[V2,04/12] hw/9pfs: Open and create files

diff --git a/fsdev/virtfs-proxy-helper.c b/fsdev/virtfs-proxy-helper.c
index 69daf7c..68d27f1 100644
--- a/fsdev/virtfs-proxy-helper.c
+++ b/fsdev/virtfs-proxy-helper.c
@@ -30,6 +30,8 @@ 
 #include "qemu-common.h"
 #include "virtio-9p-marshal.h"
 #include "hw/9pfs/virtio-9p-proxy.h"
+#include "fsdev/virtio-9p-marshal.h"
+
 
 #define PROGNAME "virtfs-proxy-helper"
 
@@ -148,20 +150,125 @@  static int read_request(int sockfd, struct iovec *iovec)
     ProxyHeader header;
 
     /* read the header */
-    retval = socket_read(sockfd, iovec->iov_base, sizeof(header));
-    if (retval != sizeof(header)) {
+    retval = socket_read(sockfd, iovec->iov_base, HDR_SZ);
+    if (retval != HDR_SZ) {
         return -EIO;
     }
     /* unmarshal header */
     proxy_unmarshal(iovec, 1, 0, "dd", &header.type, &header.size);
     /* read the request */
-    retval = socket_read(sockfd, iovec->iov_base + sizeof(header), header.size);
+    retval = socket_read(sockfd, iovec->iov_base + HDR_SZ, header.size);
     if (retval != header.size) {
         return -EIO;
     }
     return header.type;
 }
 
+static void send_fd(int sockfd, int fd)
+{
+    struct msghdr msg = { };
+    struct iovec iov;
+    struct cmsghdr *cmsg;
+    int retval, data;
+    union MsgControl msg_control;
+
+    iov.iov_base = &data;
+    iov.iov_len = sizeof(data);
+
+    memset(&msg, 0, sizeof(msg));
+    msg.msg_iov = &iov;
+    msg.msg_iovlen = 1;
+    /* No ancillary data on error */
+    if (fd < 0) {
+        /*
+         * fd is really negative errno if the request failed. Or simply
+         * zero if the request is successful and it doesn't need a file
+         * descriptor.
+         */
+        data = fd;
+    } else {
+        data = V9FS_FD_VALID;
+        msg.msg_control = &msg_control;
+        msg.msg_controllen = sizeof(msg_control);
+
+        cmsg = &msg_control.cmsg;
+        cmsg->cmsg_len = CMSG_LEN(sizeof(fd));
+        cmsg->cmsg_level = SOL_SOCKET;
+        cmsg->cmsg_type = SCM_RIGHTS;
+        memcpy(CMSG_DATA(cmsg), &fd, sizeof(fd));
+    }
+
+    do {
+        retval = sendmsg(sockfd, &msg, 0);
+    } while (retval < 0 && errno == EINTR);
+    if (retval < 0) {
+        do_perror("sendmsg");
+        exit(1);
+    }
+    if (fd >= 0) {
+        close(fd);
+    }
+}
+
+/*
+ * from man 7 capabilities, section
+ * Effect of User ID Changes on Capabilities:
+ * 4. If the file system user ID is changed from 0 to nonzero (see setfsuid(2))
+ * then the following capabilities are cleared from the effective set:
+ * CAP_CHOWN, CAP_DAC_OVERRIDE, CAP_DAC_READ_SEARCH,  CAP_FOWNER, CAP_FSETID,
+ * CAP_LINUX_IMMUTABLE  (since  Linux 2.2.30), CAP_MAC_OVERRIDE, and CAP_MKNOD
+ * (since Linux 2.2.30). If the file system UID is changed from nonzero to 0,
+ * then any of these capabilities that are enabled in the permitted set
+ * are enabled in the effective set.
+ */
+static int setfsugid(int uid, int gid)
+{
+    setfsgid(gid);
+    setfsuid(uid);
+    return cap_set();
+}
+
+/*
+ * create a file and send fd on success
+ * return -errno on error
+ */
+static int do_create(struct iovec *iovec)
+{
+    V9fsString path;
+    int flags, fd, mode, uid, gid, cur_uid, cur_gid;
+    proxy_unmarshal(iovec, 1, HDR_SZ, "sdddd",
+                   &path, &flags, &mode, &uid, &gid);
+    cur_uid = geteuid();
+    cur_gid = getegid();
+    if (setfsugid(uid, gid) < 0) {
+        return -EPERM;
+    }
+    fd = open(path.data, flags, mode);
+    if (fd < 0) {
+        fd = -errno;
+    }
+    v9fs_string_free(&path);
+    setfsugid(cur_uid, cur_gid);
+    return fd;
+}
+
+/*
+ * open a file and send fd on success
+ * return -errno on error
+ */
+static int do_open(struct iovec *iovec)
+{
+    V9fsString path;
+    int flags, fd;
+    proxy_unmarshal(iovec, 1, HDR_SZ, "sd", &path, &flags);
+    fd = open(path.data, flags);
+    if (fd < 0) {
+        fd = -errno;
+    }
+    v9fs_string_free(&path);
+    return fd;
+}
+
 static void usage(char *prog)
 {
     fprintf(stderr, "usage: %s\n"
@@ -173,15 +280,34 @@  static void usage(char *prog)
 
 static int process_requests(int sock)
 {
-    int type;
+    int type, retval = 0;
     struct iovec iovec;
 
     iovec.iov_base = g_malloc(BUFF_SZ);
     iovec.iov_len = BUFF_SZ;
     while (1) {
         type = read_request(sock, &iovec);
-        if (type <= 0) {
+        switch (type) {
+        case T_OPEN:
+            retval = do_open(&iovec);
+            break;
+        case T_CREATE:
+            retval = do_create(&iovec);
+            break;
+        default:
+            goto error;
+            break;
+        }
+
+        /* Send response */
+        switch (type) {
+        case T_OPEN:
+        case T_CREATE:
+            send_fd(sock, retval);
+            break;
+        default:
             goto error;
+            break;
         }
     }
     (void)socket_write;
diff --git a/hw/9pfs/virtio-9p-proxy.c b/hw/9pfs/virtio-9p-proxy.c
index 0e539e3..8cc55d6 100644
--- a/hw/9pfs/virtio-9p-proxy.c
+++ b/hw/9pfs/virtio-9p-proxy.c
@@ -22,6 +22,144 @@  typedef struct V9fsProxy {
     struct iovec iovec;
 } V9fsProxy;
 
+/*
+ * Return received file descriptor on success and -errno on failure.
+ * sock_error is set to 1 whenever there is error in socket IO
+ */
+static int v9fs_receivefd(int sockfd, int *sock_error)
+{
+    struct msghdr msg = { };
+    struct iovec iov;
+    union MsgControl msg_control;
+    struct cmsghdr *cmsg;
+    int retval, data, fd;
+
+    iov.iov_base = &data;
+    iov.iov_len = sizeof(data);
+
+    *sock_error = 0;
+    memset(&msg, 0, sizeof(msg));
+    msg.msg_iov = &iov;
+    msg.msg_iovlen = 1;
+    msg.msg_control = &msg_control;
+    msg.msg_controllen = sizeof(msg_control);
+
+    do {
+        retval = recvmsg(sockfd, &msg, 0);
+    } while (retval < 0 && errno == EINTR);
+    if (retval <= 0) {
+        *sock_error = 1;
+        return -EIO;
+    }
+
+    /*
+     * data is set to V9FS_FD_VALID, if ancillary data is sent.  If this
+     * request doesn't need ancillary data (fd) or an error occurred,
+     * data is set to negative errno value.
+     */
+    if (data != V9FS_FD_VALID) {
+        return data;
+    }
+
+    /*
+     * File descriptor (fd) is sent in the ancillary data. Check if we
+     * indeed received it. One of the reasons to fail to receive it is if
+     * we exceeded the maximum number of file descriptors!
+     */
+    for (cmsg = CMSG_FIRSTHDR(&msg); cmsg; cmsg = CMSG_NXTHDR(&msg, cmsg)) {
+        if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)) ||
+            cmsg->cmsg_level != SOL_SOCKET ||
+            cmsg->cmsg_type != SCM_RIGHTS) {
+            continue;
+        }
+        fd = *((int *)CMSG_DATA(cmsg));
+        return fd;
+    }
+
+    return -ENFILE; /* Ancillary data sent but not received */
+}
+
+/*
+ * Proxy->header and proxy->request written to socket by QEMU process.
+ * This request read by proxy helper process
+ * returns 0 on success and -errno on error
+ */
+static int v9fs_request(V9fsProxy *proxy, int type,
+                        void *response, const char *fmt, ...)
+{
+    int retval;
+    ProxyHeader header;
+    va_list ap;
+    V9fsString *path;
+    int sock_error, flags, mode, uid, gid;
+    struct iovec *iovec = NULL;
+
+    qemu_mutex_lock(&proxy->mutex);
+
+    if (proxy->sockfd == -1) {
+        goto error;
+    }
+    iovec = &proxy->iovec;
+
+    va_start(ap, fmt);
+    switch (type) {
+    case T_OPEN:
+        path = va_arg(ap, V9fsString *);
+        flags = va_arg(ap, int);
+        header.size = proxy_marshal(iovec, 1, HDR_SZ,
+                                   "sd", path, flags);
+        header.type = T_OPEN;
+        proxy_marshal(iovec, 1, 0, "dd", header.type, header.size);
+        header.size += HDR_SZ;
+        break;
+    case T_CREATE:
+        path = va_arg(ap, V9fsString *);
+        flags = va_arg(ap, int);
+        mode = va_arg(ap, int);
+        uid = va_arg(ap, int);
+        gid = va_arg(ap, int);
+        header.size = proxy_marshal(iovec, 1, HDR_SZ, "sdddd", path,
+                                   flags, mode, uid, gid);
+        header.type = T_CREATE;
+        proxy_marshal(iovec, 1, 0, "dd", header.type, header.size);
+        header.size += HDR_SZ;
+        break;
+    default:
+        error_report("Invalid type %d\n", type);
+        va_end(ap);
+        goto close_error;
+        break;
+    }
+    va_end(ap);
+
+    retval = qemu_write_full(proxy->sockfd, iovec->iov_base, header.size);
+    if (retval != header.size) {
+        goto close_error;
+    }
+
+    switch (type) {
+    case T_OPEN:
+    case T_CREATE:
+        /*
+         * A file descriptor is returned as response for
+         * T_OPEN,T_CREATE on success
+         */
+        retval = v9fs_receivefd(proxy->sockfd, &sock_error);
+        if (sock_error) {
+            goto close_error;
+        }
+        break;
+    }
+    qemu_mutex_unlock(&proxy->mutex);
+    return retval;
+close_error:
+    close(proxy->sockfd);
+    proxy->sockfd = -1;
+error:
+    qemu_mutex_unlock(&proxy->mutex);
+    return -EIO;
+}
+
 static int proxy_lstat(FsContext *fs_ctx, V9fsPath *fs_path, struct stat *stbuf)
 {
     errno = EOPNOTSUPP;
@@ -48,16 +186,35 @@  static int proxy_closedir(FsContext *ctx, V9fsFidOpenState *fs)
 static int proxy_open(FsContext *ctx, V9fsPath *fs_path,
                       int flags, V9fsFidOpenState *fs)
 {
-    fs->fd = -1;
+    fs->fd = v9fs_request(ctx->private, T_OPEN, NULL, "sd",
+                          fs_path, flags);
+    if (fs->fd < 0) {
+        errno = -fs->fd;
+        fs->fd = -1;
+    }
     return fs->fd;
 }
 
 static int proxy_opendir(FsContext *ctx,
                          V9fsPath *fs_path, V9fsFidOpenState *fs)
 {
+    int serrno, fd;
+
     fs->dir = NULL;
-    errno = EOPNOTSUPP;
-    return -1;
+    fd = v9fs_request(ctx->private, T_OPEN, NULL, "sd",
+                      fs_path, O_DIRECTORY);
+    if (fd < 0) {
+        errno = -fd;
+        return -1;
+    }
+    fs->dir = fdopendir(fd);
+    if (!fs->dir) {
+        serrno = errno;
+        close(fd);
+        errno = serrno;
+        return -1;
+    }
+    return 0;
 }
 
 static void proxy_rewinddir(FsContext *ctx, V9fsFidOpenState *fs)
@@ -159,9 +316,20 @@  static int proxy_fstat(FsContext *fs_ctx,
 static int proxy_open2(FsContext *fs_ctx, V9fsPath *dir_path, const char *name,
                        int flags, FsCred *credp, V9fsFidOpenState *fs)
 {
-    fs->fd = -1;
-    errno = EOPNOTSUPP;
-    return -1;
+    V9fsString fullname;
+
+    v9fs_string_init(&fullname);
+    v9fs_string_sprintf(&fullname, "%s/%s", dir_path->data, name);
+
+    fs->fd = v9fs_request(fs_ctx->private, T_CREATE, NULL, "sdddd",
+                          &fullname, flags, credp->fc_mode,
+                          credp->fc_uid, credp->fc_gid);
+    v9fs_string_free(&fullname);
+    if (fs->fd < 0) {
+        errno = -fs->fd;
+        fs->fd = -1;
+    }
+    return fs->fd;
 }
 
 
diff --git a/hw/9pfs/virtio-9p-proxy.h b/hw/9pfs/virtio-9p-proxy.h
index 120e940..f30e367 100644
--- a/hw/9pfs/virtio-9p-proxy.h
+++ b/hw/9pfs/virtio-9p-proxy.h
@@ -2,6 +2,7 @@ 
 #define _QEMU_VIRTIO_9P_PROXY_H
 
 #define BUFF_SZ (4 * 1024)
+#define V9FS_FD_VALID INT_MAX
 
 #define proxy_unmarshal(in_sg, in_elem, offset, fmt, args...) \
     v9fs_unmarshal(in_sg, in_elem, offset, 0 /* convert */, fmt, ##args)
@@ -17,4 +18,12 @@  typedef struct {
     int type;
     int size;
 } ProxyHeader;
+
+#define HDR_SZ (sizeof(ProxyHeader))
+
+enum {
+    T_OPEN = 1,
+    T_CREATE,
+};
+
 #endif