QIOChannelSocket: Implement io_writev zero copy flag & io_flush for CONFIG_LINUX

For CONFIG_LINUX, implement the new zero copy flag and the optional callback
io_flush on QIOChannelSocket, but enables it only when MSG_ZEROCOPY
feature is available in the host kernel, which is checked on
qio_channel_socket_connect_sync()

qio_channel_socket_flush() was implemented by counting how many times
sendmsg(...,MSG_ZEROCOPY) was successfully called, and then reading the
socket's error queue, in order to find how many of them finished sending.
Flush will loop until those counters are the same, or until some error occurs.

Notes on using writev() with QIO_CHANNEL_WRITE_FLAG_ZERO_COPY:
1: Buffer
- As MSG_ZEROCOPY tells the kernel to use the same user buffer to avoid copying,
some caution is necessary to avoid overwriting any buffer before it's sent.
If something like this happen, a newer version of the buffer may be sent instead.
- If this is a problem, it's recommended to call qio_channel_flush() before freeing
or re-using the buffer.

2: Locked memory
- When using MSG_ZERCOCOPY, the buffer memory will be locked after queued, and
unlocked after it's sent.
- Depending on the size of each buffer, and how often it's sent, it may require
a larger amount of locked memory than usually available to non-root user.
- If the required amount of locked memory is not available, writev_zero_copy
will return an error, which can abort an operation like migration,
- Because of this, when an user code wants to add zero copy as a feature, it
requires a mechanism to disable it, so it can still be accessible to less
privileged users.

Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Message-Id: <20220513062836.965425-4-leobras@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

1 files changed, 112 insertions, 4 deletions

diff --git a/io/channel-socket.c b/io/channel-socket.c
index 05c425abb8..dc9c165de1 100644
--- a/io/channel-socket.c
+++ b/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;
 }
 
@@ -533,6 +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));
 
@@ -557,15 +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;
@@ -659,6 +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,
@@ -789,6 +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 = {