[V4,2/8] Provide chroot environment server side interfaces

diff --git a/Makefile.objs b/Makefile.objs
index bc0344c..3007b6d 100644
--- a/Makefile.objs
+++ b/Makefile.objs
@@ -273,6 +273,7 @@  hw-obj-$(CONFIG_SOUND) += $(sound-obj-y)
 9pfs-nested-$(CONFIG_VIRTFS) = virtio-9p-debug.o
 9pfs-nested-$(CONFIG_VIRTFS) +=  virtio-9p-local.o virtio-9p-xattr.o
 9pfs-nested-$(CONFIG_VIRTFS) +=   virtio-9p-xattr-user.o virtio-9p-posix-acl.o
+9pfs-nested-$(CONFIG_VIRTFS) +=   virtio-9p-chroot.o
 
 hw-obj-$(CONFIG_REALLY_VIRTFS) += $(addprefix 9pfs/, $(9pfs-nested-y))
 $(addprefix 9pfs/, $(9pfs-nested-y)): CFLAGS +=  -I$(SRC_PATH)/hw/
diff --git a/hw/9pfs/virtio-9p-chroot.c b/hw/9pfs/virtio-9p-chroot.c
new file mode 100644
index 0000000..5150ff0
--- /dev/null
+++ b/hw/9pfs/virtio-9p-chroot.c
@@ -0,0 +1,212 @@ 
+/*
+ * Virtio 9p chroot environment for contained access to exported path
+ *
+ * Copyright IBM, Corp. 2011
+ *
+ * Authors:
+ * M. Mohan Kumar <mohan@in.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the copying file in the top-level directory
+ *
+ */
+
+#include <sys/fsuid.h>
+#include <sys/resource.h>
+#include <signal.h>
+#include "virtio.h"
+#include "qemu_socket.h"
+#include "qemu-thread.h"
+#include "qerror.h"
+#include "virtio-9p.h"
+#include "virtio-9p-chroot.h"
+
+/*
+ * Structure used by chroot functions to transmit file descriptor and
+ * error info
+ */
+typedef struct {
+    int fi_fd;
+#define FI_FDVALID 1
+#define FI_SOCKERR 2
+    int fi_flags;
+    int fi_error;
+} FdInfo;
+
+union MsgControl {
+    struct cmsghdr cmsg;
+    char control[CMSG_SPACE(sizeof(int))];
+};
+
+/* Send file descriptor and error status to qemu process */
+static void chroot_sendfd(int sockfd, const FdInfo *fd_info)
+{
+    struct msghdr msg = { };
+    struct iovec iov;
+    struct cmsghdr *cmsg;
+    int retval;
+    union MsgControl msg_control;
+
+    iov.iov_base = (void *)fd_info;
+    iov.iov_len = sizeof(*fd_info);
+
+    memset(&msg, 0, sizeof(msg));
+    msg.msg_iov = &iov;
+    msg.msg_iovlen = 1;
+    /* No ancillary data on error/fd invalid flag */
+    if (fd_info->fi_flags & FI_FDVALID) {
+        msg.msg_control = &msg_control;
+        msg.msg_controllen = sizeof(msg_control);
+
+        cmsg = &msg_control.cmsg;
+        cmsg->cmsg_len = CMSG_LEN(sizeof(fd_info->fi_fd));
+        cmsg->cmsg_level = SOL_SOCKET;
+        cmsg->cmsg_type = SCM_RIGHTS;
+        memcpy(CMSG_DATA(cmsg), &fd_info->fi_fd, sizeof(fd_info->fi_fd));
+    }
+    retval = sendmsg(sockfd, &msg, 0);
+    if (retval == EPIPE || retval == EBADF) {
+        _exit(1);
+    }
+    if (fd_info->fi_flags & FI_FDVALID) {
+        close(fd_info->fi_fd);
+    }
+}
+
+/* Read V9fsFileObjectRequest written by QEMU process */
+static int chroot_read_request(int sockfd, V9fsFileObjectRequest *request)
+{
+    int retval;
+    retval = qemu_read_full(sockfd, request, sizeof(request->data));
+    if (retval != sizeof(request->data)) {
+        if (errno == EBADF) {
+            _exit(1);
+        }
+        return EIO;
+    }
+    request->path.path = qemu_mallocz(request->data.path_len + 1);
+    retval = qemu_read_full(sockfd, (void *)request->path.path,
+                        request->data.path_len);
+    if (retval != request->data.path_len) {
+        qemu_free((void *)request->path.path);
+        if (errno == EBADF) {
+            _exit(1);
+        }
+        return EIO;
+    }
+    if (request->data.oldpath_len > 0) {
+        request->path.old_path =
+                qemu_mallocz(request->data.oldpath_len + 1);
+        retval = qemu_read_full(sockfd, (void *)request->path.old_path,
+                            request->data.oldpath_len);
+        if (retval != request->data.oldpath_len) {
+            qemu_free((void *)request->path.path);
+            qemu_free((void *)request->path.old_path);
+            if (errno == EBADF) {
+                _exit(1);
+            }
+            return EIO;
+        }
+    }
+    return 0;
+}
+
+static int chroot_daemonize(int chroot_sock)
+{
+    sigset_t sigset;
+    struct rlimit nr_fd;
+    int fd;
+
+    /* Block all signals for this process */
+    sigprocmask(SIG_SETMASK, &sigset, NULL);
+
+    /* Daemonize */
+    if (setsid() < 0) {
+        return errno;
+    }
+
+    /* Close other file descriptors */
+    getrlimit(RLIMIT_NOFILE, &nr_fd);
+    for (fd = 0; fd < nr_fd.rlim_cur; fd++) {
+        if (fd != chroot_sock) {
+            close(fd);
+        }
+    }
+    chdir("/");
+
+    /* Create files with mode as requested by client */
+    umask(0);
+    return 0;
+}
+
+/*
+ * Fork a process and chroot into the share path. Communication
+ * between qemu process and chroot process happens via socket
+ * All file descriptors (including stdout and stderr) are closed
+ * except one socket descriptor (which is used for communicating
+ * between qemu process and chroot process)
+ */
+int v9fs_chroot(FsContext *fs_ctx)
+{
+    int fd_pair[2], chroot_sock, error;
+    V9fsFileObjectRequest request;
+    pid_t pid;
+    uint64_t code;
+    FdInfo fd_info;
+
+    if (socketpair(PF_UNIX, SOCK_STREAM, 0, fd_pair) < 0) {
+        error_report("socketpair %s", strerror(errno));
+        return -1;
+    }
+
+    pid = fork();
+    if (pid < 0) {
+        error_report("fork %s", strerror(errno));
+        return -1;
+    }
+    if (pid != 0) {
+        fs_ctx->chroot_socket = fd_pair[0];
+        close(fd_pair[1]);
+        return 0;
+    }
+
+    close(fd_pair[0]);
+    chroot_sock = fd_pair[1];
+    if (chroot(fs_ctx->fs_root) < 0) {
+        code = CHROOT_ERROR << 32 | errno;
+        error = qemu_write_full(chroot_sock, &code, sizeof(code));
+        _exit(1);
+    }
+
+    error = chroot_daemonize(chroot_sock);
+    if (error) {
+        code = SETSID_ERROR << 32 | error;
+        error = qemu_write_full(chroot_sock, &code, sizeof(code));
+        _exit(1);
+    }
+
+    /*
+     * Write 0 to chroot socket to indicate chroot process creation is
+     * successful
+     */
+    code = 0;
+    if (qemu_write_full(chroot_sock, &code, sizeof(code))
+                    != sizeof(code)) {
+        _exit(1);
+    }
+    /* get the request from the socket */
+    while (1) {
+        memset(&fd_info, 0, sizeof(fd_info));
+        if (chroot_read_request(chroot_sock, &request) == EIO) {
+            fd_info.fi_fd = 0;
+            fd_info.fi_error = EIO;
+            fd_info.fi_flags = FI_SOCKERR;
+            chroot_sendfd(chroot_sock, &fd_info);
+            continue;
+        }
+        qemu_free((void *)request.path.path);
+        if (request.data.oldpath_len) {
+            qemu_free((void *)request.path.old_path);
+        }
+    }
+}
diff --git a/hw/9pfs/virtio-9p-chroot.h b/hw/9pfs/virtio-9p-chroot.h
new file mode 100644
index 0000000..6f3fd14
--- /dev/null
+++ b/hw/9pfs/virtio-9p-chroot.h
@@ -0,0 +1,41 @@ 
+#ifndef _QEMU_VIRTIO_9P_CHROOT_H
+#define _QEMU_VIRTIO_9P_CHROOT_H
+
+/* types for V9fsFileObjectRequest */
+#define T_OPEN      1
+#define T_CREATE    2
+#define T_MKDIR     3
+#define T_MKNOD     4
+#define T_SYMLINK   5
+#define T_LINK      6
+#define CHROOT_ERROR 1ULL
+#define SETSID_ERROR 2ULL
+
+struct V9fsFileObjectData
+{
+    int flags;
+    int mode;
+    uid_t uid;
+    gid_t gid;
+    dev_t dev;
+    int path_len;
+    int oldpath_len;
+    int type;
+};
+
+struct V9fsFileObjectPath
+{
+    const char *path;
+    const char *old_path;
+};
+
+typedef struct V9fsFileObjectRequest
+{
+    struct V9fsFileObjectData data;
+    struct V9fsFileObjectPath path;
+} V9fsFileObjectRequest;
+
+
+int v9fs_chroot(FsContext *fs_ctx);
+
+#endif /* _QEMU_VIRTIO_9P_CHROOT_H */
diff --git a/hw/9pfs/virtio-9p.c b/hw/9pfs/virtio-9p.c
index 27e7750..fc006a9 100644
--- a/hw/9pfs/virtio-9p.c
+++ b/hw/9pfs/virtio-9p.c
@@ -14,10 +14,13 @@ 
 #include "virtio.h"
 #include "pc.h"
 #include "qemu_socket.h"
+#include "qerror.h"
 #include "virtio-9p.h"
 #include "fsdev/qemu-fsdev.h"
 #include "virtio-9p-debug.h"
 #include "virtio-9p-xattr.h"
+#include "virtio-9p-chroot.h"
+#include <pthread.h>
 
 int debug_9p_pdu;
 
@@ -3743,5 +3746,35 @@  VirtIODevice *virtio_9p_init(DeviceState *dev, V9fsConf *conf)
                         s->tag_len;
     s->vdev.get_config = virtio_9p_get_config;
 
+    if (s->ctx.fs_sm == SM_PASSTHROUGH) {
+        uint64_t code;
+        pthread_mutex_init(&s->ctx.chroot_mutex, 0);
+        s->ctx.chroot_ioerror = 0;
+        if (v9fs_chroot(&s->ctx) < 0) {
+            exit(1);
+        }
+
+        /*
+         * Chroot process sends 0 to indicate chroot process creation is
+         * successful
+         */
+        if (read(s->ctx.chroot_socket, &code, sizeof(code)) != sizeof(code)) {
+            error_report("chroot process creation failed");
+            exit(1);
+        }
+        if (code != 0) {
+            switch (code >> 32) {
+            case CHROOT_ERROR:
+                error_report("chroot system call failed: %s",
+                                strerror(code & 0xFFFFFFFF));
+                break;
+            case SETSID_ERROR:
+                error_report("setsid failed: %s", strerror(code & 0xFFFFFFFF));
+                break;
+            }
+            exit(1);
+        }
+    }
+
     return &s->vdev;
 }
diff --git a/hw/file-op-9p.h b/hw/file-op-9p.h
index c7731c2..0cd7728 100644
--- a/hw/file-op-9p.h
+++ b/hw/file-op-9p.h
@@ -55,6 +55,9 @@  typedef struct FsContext
     SecModel fs_sm;
     uid_t uid;
     struct xattr_operations **xops;
+    pthread_mutex_t chroot_mutex;
+    int chroot_socket;
+    int chroot_ioerror;
 } FsContext;
 
 extern void cred_init(FsCred *);