Revision e35bdc123a4ace9f4d3fccaaf88907014e2438cd authored by Kevin Wolf on 05 October 2018, 16:57:40 UTC, committed by Kevin Wolf on 05 November 2018, 14:09:55 UTC
If a management application builds the block graph node by node, the
protocol layer doesn't inherit its read-only option from the format
layer any more, so it must be set explicitly.

Backing files should work on read-only storage, but at the same time, a
block job like commit should be able to reopen them read-write if they
are on read-write storage. However, without option inheritance, reopen
only changes the read-only option for the root node (typically the
format layer), but not the protocol layer, so reopening fails (the
format layer wants to get write permissions, but the protocol layer is
still read-only).

A simple workaround for the problem in the management tool would be to
open the protocol layer always read-write and to make only the format
layer read-only for backing files. However, sometimes the file is
actually stored on read-only storage and we don't know whether the image
can be opened read-write (for example, for NBD it depends on the server
we're trying to connect to). This adds an option that makes QEMU try to
open the image read-write, but allows it to degrade to a read-only mode
without returning an error.

The documentation for this option is consciously phrased in a way that
allows QEMU to switch to a better model eventually: Instead of trying
when the image is first opened, making the read-only flag dynamic and
changing it automatically whenever the first BLK_PERM_WRITE user is
attached or the last one is detached would be much more useful
behaviour.

Unfortunately, this more useful behaviour is also a lot harder to
implement, and libvirt needs a solution now before it can switch to
-blockdev, so let's start with this easier approach for now.

Instead of adding a new auto-read-only option, turning the existing
read-only into an enum (with a bool alternate for compatibility) was
considered, but it complicated the implementation to the point that it
didn't seem to be worth it.

Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
1 parent eeae6a5
Raw File
tap-linux.c
/*
 * QEMU System Emulator
 *
 * Copyright (c) 2003-2008 Fabrice Bellard
 * Copyright (c) 2009 Red Hat, Inc.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

#include "qemu/osdep.h"
#include "tap_int.h"
#include "tap-linux.h"
#include "net/tap.h"

#include <net/if.h>
#include <sys/ioctl.h>

#include "sysemu/sysemu.h"
#include "qapi/error.h"
#include "qemu/error-report.h"
#include "qemu/cutils.h"

#define PATH_NET_TUN "/dev/net/tun"

int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
             int vnet_hdr_required, int mq_required, Error **errp)
{
    struct ifreq ifr;
    int fd, ret;
    int len = sizeof(struct virtio_net_hdr);
    unsigned int features;

    TFR(fd = open(PATH_NET_TUN, O_RDWR));
    if (fd < 0) {
        error_setg_errno(errp, errno, "could not open %s", PATH_NET_TUN);
        return -1;
    }
    memset(&ifr, 0, sizeof(ifr));
    ifr.ifr_flags = IFF_TAP | IFF_NO_PI;

    if (ioctl(fd, TUNGETFEATURES, &features) == -1) {
        warn_report("TUNGETFEATURES failed: %s", strerror(errno));
        features = 0;
    }

    if (features & IFF_ONE_QUEUE) {
        ifr.ifr_flags |= IFF_ONE_QUEUE;
    }

    if (*vnet_hdr) {
        if (features & IFF_VNET_HDR) {
            *vnet_hdr = 1;
            ifr.ifr_flags |= IFF_VNET_HDR;
        } else {
            *vnet_hdr = 0;
        }

        if (vnet_hdr_required && !*vnet_hdr) {
            error_setg(errp, "vnet_hdr=1 requested, but no kernel "
                       "support for IFF_VNET_HDR available");
            close(fd);
            return -1;
        }
        /*
         * Make sure vnet header size has the default value: for a persistent
         * tap it might have been modified e.g. by another instance of qemu.
         * Ignore errors since old kernels do not support this ioctl: in this
         * case the header size implicitly has the correct value.
         */
        ioctl(fd, TUNSETVNETHDRSZ, &len);
    }

    if (mq_required) {
        if (!(features & IFF_MULTI_QUEUE)) {
            error_setg(errp, "multiqueue required, but no kernel "
                       "support for IFF_MULTI_QUEUE available");
            close(fd);
            return -1;
        } else {
            ifr.ifr_flags |= IFF_MULTI_QUEUE;
        }
    }

    if (ifname[0] != '\0')
        pstrcpy(ifr.ifr_name, IFNAMSIZ, ifname);
    else
        pstrcpy(ifr.ifr_name, IFNAMSIZ, "tap%d");
    ret = ioctl(fd, TUNSETIFF, (void *) &ifr);
    if (ret != 0) {
        if (ifname[0] != '\0') {
            error_setg_errno(errp, errno, "could not configure %s (%s)",
                             PATH_NET_TUN, ifr.ifr_name);
        } else {
            error_setg_errno(errp, errno, "could not configure %s",
                             PATH_NET_TUN);
        }
        close(fd);
        return -1;
    }
    pstrcpy(ifname, ifname_size, ifr.ifr_name);
    fcntl(fd, F_SETFL, O_NONBLOCK);
    return fd;
}

/* sndbuf implements a kind of flow control for tap.
 * Unfortunately when it's enabled, and packets are sent
 * to other guests on the same host, the receiver
 * can lock up the transmitter indefinitely.
 *
 * To avoid packet loss, sndbuf should be set to a value lower than the tx
 * queue capacity of any destination network interface.
 * Ethernet NICs generally have txqueuelen=1000, so 1Mb is
 * a good value, given a 1500 byte MTU.
 */
#define TAP_DEFAULT_SNDBUF 0

void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp)
{
    int sndbuf;

    sndbuf = !tap->has_sndbuf       ? TAP_DEFAULT_SNDBUF :
             tap->sndbuf > INT_MAX  ? INT_MAX :
             tap->sndbuf;

    if (!sndbuf) {
        sndbuf = INT_MAX;
    }

    if (ioctl(fd, TUNSETSNDBUF, &sndbuf) == -1 && tap->has_sndbuf) {
        error_setg_errno(errp, errno, "TUNSETSNDBUF ioctl failed");
    }
}

int tap_probe_vnet_hdr(int fd)
{
    struct ifreq ifr;

    if (ioctl(fd, TUNGETIFF, &ifr) != 0) {
        error_report("TUNGETIFF ioctl() failed: %s", strerror(errno));
        return 0;
    }

    return ifr.ifr_flags & IFF_VNET_HDR;
}

int tap_probe_has_ufo(int fd)
{
    unsigned offload;

    offload = TUN_F_CSUM | TUN_F_UFO;

    if (ioctl(fd, TUNSETOFFLOAD, offload) < 0)
        return 0;

    return 1;
}

/* Verify that we can assign given length */
int tap_probe_vnet_hdr_len(int fd, int len)
{
    int orig;
    if (ioctl(fd, TUNGETVNETHDRSZ, &orig) == -1) {
        return 0;
    }
    if (ioctl(fd, TUNSETVNETHDRSZ, &len) == -1) {
        return 0;
    }
    /* Restore original length: we can't handle failure. */
    if (ioctl(fd, TUNSETVNETHDRSZ, &orig) == -1) {
        fprintf(stderr, "TUNGETVNETHDRSZ ioctl() failed: %s. Exiting.\n",
                strerror(errno));
        abort();
        return -errno;
    }
    return 1;
}

void tap_fd_set_vnet_hdr_len(int fd, int len)
{
    if (ioctl(fd, TUNSETVNETHDRSZ, &len) == -1) {
        fprintf(stderr, "TUNSETVNETHDRSZ ioctl() failed: %s. Exiting.\n",
                strerror(errno));
        abort();
    }
}

int tap_fd_set_vnet_le(int fd, int is_le)
{
    int arg = is_le ? 1 : 0;

    if (!ioctl(fd, TUNSETVNETLE, &arg)) {
        return 0;
    }

    /* Check if our kernel supports TUNSETVNETLE */
    if (errno == EINVAL) {
        return -errno;
    }

    error_report("TUNSETVNETLE ioctl() failed: %s.", strerror(errno));
    abort();
}

int tap_fd_set_vnet_be(int fd, int is_be)
{
    int arg = is_be ? 1 : 0;

    if (!ioctl(fd, TUNSETVNETBE, &arg)) {
        return 0;
    }

    /* Check if our kernel supports TUNSETVNETBE */
    if (errno == EINVAL) {
        return -errno;
    }

    error_report("TUNSETVNETBE ioctl() failed: %s.", strerror(errno));
    abort();
}

void tap_fd_set_offload(int fd, int csum, int tso4,
                        int tso6, int ecn, int ufo)
{
    unsigned int offload = 0;

    /* Check if our kernel supports TUNSETOFFLOAD */
    if (ioctl(fd, TUNSETOFFLOAD, 0) != 0 && errno == EINVAL) {
        return;
    }

    if (csum) {
        offload |= TUN_F_CSUM;
        if (tso4)
            offload |= TUN_F_TSO4;
        if (tso6)
            offload |= TUN_F_TSO6;
        if ((tso4 || tso6) && ecn)
            offload |= TUN_F_TSO_ECN;
        if (ufo)
            offload |= TUN_F_UFO;
    }

    if (ioctl(fd, TUNSETOFFLOAD, offload) != 0) {
        offload &= ~TUN_F_UFO;
        if (ioctl(fd, TUNSETOFFLOAD, offload) != 0) {
            fprintf(stderr, "TUNSETOFFLOAD ioctl() failed: %s\n",
                    strerror(errno));
        }
    }
}

/* Enable a specific queue of tap. */
int tap_fd_enable(int fd)
{
    struct ifreq ifr;
    int ret;

    memset(&ifr, 0, sizeof(ifr));

    ifr.ifr_flags = IFF_ATTACH_QUEUE;
    ret = ioctl(fd, TUNSETQUEUE, (void *) &ifr);

    if (ret != 0) {
        error_report("could not enable queue");
    }

    return ret;
}

/* Disable a specific queue of tap/ */
int tap_fd_disable(int fd)
{
    struct ifreq ifr;
    int ret;

    memset(&ifr, 0, sizeof(ifr));

    ifr.ifr_flags = IFF_DETACH_QUEUE;
    ret = ioctl(fd, TUNSETQUEUE, (void *) &ifr);

    if (ret != 0) {
        error_report("could not disable queue");
    }

    return ret;
}

int tap_fd_get_ifname(int fd, char *ifname)
{
    struct ifreq ifr;

    if (ioctl(fd, TUNGETIFF, &ifr) != 0) {
        error_report("TUNGETIFF ioctl() failed: %s",
                     strerror(errno));
        return -1;
    }

    pstrcpy(ifname, sizeof(ifr.ifr_name), ifr.ifr_name);
    return 0;
}
back to top