qemu-e2k/net/tap-linux.c

332 lines
8.7 KiB
C
Raw Normal View History

/*
* 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 "qemu-common.h"
#include "tap_int.h"
#include "tap-linux.h"
#include "net/tap.h"
#include <net/if.h>
#include <sys/ioctl.h>
2016-03-14 09:01:28 +01:00
#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) {
Convert error_report() to warn_report() Convert all uses of error_report("warning:"... to use warn_report() instead. This helps standardise on a single method of printing warnings to the user. All of the warnings were changed using these two commands: find ./* -type f -exec sed -i \ 's|error_report(".*warning[,:] |warn_report("|Ig' {} + Indentation fixed up manually afterwards. The test-qdev-global-props test case was manually updated to ensure that this patch passes make check (as the test cases are case sensitive). Signed-off-by: Alistair Francis <alistair.francis@xilinx.com> Suggested-by: Thomas Huth <thuth@redhat.com> Cc: Jeff Cody <jcody@redhat.com> Cc: Kevin Wolf <kwolf@redhat.com> Cc: Max Reitz <mreitz@redhat.com> Cc: Ronnie Sahlberg <ronniesahlberg@gmail.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Peter Lieven <pl@kamp.de> Cc: Josh Durgin <jdurgin@redhat.com> Cc: "Richard W.M. Jones" <rjones@redhat.com> Cc: Markus Armbruster <armbru@redhat.com> Cc: Peter Crosthwaite <crosthwaite.peter@gmail.com> Cc: Richard Henderson <rth@twiddle.net> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Greg Kurz <groug@kaod.org> Cc: Rob Herring <robh@kernel.org> Cc: Peter Maydell <peter.maydell@linaro.org> Cc: Peter Chubb <peter.chubb@nicta.com.au> Cc: Eduardo Habkost <ehabkost@redhat.com> Cc: Marcel Apfelbaum <marcel@redhat.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Igor Mammedov <imammedo@redhat.com> Cc: David Gibson <david@gibson.dropbear.id.au> Cc: Alexander Graf <agraf@suse.de> Cc: Gerd Hoffmann <kraxel@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Cornelia Huck <cohuck@redhat.com> Cc: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: David Gibson <david@gibson.dropbear.id.au> Acked-by: Greg Kurz <groug@kaod.org> Acked-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed by: Peter Chubb <peter.chubb@data61.csiro.au> Acked-by: Max Reitz <mreitz@redhat.com> Acked-by: Marcel Apfelbaum <marcel@redhat.com> Message-Id: <e1cfa2cd47087c248dd24caca9c33d9af0c499b0.1499866456.git.alistair.francis@xilinx.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Markus Armbruster <armbru@redhat.com>
2017-07-12 15:57:41 +02:00
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");
}
}
net: detect errors from probing vnet hdr flag for TAP devices When QEMU sets up a tap based network device backend, it mostly ignores errors reported from various ioctl() calls it makes, assuming the TAP file descriptor is valid. This assumption can easily be violated when the user is passing in a pre-opened file descriptor. At best, the ioctls may fail with a -EBADF, but if the user passes in a bogus FD number that happens to clash with a FD number that QEMU has opened internally for another reason, a wide variety of errnos may result, as the TUNGETIFF ioctl number may map to a completely different command on a different type of file. By ignoring all these errors, QEMU sets up a zombie network backend that will never pass any data. Even worse, when QEMU shuts down, or that network backend is hot-removed, it will close this bogus file descriptor, which could belong to another QEMU device backend. There's no obvious guaranteed reliable way to detect that a FD genuinely is a TAP device, as opposed to a UNIX socket, or pipe, or something else. Checking the errno from probing vnet hdr flag though, does catch the big common cases. ie calling TUNGETIFF will return EBADF for an invalid FD, and ENOTTY when FD is a UNIX socket, or pipe which catches accidental collisions with FDs used for stdio, or monitor socket. Previously the example below where bogus fd 9 collides with the FD used for the chardev saw: $ ./x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hostnet0,fd=9 \ -chardev socket,id=charchannel0,path=/tmp/qga,server,nowait \ -monitor stdio -vnc :0 qemu-system-x86_64: -netdev tap,id=hostnet0,fd=9: TUNGETIFF ioctl() failed: Inappropriate ioctl for device TUNSETOFFLOAD ioctl() failed: Bad address QEMU 2.9.1 monitor - type 'help' for more information (qemu) Warning: netdev hostnet0 has no peer which gives a running QEMU with a zombie network backend. With this change applied we get an error message and QEMU immediately exits before carrying on and making a bigger disaster: $ ./x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hostnet0,fd=9 \ -chardev socket,id=charchannel0,path=/tmp/qga,server,nowait \ -monitor stdio -vnc :0 qemu-system-x86_64: -netdev tap,id=hostnet0,vhost=on,fd=9: Unable to query TUNGETIFF on FD 9: Inappropriate ioctl for device Reported-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Signed-off-by: Daniel P. Berrange <berrange@redhat.com> Tested-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Message-id: 20171027085548.3472-1-berrange@redhat.com [lv: to simplify, don't check on EINVAL with TUNGETIFF as it exists since v2.6.27] Signed-off-by: Laurent Vivier <lvivier@redhat.com> Signed-off-by: Jason Wang <jasowang@redhat.com>
2020-07-07 20:45:15 +02:00
int tap_probe_vnet_hdr(int fd, Error **errp)
{
struct ifreq ifr;
if (ioctl(fd, TUNGETIFF, &ifr) != 0) {
net: detect errors from probing vnet hdr flag for TAP devices When QEMU sets up a tap based network device backend, it mostly ignores errors reported from various ioctl() calls it makes, assuming the TAP file descriptor is valid. This assumption can easily be violated when the user is passing in a pre-opened file descriptor. At best, the ioctls may fail with a -EBADF, but if the user passes in a bogus FD number that happens to clash with a FD number that QEMU has opened internally for another reason, a wide variety of errnos may result, as the TUNGETIFF ioctl number may map to a completely different command on a different type of file. By ignoring all these errors, QEMU sets up a zombie network backend that will never pass any data. Even worse, when QEMU shuts down, or that network backend is hot-removed, it will close this bogus file descriptor, which could belong to another QEMU device backend. There's no obvious guaranteed reliable way to detect that a FD genuinely is a TAP device, as opposed to a UNIX socket, or pipe, or something else. Checking the errno from probing vnet hdr flag though, does catch the big common cases. ie calling TUNGETIFF will return EBADF for an invalid FD, and ENOTTY when FD is a UNIX socket, or pipe which catches accidental collisions with FDs used for stdio, or monitor socket. Previously the example below where bogus fd 9 collides with the FD used for the chardev saw: $ ./x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hostnet0,fd=9 \ -chardev socket,id=charchannel0,path=/tmp/qga,server,nowait \ -monitor stdio -vnc :0 qemu-system-x86_64: -netdev tap,id=hostnet0,fd=9: TUNGETIFF ioctl() failed: Inappropriate ioctl for device TUNSETOFFLOAD ioctl() failed: Bad address QEMU 2.9.1 monitor - type 'help' for more information (qemu) Warning: netdev hostnet0 has no peer which gives a running QEMU with a zombie network backend. With this change applied we get an error message and QEMU immediately exits before carrying on and making a bigger disaster: $ ./x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hostnet0,fd=9 \ -chardev socket,id=charchannel0,path=/tmp/qga,server,nowait \ -monitor stdio -vnc :0 qemu-system-x86_64: -netdev tap,id=hostnet0,vhost=on,fd=9: Unable to query TUNGETIFF on FD 9: Inappropriate ioctl for device Reported-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Signed-off-by: Daniel P. Berrange <berrange@redhat.com> Tested-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Message-id: 20171027085548.3472-1-berrange@redhat.com [lv: to simplify, don't check on EINVAL with TUNGETIFF as it exists since v2.6.27] Signed-off-by: Laurent Vivier <lvivier@redhat.com> Signed-off-by: Jason Wang <jasowang@redhat.com>
2020-07-07 20:45:15 +02:00
/* TUNGETIFF is available since kernel v2.6.27 */
error_setg_errno(errp, errno,
"Unable to query TUNGETIFF on FD %d", fd);
return -1;
}
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;
}
int tap_fd_set_steering_ebpf(int fd, int prog_fd)
{
if (ioctl(fd, TUNSETSTEERINGEBPF, (void *) &prog_fd) != 0) {
error_report("Issue while setting TUNSETSTEERINGEBPF:"
" %s with fd: %d, prog_fd: %d",
strerror(errno), fd, prog_fd);
return -1;
}
return 0;
}