[PULL 25/26] io: Add support for MSG_PEEK for socket channel

[Juan Quintela <quintela@redhat.com>]

From: "manish.mishra" <manish.mishra@nutanix.com>

MSG_PEEK peeks at the channel, The data is treated as unread and
the next read shall still return this data. This support is
currently added only for socket class. Extra parameter 'flags'
is added to io_readv calls to pass extra read flags like MSG_PEEK.

Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Daniel P. Berrange <berrange@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Suggested-by: Daniel P. Berrange <berrange@redhat.com>
Signed-off-by: manish.mishra <manish.mishra@nutanix.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
---
 include/io/channel.h                |  6 ++++++
 chardev/char-socket.c               |  4 ++--
 io/channel-buffer.c                 |  1 +
 io/channel-command.c                |  1 +
 io/channel-file.c                   |  1 +
 io/channel-null.c                   |  1 +
 io/channel-socket.c                 | 19 ++++++++++++++++++-
 io/channel-tls.c                    |  1 +
 io/channel-websock.c                |  1 +
 io/channel.c                        | 16 ++++++++++++----
 migration/channel-block.c           |  1 +
 migration/rdma.c                    |  1 +
 scsi/qemu-pr-helper.c               |  2 +-
 tests/qtest/tpm-emu.c               |  2 +-
 tests/unit/test-io-channel-socket.c |  1 +
 util/vhost-user-server.c            |  2 +-
 16 files changed, 50 insertions(+), 10 deletions(-)

diff --git a/include/io/channel.h b/include/io/channel.h
index 78b15f7870..153fbd2904 100644
--- a/include/io/channel.h
+++ b/include/io/channel.h
@@ -34,6 +34,8 @@ OBJECT_DECLARE_TYPE(QIOChannel, QIOChannelClass,
 
 #define QIO_CHANNEL_WRITE_FLAG_ZERO_COPY 0x1
 
+#define QIO_CHANNEL_READ_FLAG_MSG_PEEK 0x1
+
 typedef enum QIOChannelFeature QIOChannelFeature;
 
 enum QIOChannelFeature {
@@ -41,6 +43,7 @@ enum QIOChannelFeature {
     QIO_CHANNEL_FEATURE_SHUTDOWN,
     QIO_CHANNEL_FEATURE_LISTEN,
     QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY,
+    QIO_CHANNEL_FEATURE_READ_MSG_PEEK,
 };
 
 
@@ -114,6 +117,7 @@ struct QIOChannelClass {
                         size_t niov,
                         int **fds,
                         size_t *nfds,
+                        int flags,
                         Error **errp);
     int (*io_close)(QIOChannel *ioc,
                     Error **errp);
@@ -188,6 +192,7 @@ void qio_channel_set_name(QIOChannel *ioc,
  * @niov: the length of the @iov array
  * @fds: pointer to an array that will received file handles
  * @nfds: pointer filled with number of elements in @fds on return
+ * @flags: read flags (QIO_CHANNEL_READ_FLAG_*)
  * @errp: pointer to a NULL-initialized error object
  *
  * Read data from the IO channel, storing it in the
@@ -224,6 +229,7 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc,
                                size_t niov,
                                int **fds,
                                size_t *nfds,
+                               int flags,
                                Error **errp);
 
 
diff --git a/chardev/char-socket.c b/chardev/char-socket.c
index 29ffe5075e..c2265436ac 100644
--- a/chardev/char-socket.c
+++ b/chardev/char-socket.c
@@ -283,11 +283,11 @@ static ssize_t tcp_chr_recv(Chardev *chr, char *buf, size_t len)
     if (qio_channel_has_feature(s->ioc, QIO_CHANNEL_FEATURE_FD_PASS)) {
         ret = qio_channel_readv_full(s->ioc, &iov, 1,
                                      &msgfds, &msgfds_num,
-                                     NULL);
+                                     0, NULL);
     } else {
         ret = qio_channel_readv_full(s->ioc, &iov, 1,
                                      NULL, NULL,
-                                     NULL);
+                                     0, NULL);
     }
 
     if (msgfds_num) {
diff --git a/io/channel-buffer.c b/io/channel-buffer.c
index bf52011be2..8096180f85 100644
--- a/io/channel-buffer.c
+++ b/io/channel-buffer.c
@@ -54,6 +54,7 @@ static ssize_t qio_channel_buffer_readv(QIOChannel *ioc,
                                         size_t niov,
                                         int **fds,
                                         size_t *nfds,
+                                        int flags,
                                         Error **errp)
 {
     QIOChannelBuffer *bioc = QIO_CHANNEL_BUFFER(ioc);
diff --git a/io/channel-command.c b/io/channel-command.c
index 74516252ba..e7edd091af 100644
--- a/io/channel-command.c
+++ b/io/channel-command.c
@@ -203,6 +203,7 @@ static ssize_t qio_channel_command_readv(QIOChannel *ioc,
                                          size_t niov,
                                          int **fds,
                                          size_t *nfds,
+                                         int flags,
                                          Error **errp)
 {
     QIOChannelCommand *cioc = QIO_CHANNEL_COMMAND(ioc);
diff --git a/io/channel-file.c b/io/channel-file.c
index b67687c2aa..d76663e6ae 100644
--- a/io/channel-file.c
+++ b/io/channel-file.c
@@ -86,6 +86,7 @@ static ssize_t qio_channel_file_readv(QIOChannel *ioc,
                                       size_t niov,
                                       int **fds,
                                       size_t *nfds,
+                                      int flags,
                                       Error **errp)
 {
     QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);
diff --git a/io/channel-null.c b/io/channel-null.c
index 75e3781507..4fafdb770d 100644
--- a/io/channel-null.c
+++ b/io/channel-null.c
@@ -60,6 +60,7 @@ qio_channel_null_readv(QIOChannel *ioc,
                        size_t niov,
                        int **fds G_GNUC_UNUSED,
                        size_t *nfds G_GNUC_UNUSED,
+                       int flags,
                        Error **errp)
 {
     QIOChannelNull *nioc = QIO_CHANNEL_NULL(ioc);
diff --git a/io/channel-socket.c b/io/channel-socket.c
index b76dca9cc1..7aca84f61a 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -173,6 +173,9 @@ int qio_channel_socket_connect_sync(QIOChannelSocket *ioc,
     }
 #endif
 
+    qio_channel_set_feature(QIO_CHANNEL(ioc),
+                            QIO_CHANNEL_FEATURE_READ_MSG_PEEK);
+
     return 0;
 }
 
@@ -406,6 +409,9 @@ qio_channel_socket_accept(QIOChannelSocket *ioc,
     }
 #endif /* WIN32 */
 
+    qio_channel_set_feature(QIO_CHANNEL(cioc),
+                            QIO_CHANNEL_FEATURE_READ_MSG_PEEK);
+
     trace_qio_channel_socket_accept_complete(ioc, cioc, cioc->fd);
     return cioc;
 
@@ -496,6 +502,7 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc,
                                         size_t niov,
                                         int **fds,
                                         size_t *nfds,
+                                        int flags,
                                         Error **errp)
 {
     QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
@@ -517,6 +524,10 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc,
 
     }
 
+    if (flags & QIO_CHANNEL_READ_FLAG_MSG_PEEK) {
+        sflags |= MSG_PEEK;
+    }
+
  retry:
     ret = recvmsg(sioc->fd, &msg, sflags);
     if (ret < 0) {
@@ -624,11 +635,17 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc,
                                         size_t niov,
                                         int **fds,
                                         size_t *nfds,
+                                        int flags,
                                         Error **errp)
 {
     QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
     ssize_t done = 0;
     ssize_t i;
+    int sflags = 0;
+
+    if (flags & QIO_CHANNEL_READ_FLAG_MSG_PEEK) {
+        sflags |= MSG_PEEK;
+    }
 
     for (i = 0; i < niov; i++) {
         ssize_t ret;
@@ -636,7 +653,7 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc,
         ret = recv(sioc->fd,
                    iov[i].iov_base,
                    iov[i].iov_len,
-                   0);
+                   sflags);
         if (ret < 0) {
             if (errno == EAGAIN) {
                 if (done) {
diff --git a/io/channel-tls.c b/io/channel-tls.c
index 4ce890a538..c730cb8ec5 100644
--- a/io/channel-tls.c
+++ b/io/channel-tls.c
@@ -260,6 +260,7 @@ static ssize_t qio_channel_tls_readv(QIOChannel *ioc,
                                      size_t niov,
                                      int **fds,
                                      size_t *nfds,
+                                     int flags,
                                      Error **errp)
 {
     QIOChannelTLS *tioc = QIO_CHANNEL_TLS(ioc);
diff --git a/io/channel-websock.c b/io/channel-websock.c
index fb4932ade7..a12acc27cf 100644
--- a/io/channel-websock.c
+++ b/io/channel-websock.c
@@ -1081,6 +1081,7 @@ static ssize_t qio_channel_websock_readv(QIOChannel *ioc,
                                          size_t niov,
                                          int **fds,
                                          size_t *nfds,
+                                         int flags,
                                          Error **errp)
 {
     QIOChannelWebsock *wioc = QIO_CHANNEL_WEBSOCK(ioc);
diff --git a/io/channel.c b/io/channel.c
index 0640941ac5..a8c7f11649 100644
--- a/io/channel.c
+++ b/io/channel.c
@@ -52,6 +52,7 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc,
                                size_t niov,
                                int **fds,
                                size_t *nfds,
+                               int flags,
                                Error **errp)
 {
     QIOChannelClass *klass = QIO_CHANNEL_GET_CLASS(ioc);
@@ -63,7 +64,14 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc,
         return -1;
     }
 
-    return klass->io_readv(ioc, iov, niov, fds, nfds, errp);
+    if ((flags & QIO_CHANNEL_READ_FLAG_MSG_PEEK) &&
+        !qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_READ_MSG_PEEK)) {
+        error_setg_errno(errp, EINVAL,
+                         "Channel does not support peek read");
+        return -1;
+    }
+
+    return klass->io_readv(ioc, iov, niov, fds, nfds, flags, errp);
 }
 
 
@@ -146,7 +154,7 @@ int qio_channel_readv_full_all_eof(QIOChannel *ioc,
     while ((nlocal_iov > 0) || local_fds) {
         ssize_t len;
         len = qio_channel_readv_full(ioc, local_iov, nlocal_iov, local_fds,
-                                     local_nfds, errp);
+                                     local_nfds, 0, errp);
         if (len == QIO_CHANNEL_ERR_BLOCK) {
             if (qemu_in_coroutine()) {
                 qio_channel_yield(ioc, G_IO_IN);
@@ -284,7 +292,7 @@ ssize_t qio_channel_readv(QIOChannel *ioc,
                           size_t niov,
                           Error **errp)
 {
-    return qio_channel_readv_full(ioc, iov, niov, NULL, NULL, errp);
+    return qio_channel_readv_full(ioc, iov, niov, NULL, NULL, 0, errp);
 }
 
 
@@ -303,7 +311,7 @@ ssize_t qio_channel_read(QIOChannel *ioc,
                          Error **errp)
 {
     struct iovec iov = { .iov_base = buf, .iov_len = buflen };
-    return qio_channel_readv_full(ioc, &iov, 1, NULL, NULL, errp);
+    return qio_channel_readv_full(ioc, &iov, 1, NULL, NULL, 0, errp);
 }
 
 
diff --git a/migration/channel-block.c b/migration/channel-block.c
index f4ab53acdb..b7374363c3 100644
--- a/migration/channel-block.c
+++ b/migration/channel-block.c
@@ -53,6 +53,7 @@ qio_channel_block_readv(QIOChannel *ioc,
                         size_t niov,
                         int **fds,
                         size_t *nfds,
+                        int flags,
                         Error **errp)
 {
     QIOChannelBlock *bioc = QIO_CHANNEL_BLOCK(ioc);
diff --git a/migration/rdma.c b/migration/rdma.c
index 0ba1668d70..288eadc2d2 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -2857,6 +2857,7 @@ static ssize_t qio_channel_rdma_readv(QIOChannel *ioc,
                                       size_t niov,
                                       int **fds,
                                       size_t *nfds,
+                                      int flags,
                                       Error **errp)
 {
     QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc);
diff --git a/scsi/qemu-pr-helper.c b/scsi/qemu-pr-helper.c
index 196b78c00d..199227a556 100644
--- a/scsi/qemu-pr-helper.c
+++ b/scsi/qemu-pr-helper.c
@@ -614,7 +614,7 @@ static int coroutine_fn prh_read(PRHelperClient *client, void *buf, int sz,
         iov.iov_base = buf;
         iov.iov_len = sz;
         n_read = qio_channel_readv_full(QIO_CHANNEL(client->ioc), &iov, 1,
-                                        &fds, &nfds, errp);
+                                        &fds, &nfds, 0, errp);
 
         if (n_read == QIO_CHANNEL_ERR_BLOCK) {
             qio_channel_yield(QIO_CHANNEL(client->ioc), G_IO_IN);
diff --git a/tests/qtest/tpm-emu.c b/tests/qtest/tpm-emu.c
index 73e0000a2c..f05fe12f01 100644
--- a/tests/qtest/tpm-emu.c
+++ b/tests/qtest/tpm-emu.c
@@ -115,7 +115,7 @@ void *tpm_emu_ctrl_thread(void *data)
         int *pfd = NULL;
         size_t nfd = 0;
 
-        qio_channel_readv_full(ioc, &iov, 1, &pfd, &nfd, &error_abort);
+        qio_channel_readv_full(ioc, &iov, 1, &pfd, &nfd, 0, &error_abort);
         cmd = be32_to_cpu(cmd);
         g_assert_cmpint(cmd, ==, CMD_SET_DATAFD);
         g_assert_cmpint(nfd, ==, 1);
diff --git a/tests/unit/test-io-channel-socket.c b/tests/unit/test-io-channel-socket.c
index b36a5d972a..b964bb202d 100644
--- a/tests/unit/test-io-channel-socket.c
+++ b/tests/unit/test-io-channel-socket.c
@@ -460,6 +460,7 @@ static void test_io_channel_unix_fd_pass(void)
                            G_N_ELEMENTS(iorecv),
                            &fdrecv,
                            &nfdrecv,
+                           0,
                            &error_abort);
 
     g_assert(nfdrecv == G_N_ELEMENTS(fdsend));
diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c
index 232984ace6..145eb17c08 100644
--- a/util/vhost-user-server.c
+++ b/util/vhost-user-server.c
@@ -116,7 +116,7 @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg)
          * qio_channel_readv_full may have short reads, keeping calling it
          * until getting VHOST_USER_HDR_SIZE or 0 bytes in total
          */
-        rc = qio_channel_readv_full(ioc, &iov, 1, &fds, &nfds, &local_err);
+        rc = qio_channel_readv_full(ioc, &iov, 1, &fds, &nfds, 0, &local_err);
         if (rc < 0) {
             if (rc == QIO_CHANNEL_ERR_BLOCK) {
                 assert(local_err == NULL);
-- 
2.39.1