migration: SCM_RIGHTS for QEMUFile

Define functions to put/get file descriptors to/from a QEMUFile, for qio
channels that support SCM_RIGHTS.  Maintain ordering such that
  put(A), put(fd), put(B)
followed by
  get(A), get(fd), get(B)
always succeeds.  Other get orderings may succeed but are not guaranteed.

Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Link: https://lore.kernel.org/r/1736967650-129648-14-git-send-email-steven.sistare@oracle.com
Signed-off-by: Fabiano Rosas <farosas@suse.de>

migration/qemu-file.c

@@ -37,6 +37,11 @@
 #define IO_BUF_SIZE 32768
 #define MAX_IOV_SIZE MIN_CONST(IOV_MAX, 64)
 
+typedef struct FdEntry {
+    QTAILQ_ENTRY(FdEntry) entry;
+    int fd;
+} FdEntry;
+
 struct QEMUFile {
     QIOChannel *ioc;
     bool is_writable;
@@ -51,6 +56,9 @@ struct QEMUFile {
 
     int last_error;
     Error *last_error_obj;
+
+    bool can_pass_fd;
+    QTAILQ_HEAD(, FdEntry) fds;
 };
 
 /*
@@ -109,6 +117,8 @@ static QEMUFile *qemu_file_new_impl(QIOChannel *ioc, bool is_writable)
     object_ref(ioc);
     f->ioc = ioc;
     f->is_writable = is_writable;
+    f->can_pass_fd = qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_FD_PASS);
+    QTAILQ_INIT(&f->fds);
 
     return f;
 }
@@ -310,6 +320,10 @@ static ssize_t coroutine_mixed_fn qemu_fill_buffer(QEMUFile *f)
     int len;
     int pending;
     Error *local_error = NULL;
+    g_autofree int *fds = NULL;
+    size_t nfd = 0;
+    int **pfds = f->can_pass_fd ? &fds : NULL;
+    size_t *pnfd = f->can_pass_fd ? &nfd : NULL;
 
     assert(!qemu_file_is_writable(f));
 
@@ -325,10 +339,9 @@ static ssize_t coroutine_mixed_fn qemu_fill_buffer(QEMUFile *f)
     }
 
     do {
-        len = qio_channel_read(f->ioc,
-                               (char *)f->buf + pending,
-                               IO_BUF_SIZE - pending,
-                               &local_error);
+        struct iovec iov = { f->buf + pending, IO_BUF_SIZE - pending };
+        len = qio_channel_readv_full(f->ioc, &iov, 1, pfds, pnfd, 0,
+                                     &local_error);
         if (len == QIO_CHANNEL_ERR_BLOCK) {
             if (qemu_in_coroutine()) {
                 qio_channel_yield(f->ioc, G_IO_IN);
@@ -348,9 +361,66 @@ static ssize_t coroutine_mixed_fn qemu_fill_buffer(QEMUFile *f)
         qemu_file_set_error_obj(f, len, local_error);
     }
 
+    for (int i = 0; i < nfd; i++) {
+        FdEntry *fde = g_new0(FdEntry, 1);
+        fde->fd = fds[i];
+        QTAILQ_INSERT_TAIL(&f->fds, fde, entry);
+    }
+
     return len;
 }
 
+int qemu_file_put_fd(QEMUFile *f, int fd)
+{
+    int ret = 0;
+    QIOChannel *ioc = qemu_file_get_ioc(f);
+    Error *err = NULL;
+    struct iovec iov = { (void *)" ", 1 };
+
+    /*
+     * Send a dummy byte so qemu_fill_buffer on the receiving side does not
+     * fail with a len=0 error.  Flush first to maintain ordering wrt other
+     * data.
+     */
+
+    qemu_fflush(f);
+    if (qio_channel_writev_full(ioc, &iov, 1, &fd, 1, 0, &err) < 1) {
+        error_report_err(error_copy(err));
+        qemu_file_set_error_obj(f, -EIO, err);
+        ret = -1;
+    }
+    trace_qemu_file_put_fd(f->ioc->name, fd, ret);
+    return ret;
+}
+
+int qemu_file_get_fd(QEMUFile *f)
+{
+    int fd = -1;
+    FdEntry *fde;
+
+    if (!f->can_pass_fd) {
+        Error *err = NULL;
+        error_setg(&err, "%s does not support fd passing", f->ioc->name);
+        error_report_err(error_copy(err));
+        qemu_file_set_error_obj(f, -EIO, err);
+        goto out;
+    }
+
+    /* Force the dummy byte and its fd passenger to appear. */
+    qemu_peek_byte(f, 0);
+
+    fde = QTAILQ_FIRST(&f->fds);
+    if (fde) {
+        qemu_get_byte(f);       /* Drop the dummy byte */
+        fd = fde->fd;
+        QTAILQ_REMOVE(&f->fds, fde, entry);
+        g_free(fde);
+    }
+out:
+    trace_qemu_file_get_fd(f->ioc->name, fd);
+    return fd;
+}
+
 /** Closes the file
  *
  * Returns negative error value if any error happened on previous operations or
@@ -361,11 +431,17 @@ static ssize_t coroutine_mixed_fn qemu_fill_buffer(QEMUFile *f)
  */
 int qemu_fclose(QEMUFile *f)
 {
+    FdEntry *fde, *next;
     int ret = qemu_fflush(f);
     int ret2 = qio_channel_close(f->ioc, NULL);
     if (ret >= 0) {
         ret = ret2;
     }
+    QTAILQ_FOREACH_SAFE(fde, &f->fds, entry, next) {
+        warn_report("qemu_fclose: received fd %d was never claimed", fde->fd);
+        close(fde->fd);
+        g_free(fde);
+    }
     g_clear_pointer(&f->ioc, object_unref);
     error_free(f->last_error_obj);
     g_free(f);

migration/qemu-file.h

@@ -79,5 +79,7 @@ size_t qemu_get_buffer_at(QEMUFile *f, const uint8_t *buf, size_t buflen,
                           off_t pos);
 
 QIOChannel *qemu_file_get_ioc(QEMUFile *file);
+int qemu_file_put_fd(QEMUFile *f, int fd);
+int qemu_file_get_fd(QEMUFile *f);
 
 #endif

migration/trace-events

@@ -88,6 +88,8 @@ put_qlist_end(const char *field_name, const char *vmsd_name) "%s(%s)"
 
 # qemu-file.c
 qemu_file_fclose(void) ""
+qemu_file_put_fd(const char *name, int fd, int ret) "ioc %s, fd %d -> status %d"
+qemu_file_get_fd(const char *name, int fd) "ioc %s -> fd %d"
 
 # ram.c
 get_queued_page(const char *block_name, uint64_t tmp_offset, unsigned long page_abs) "%s/0x%" PRIx64 " page_abs=0x%lx"