Merge tag 'pull-migration-20220516a' of https://gitlab.com/dagrh/qemu …

…into staging

Migration pull 2022-05-16

(This replaces the 28th April through 10th May sets)
Compared to that last set it just has the Alpine
uring check that Leo has added; although that's also
now fixed upstream in Alpine.

It contains:
  TLS test fixes from Dan
  Zerocopy migration feature from Leo

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEERfXHG0oMt/uXep+pBRYzHrxb/ecFAmKCY80ACgkQBRYzHrxb
# /eeEEhAAoUogch7ifxFItr1EA0AU6Sgd3Dcn8wY9pm0NySVg7OcIpk1H++A3CgIh
# bubJSwRmpIxGw+5q5w5OvBukFCGYMlAK7J8k1tZmaqdKS8wD0ZwhpPyqTWd14Q/v
# xXSGOQfHMMvbBILiXPjSkfNw8yKJhZr+lW39uMz/kZRwZUmTcrdKAT3Q8PW+1DI9
# v3mNoFNXqtDlHcQ4nQ1TGk/RDO6oXDlTJwdnjoJT3Dopf8Jhl2etvZgVk2kOf4i5
# LmJbSVBr5FNOhJ6P4WL4OEQFOiXXquKdfuGTXIGGhkrW2WkPZulQwB6uO4Gv1wf2
# aj9bLDAFoPxFx2zYS6S/9L6rGeBMcTL9xHCfzyylM6YRjoscRdxXc67PClw71JUy
# regsoSQej0FpmsGx0uuAsDjCELleVIjeYzuQo5OYOP1BCg/5unLIrMgkyQw7COJI
# w+MIZq7IqvUTehU2yXpUGOqPkyDLBlib92dMRgqqG9r9UU7iL3BREbGW4ugW+GM2
# a9k8W9HjyDIIODsdXy1ugPHgjr/arHDAPgYosJMLvjTfdJDcIldAw6CbCcqhCDES
# UOjMVN9VS+716nY2AqvtEHxf47YwqmeRb+tg4SQ0dHLH5Pvfe2bk1sbZiiQpcelt
# Bd88yeBOpcmdzJVur2V4fEZXu5JB/qt/jeJeQa82hS3k93PWm/w=
# =Axhk
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 16 May 2022 07:46:37 AM PDT
# gpg:                using RSA key 45F5C71B4A0CB7FB977A9FA90516331EBC5BFDE7
# gpg: Good signature from "Dr. David Alan Gilbert (RH2) <dgilbert@redhat.com>" [full]

* tag 'pull-migration-20220516a' of https://gitlab.com/dagrh/qemu:
  multifd: Implement zero copy write in multifd migration (multifd-zero-copy)
  multifd: Send header packet without flags if zero-copy-send is enabled
  multifd: multifd_send_sync_main now returns negative on error
  migration: Add migrate_use_tls() helper
  migration: Add zero-copy-send parameter for QMP/HMP for Linux
  QIOChannelSocket: Implement io_writev zero copy flag & io_flush for CONFIG_LINUX
  QIOChannel: Add flags on io_writev and introduce io_flush callback
  meson.build: Fix docker-test-build@alpine when including linux/errqueue.h
  tests: ensure migration status isn't reported as failed
  tests: add multifd migration tests of TLS with x509 credentials
  tests: add multifd migration tests of TLS with PSK credentials
  tests: convert multifd migration tests to use common helper
  tests: convert XBZRLE migration test to use common helper
  tests: add migration tests of TLS with x509 credentials
  tests: add migration tests of TLS with PSK credentials
  tests: add more helper macros for creating TLS x509 certs
  tests: fix encoding of IP addresses in x509 certs

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

chardev/char-io.c

@@ -122,7 +122,7 @@ int io_channel_send_full(QIOChannel *ioc,
 
         ret = qio_channel_writev_full(
             ioc, &iov, 1,
-            fds, nfds, NULL);
+            fds, nfds, 0, NULL);
         if (ret == QIO_CHANNEL_ERR_BLOCK) {
             if (offset) {
                 return offset;

hw/remote/mpqemu-link.c

@@ -68,7 +68,7 @@ bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp)
     }
 
     if (!qio_channel_writev_full_all(ioc, send, G_N_ELEMENTS(send),
-                                    fds, nfds, errp)) {
+                                    fds, nfds, 0, errp)) {
         ret = true;
     } else {
         trace_mpqemu_send_io_error(msg->cmd, msg->size, nfds);

include/io/channel-socket.h

@@ -47,6 +47,8 @@ struct QIOChannelSocket {
     socklen_t localAddrLen;
     struct sockaddr_storage remoteAddr;
     socklen_t remoteAddrLen;
+    ssize_t zero_copy_queued;
+    ssize_t zero_copy_sent;
 };
 
 

include/io/channel.h

@@ -32,12 +32,15 @@ OBJECT_DECLARE_TYPE(QIOChannel, QIOChannelClass,
 
 #define QIO_CHANNEL_ERR_BLOCK -2
 
+#define QIO_CHANNEL_WRITE_FLAG_ZERO_COPY 0x1
+
 typedef enum QIOChannelFeature QIOChannelFeature;
 
 enum QIOChannelFeature {
     QIO_CHANNEL_FEATURE_FD_PASS,
     QIO_CHANNEL_FEATURE_SHUTDOWN,
     QIO_CHANNEL_FEATURE_LISTEN,
+    QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY,
 };
 
 
@@ -104,6 +107,7 @@ struct QIOChannelClass {
                          size_t niov,
                          int *fds,
                          size_t nfds,
+                         int flags,
                          Error **errp);
     ssize_t (*io_readv)(QIOChannel *ioc,
                         const struct iovec *iov,
@@ -136,6 +140,8 @@ struct QIOChannelClass {
                                   IOHandler *io_read,
                                   IOHandler *io_write,
                                   void *opaque);
+    int (*io_flush)(QIOChannel *ioc,
+                    Error **errp);
 };
 
 /* General I/O handling functions */
@@ -228,6 +234,7 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc,
  * @niov: the length of the @iov array
  * @fds: an array of file handles to send
  * @nfds: number of file handles in @fds
+ * @flags: write flags (QIO_CHANNEL_WRITE_FLAG_*)
  * @errp: pointer to a NULL-initialized error object
  *
  * Write data to the IO channel, reading it from the
@@ -260,6 +267,7 @@ ssize_t qio_channel_writev_full(QIOChannel *ioc,
                                 size_t niov,
                                 int *fds,
                                 size_t nfds,
+                                int flags,
                                 Error **errp);
 
 /**
@@ -837,6 +845,7 @@ int qio_channel_readv_full_all(QIOChannel *ioc,
  * @niov: the length of the @iov array
  * @fds: an array of file handles to send
  * @nfds: number of file handles in @fds
+ * @flags: write flags (QIO_CHANNEL_WRITE_FLAG_*)
  * @errp: pointer to a NULL-initialized error object
  *
  *
@@ -846,13 +855,40 @@ int qio_channel_readv_full_all(QIOChannel *ioc,
  * to be written, yielding from the current coroutine
  * if required.
  *
+ * If QIO_CHANNEL_WRITE_FLAG_ZERO_COPY is passed in flags,
+ * instead of waiting for all requested data to be written,
+ * this function will wait until it's all queued for writing.
+ * In this case, if the buffer gets changed between queueing and
+ * sending, the updated buffer will be sent. If this is not a
+ * desired behavior, it's suggested to call qio_channel_flush()
+ * before reusing the buffer.
+ *
  * Returns: 0 if all bytes were written, or -1 on error
  */
 
 int qio_channel_writev_full_all(QIOChannel *ioc,
                                 const struct iovec *iov,
                                 size_t niov,
                                 int *fds, size_t nfds,
-                                Error **errp);
+                                int flags, Error **errp);
+
+/**
+ * qio_channel_flush:
+ * @ioc: the channel object
+ * @errp: pointer to a NULL-initialized error object
+ *
+ * Will block until every packet queued with
+ * qio_channel_writev_full() + QIO_CHANNEL_WRITE_FLAG_ZERO_COPY
+ * is sent, or return in case of any error.
+ *
+ * If not implemented, acts as a no-op, and returns 0.
+ *
+ * Returns -1 if any error is found,
+ *          1 if every send failed to use zero copy.
+ *          0 otherwise.
+ */
+
+int qio_channel_flush(QIOChannel *ioc,
+                      Error **errp);
 
 #endif /* QIO_CHANNEL_H */

io/channel-buffer.c

@@ -81,6 +81,7 @@ static ssize_t qio_channel_buffer_writev(QIOChannel *ioc,
                                          size_t niov,
                                          int *fds,
                                          size_t nfds,
+                                         int flags,
                                          Error **errp)
 {
     QIOChannelBuffer *bioc = QIO_CHANNEL_BUFFER(ioc);

io/channel-command.c

@@ -276,6 +276,7 @@ static ssize_t qio_channel_command_writev(QIOChannel *ioc,
                                           size_t niov,
                                           int *fds,
                                           size_t nfds,
+                                          int flags,
                                           Error **errp)
 {
     QIOChannelCommand *cioc = QIO_CHANNEL_COMMAND(ioc);

io/channel-file.c

@@ -114,6 +114,7 @@ static ssize_t qio_channel_file_writev(QIOChannel *ioc,
                                        size_t niov,
                                        int *fds,
                                        size_t nfds,
+                                       int flags,
                                        Error **errp)
 {
     QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);

io/channel-socket.c

@@ -25,6 +25,14 @@
 #include "io/channel-watch.h"
 #include "trace.h"
 #include "qapi/clone-visitor.h"
+#ifdef CONFIG_LINUX
+#include <linux/errqueue.h>
+#include <sys/socket.h>
+
+#if (defined(MSG_ZEROCOPY) && defined(SO_ZEROCOPY))
+#define QEMU_MSG_ZEROCOPY
+#endif
+#endif
 
 #define SOCKET_MAX_FDS 16
 
@@ -54,6 +62,8 @@ qio_channel_socket_new(void)
 
     sioc = QIO_CHANNEL_SOCKET(object_new(TYPE_QIO_CHANNEL_SOCKET));
     sioc->fd = -1;
+    sioc->zero_copy_queued = 0;
+    sioc->zero_copy_sent = 0;
 
     ioc = QIO_CHANNEL(sioc);
     qio_channel_set_feature(ioc, QIO_CHANNEL_FEATURE_SHUTDOWN);
@@ -153,6 +163,16 @@ int qio_channel_socket_connect_sync(QIOChannelSocket *ioc,
         return -1;
     }
 
+#ifdef QEMU_MSG_ZEROCOPY
+    int ret, v = 1;
+    ret = setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &v, sizeof(v));
+    if (ret == 0) {
+        /* Zero copy available on host */
+        qio_channel_set_feature(QIO_CHANNEL(ioc),
+                                QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY);
+    }
+#endif
+
     return 0;
 }
 
@@ -524,6 +544,7 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
                                          size_t niov,
                                          int *fds,
                                          size_t nfds,
+                                         int flags,
                                          Error **errp)
 {
     QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
@@ -532,6 +553,7 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
     char control[CMSG_SPACE(sizeof(int) * SOCKET_MAX_FDS)];
     size_t fdsize = sizeof(int) * nfds;
     struct cmsghdr *cmsg;
+    int sflags = 0;
 
     memset(control, 0, CMSG_SPACE(sizeof(int) * SOCKET_MAX_FDS));
 
@@ -556,15 +578,31 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
         memcpy(CMSG_DATA(cmsg), fds, fdsize);
     }
 
+#ifdef QEMU_MSG_ZEROCOPY
+    if (flags & QIO_CHANNEL_WRITE_FLAG_ZERO_COPY) {
+        sflags = MSG_ZEROCOPY;
+    }
+#endif
+
  retry:
-    ret = sendmsg(sioc->fd, &msg, 0);
+    ret = sendmsg(sioc->fd, &msg, sflags);
     if (ret <= 0) {
-        if (errno == EAGAIN) {
+        switch (errno) {
+        case EAGAIN:
             return QIO_CHANNEL_ERR_BLOCK;
-        }
-        if (errno == EINTR) {
+        case EINTR:
             goto retry;
+#ifdef QEMU_MSG_ZEROCOPY
+        case ENOBUFS:
+            if (sflags & MSG_ZEROCOPY) {
+                error_setg_errno(errp, errno,
+                                 "Process can't lock enough memory for using MSG_ZEROCOPY");
+                return -1;
+            }
+            break;
+#endif
         }
+
         error_setg_errno(errp, errno,
                          "Unable to write to socket");
         return -1;
@@ -619,6 +657,7 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
                                          size_t niov,
                                          int *fds,
                                          size_t nfds,
+                                         int flags,
                                          Error **errp)
 {
     QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
@@ -657,6 +696,74 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
 }
 #endif /* WIN32 */
 
+
+#ifdef QEMU_MSG_ZEROCOPY
+static int qio_channel_socket_flush(QIOChannel *ioc,
+                                    Error **errp)
+{
+    QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
+    struct msghdr msg = {};
+    struct sock_extended_err *serr;
+    struct cmsghdr *cm;
+    char control[CMSG_SPACE(sizeof(*serr))];
+    int received;
+    int ret = 1;
+
+    msg.msg_control = control;
+    msg.msg_controllen = sizeof(control);
+    memset(control, 0, sizeof(control));
+
+    while (sioc->zero_copy_sent < sioc->zero_copy_queued) {
+        received = recvmsg(sioc->fd, &msg, MSG_ERRQUEUE);
+        if (received < 0) {
+            switch (errno) {
+            case EAGAIN:
+                /* Nothing on errqueue, wait until something is available */
+                qio_channel_wait(ioc, G_IO_ERR);
+                continue;
+            case EINTR:
+                continue;
+            default:
+                error_setg_errno(errp, errno,
+                                 "Unable to read errqueue");
+                return -1;
+            }
+        }
+
+        cm = CMSG_FIRSTHDR(&msg);
+        if (cm->cmsg_level != SOL_IP &&
+            cm->cmsg_type != IP_RECVERR) {
+            error_setg_errno(errp, EPROTOTYPE,
+                             "Wrong cmsg in errqueue");
+            return -1;
+        }
+
+        serr = (void *) CMSG_DATA(cm);
+        if (serr->ee_errno != SO_EE_ORIGIN_NONE) {
+            error_setg_errno(errp, serr->ee_errno,
+                             "Error on socket");
+            return -1;
+        }
+        if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY) {
+            error_setg_errno(errp, serr->ee_origin,
+                             "Error not from zero copy");
+            return -1;
+        }
+
+        /* No errors, count successfully finished sendmsg()*/
+        sioc->zero_copy_sent += serr->ee_data - serr->ee_info + 1;
+
+        /* If any sendmsg() succeeded using zero copy, return 0 at the end */
+        if (serr->ee_code != SO_EE_CODE_ZEROCOPY_COPIED) {
+            ret = 0;
+        }
+    }
+
+    return ret;
+}
+
+#endif /* QEMU_MSG_ZEROCOPY */
+
 static int
 qio_channel_socket_set_blocking(QIOChannel *ioc,
                                 bool enabled,
@@ -787,6 +894,9 @@ static void qio_channel_socket_class_init(ObjectClass *klass,
     ioc_klass->io_set_delay = qio_channel_socket_set_delay;
     ioc_klass->io_create_watch = qio_channel_socket_create_watch;
     ioc_klass->io_set_aio_fd_handler = qio_channel_socket_set_aio_fd_handler;
+#ifdef QEMU_MSG_ZEROCOPY
+    ioc_klass->io_flush = qio_channel_socket_flush;
+#endif
 }
 
 static const TypeInfo qio_channel_socket_info = {

io/channel-tls.c

@@ -301,6 +301,7 @@ static ssize_t qio_channel_tls_writev(QIOChannel *ioc,
                                       size_t niov,
                                       int *fds,
                                       size_t nfds,
+                                      int flags,
                                       Error **errp)
 {
     QIOChannelTLS *tioc = QIO_CHANNEL_TLS(ioc);

io/channel-websock.c

@@ -1127,6 +1127,7 @@ static ssize_t qio_channel_websock_writev(QIOChannel *ioc,
                                           size_t niov,
                                           int *fds,
                                           size_t nfds,
+                                          int flags,
                                           Error **errp)
 {
     QIOChannelWebsock *wioc = QIO_CHANNEL_WEBSOCK(ioc);