64, false); + c->icc_apr[GICV3_G1NS][3] = reg64; + kvm_gicc_access(s, ICC_AP1R_EL1(2), ncpu, ®64, false); + c->icc_apr[GICV3_G1NS][2] = reg64; + case 6: + kvm_gicc_access(s, ICC_AP1R_EL1(1), ncpu, ®64, false); + c->icc_apr[GICV3_G1NS][1] = reg64; + default: + kvm_gicc_access(s, ICC_AP1R_EL1(0), ncpu, ®64, 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 76097b4830..32ffa0bf35 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -17,8 +17,8 @@ #include "hw/sysbus.h" #include "qemu/timer.h" #include "hw/arm/arm.h" +#include "hw/arm/armv7m_nvic.h" #include "target/arm/cpu.h" -#include "exec/address-spaces.h" #include "qemu/log.h" #include "trace.h" @@ -47,7 +47,6 @@ * "exception" more or less interchangeably. */ #define NVIC_FIRST_IRQ 16 -#define NVIC_MAX_VECTORS 512 #define NVIC_MAX_IRQ (NVIC_MAX_VECTORS - NVIC_FIRST_IRQ) /* Effective running priority of the CPU when no exception is active @@ -55,116 +54,10 @@ */ #define NVIC_NOEXC_PRIO 0x100 -typedef struct VecInfo { - /* Exception priorities can range from -3 to 255; only the unmodifiable - * priority values for RESET, NMI and HardFault can be negative. - */ - int16_t prio; - uint8_t enabled; - uint8_t pending; - uint8_t active; - uint8_t level; /* exceptions <=15 never set level */ -} VecInfo; - -typedef struct NVICState { - /*< private >*/ - SysBusDevice parent_obj; - /*< public >*/ - - ARMCPU *cpu; - - VecInfo vectors[NVIC_MAX_VECTORS]; - uint32_t prigroup; - - /* vectpending and exception_prio are both cached state that can - * be recalculated from the vectors[] array and the prigroup field. - */ - unsigned int vectpending; /* highest prio pending enabled exception */ - int exception_prio; /* group prio of the highest prio active exception */ - - struct { - uint32_t control; - uint32_t reload; - int64_t tick; - QEMUTimer *timer; - } systick; - - MemoryRegion sysregmem; - MemoryRegion container; - - uint32_t num_irq; - qemu_irq excpout; - qemu_irq sysresetreq; -} NVICState; - -#define TYPE_NVIC "armv7m_nvic" - -#define NVIC(obj) \ - OBJECT_CHECK(NVICState, (obj), TYPE_NVIC) - 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 - -#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(NVICState *s) -{ - if (s->systick.control & SYSTICK_CLKSOURCE) - return system_clock_scale; - else - return 1000; -} - -static void systick_reload(NVICState *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. - */ - if ((s->systick.control & SYSTICK_ENABLE) == 0) { - return; - } - - 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); -} - -static void systick_timer_tick(void * opaque) -{ - NVICState *s = (NVICState *)opaque; - s->systick.control |= SYSTICK_COUNTFLAG; - if (s->systick.control & SYSTICK_TICKINT) { - /* Trigger the interrupt. */ - armv7m_nvic_set_pending(s, ARMV7M_EXCP_SYSTICK); - } - if (s->systick.reload == 0) { - s->systick.control &= ~SYSTICK_ENABLE; - } else { - systick_reload(s, 0); - } -} - -static void systick_reset(NVICState *s) -{ - s->systick.control = 0; - s->systick.reload = 0; - s->systick.tick = 0; - timer_del(s->systick.timer); -} - static int nvic_pending_prio(NVICState *s) { /* return the priority of the current pending interrupt, @@ -510,30 +403,6 @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset) switch (offset) { case 4: /* Interrupt Control Type. */ return ((s->num_irq - NVIC_FIRST_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; case 0xd00: /* CPUID Base. */ return cpu->midr; case 0xd04: /* Interrupt Control State. */ @@ -668,40 +537,8 @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset) 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); @@ -1000,16 +837,12 @@ static const VMStateDescription vmstate_VecInfo = { static const VMStateDescription vmstate_nvic = { .name = "armv7m_nvic", - .version_id = 3, - .minimum_version_id = 3, + .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(systick.control, NVICState), - VMSTATE_UINT32(systick.reload, NVICState), - VMSTATE_INT64(systick.tick, NVICState), - VMSTATE_TIMER_PTR(systick.timer, NVICState), VMSTATE_UINT32(prigroup, NVICState), VMSTATE_END_OF_LIST() } @@ -1047,13 +880,26 @@ static void armv7m_nvic_reset(DeviceState *dev) s->exception_prio = NVIC_NOEXC_PRIO; s->vectpending = 0; +} - systick_reset(s); +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) { NVICState *s = NVIC(dev); + SysBusDevice *systick_sbd; + Error *err = NULL; s->cpu = ARM_CPU(qemu_get_cpu(0)); assert(s->cpu); @@ -1068,10 +914,19 @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp) /* 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; + } + 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 - 0x1c - systick + * 0x010 - 0xff - systick * 0x100..0x7ec - NVIC * 0x7f0..0xcff - Reserved * 0xd00..0xd3c - SCS registers @@ -1089,12 +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); + memory_region_add_subregion_overlap(&s->container, 0x10, + sysbus_mmio_get_region(systick_sbd, 0), + 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); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->container); } static void armv7m_nvic_instance_init(Object *obj) @@ -1109,8 +963,12 @@ static void armv7m_nvic_instance_init(Object *obj) 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) 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/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/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/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/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" |