| Message ID | 20230512122902.34345-4-andrew@daynix.com |
|---|---|
| State | New |
| Headers | show |
| Series | eBPF RSS through QMP support. | expand |
On Fri, May 12, 2023 at 03:28:59PM +0300, Andrew Melnychenko wrote: > eBPF RSS program and maps may now be passed during initialization. > Initially was implemented for libvirt to launch qemu without permissions, > and initialized eBPF program through the helper. > > Signed-off-by: Andrew Melnychenko <andrew@daynix.com> > --- > hw/net/virtio-net.c | 55 ++++++++++++++++++++++++++++++---- > include/hw/virtio/virtio-net.h | 1 + > 2 files changed, 50 insertions(+), 6 deletions(-) > > diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c > index 53e1c326433..a62d7936948 100644 > --- a/hw/net/virtio-net.c > +++ b/hw/net/virtio-net.c > @@ -42,6 +42,7 @@ > #include "sysemu/sysemu.h" > #include "trace.h" > #include "monitor/qdev.h" > +#include "monitor/monitor.h" > #include "hw/pci/pci_device.h" > #include "net_rx_pkt.h" > #include "hw/virtio/vhost.h" > @@ -1305,14 +1306,55 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n) > virtio_net_attach_ebpf_to_backend(n->nic, -1); > } > > -static bool virtio_net_load_ebpf(VirtIONet *n) > +static bool virtio_net_load_ebpf_fds(VirtIONet *n, Error **errp) > { > - if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) { > - /* backend does't support steering ebpf */ > - return false; > + int fds[EBPF_RSS_MAX_FDS] = { [0 ... EBPF_RSS_MAX_FDS - 1] = -1}; Interesting, I didn't realize this initialization syntax was possible ! > + int nfds = 0; > + int ret = true; > + int i = 0; > + g_autofree char **fds_strs = g_strsplit(n->ebpf_rss_fds, ":", 0) You can't use 'g_autofree' with 'char **' I'm afraid, as that'll merely g_free() the array, but not the individual strings. Needs to be g_auto(GStrv) fds_strs GStrv is a typedef for "char **" which gets g_strfreev() attached as its destructor. > + > + ERRP_GUARD(); > + > + if (g_strv_length(fds_strs) != EBPF_RSS_MAX_FDS) { > + error_setg(errp, > + "Expected %d file descriptors but got %d", > + EBPF_RSS_MAX_FDS, g_strv_length(fds_strs)); > + return false; > + } > + > + for (i = 0; i < nfds; i++) { > + fds[i] = monitor_fd_param(monitor_cur(), fds_strs[i], errp); > + if (*errp) { > + ret = false; > + goto exit; > + } > + } > + > + ret = ebpf_rss_load_fds(&n->ebpf_rss, fds[0], fds[1], fds[2], fds[3]); > + > +exit: > + if (!ret || *errp) { > + for (i = 0; i < nfds && fds[i] != -1; i++) { > + close(fds[i]); > + } > } > > - return ebpf_rss_load(&n->ebpf_rss); > + return ret; > +} > + > +static bool virtio_net_load_ebpf(VirtIONet *n, Error **errp) > +{ > + bool ret = false; > + > + if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) { > + if (!(n->ebpf_rss_fds > + && virtio_net_load_ebpf_fds(n, errp))) { > + ret = ebpf_rss_load(&n->ebpf_rss); > + } > + } > + > + return ret; > } > > static void virtio_net_unload_ebpf(VirtIONet *n) > @@ -3738,7 +3780,7 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) > net_rx_pkt_init(&n->rx_pkt); > > if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) { > - virtio_net_load_ebpf(n); > + virtio_net_load_ebpf(n, errp); > } > } > > @@ -3900,6 +3942,7 @@ static Property virtio_net_properties[] = { > VIRTIO_NET_F_RSS, false), > DEFINE_PROP_BIT64("hash", VirtIONet, host_features, > VIRTIO_NET_F_HASH_REPORT, false), > + DEFINE_PROP_STRING("ebpf_rss_fds", VirtIONet, ebpf_rss_fds), > DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features, > VIRTIO_NET_F_RSC_EXT, false), > DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout, > diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h > index ef234ffe7ef..e10ce88f918 100644 > --- a/include/hw/virtio/virtio-net.h > +++ b/include/hw/virtio/virtio-net.h > @@ -219,6 +219,7 @@ struct VirtIONet { > VirtioNetRssData rss_data; > struct NetRxPkt *rx_pkt; > struct EBPFRSSContext ebpf_rss; > + char *ebpf_rss_fds; > }; > > size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev, > -- > 2.39.1 > With regards, Daniel
Hi all, On Mon, May 15, 2023 at 12:38 PM Daniel P. Berrangé <berrange@redhat.com> wrote: > > On Fri, May 12, 2023 at 03:28:59PM +0300, Andrew Melnychenko wrote: > > eBPF RSS program and maps may now be passed during initialization. > > Initially was implemented for libvirt to launch qemu without permissions, > > and initialized eBPF program through the helper. > > > > Signed-off-by: Andrew Melnychenko <andrew@daynix.com> > > --- > > hw/net/virtio-net.c | 55 ++++++++++++++++++++++++++++++---- > > include/hw/virtio/virtio-net.h | 1 + > > 2 files changed, 50 insertions(+), 6 deletions(-) > > > > diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c > > index 53e1c326433..a62d7936948 100644 > > --- a/hw/net/virtio-net.c > > +++ b/hw/net/virtio-net.c > > @@ -42,6 +42,7 @@ > > #include "sysemu/sysemu.h" > > #include "trace.h" > > #include "monitor/qdev.h" > > +#include "monitor/monitor.h" > > #include "hw/pci/pci_device.h" > > #include "net_rx_pkt.h" > > #include "hw/virtio/vhost.h" > > @@ -1305,14 +1306,55 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n) > > virtio_net_attach_ebpf_to_backend(n->nic, -1); > > } > > > > -static bool virtio_net_load_ebpf(VirtIONet *n) > > +static bool virtio_net_load_ebpf_fds(VirtIONet *n, Error **errp) > > { > > - if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) { > > - /* backend does't support steering ebpf */ > > - return false; > > + int fds[EBPF_RSS_MAX_FDS] = { [0 ... EBPF_RSS_MAX_FDS - 1] = -1}; > > Interesting, I didn't realize this initialization syntax was possible ! > > > + int nfds = 0; > > + int ret = true; > > + int i = 0; > > + g_autofree char **fds_strs = g_strsplit(n->ebpf_rss_fds, ":", 0) > > You can't use 'g_autofree' with 'char **' I'm afraid, as that'll > merely g_free() the array, but not the individual strings. > > Needs to be > > g_auto(GStrv) fds_strs > > GStrv is a typedef for "char **" which gets g_strfreev() attached > as its destructor. Oh yeah, I've missed that! Thank you. > > > > + > > + ERRP_GUARD(); > > + > > + if (g_strv_length(fds_strs) != EBPF_RSS_MAX_FDS) { > > + error_setg(errp, > > + "Expected %d file descriptors but got %d", > > + EBPF_RSS_MAX_FDS, g_strv_length(fds_strs)); > > + return false; > > + } > > + > > + for (i = 0; i < nfds; i++) { > > + fds[i] = monitor_fd_param(monitor_cur(), fds_strs[i], errp); > > + if (*errp) { > > + ret = false; > > + goto exit; > > + } > > + } > > + > > + ret = ebpf_rss_load_fds(&n->ebpf_rss, fds[0], fds[1], fds[2], fds[3]); > > + > > +exit: > > + if (!ret || *errp) { > > + for (i = 0; i < nfds && fds[i] != -1; i++) { > > + close(fds[i]); > > + } > > } > > > > - return ebpf_rss_load(&n->ebpf_rss); > > + return ret; > > +} > > + > > +static bool virtio_net_load_ebpf(VirtIONet *n, Error **errp) > > +{ > > + bool ret = false; > > + > > + if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) { > > + if (!(n->ebpf_rss_fds > > + && virtio_net_load_ebpf_fds(n, errp))) { > > + ret = ebpf_rss_load(&n->ebpf_rss); > > + } > > + } > > + > > + return ret; > > } > > > > static void virtio_net_unload_ebpf(VirtIONet *n) > > @@ -3738,7 +3780,7 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) > > net_rx_pkt_init(&n->rx_pkt); > > > > if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) { > > - virtio_net_load_ebpf(n); > > + virtio_net_load_ebpf(n, errp); > > } > > } > > > > @@ -3900,6 +3942,7 @@ static Property virtio_net_properties[] = { > > VIRTIO_NET_F_RSS, false), > > DEFINE_PROP_BIT64("hash", VirtIONet, host_features, > > VIRTIO_NET_F_HASH_REPORT, false), > > + DEFINE_PROP_STRING("ebpf_rss_fds", VirtIONet, ebpf_rss_fds), > > DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features, > > VIRTIO_NET_F_RSC_EXT, false), > > DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout, > > diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h > > index ef234ffe7ef..e10ce88f918 100644 > > --- a/include/hw/virtio/virtio-net.h > > +++ b/include/hw/virtio/virtio-net.h > > @@ -219,6 +219,7 @@ struct VirtIONet { > > VirtioNetRssData rss_data; > > struct NetRxPkt *rx_pkt; > > struct EBPFRSSContext ebpf_rss; > > + char *ebpf_rss_fds; > > }; > > > > size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev, > > -- > > 2.39.1 > > > > With regards, > Daniel > -- > |: https://berrange.com -o- https://www.flickr.com/photos/dberrange :| > |: https://libvirt.org -o- https://fstop138.berrange.com :| > |: https://entangle-photo.org -o- https://www.instagram.com/dberrange :| >
On Mon, May 15, 2023 at 10:38:44AM +0100, Daniel P. Berrangé wrote: > > > -static bool virtio_net_load_ebpf(VirtIONet *n) > > +static bool virtio_net_load_ebpf_fds(VirtIONet *n, Error **errp) > > { > > - if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) { > > - /* backend does't support steering ebpf */ > > - return false; > > + int fds[EBPF_RSS_MAX_FDS] = { [0 ... EBPF_RSS_MAX_FDS - 1] = -1}; > > Interesting, I didn't realize this initialization syntax was possible ! It's not standard, but if both gcc and clang support it, it would not be the first time we've relied on useful compiler extensions.
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index 53e1c326433..a62d7936948 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -42,6 +42,7 @@ #include "sysemu/sysemu.h" #include "trace.h" #include "monitor/qdev.h" +#include "monitor/monitor.h" #include "hw/pci/pci_device.h" #include "net_rx_pkt.h" #include "hw/virtio/vhost.h" @@ -1305,14 +1306,55 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n) virtio_net_attach_ebpf_to_backend(n->nic, -1); } -static bool virtio_net_load_ebpf(VirtIONet *n) +static bool virtio_net_load_ebpf_fds(VirtIONet *n, Error **errp) { - if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) { - /* backend does't support steering ebpf */ - return false; + int fds[EBPF_RSS_MAX_FDS] = { [0 ... EBPF_RSS_MAX_FDS - 1] = -1}; + int nfds = 0; + int ret = true; + int i = 0; + g_autofree char **fds_strs = g_strsplit(n->ebpf_rss_fds, ":", 0); + + ERRP_GUARD(); + + if (g_strv_length(fds_strs) != EBPF_RSS_MAX_FDS) { + error_setg(errp, + "Expected %d file descriptors but got %d", + EBPF_RSS_MAX_FDS, g_strv_length(fds_strs)); + return false; + } + + for (i = 0; i < nfds; i++) { + fds[i] = monitor_fd_param(monitor_cur(), fds_strs[i], errp); + if (*errp) { + ret = false; + goto exit; + } + } + + ret = ebpf_rss_load_fds(&n->ebpf_rss, fds[0], fds[1], fds[2], fds[3]); + +exit: + if (!ret || *errp) { + for (i = 0; i < nfds && fds[i] != -1; i++) { + close(fds[i]); + } } - return ebpf_rss_load(&n->ebpf_rss); + return ret; +} + +static bool virtio_net_load_ebpf(VirtIONet *n, Error **errp) +{ + bool ret = false; + + if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) { + if (!(n->ebpf_rss_fds + && virtio_net_load_ebpf_fds(n, errp))) { + ret = ebpf_rss_load(&n->ebpf_rss); + } + } + + return ret; } static void virtio_net_unload_ebpf(VirtIONet *n) @@ -3738,7 +3780,7 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) net_rx_pkt_init(&n->rx_pkt); if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) { - virtio_net_load_ebpf(n); + virtio_net_load_ebpf(n, errp); } } @@ -3900,6 +3942,7 @@ static Property virtio_net_properties[] = { VIRTIO_NET_F_RSS, false), DEFINE_PROP_BIT64("hash", VirtIONet, host_features, VIRTIO_NET_F_HASH_REPORT, false), + DEFINE_PROP_STRING("ebpf_rss_fds", VirtIONet, ebpf_rss_fds), DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features, VIRTIO_NET_F_RSC_EXT, false), DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout, diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h index ef234ffe7ef..e10ce88f918 100644 --- a/include/hw/virtio/virtio-net.h +++ b/include/hw/virtio/virtio-net.h @@ -219,6 +219,7 @@ struct VirtIONet { VirtioNetRssData rss_data; struct NetRxPkt *rx_pkt; struct EBPFRSSContext ebpf_rss; + char *ebpf_rss_fds; }; size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev,
eBPF RSS program and maps may now be passed during initialization. Initially was implemented for libvirt to launch qemu without permissions, and initialized eBPF program through the helper. Signed-off-by: Andrew Melnychenko <andrew@daynix.com> --- hw/net/virtio-net.c | 55 ++++++++++++++++++++++++++++++---- include/hw/virtio/virtio-net.h | 1 + 2 files changed, 50 insertions(+), 6 deletions(-)