- dev - passt

[PATCH] ndp: Don't send unsolicited RAs if NDP is disabled
by David Gibson 19 Nov '24

19 Nov '24

We recently added support for sending unsolicited NDP Router Advertisement packets. While we (correctly) disable this if the --no-ra option is given we incorrectly still send them if --no-ndp is set. Fix the oversight. Fixes: 6e1e44293ef9 ("ndp: Send unsolicited Router Advertisements") Signed-off-by: David Gibson <david(a)gibson.dropbear.id.au> --- passt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/passt.c b/passt.c index a51a4e1..06e0a33 100644 --- a/passt.c +++ b/passt.c @@ -109,7 +109,8 @@ static void post_handler(struct ctx *c, const struct timespec *now) flow_defer_handler(c, now); #undef CALL_PROTO_HANDLER - ndp_timer(c, now); + if (!c->no_ndp) + ndp_timer(c, now); } /** -- 2.47.0

2 1

[PATCH v2] dhcp, dhcpv6: Add hostname and client fqdn ops
by Enrique Llorente 19 Nov '24

19 Nov '24

Both DHCPv4 and DHCPv6 has the capability to pass the hostname to clients, the DHCPv4 uses option 12 (hostname) while the DHCPv6 uses option 39 (client fqdn), for some virt deployments like kubevirt is expected to have the VirtualMachine name as the guest hostname. This change add the -H --hostname to configure the DHCPv4 and DHCPv6 options to will send hostname to clients. Signed-off-by: Enrique Llorente <ellorent(a)redhat.com> --- conf.c | 13 ++++++++++--- dhcp.c | 8 +++++++- dhcpv6.c | 44 +++++++++++++++++++++++++++++++++++++++++++- passt.h | 2 ++ test/lib/setup | 10 +++++----- test/passt.mbuto | 1 + test/passt/dhcp | 11 ++++++++++- 7 files changed, 78 insertions(+), 11 deletions(-) diff --git a/conf.c b/conf.c index 14411b4..ddb585c 100644 --- a/conf.c +++ b/conf.c @@ -847,7 +847,8 @@ static void usage(const char *name, FILE *f, int status) " --freebind Bind to any address for forwarding\n" " --no-map-gw Don't map gateway address to host\n" " -4, --ipv4-only Enable IPv4 operation only\n" - " -6, --ipv6-only Enable IPv6 operation only\n"); + " -6, --ipv6-only Enable IPv6 operation only\n" + " -H, --hostname NAME Hostname to configure client with\n"); if (strstr(name, "pasta")) goto pasta_opts; @@ -1303,6 +1304,7 @@ void conf(struct ctx *c, int argc, char **argv) {"map-guest-addr", required_argument, NULL, 22 }, {"host-lo-to-ns-lo", no_argument, NULL, 23 }, {"dns-host", required_argument, NULL, 24 }, + {"hostname", required_argument, NULL, 'H' }, { 0 }, }; const char *logname = (c->mode == MODE_PASTA) ? "pasta" : "passt"; @@ -1325,9 +1327,9 @@ void conf(struct ctx *c, int argc, char **argv) if (c->mode == MODE_PASTA) { c->no_dhcp_dns = c->no_dhcp_dns_search = 1; fwd_default = FWD_AUTO; - optstring = "+dqfel:hF:I:p:P:m:a:n:M:g:i:o:D:S:46t:u:T:U:"; + optstring = "+dqfel:hF:I:p:P:m:a:n:M:g:i:o:D:S:46t:u:T:U:H:"; } else { - optstring = "+dqfel:hs:F:p:P:m:a:n:M:g:i:o:D:S:461t:u:"; + optstring = "+dqfel:hs:F:p:P:m:a:n:M:g:i:o:D:S:461t:u:H:"; } c->tcp.fwd_in.mode = c->tcp.fwd_out.mode = FWD_UNSET; @@ -1680,6 +1682,11 @@ void conf(struct ctx *c, int argc, char **argv) c->one_off = true; break; + case 'H': + ret = snprintf(c->hostname.n, sizeof(c->hostname.n), "%s", optarg); + if (ret <= 0 || ret >= (int)sizeof(c->hostname.n)) + die("Invalid hostname: %s", optarg); + break; case 't': case 'u': case 'T': diff --git a/dhcp.c b/dhcp.c index a06f143..ec7e78a 100644 --- a/dhcp.c +++ b/dhcp.c @@ -275,7 +275,7 @@ static void opt_set_dns_search(const struct ctx *c, size_t max_len) */ int dhcp(const struct ctx *c, const struct pool *p) { - size_t mlen, dlen, offset = 0, opt_len, opt_off = 0; + size_t mlen, dlen, offset = 0, opt_len, opt_off = 0, hostname_len; char macstr[ETH_ADDRSTRLEN]; const struct ethhdr *eh; const struct iphdr *iph; @@ -375,6 +375,12 @@ int dhcp(const struct ctx *c, const struct pool *p) opts[6].slen += sizeof(uint32_t); } + hostname_len = strlen(c->hostname.n); + if ( hostname_len > 0 ) { + opts[12].slen = hostname_len; + memcpy(opts[12].s, &c->hostname.n, hostname_len); + } + if (!c->no_dhcp_dns_search) opt_set_dns_search(c, sizeof(m->o)); diff --git a/dhcpv6.c b/dhcpv6.c index 14a5c7e..190dc0e 100644 --- a/dhcpv6.c +++ b/dhcpv6.c @@ -48,6 +48,7 @@ struct opt_hdr { # define STATUS_NOTONLINK htons_constant(4) # define OPT_DNS_SERVERS htons_constant(23) # define OPT_DNS_SEARCH htons_constant(24) +# define OPT_CLIENT_FQDN htons_constant(39) #define STR_NOTONLINK "Prefix not appropriate for link." uint16_t l; @@ -163,6 +164,18 @@ struct opt_dns_search { char list[MAXDNSRCH * NS_MAXDNAME]; } __attribute__((packed)); +/** + * struct opt_client_fqdn - Client FQDN option (RFC 4704) + * @hdr: Option header + * @flags: Flags as stated at RFC 4704 + * @hostname: Client fqdn + */ +struct opt_client_fqdn{ + struct opt_hdr hdr; + uint8_t flags; + uint8_t hostname[NS_MAXDNAME]; +} __attribute__((packed)); + /** * struct msg_hdr - DHCPv6 client/server message header * @type: DHCP message type @@ -191,6 +204,7 @@ struct msg_hdr { * @ia_na: Non-temporary Address option * @ia_addr: Address for IA_NA * @client_id: Client Identifier, variable length + * @client_fqdn: Client FQDN, variable length * @dns_servers: DNS Recursive Name Server, here just for storage size * @dns_search: Domain Search List, here just for storage size */ @@ -203,10 +217,10 @@ static struct resp_t { struct opt_client_id client_id; struct opt_dns_servers dns_servers; struct opt_dns_search dns_search; + struct opt_client_fqdn client_fqdn; } __attribute__((__packed__)) resp = { { 0 }, SERVER_ID, - { { OPT_IA_NA, OPT_SIZE_CONV(sizeof(struct opt_ia_na) + sizeof(struct opt_ia_addr) - sizeof(struct opt_hdr)) }, @@ -228,6 +242,10 @@ static struct resp_t { { { OPT_DNS_SEARCH, 0, }, { 0 }, }, + + { { OPT_CLIENT_FQDN, 0, }, + (uint8_t)~0U, { 0 }, + }, }; static const struct opt_status_code sc_not_on_link = { @@ -416,6 +434,29 @@ search: return offset; } +/** + * dhcpv6_client_fqdn_fill() - Fill in client FQDN option + * @c: Execution context + * @buf: Response message buffer where options will be appended + * @offset: Offset in message buffer for new options + * + * Return: updated length of response message buffer. + */ +static size_t dhcpv6_client_fqdn_fill(const struct ctx *c, char *buf, int offset) +{ + uint16_t hostname_len = strlen(c->hostname.n); + if (hostname_len > 0) { + struct opt_client_fqdn *o = (struct opt_client_fqdn*)(buf + offset); + o->hdr.t = OPT_CLIENT_FQDN; + o->hdr.l = htons(hostname_len+2); + o->flags = 0x00; + *o->hostname = hostname_len; + memcpy(o->hostname+1, c->hostname.n, hostname_len); + offset += sizeof(struct opt_hdr) + hostname_len+2; + } + return offset; +} + /** * dhcpv6() - Check if this is a DHCPv6 message, reply as needed * @c: Execution context @@ -549,6 +590,7 @@ int dhcpv6(struct ctx *c, const struct pool *p, n = offsetof(struct resp_t, client_id) + sizeof(struct opt_hdr) + ntohs(client_id->l); n = dhcpv6_dns_fill(c, (char *)&resp, n); + n = dhcpv6_client_fqdn_fill(c, (char*)&resp, n); resp.hdr.xid = mh->xid; diff --git a/passt.h b/passt.h index 72c7f72..d9864e6 100644 --- a/passt.h +++ b/passt.h @@ -205,6 +205,7 @@ struct ip6_ctx { * @ifi4: Index of template interface for IPv4, 0 if IPv4 disabled * @ip: IPv4 configuration * @dns_search: DNS search list + * @hostname: Client hostname * @ifi6: Index of template interface for IPv6, 0 if IPv6 disabled * @ip6: IPv6 configuration * @pasta_ifn: Name of namespace interface for pasta @@ -262,6 +263,7 @@ struct ctx { struct ip4_ctx ip4; struct fqdn dns_search[MAXDNSRCH]; + struct fqdn hostname; unsigned int ifi6; struct ip6_ctx ip6; diff --git a/test/lib/setup b/test/lib/setup index 5338393..9c7aac9 100755 --- a/test/lib/setup +++ b/test/lib/setup @@ -49,7 +49,7 @@ setup_passt() { context_run passt "make clean" context_run passt "make valgrind" - context_run_bg passt "valgrind --max-stackframe=$((4 * 1024 * 1024)) --trace-children=yes --vgdb=no --error-exitcode=1 --suppressions=test/valgrind.supp ./passt ${__opts} -s ${STATESETUP}/passt.socket -f -t 10001 -u 10001 -P ${STATESETUP}/passt.pid" + context_run_bg passt "valgrind --max-stackframe=$((4 * 1024 * 1024)) --trace-children=yes --vgdb=no --error-exitcode=1 --suppressions=test/valgrind.supp ./passt ${__opts} -s ${STATESETUP}/passt.socket -f -t 10001 -u 10001 -H passt1 -P ${STATESETUP}/passt.pid" # pidfile isn't created until passt is listening wait_for [ -f "${STATESETUP}/passt.pid" ] @@ -146,11 +146,11 @@ setup_passt_in_ns() { if [ ${VALGRIND} -eq 1 ]; then context_run passt "make clean" context_run passt "make valgrind" - context_run_bg passt "valgrind --max-stackframe=$((4 * 1024 * 1024)) --trace-children=yes --vgdb=no --error-exitcode=1 --suppressions=test/valgrind.supp ./passt -f ${__opts} -s ${STATESETUP}/passt.socket -t 10001,10011,10021,10031 -u 10001,10011,10021,10031 -P ${STATESETUP}/passt.pid --map-host-loopback ${__map_ns4} --map-host-loopback ${__map_ns6}" + context_run_bg passt "valgrind --max-stackframe=$((4 * 1024 * 1024)) --trace-children=yes --vgdb=no --error-exitcode=1 --suppressions=test/valgrind.supp ./passt -f ${__opts} -s ${STATESETUP}/passt.socket -H passt1 -t 10001,10011,10021,10031 -u 10001,10011,10021,10031 -P ${STATESETUP}/passt.pid --map-host-loopback ${__map_ns4} --map-host-loopback ${__map_ns6}" else context_run passt "make clean" context_run passt "make" - context_run_bg passt "./passt -f ${__opts} -s ${STATESETUP}/passt.socket -t 10001,10011,10021,10031 -u 10001,10011,10021,10031 -P ${STATESETUP}/passt.pid --map-host-loopback ${__map_ns4} --map-host-loopback ${__map_ns6}" + context_run_bg passt "./passt -f ${__opts} -s ${STATESETUP}/passt.socket -H passt1 -t 10001,10011,10021,10031 -u 10001,10011,10021,10031 -P ${STATESETUP}/passt.pid --map-host-loopback ${__map_ns4} --map-host-loopback ${__map_ns6}" fi wait_for [ -f "${STATESETUP}/passt.pid" ] @@ -215,7 +215,7 @@ setup_two_guests() { [ ${DEBUG} -eq 1 ] && __opts="${__opts} -d" [ ${TRACE} -eq 1 ] && __opts="${__opts} --trace" - context_run_bg passt_1 "./passt -s ${STATESETUP}/passt_1.socket -P ${STATESETUP}/passt_1.pid -f ${__opts} -t 10001 -u 10001" + context_run_bg passt_1 "./passt -s ${STATESETUP}/passt_1.socket -P ${STATESETUP}/passt_1.pid -f ${__opts} -H passt1 -t 10001 -u 10001" wait_for [ -f "${STATESETUP}/passt_1.pid" ] __opts= @@ -223,7 +223,7 @@ setup_two_guests() { [ ${DEBUG} -eq 1 ] && __opts="${__opts} -d" [ ${TRACE} -eq 1 ] && __opts="${__opts} --trace" - context_run_bg passt_2 "./passt -s ${STATESETUP}/passt_2.socket -P ${STATESETUP}/passt_2.pid -f ${__opts} -t 10004 -u 10004" + context_run_bg passt_2 "./passt -s ${STATESETUP}/passt_2.socket -P ${STATESETUP}/passt_2.pid -f ${__opts} --hostname passt2 -t 10004 -u 10004" wait_for [ -f "${STATESETUP}/passt_2.pid" ] GUEST_1_CID=94557 diff --git a/test/passt.mbuto b/test/passt.mbuto index 138d365..bcd9041 100755 --- a/test/passt.mbuto +++ b/test/passt.mbuto @@ -55,6 +55,7 @@ set >> \$LOG [ -n "\${new_dhcp6_name_servers}" ] && for d in \${new_dhcp6_name_servers}; do echo "nameserver \${d}%\${interface}" >> /etc/resolv.conf; done [ -n "\${new_dhcp6_domain_search}" ] && (printf "search"; for d in \${new_dhcp6_domain_search}; do printf " %s" "\${d}"; done; printf "\n") >> /etc/resolv.conf [ -n "\${new_host_name}" ] && hostname "\${new_host_name}" +[ -n "\${new_fqdn_hostname}" ] && hostname "\${new_fqdn_hostname}" exit 0 EOF chmod 755 /sbin/dhclient-script diff --git a/test/passt/dhcp b/test/passt/dhcp index 9925ab9..36535f2 100644 --- a/test/passt/dhcp +++ b/test/passt/dhcp @@ -11,7 +11,7 @@ # Copyright (c) 2021 Red Hat GmbH # Author: Stefano Brivio <sbrivio(a)redhat.com> -gtools ip jq dhclient sed tr +gtools ip jq dhclient sed tr hostname htools ip jq sed tr head test Interface name @@ -47,7 +47,12 @@ gout SEARCH sed 's/\. / /g' /etc/resolv.conf | sed 's/\.$//g' | sed -n 's/^searc hout HOST_SEARCH sed 's/\. / /g' /etc/resolv.conf | sed 's/\.$//g' | sed -n 's/^search $.*$/\1/p' | tr ' \n' ',' | sed 's/,$//;s/$/\n/' check [ "__SEARCH__" = "__HOST_SEARCH__" ] +test DHCP: Hostname +gout HOSTNAME hostname +check [ "__HOSTNAME__" = "passt1" ] + test DHCPv6: address +guest hostname none guest /sbin/dhclient -6 __IFNAME__ # Wait for DAD to complete guest while ip -j -6 addr show tentative | jq -e '.[].addr_info'; do sleep 0.1; done @@ -70,3 +75,7 @@ test DHCPv6: search list gout SEARCH6 sed 's/\. / /g' /etc/resolv.conf | sed 's/\.$//g' | sed -n 's/^search $.*$/\1/p' | tr ' \n' ',' | sed 's/,$//;s/$/\n/' hout HOST_SEARCH6 sed 's/\. / /g' /etc/resolv.conf | sed 's/\.$//g' | sed -n 's/^search $.*$/\1/p' | tr ' \n' ',' | sed 's/,$//;s/$/\n/' check [ "__SEARCH6__" = "__HOST_SEARCH6__" ] + +test DHCPv6: Hostname +gout HOSTNAME hostname +check [ "__HOSTNAME__" = "passt1" ] -- 2.47.0

3 7

[PATCH v12 00/10] Add vhost-user support to passt. (part 3)
by Laurent Vivier 18 Nov '24

18 Nov '24

This series of patches adds vhost-user support to passt and then allows passt to connect to QEMU network backend using virtqueue rather than a socket. With QEMU, rather than using to connect: -netdev stream,id=s,server=off,addr.type=unix,addr.path=/tmp/passt_1.socket we will use: -chardev socket,id=chr0,path=/tmp/passt_1.socket -netdev vhost-user,id=netdev0,chardev=chr0 -device virtio-net,netdev=netdev0 -object memory-backend-memfd,id=memfd0,share=on,size=$RAMSIZE -numa node,memdev=memfd0 The memory backend is needed to share data between passt and QEMU. Performance comparison between "-netdev stream" and "-netdev vhost-user": $ iperf3 -c localhost -p 10001 -t 60 -6 -u -b 50G socket: [ 5] 0.00-60.05 sec 95.6 GBytes 13.7 Gbits/sec 0.017 ms 6998988/10132413 (69%) receiver vhost-user: [ 5] 0.00-60.04 sec 237 GBytes 33.9 Gbits/sec 0.006 ms 53673/7813770 (0.69%) receiver $ iperf3 -c localhost -p 10001 -t 60 -4 -u -b 50G socket: [ 5] 0.00-60.05 sec 98.9 GBytes 14.1 Gbits/sec 0.018 ms 6260735/9501832 (66%) receiver vhost-user: [ 5] 0.00-60.05 sec 235 GBytes 33.7 Gbits/sec 0.008 ms 37581/7752699 (0.48%) receiver $ iperf3 -c localhost -p 10001 -t 60 -6 socket: [ 5] 0.00-60.00 sec 17.3 GBytes 2.48 Gbits/sec 0 sender [ 5] 0.00-60.06 sec 17.3 GBytes 2.48 Gbits/sec receiver vhost-user: [ 5] 0.00-60.00 sec 191 GBytes 27.4 Gbits/sec 0 sender [ 5] 0.00-60.05 sec 191 GBytes 27.3 Gbits/sec receiver $ iperf3 -c localhost -p 10001 -t 60 -4 socket: [ 5] 0.00-60.00 sec 15.6 GBytes 2.24 Gbits/sec 0 sender [ 5] 0.00-60.06 sec 15.6 GBytes 2.24 Gbits/sec receiver vhost-user: [ 5] 0.00-60.00 sec 189 GBytes 27.1 Gbits/sec 0 sender [ 5] 0.00-60.04 sec 189 GBytes 27.0 Gbits/sec receiver v12: - rebase - address comments from Stefano v11: - rebase - address comments from David on v10 v10: - rebase v9 on top of my changes - remove last 4 patches from v9 as 'tcp: Pass TCP header and payload separately to tcp_fill_headers[46]()' introduces a regression in "make check" for me. - addressed comments from David - I tried to cleanup iov management, but I was not able to remove the update of the first iov to point to the header or to the data - upd_vu_hdrlen()/tcp_vu_hdrlen() includes now the size of the virtio-net header - I didn't address comments from Stefano. - I didn't fix the bug with seek_offset_cap v9: [David Gibson] - Rebased on current main - Conflicts with v4/v6 buffer merge addressed - Conflicts with TCP options construction rework addressed - Added several cleanup patches on top - Added a number of IOV and buffer cleanups on top - The aim is that these should allow more sharing of logic between the vhost-user and non-vhost-user pathes, although they've only minimally accomplished that so far. v8: - remove iov_size() from vu_collect_one_frame() - move vu_packet_check_range() to vu_common.c - fix UDP when dlen is 0. v7: - rebase - use vu_collect_one_frame() to do vu_collect() (collect multiple frame) - add vhost-user tests from Stefano v6: - rebase - extract 3 patches from "vhost-user: add vhost-user": passt: rename tap_sock_init() to tap_backend_init() tcp: Export headers functions udp: Prepare udp.c to be shared with vhost-user - introduce new functions vu_collect_one_frame(), vu_collect(), vu_set_vnethdr(), vu_flush(), vu_send_single() to be called from tcp_vu.c, udp_vu.c and ICMP/DHCP where vhost-user code was duplicated. v5: - rebase on top of 2024_09_06.6b38f07 - rework udp_vu.c as ref.udp.v6 has been removed and we need to know if we receive IPv4 or IPv6 frame when we prepare the guest buffers for recvmsg() - remove vnet->hdrlen as the size is always the same with virtio-net v1 - address comments from David and Stefano v4: - rebase on top of 2024_08_21.1d6142f (rebasing on top of 620e19a1b48a ("udp: Merge udp[46]_mh_recv arrays") introduces a regression in the measure of the latency with UDP because I think I don't replace correctly ref.udp.v6 that is removed by this commit) - Addressed most of the comments from David and Stefano (I didn't want to postpone this version to next week, so I'll address the remaining comments in the next version). v3: - rebase on top of flow table - update tcp_vu.c to look like udp_vu.c (recv()/prepare()/send_frame()) - address comments from Stefano and David on version 2 v2: - remove PATCH 4 - rewrite PATCH 2 and 3 to follow passt coding style - move some code from PATCH 3 to PATCH 4 (previously PATCH 5) - partially addressed David's comment on PATCH 5 David Gibson (2): tcp_vu: Share more header construction between IPv4 and IPv6 paths tcp: Move tcp_l2_buf_fill_headers() to tcp_buf.c Laurent Vivier (7): packet: replace struct desc by struct iovec vhost-user: introduce virtio API vhost-user: introduce vhost-user API udp: Prepare udp.c to be shared with vhost-user tcp: Export headers functions passt: rename tap_sock_init() to tap_backend_init() vhost-user: add vhost-user Stefano Brivio (1): test: Add tests for passt in vhost-user mode Makefile | 9 +- conf.c | 19 +- epoll_type.h | 4 + iov.c | 1 - isolation.c | 17 +- packet.c | 91 ++-- packet.h | 22 +- passt.1 | 10 +- passt.c | 11 +- passt.h | 7 + pcap.c | 1 - tap.c | 129 ++++-- tap.h | 7 +- tcp.c | 76 +--- tcp_buf.c | 39 +- tcp_internal.h | 19 +- tcp_vu.c | 493 +++++++++++++++++++++ tcp_vu.h | 12 + test/lib/perf_report | 15 + test/lib/setup | 77 +++- test/lib/setup_ugly | 2 +- test/passt_vu | 1 + test/passt_vu_in_ns | 1 + test/perf/passt_vu_tcp | 211 +++++++++ test/perf/passt_vu_udp | 159 +++++++ test/run | 25 ++ test/two_guests_vu | 1 + udp.c | 85 ++-- udp_internal.h | 34 ++ udp_vu.c | 335 ++++++++++++++ udp_vu.h | 13 + util.h | 9 + vhost_user.c | 981 +++++++++++++++++++++++++++++++++++++++++ vhost_user.h | 206 +++++++++ virtio.c | 645 +++++++++++++++++++++++++++ virtio.h | 184 ++++++++ vu_common.c | 285 ++++++++++++ vu_common.h | 60 +++ 38 files changed, 4094 insertions(+), 202 deletions(-) create mode 100644 tcp_vu.c create mode 100644 tcp_vu.h create mode 120000 test/passt_vu create mode 120000 test/passt_vu_in_ns create mode 100644 test/perf/passt_vu_tcp create mode 100644 test/perf/passt_vu_udp create mode 120000 test/two_guests_vu create mode 100644 udp_internal.h create mode 100644 udp_vu.c create mode 100644 udp_vu.h create mode 100644 vhost_user.c create mode 100644 vhost_user.h create mode 100644 virtio.c create mode 100644 virtio.h create mode 100644 vu_common.c create mode 100644 vu_common.h -- 2.47.0

2 13

[PATCH v2] ndp: Don't send unsolicited router advertisement if we can't, yet
by Stefano Brivio 18 Nov '24

18 Nov '24

ndp_timer() is called right away on the first epoll_wait() cycle, when the communication channel to the guest isn't ready yet: 1.0038: NDP: sending unsolicited RA, next in 264s 1.0038: tap: failed to send 1 frames of 1 check that it's up before sending it. This effectively delays the first gratuitous router advertisement, which is probably a good idea given that we expect the guest to send a router solicitation right away. Fixes: 6e1e44293ef9 ("ndp: Send unsolicited Router Advertisements") Signed-off-by: Stefano Brivio <sbrivio(a)redhat.com> --- Oops, I sent a previous/wrong version of the patch as v1. ndp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ndp.c b/ndp.c index 7ee44b2..1752d64 100644 --- a/ndp.c +++ b/ndp.c @@ -391,7 +391,7 @@ void ndp_timer(const struct ctx *c, const struct timespec *now) time_t max_rtr_adv_interval = DEFAULT_MAX_RTR_ADV_INTERVAL; time_t min_rtr_adv_interval, interval; - if (c->no_ra || now->tv_sec < next_ra) + if (c->fd_tap < 0 || c->no_ra || now->tv_sec < next_ra) return; /* We must advertise before the route's lifetime expires */ -- 2.43.0

2 1

[PATCH] ndp: Don't send unsolicited router advertisement if we can't, yet
by Stefano Brivio 15 Nov '24

15 Nov '24

ndp_timer() is called right away on the first epoll_wait() cycle, when the communication channel to the guest isn't ready yet: 1.0038: NDP: sending unsolicited RA, next in 264s 1.0038: tap: failed to send 1 frames of 1 check that it's up before sending it. This effectively delays the first gratuitous router advertisement, which is probably a good idea given that we expect the guest to send a router solicitation right away. Fixes: 6e1e44293ef9 ("ndp: Send unsolicited Router Advertisements") Signed-off-by: Stefano Brivio <sbrivio(a)redhat.com> --- ndp.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/ndp.c b/ndp.c index 7ee44b2..b458785 100644 --- a/ndp.c +++ b/ndp.c @@ -420,9 +420,12 @@ void ndp_timer(const struct ctx *c, const struct timespec *now) interval = min_rtr_adv_interval + random() % (max_rtr_adv_interval - min_rtr_adv_interval); - info("NDP: sending unsolicited RA, next in %llds", (long long)interval); + if (next_ra) { + info("NDP: sending unsolicited RA, next in %llds", + (long long)interval); - ndp_ra(c, &in6addr_ll_all_nodes); + ndp_ra(c, &in6addr_ll_all_nodes); + } next_ra = now->tv_sec + interval; } -- 2.43.0

1 0

[PATCH v11 00/10] Add vhost-user support to passt. (part 3)
by Laurent Vivier 15 Nov '24

15 Nov '24

This series of patches adds vhost-user support to passt and then allows passt to connect to QEMU network backend using virtqueue rather than a socket. With QEMU, rather than using to connect: -netdev stream,id=s,server=off,addr.type=unix,addr.path=/tmp/passt_1.socket we will use: -chardev socket,id=chr0,path=/tmp/passt_1.socket -netdev vhost-user,id=netdev0,chardev=chr0 -device virtio-net,netdev=netdev0 -object memory-backend-memfd,id=memfd0,share=on,size=$RAMSIZE -numa node,memdev=memfd0 The memory backend is needed to share data between passt and QEMU. Performance comparison between "-netdev stream" and "-netdev vhost-user": $ iperf3 -c localhost -p 10001 -t 60 -6 -u -b 50G socket: [ 5] 0.00-60.05 sec 95.6 GBytes 13.7 Gbits/sec 0.017 ms 6998988/10132413 (69%) receiver vhost-user: [ 5] 0.00-60.04 sec 237 GBytes 33.9 Gbits/sec 0.006 ms 53673/7813770 (0.69%) receiver $ iperf3 -c localhost -p 10001 -t 60 -4 -u -b 50G socket: [ 5] 0.00-60.05 sec 98.9 GBytes 14.1 Gbits/sec 0.018 ms 6260735/9501832 (66%) receiver vhost-user: [ 5] 0.00-60.05 sec 235 GBytes 33.7 Gbits/sec 0.008 ms 37581/7752699 (0.48%) receiver $ iperf3 -c localhost -p 10001 -t 60 -6 socket: [ 5] 0.00-60.00 sec 17.3 GBytes 2.48 Gbits/sec 0 sender [ 5] 0.00-60.06 sec 17.3 GBytes 2.48 Gbits/sec receiver vhost-user: [ 5] 0.00-60.00 sec 191 GBytes 27.4 Gbits/sec 0 sender [ 5] 0.00-60.05 sec 191 GBytes 27.3 Gbits/sec receiver $ iperf3 -c localhost -p 10001 -t 60 -4 socket: [ 5] 0.00-60.00 sec 15.6 GBytes 2.24 Gbits/sec 0 sender [ 5] 0.00-60.06 sec 15.6 GBytes 2.24 Gbits/sec receiver vhost-user: [ 5] 0.00-60.00 sec 189 GBytes 27.1 Gbits/sec 0 sender [ 5] 0.00-60.04 sec 189 GBytes 27.0 Gbits/sec receiver v11: - rebase - address comments from David on v10 v10: - rebase v9 on top of my changes - remove last 4 patches from v9 as 'tcp: Pass TCP header and payload separately to tcp_fill_headers[46]()' introduces a regression in "make check" for me. - addressed comments from David - I tried to cleanup iov management, but I was not able to remove the update of the first iov to point to the header or to the data - upd_vu_hdrlen()/tcp_vu_hdrlen() includes now the size of the virtio-net header - I didn't address comments from Stefano. - I didn't fix the bug with seek_offset_cap v9: [David Gibson] - Rebased on current main - Conflicts with v4/v6 buffer merge addressed - Conflicts with TCP options construction rework addressed - Added several cleanup patches on top - Added a number of IOV and buffer cleanups on top - The aim is that these should allow more sharing of logic between the vhost-user and non-vhost-user pathes, although they've only minimally accomplished that so far. v8: - remove iov_size() from vu_collect_one_frame() - move vu_packet_check_range() to vu_common.c - fix UDP when dlen is 0. v7: - rebase - use vu_collect_one_frame() to do vu_collect() (collect multiple frame) - add vhost-user tests from Stefano v6: - rebase - extract 3 patches from "vhost-user: add vhost-user": passt: rename tap_sock_init() to tap_backend_init() tcp: Export headers functions udp: Prepare udp.c to be shared with vhost-user - introduce new functions vu_collect_one_frame(), vu_collect(), vu_set_vnethdr(), vu_flush(), vu_send_single() to be called from tcp_vu.c, udp_vu.c and ICMP/DHCP where vhost-user code was duplicated. v5: - rebase on top of 2024_09_06.6b38f07 - rework udp_vu.c as ref.udp.v6 has been removed and we need to know if we receive IPv4 or IPv6 frame when we prepare the guest buffers for recvmsg() - remove vnet->hdrlen as the size is always the same with virtio-net v1 - address comments from David and Stefano v4: - rebase on top of 2024_08_21.1d6142f (rebasing on top of 620e19a1b48a ("udp: Merge udp[46]_mh_recv arrays") introduces a regression in the measure of the latency with UDP because I think I don't replace correctly ref.udp.v6 that is removed by this commit) - Addressed most of the comments from David and Stefano (I didn't want to postpone this version to next week, so I'll address the remaining comments in the next version). v3: - rebase on top of flow table - update tcp_vu.c to look like udp_vu.c (recv()/prepare()/send_frame()) - address comments from Stefano and David on version 2 v2: - remove PATCH 4 - rewrite PATCH 2 and 3 to follow passt coding style - move some code from PATCH 3 to PATCH 4 (previously PATCH 5) - partially addressed David's comment on PATCH 5 David Gibson (2): tcp_vu: Share more header construction between IPv4 and IPv6 paths tcp: Move tcp_l2_buf_fill_headers() to tcp_buf.c Laurent Vivier (7): packet: replace struct desc by struct iovec vhost-user: introduce virtio API vhost-user: introduce vhost-user API udp: Prepare udp.c to be shared with vhost-user tcp: Export headers functions passt: rename tap_sock_init() to tap_backend_init() vhost-user: add vhost-user Stefano Brivio (1): test: Add tests for passt in vhost-user mode Makefile | 9 +- conf.c | 21 +- epoll_type.h | 4 + iov.c | 1 - isolation.c | 17 +- packet.c | 91 ++-- packet.h | 22 +- passt.1 | 10 +- passt.c | 11 +- passt.h | 7 + pcap.c | 1 - tap.c | 129 ++++-- tap.h | 7 +- tcp.c | 76 +--- tcp_buf.c | 39 +- tcp_internal.h | 19 +- tcp_vu.c | 494 +++++++++++++++++++++ tcp_vu.h | 12 + test/lib/perf_report | 15 + test/lib/setup | 77 +++- test/lib/setup_ugly | 2 +- test/passt_vu | 1 + test/passt_vu_in_ns | 1 + test/perf/passt_vu_tcp | 211 +++++++++ test/perf/passt_vu_udp | 159 +++++++ test/run | 25 ++ test/two_guests_vu | 1 + udp.c | 85 ++-- udp_internal.h | 34 ++ udp_vu.c | 336 ++++++++++++++ udp_vu.h | 13 + util.h | 9 + vhost_user.c | 981 +++++++++++++++++++++++++++++++++++++++++ vhost_user.h | 206 +++++++++ virtio.c | 660 +++++++++++++++++++++++++++ virtio.h | 184 ++++++++ vu_common.c | 285 ++++++++++++ vu_common.h | 60 +++ 38 files changed, 4113 insertions(+), 202 deletions(-) create mode 100644 tcp_vu.c create mode 100644 tcp_vu.h create mode 120000 test/passt_vu create mode 120000 test/passt_vu_in_ns create mode 100644 test/perf/passt_vu_tcp create mode 100644 test/perf/passt_vu_udp create mode 120000 test/two_guests_vu create mode 100644 udp_internal.h create mode 100644 udp_vu.c create mode 100644 udp_vu.h create mode 100644 vhost_user.c create mode 100644 vhost_user.h create mode 100644 virtio.c create mode 100644 virtio.h create mode 100644 vu_common.c create mode 100644 vu_common.h -- 2.47.0

2 13

[PATCH v8 0/8] Add vhost-user support to passt. (part 3)
by Laurent Vivier 15 Nov '24

15 Nov '24

This series of patches adds vhost-user support to passt and then allows passt to connect to QEMU network backend using virtqueue rather than a socket. With QEMU, rather than using to connect: -netdev stream,id=s,server=off,addr.type=unix,addr.path=/tmp/passt_1.socket we will use: -chardev socket,id=chr0,path=/tmp/passt_1.socket -netdev vhost-user,id=netdev0,chardev=chr0 -device virtio-net,netdev=netdev0 -object memory-backend-memfd,id=memfd0,share=on,size=$RAMSIZE -numa node,memdev=memfd0 The memory backend is needed to share data between passt and QEMU. Performance comparison between "-netdev stream" and "-netdev vhost-user": $ iperf3 -c localhost -p 10001 -t 60 -6 -u -b 50G socket: [ 5] 0.00-60.05 sec 95.6 GBytes 13.7 Gbits/sec 0.017 ms 6998988/10132413 (69%) receiver vhost-user: [ 5] 0.00-60.04 sec 237 GBytes 33.9 Gbits/sec 0.006 ms 53673/7813770 (0.69%) receiver $ iperf3 -c localhost -p 10001 -t 60 -4 -u -b 50G socket: [ 5] 0.00-60.05 sec 98.9 GBytes 14.1 Gbits/sec 0.018 ms 6260735/9501832 (66%) receiver vhost-user: [ 5] 0.00-60.05 sec 235 GBytes 33.7 Gbits/sec 0.008 ms 37581/7752699 (0.48%) receiver $ iperf3 -c localhost -p 10001 -t 60 -6 socket: [ 5] 0.00-60.00 sec 17.3 GBytes 2.48 Gbits/sec 0 sender [ 5] 0.00-60.06 sec 17.3 GBytes 2.48 Gbits/sec receiver vhost-user: [ 5] 0.00-60.00 sec 191 GBytes 27.4 Gbits/sec 0 sender [ 5] 0.00-60.05 sec 191 GBytes 27.3 Gbits/sec receiver $ iperf3 -c localhost -p 10001 -t 60 -4 socket: [ 5] 0.00-60.00 sec 15.6 GBytes 2.24 Gbits/sec 0 sender [ 5] 0.00-60.06 sec 15.6 GBytes 2.24 Gbits/sec receiver vhost-user: [ 5] 0.00-60.00 sec 189 GBytes 27.1 Gbits/sec 0 sender [ 5] 0.00-60.04 sec 189 GBytes 27.0 Gbits/sec receiver v8: - remove iov_size() from vu_collect_one_frame() - move vu_packet_check_range() to vu_common.c - fix UDP when dlen is 0. v7: - rebase - use vu_collect_one_frame() to do vu_collect() (collect multiple frame) - add vhost-user tests from Stefano v6: - rebase - extract 3 patches from "vhost-user: add vhost-user": passt: rename tap_sock_init() to tap_backend_init() tcp: Export headers functions udp: Prepare udp.c to be shared with vhost-user - introduce new functions vu_collect_one_frame(), vu_collect(), vu_set_vnethdr(), vu_flush(), vu_send_single() to be called from tcp_vu.c, udp_vu.c and ICMP/DHCP where vhost-user code was duplicated. v5: - rebase on top of 2024_09_06.6b38f07 - rework udp_vu.c as ref.udp.v6 has been removed and we need to know if we receive IPv4 or IPv6 frame when we prepare the guest buffers for recvmsg() - remove vnet->hdrlen as the size is always the same with virtio-net v1 - address comments from David and Stefano v4: - rebase on top of 2024_08_21.1d6142f (rebasing on top of 620e19a1b48a ("udp: Merge udp[46]_mh_recv arrays") introduces a regression in the measure of the latency with UDP because I think I don't replace correctly ref.udp.v6 that is removed by this commit) - Addressed most of the comments from David and Stefano (I didn't want to postpone this version to next week, so I'll address the remaining comments in the next version). v3: - rebase on top of flow table - update tcp_vu.c to look like udp_vu.c (recv()/prepare()/send_frame()) - address comments from Stefano and David on version 2 v2: - remove PATCH 4 - rewrite PATCH 2 and 3 to follow passt coding style - move some code from PATCH 3 to PATCH 4 (previously PATCH 5) - partially addressed David's comment on PATCH 5 Laurent Vivier (7): packet: replace struct desc by struct iovec vhost-user: introduce virtio API vhost-user: introduce vhost-user API udp: Prepare udp.c to be shared with vhost-user tcp: Export headers functions passt: rename tap_sock_init() to tap_backend_init() vhost-user: add vhost-user Stefano Brivio (1): test: Add tests for passt in vhost-user mode Makefile | 9 +- conf.c | 21 +- epoll_type.h | 4 + iov.c | 1 - isolation.c | 15 +- packet.c | 91 ++-- packet.h | 22 +- passt.1 | 10 +- passt.c | 11 +- passt.h | 6 + pcap.c | 1 - tap.c | 128 ++++-- tap.h | 7 +- tcp.c | 37 +- tcp_internal.h | 15 + tcp_vu.c | 476 ++++++++++++++++++++ tcp_vu.h | 12 + test/lib/perf_report | 15 + test/lib/setup | 77 +++- test/lib/setup_ugly | 2 +- test/passt_vu | 1 + test/passt_vu_in_ns | 1 + test/perf/passt_vu_tcp | 211 +++++++++ test/perf/passt_vu_udp | 159 +++++++ test/run | 25 ++ test/two_guests_vu | 1 + udp.c | 84 ++-- udp_internal.h | 34 ++ udp_vu.c | 336 ++++++++++++++ udp_vu.h | 13 + util.h | 8 + vhost_user.c | 977 +++++++++++++++++++++++++++++++++++++++++ vhost_user.h | 206 +++++++++ virtio.c | 660 ++++++++++++++++++++++++++++ virtio.h | 184 ++++++++ vu_common.c | 385 ++++++++++++++++ vu_common.h | 47 ++ 37 files changed, 4138 insertions(+), 154 deletions(-) create mode 100644 tcp_vu.c create mode 100644 tcp_vu.h create mode 120000 test/passt_vu create mode 120000 test/passt_vu_in_ns create mode 100644 test/perf/passt_vu_tcp create mode 100644 test/perf/passt_vu_udp create mode 120000 test/two_guests_vu create mode 100644 udp_internal.h create mode 100644 udp_vu.c create mode 100644 udp_vu.h create mode 100644 vhost_user.c create mode 100644 vhost_user.h create mode 100644 virtio.c create mode 100644 virtio.h create mode 100644 vu_common.c create mode 100644 vu_common.h -- 2.46.2

3 49

[PATCH] selinux: Use auth_read_passwd() interface for all our getpwnam() needs
by Stefano Brivio 14 Nov '24

14 Nov '24

If passt or pasta are started as root, we need to read the passwd file (be it /etc/passwd or whatever sssd provides) to find out UID and GID of 'nobody' so that we can switch to it. Instead of a bunch of allow rules for passwd_file_t and sssd macros, use the more convenient auth_read_passwd() interface which should cover our usage of getpwnam(). The existing rules weren't actually enough: # strace -e openat passt -f [...] Started as root, will change to nobody. openat(AT_FDCWD, "/etc/nsswitch.conf", O_RDONLY|O_CLOEXEC) = 4 openat(AT_FDCWD, "/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 4 openat(AT_FDCWD, "/lib64/libnss_sss.so.2", O_RDONLY|O_CLOEXEC) = 4 openat(AT_FDCWD, "/var/lib/sss/mc/passwd", O_RDONLY|O_CLOEXEC) = -1 EACCES (Permission denied) openat(AT_FDCWD, "/var/lib/sss/mc/passwd", O_RDONLY|O_CLOEXEC) = -1 EACCES (Permission denied) openat(AT_FDCWD, "/etc/passwd", O_RDONLY|O_CLOEXEC) = 4 with corresponding SELinux warnings logged in audit.log. Reported-by: Minxi Hou <mhou(a)redhat.com> Analysed-by: Miloš Malik <mmalik(a)redhat.com> Signed-off-by: Stefano Brivio <sbrivio(a)redhat.com> --- contrib/selinux/passt.te | 5 +---- contrib/selinux/pasta.te | 9 +-------- 2 files changed, 2 insertions(+), 12 deletions(-) diff --git a/contrib/selinux/passt.te b/contrib/selinux/passt.te index 80bf780..c6cea34 100644 --- a/contrib/selinux/passt.te +++ b/contrib/selinux/passt.te @@ -47,8 +47,6 @@ require { type port_t; type http_port_t; - type passwd_file_t; - class netlink_route_socket { bind create nlmsg_read }; type sysctl_net_t; @@ -96,8 +94,7 @@ allow passt_t self:capability { sys_tty_config setpcap net_bind_service setuid s allow passt_t self:cap_userns { setpcap sys_admin sys_ptrace }; allow passt_t self:user_namespace create; -allow passt_t passwd_file_t:file read_file_perms; -sssd_search_lib(passt_t) +auth_read_passwd(passt_t) allow passt_t proc_net_t:file read; allow passt_t net_conf_t:file { open read }; diff --git a/contrib/selinux/pasta.te b/contrib/selinux/pasta.te index 310383c..69be081 100644 --- a/contrib/selinux/pasta.te +++ b/contrib/selinux/pasta.te @@ -68,9 +68,6 @@ require { type system_dbusd_t; type systemd_hostnamed_t; type systemd_systemctl_exec_t; - type passwd_file_t; - type sssd_public_t; - type sssd_var_lib_t; class dbus send_msg; class system module_request; class system status; @@ -115,8 +112,7 @@ allow pasta_t self:capability { setpcap net_bind_service sys_tty_config dac_read allow pasta_t self:cap_userns { setpcap sys_admin sys_ptrace net_admin net_bind_service }; allow pasta_t self:user_namespace create; -allow pasta_t passwd_file_t:file read_file_perms; -sssd_search_lib(pasta_t) +auth_read_passwd(pasta_t) domain_auto_trans(pasta_t, bin_t, unconfined_t); domain_auto_trans(pasta_t, shell_exec_t, unconfined_t); @@ -178,12 +174,9 @@ allow pasta_t init_t:system status; allow pasta_t unconfined_t:dir search; allow pasta_t unconfined_t:file read; allow pasta_t unconfined_t:lnk_file read; -allow pasta_t passwd_file_t:file { getattr open read }; allow pasta_t self:process { setpgid setcap }; allow pasta_t shell_exec_t:file { execute execute_no_trans map }; -allow pasta_t sssd_var_lib_t:dir search; -allow pasta_t sssd_public_t:dir search; allow pasta_t hostname_exec_t:file { execute execute_no_trans getattr open read map }; allow pasta_t system_dbusd_t:unix_stream_socket connectto; allow pasta_t system_dbusd_t:dbus send_msg; -- 2.43.0

1 0

[PATCH v2 0/8] ndp: Unsolicited RAs
by David Gibson 14 Nov '24

14 Nov '24

The default route a guest obtains via NDP has an expiry. We set this to the maximum allowed, 65535s (about 18 hours). We missed, however, that after that expiry, the guest won't send a new Router Solicitation. Instead it expects an unsolicited Router Advertisement to have come at some point before the expiry. This means that on an IPv6 setup, the default will disappear after 18 hours. Correct this by sending unsolicited Router Advertisements as required by RFC 4861. Along the way we make a number of small cleanups to the NDP code. Link: https://github.com/kubevirt/kubevirt/issues/13191 v2: * Some minor stylistic fixes * Use srandom() * Better explanation of the random requirements for the RAs David Gibson (8): ndp: Remove redundant update to addr_seen ndp: Add ndp_send() helper ndp: Split out helpers for sending specific NDP message types ndp: Use struct assignment in preference to memcpy() for IPv6 addresses ndp: Make route lifetime a #define util: Add general low-level random bytes helper passt: Seed libc's pseudo random number generator ndp: Send unsolicited Router Advertisements ip.h | 9 +++ ndp.c | 219 +++++++++++++++++++++++++++++++++++++------------------- ndp.h | 7 +- passt.c | 42 ++++------- util.c | 54 ++++++++++++++ util.h | 2 + 6 files changed, 228 insertions(+), 105 deletions(-) -- 2.47.0

2 9

[PATCH v10 00/12] Add vhost-user support to passt. (part 3)
by Laurent Vivier 14 Nov '24

14 Nov '24

This series of patches adds vhost-user support to passt and then allows passt to connect to QEMU network backend using virtqueue rather than a socket. With QEMU, rather than using to connect: -netdev stream,id=s,server=off,addr.type=unix,addr.path=/tmp/passt_1.socket we will use: -chardev socket,id=chr0,path=/tmp/passt_1.socket -netdev vhost-user,id=netdev0,chardev=chr0 -device virtio-net,netdev=netdev0 -object memory-backend-memfd,id=memfd0,share=on,size=$RAMSIZE -numa node,memdev=memfd0 The memory backend is needed to share data between passt and QEMU. Performance comparison between "-netdev stream" and "-netdev vhost-user": $ iperf3 -c localhost -p 10001 -t 60 -6 -u -b 50G socket: [ 5] 0.00-60.05 sec 95.6 GBytes 13.7 Gbits/sec 0.017 ms 6998988/10132413 (69%) receiver vhost-user: [ 5] 0.00-60.04 sec 237 GBytes 33.9 Gbits/sec 0.006 ms 53673/7813770 (0.69%) receiver $ iperf3 -c localhost -p 10001 -t 60 -4 -u -b 50G socket: [ 5] 0.00-60.05 sec 98.9 GBytes 14.1 Gbits/sec 0.018 ms 6260735/9501832 (66%) receiver vhost-user: [ 5] 0.00-60.05 sec 235 GBytes 33.7 Gbits/sec 0.008 ms 37581/7752699 (0.48%) receiver $ iperf3 -c localhost -p 10001 -t 60 -6 socket: [ 5] 0.00-60.00 sec 17.3 GBytes 2.48 Gbits/sec 0 sender [ 5] 0.00-60.06 sec 17.3 GBytes 2.48 Gbits/sec receiver vhost-user: [ 5] 0.00-60.00 sec 191 GBytes 27.4 Gbits/sec 0 sender [ 5] 0.00-60.05 sec 191 GBytes 27.3 Gbits/sec receiver $ iperf3 -c localhost -p 10001 -t 60 -4 socket: [ 5] 0.00-60.00 sec 15.6 GBytes 2.24 Gbits/sec 0 sender [ 5] 0.00-60.06 sec 15.6 GBytes 2.24 Gbits/sec receiver vhost-user: [ 5] 0.00-60.00 sec 189 GBytes 27.1 Gbits/sec 0 sender [ 5] 0.00-60.04 sec 189 GBytes 27.0 Gbits/sec receiver v10: - rebase v9 on top of my changes - remove last 4 patches from v9 as 'tcp: Pass TCP header and payload separately to tcp_fill_headers[46]()' introduces a regression in "make check" for me. - addressed comments from David - I tried to cleanup iov management, but I was not able to remove the update of the first iov to point to the header or to the data - upd_vu_hdrlen()/tcp_vu_hdrlen() includes now the size of the virtio-net header - I didn't address comments from Stefano. - I didn't fix the bug with seek_offset_cap v9: [David Gibson] - Rebased on current main - Conflicts with v4/v6 buffer merge addressed - Conflicts with TCP options construction rework addressed - Added several cleanup patches on top - Added a number of IOV and buffer cleanups on top - The aim is that these should allow more sharing of logic between the vhost-user and non-vhost-user pathes, although they've only minimally accomplished that so far. v8: - remove iov_size() from vu_collect_one_frame() - move vu_packet_check_range() to vu_common.c - fix UDP when dlen is 0. v7: - rebase - use vu_collect_one_frame() to do vu_collect() (collect multiple frame) - add vhost-user tests from Stefano v6: - rebase - extract 3 patches from "vhost-user: add vhost-user": passt: rename tap_sock_init() to tap_backend_init() tcp: Export headers functions udp: Prepare udp.c to be shared with vhost-user - introduce new functions vu_collect_one_frame(), vu_collect(), vu_set_vnethdr(), vu_flush(), vu_send_single() to be called from tcp_vu.c, udp_vu.c and ICMP/DHCP where vhost-user code was duplicated. v5: - rebase on top of 2024_09_06.6b38f07 - rework udp_vu.c as ref.udp.v6 has been removed and we need to know if we receive IPv4 or IPv6 frame when we prepare the guest buffers for recvmsg() - remove vnet->hdrlen as the size is always the same with virtio-net v1 - address comments from David and Stefano v4: - rebase on top of 2024_08_21.1d6142f (rebasing on top of 620e19a1b48a ("udp: Merge udp[46]_mh_recv arrays") introduces a regression in the measure of the latency with UDP because I think I don't replace correctly ref.udp.v6 that is removed by this commit) - Addressed most of the comments from David and Stefano (I didn't want to postpone this version to next week, so I'll address the remaining comments in the next version). v3: - rebase on top of flow table - update tcp_vu.c to look like udp_vu.c (recv()/prepare()/send_frame()) - address comments from Stefano and David on version 2 v2: - remove PATCH 4 - rewrite PATCH 2 and 3 to follow passt coding style - move some code from PATCH 3 to PATCH 4 (previously PATCH 5) - partially addressed David's comment on PATCH 5 David Gibson (4): tcp: Use only netinet/tcp.h instead of linux/tcp.h tcp_vu: Share more header construction between IPv4 and IPv6 paths tcp: Move tcp_l2_buf_fill_headers() to tcp_buf.c tcp: Adjust iov_len before filling headers Laurent Vivier (7): packet: replace struct desc by struct iovec vhost-user: introduce virtio API vhost-user: introduce vhost-user API udp: Prepare udp.c to be shared with vhost-user tcp: Export headers functions passt: rename tap_sock_init() to tap_backend_init() vhost-user: add vhost-user Stefano Brivio (1): test: Add tests for passt in vhost-user mode Makefile | 9 +- conf.c | 21 +- epoll_type.h | 4 + iov.c | 1 - isolation.c | 17 +- packet.c | 91 ++-- packet.h | 22 +- passt.1 | 10 +- passt.c | 11 +- passt.h | 7 + pcap.c | 1 - tap.c | 129 ++++-- tap.h | 7 +- tcp.c | 76 +--- tcp_buf.c | 41 +- tcp_internal.h | 19 +- tcp_vu.c | 498 +++++++++++++++++++++ tcp_vu.h | 12 + test/lib/perf_report | 15 + test/lib/setup | 77 +++- test/lib/setup_ugly | 2 +- test/passt_vu | 1 + test/passt_vu_in_ns | 1 + test/perf/passt_vu_tcp | 211 +++++++++ test/perf/passt_vu_udp | 159 +++++++ test/run | 25 ++ test/two_guests_vu | 1 + udp.c | 85 ++-- udp_internal.h | 34 ++ udp_vu.c | 336 ++++++++++++++ udp_vu.h | 13 + util.h | 8 + vhost_user.c | 981 +++++++++++++++++++++++++++++++++++++++++ vhost_user.h | 206 +++++++++ virtio.c | 660 +++++++++++++++++++++++++++ virtio.h | 184 ++++++++ vu_common.c | 285 ++++++++++++ vu_common.h | 60 +++ 38 files changed, 4116 insertions(+), 204 deletions(-) create mode 100644 tcp_vu.c create mode 100644 tcp_vu.h create mode 120000 test/passt_vu create mode 120000 test/passt_vu_in_ns create mode 100644 test/perf/passt_vu_tcp create mode 100644 test/perf/passt_vu_udp create mode 120000 test/two_guests_vu create mode 100644 udp_internal.h create mode 100644 udp_vu.c create mode 100644 udp_vu.h create mode 100644 vhost_user.c create mode 100644 vhost_user.h create mode 100644 virtio.c create mode 100644 virtio.h create mode 100644 vu_common.c create mode 100644 vu_common.h -- 2.47.0

3 18

2024

2023

2022

2021

dev