From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id B0C8B40825C for ; Tue, 24 Mar 2026 17:48:09 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1774374489; cv=none; b=jp9bc8QvgWd0XUV9mGOP6FCRk0cYVAsoUIfwquYr4YdMqMOGgg16mTDr9oTALWa7JOl0fTKgSl/MPQJnEowjn5GPzzRT/vQNwoA5dWGCHeq+gTPUFwE4ampdO8QSvBhWhVUW+06O9+8iGQZPfDbAXFMj2u15llz8EuxcOKvQCa0= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1774374489; c=relaxed/simple; bh=Q3BIh9qqJsKZ390EM//PER572SaAlm3A/Oyw5ISIYrw=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=DSoJOC6SsHhmSwY8mUhJDRYhliTJdRlvJMVC4XrF2UrTuWd35HaLiJXs3pcLjHCiJpP5g+pPnkVMlX7fMOtn0OfY0yRK6PWMFp93jiDaFJ8HSCrw8hS22fH2A6R3Aq9ZHUYT/mBRNKM+d+6U60iEcG3GlrOqQ7fzXs/XtcZ6G5I= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=Fv7zsCTx; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="Fv7zsCTx" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 0D376C19424; Tue, 24 Mar 2026 17:48:06 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1774374489; bh=Q3BIh9qqJsKZ390EM//PER572SaAlm3A/Oyw5ISIYrw=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=Fv7zsCTx80QccRXrThXaHBLVOXhFhR79mnEwLsbRKX5jKLfpFmi85AfwNMhUnuXzN pGB0Cf4/AxjqwGGz466nhe9ZqZhpWrw4C32H4i7j11Rvbo58sDyu2ZeQDMsCFPqzqQ WMikjqZy40fmrZzeHOseOfC7a4QGw5+wEql4rkfYCjEAE/kxdSXZzY9ZDVR+TMxjVN 8g05nfJ61pDmNLoSp2m2ixDknWxNKEUgjGX4Y7Y6nhqJo5uuNqHNXrbk+x98V2NDFO lDQwc4ClXsArDqY7RWHt9xY3xFZ7RQ5HCoZ6i5TN+Efpm4vH8Fo3HGEInaCAL2LlwL m6nvEkg5kqglw== From: hawk@kernel.org To: netdev@vger.kernel.org Cc: hawk@kernel.org, andrew+netdev@lunn.ch, davem@davemloft.net, edumazet@google.com, kuba@kernel.org, pabeni@redhat.com, horms@kernel.org, jhs@mojatatu.com, jiri@resnulli.us, j.koeppeler@tu-berlin.de, kernel-team@cloudflare.com Subject: [PATCH net-next 5/5] selftests: net: add veth BQL stress test Date: Tue, 24 Mar 2026 18:47:04 +0100 Message-ID: <20260324174719.1224337-7-hawk@kernel.org> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20260324174719.1224337-1-hawk@kernel.org> References: <20260324174719.1224337-1-hawk@kernel.org> Precedence: bulk X-Mailing-List: netdev@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit From: Jesper Dangaard Brouer Add a selftest that exercises veth's BQL (Byte Queue Limits) code path under sustained UDP load. The test creates a veth pair with GRO enabled (activating the NAPI path and BQL), attaches a qdisc, optionally loads iptables rules in the consumer namespace to slow NAPI processing, and floods UDP packets for a configurable duration. The test serves two purposes: benchmarking BQL's latency impact under configurable load (iptables rules, qdisc type and parameters), and detecting kernel BUG/Oops from DQL accounting mismatches. It monitors dmesg throughout the run and reports PASS/FAIL via kselftest (lib.sh). Diagnostic output is printed every 5 seconds: - BQL sysfs inflight/limit and watchdog tx_timeout counter - qdisc stats: packets, drops, requeues, backlog, qlen, overlimits - consumer PPS and NAPI-64 cycle time (shows fq_codel target impact) - sink PPS (per-period delta), latency min/avg/max (stddev at exit) - ping RTT to measure latency under load Generating enough traffic to fill the 256-entry ptr_ring requires care: the UDP sendto() path charges each SKB to sk_wmem_alloc, and the SKB stays charged (via sock_wfree destructor) until the consumer NAPI thread finishes processing it -- including any iptables rules in the receive path. With the default sk_sndbuf (~208KB from wmem_default), only ~93 packets can be in-flight before sendto(MSG_DONTWAIT) returns EAGAIN. Since 93 < 256 ring entries, the ring never fills and no backpressure occurs. The test raises wmem_max via sysctl and sets SO_SNDBUF=1MB on the flood socket to remove this bottleneck. An earlier multi-namespace routing approach avoided this limit because ip_forward creates new SKBs detached from the sender's socket. The --bql-disable option (sets limit_min=1GB) enables A/B comparison. Typical results with --nrules 6000 --qdisc-opts 'target 2ms interval 20ms': fq_codel + BQL disabled: ping RTT ~10.8ms, 15% loss, 400KB in ptr_ring fq_codel + BQL enabled: ping RTT ~0.6ms, 0% loss, 4KB in ptr_ring Both cases show identical consumer speed (~20Kpps) and fq_codel drops (~255K), proving the improvement comes purely from where packets buffer. BQL moves buffering from the ptr_ring into the qdisc, where AQM (fq_codel/CAKE) can act on it -- eliminating the "dark buffer" that hides congestion from the scheduler. The --qdisc-replace mode cycles through sfq/pfifo/fq_codel/noqueue under active traffic to verify that stale BQL state (STACK_XOFF) is properly handled during live qdisc transitions. A companion wrapper (veth_bql_test_virtme.sh) launches the test inside a virtme-ng VM, with .config validation to prevent silent stalls. Usage: sudo ./veth_bql_test.sh [--duration 300] [--nrules 100] [--qdisc sfq] [--qdisc-opts '...'] [--bql-disable] [--normal-napi] [--qdisc-replace] Signed-off-by: Jesper Dangaard Brouer Tested-by: Jonas Köppeler --- tools/testing/selftests/net/veth_bql_test.sh | 784 ++++++++++++++++++ .../selftests/net/veth_bql_test_virtme.sh | 124 +++ 2 files changed, 908 insertions(+) create mode 100755 tools/testing/selftests/net/veth_bql_test.sh create mode 100755 tools/testing/selftests/net/veth_bql_test_virtme.sh diff --git a/tools/testing/selftests/net/veth_bql_test.sh b/tools/testing/selftests/net/veth_bql_test.sh new file mode 100755 index 000000000000..9b5923341040 --- /dev/null +++ b/tools/testing/selftests/net/veth_bql_test.sh @@ -0,0 +1,784 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Veth BQL (Byte Queue Limits) stress test and A/B benchmarking tool. +# +# Creates a veth pair with GRO on and TSO off (ensures all packets use +# the NAPI/ptr_ring path where BQL operates), attaches a configurable +# qdisc, optionally loads iptables rules to slow the consumer NAPI +# processing, and floods UDP packets at maximum rate. +# +# Primary uses: +# 1) A/B comparison of latency with/without BQL (--bql-disable flag) +# 2) Testing different qdiscs and their parameters (--qdisc, --qdisc-opts) +# 3) Detecting kernel BUG/Oops from DQL accounting mismatches +# +# Key design detail -- SO_SNDBUF and wmem_max: +# The UDP sendto() path charges each SKB to the socket's sk_wmem_alloc +# counter. The SKB carries a destructor (sock_wfree) that releases the +# charge only after the consumer NAPI thread on the peer veth finishes +# processing it -- including any iptables rules in the receive path. +# With the default sk_sndbuf (~208KB from wmem_default), only ~93 +# packets (1442B each) can be in-flight before sendto() returns EAGAIN. +# Since 93 < 256 ptr_ring entries, the ring never fills and no qdisc +# backpressure occurs. The test temporarily raises the global wmem_max +# sysctl and sets SO_SNDBUF=1MB to allow enough in-flight SKBs to +# saturate the ptr_ring. The original wmem_max is restored on exit. +# +# Two TX-stop mechanisms and the dark-buffer problem: +# DRV_XOFF backpressure (commit dc82a33297fc) stops the TX queue when +# the 256-entry ptr_ring is full. The queue is released at the end of +# veth_poll() (commit 5442a9da6978) after processing up to 64 packets +# (NAPI budget). Without BQL, the entire ring is a FIFO "dark buffer" +# in front of the qdisc -- packets there are invisible to AQM. +# +# BQL adds STACK_XOFF, which dynamically limits in-flight bytes and +# stops the queue *before* the ring fills. This keeps the ring +# shallow and moves buffering into the qdisc where sojourn-based AQM +# (codel, fq_codel, CAKE/COBALT) can measure and drop packets. +# +# Sojourn time and NAPI budget interaction: +# DRV_XOFF releases backpressure once per NAPI poll (up to 64 pkts). +# During that cycle, packets queued in the qdisc accumulate sojourn +# time. With fq_codel's default target of 5ms, the threshold is: +# 5000us / 64 pkts = 78us/pkt --> ~12,800 pps consumer speed. +# Below that rate the NAPI-64 cycle exceeds the target and fq_codel +# starts dropping. Use --nrules and --qdisc-opts to experiment. +# +cd "$(dirname -- "$0")" || exit 1 +source lib.sh + +# Defaults +DURATION=300 # seconds; 307M pkts @ ~1Mpps needs ~5min +NRULES=3500 # iptables rules in consumer NS (0 to disable) +QDISC=sfq # qdisc to use (sfq, pfifo, fq_codel, etc.) +QDISC_OPTS="" # extra qdisc parameters (e.g. "target 1ms interval 10ms") +BQL_DISABLE=0 # 1 to disable BQL (sets limit_min high) +NORMAL_NAPI=0 # 1 to use normal softirq NAPI (skip threaded NAPI) +QDISC_REPLACE=0 # 1 to test qdisc replacement under active traffic +VETH_A="veth_bql0" +VETH_B="veth_bql1" +IP_A="10.99.0.1" +IP_B="10.99.0.2" +PORT=9999 +PKT_SIZE=1400 # large packets: slower producer, bigger BQL charges + +usage() { + echo "Usage: $0 [OPTIONS]" + echo " --duration SEC test duration (default: $DURATION)" + echo " --nrules N iptables rules to slow consumer (default: $NRULES, 0=disable)" + echo " --qdisc NAME qdisc to install (default: $QDISC)" + echo " --qdisc-opts STR extra qdisc params (e.g. 'target 1ms interval 10ms')" + echo " --bql-disable disable BQL for A/B comparison" + echo " --normal-napi use softirq NAPI instead of threaded NAPI" + echo " --qdisc-replace test qdisc replacement under active traffic" + exit 1 +} + +while [ $# -gt 0 ]; do + case "$1" in + --duration) DURATION="$2"; shift 2 ;; + --nrules) NRULES="$2"; shift 2 ;; + --qdisc) QDISC="$2"; shift 2 ;; + --qdisc-opts) QDISC_OPTS="$2"; shift 2 ;; + --bql-disable) BQL_DISABLE=1; shift ;; + --normal-napi) NORMAL_NAPI=1; shift ;; + --qdisc-replace) QDISC_REPLACE=1; shift ;; + --help|-h) usage ;; + *) echo "Unknown option: $1" >&2; usage ;; + esac +done + +TMPDIR=$(mktemp -d) + +FLOOD_PID="" +SINK_PID="" +PING_PID="" +BPFTRACE_PID="" + +cleanup() { + [ -n "$BPFTRACE_PID" ] && kill_process $BPFTRACE_PID + [ -n "$FLOOD_PID" ] && kill_process $FLOOD_PID + [ -n "$SINK_PID" ] && kill_process $SINK_PID + [ -n "$PING_PID" ] && kill_process $PING_PID + cleanup_all_ns + ip link del "$VETH_A" 2>/dev/null || true + [ -n "$ORIG_WMEM_MAX" ] && sysctl -qw net.core.wmem_max="$ORIG_WMEM_MAX" + rm -rf "$TMPDIR" +} +trap cleanup EXIT + +require_command gcc +require_command ethtool +require_command tc + +# --- Function definitions --- + +compile_tools() { + echo "--- Compiling UDP flood tool ---" +cat > "$TMPDIR"/udp_flood.c << 'CEOF' +#include +#include +#include +#include +#include +#include +#include +#include + +static volatile int running = 1; + +static void stop(int sig) { running = 0; } + +struct pkt_hdr { + struct timespec ts; + unsigned long seq; +}; + +int main(int argc, char **argv) +{ + struct sockaddr_in dst; + struct pkt_hdr hdr; + unsigned long count = 0; + char buf[1500]; + int sndbuf = 1048576; + int pkt_size; + int duration; + int fd; + + if (argc < 5) { + fprintf(stderr, "Usage: %s \n", + argv[0]); + return 1; + } + + pkt_size = atoi(argv[2]); + if (pkt_size < (int)sizeof(struct pkt_hdr)) + pkt_size = sizeof(struct pkt_hdr); + if (pkt_size > (int)sizeof(buf)) + pkt_size = sizeof(buf); + duration = atoi(argv[4]); + + memset(&dst, 0, sizeof(dst)); + dst.sin_family = AF_INET; + dst.sin_port = htons(atoi(argv[3])); + inet_pton(AF_INET, argv[1], &dst.sin_addr); + + fd = socket(AF_INET, SOCK_DGRAM, 0); + if (fd < 0) { + perror("socket"); + return 1; + } + + /* Raise send buffer so sk_wmem_alloc limit doesn't cap + * in-flight packets before the ptr_ring (256 entries) fills. + * Default wmem_default ~208K only allows ~93 packets. + */ + setsockopt(fd, SOL_SOCKET, SO_SNDBUF, &sndbuf, sizeof(sndbuf)); + + memset(buf, 0xAA, sizeof(buf)); + signal(SIGINT, stop); + signal(SIGTERM, stop); + signal(SIGALRM, stop); + alarm(duration); + + while (running) { + clock_gettime(CLOCK_MONOTONIC, &hdr.ts); + hdr.seq = count; + memcpy(buf, &hdr, sizeof(hdr)); + sendto(fd, buf, pkt_size, MSG_DONTWAIT, + (struct sockaddr *)&dst, sizeof(dst)); + count++; + if (!(count % 10000000)) + fprintf(stderr, " sent: %lu M packets\n", + count / 1000000); + } + + fprintf(stderr, "Total sent: %lu packets (%.1f M)\n", + count, (double)count / 1e6); + close(fd); + return 0; +} +CEOF +gcc -O2 -Wall -o "$TMPDIR"/udp_flood "$TMPDIR"/udp_flood.c || exit $ksft_fail + +# UDP sink with latency measurement +cat > "$TMPDIR"/udp_sink.c << 'CEOF' +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static volatile int running = 1; + +static void stop(int sig) { running = 0; } + +struct pkt_hdr { + struct timespec ts; + unsigned long seq; +}; + +static void print_periodic(unsigned long count, unsigned long delta_count, + double delta_sec, unsigned long drops, + unsigned long reorders, + double lat_min, double lat_sum, + double lat_max) +{ + unsigned long pps; + + if (!count) + return; + pps = delta_sec > 0 ? (unsigned long)(delta_count / delta_sec) : 0; + fprintf(stderr, " sink: %lu pkts (%lu pps) drops=%lu reorders=%lu" + " latency min/avg/max = %.3f/%.3f/%.3f ms\n", + count, pps, drops, reorders, + lat_min * 1e3, (lat_sum / count) * 1e3, + lat_max * 1e3); +} + +static void print_final(unsigned long count, double elapsed_sec, + unsigned long drops, unsigned long reorders, + double lat_min, double lat_sum, + double lat_sum_sq, double lat_max) +{ + unsigned long pps; + double avg, stddev; + + if (!count) + return; + pps = elapsed_sec > 0 ? (unsigned long)(count / elapsed_sec) : 0; + avg = lat_sum / count; + stddev = sqrt(lat_sum_sq / count - avg * avg); + fprintf(stderr, " sink: %lu pkts (%lu avg pps) drops=%lu reorders=%lu" + " latency min/avg/max/stddev = %.3f/%.3f/%.3f/%.3f ms\n", + count, pps, drops, reorders, + lat_min * 1e3, avg * 1e3, + lat_max * 1e3, stddev * 1e3); +} + +int main(int argc, char **argv) +{ + unsigned long next_seq = 0, drops = 0, reorders = 0; + double lat_min = 1e9, lat_max = 0, lat_sum = 0, lat_sum_sq = 0; + unsigned long count = 0, last_count = 0; + struct sockaddr_in addr; + char buf[2048]; + int fd, one = 1; + + if (argc < 2) { + fprintf(stderr, "Usage: %s \n", argv[0]); + return 1; + } + + fd = socket(AF_INET, SOCK_DGRAM, 0); + if (fd < 0) { + perror("socket"); + return 1; + } + setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one)); + + /* Timeout so recv() unblocks periodically to check 'running' flag. + * Needed because glibc signal() sets SA_RESTART, so SIGTERM + * does not interrupt recv(). + */ + struct timeval tv = { .tv_sec = 1 }; + setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)); + + memset(&addr, 0, sizeof(addr)); + addr.sin_family = AF_INET; + addr.sin_port = htons(atoi(argv[1])); + addr.sin_addr.s_addr = INADDR_ANY; + if (bind(fd, (struct sockaddr *)&addr, sizeof(addr)) < 0) { + perror("bind"); + return 1; + } + + signal(SIGINT, stop); + signal(SIGTERM, stop); + + struct timespec t_start, t_last_print; + + clock_gettime(CLOCK_MONOTONIC, &t_start); + t_last_print = t_start; + + while (running) { + struct pkt_hdr hdr; + struct timespec now; + ssize_t n; + double lat; + + n = recv(fd, buf, sizeof(buf), 0); + if (n < (ssize_t)sizeof(struct pkt_hdr)) + continue; + + clock_gettime(CLOCK_MONOTONIC, &now); + memcpy(&hdr, buf, sizeof(hdr)); + + /* Track drops (gaps) and reorders (late arrivals) */ + if (hdr.seq > next_seq) + drops += hdr.seq - next_seq; + if (hdr.seq < next_seq) + reorders++; + if (hdr.seq >= next_seq) + next_seq = hdr.seq + 1; + + lat = (now.tv_sec - hdr.ts.tv_sec) + + (now.tv_nsec - hdr.ts.tv_nsec) * 1e-9; + + if (lat < lat_min) + lat_min = lat; + if (lat > lat_max) + lat_max = lat; + lat_sum += lat; + lat_sum_sq += lat * lat; + count++; + + { + double since_print; + + since_print = (now.tv_sec - t_last_print.tv_sec) + + (now.tv_nsec - t_last_print.tv_nsec) * 1e-9; + if (since_print >= 5.0) { + print_periodic(count, count - last_count, + since_print, drops, + reorders, lat_min, + lat_sum, lat_max); + last_count = count; + t_last_print = now; + } + } + } + + { + struct timespec t_now; + double elapsed; + + clock_gettime(CLOCK_MONOTONIC, &t_now); + elapsed = (t_now.tv_sec - t_start.tv_sec) + + (t_now.tv_nsec - t_start.tv_nsec) * 1e-9; + print_final(count, elapsed, drops, reorders, + lat_min, lat_sum, lat_sum_sq, lat_max); + } + close(fd); + return 0; +} +CEOF +gcc -O2 -Wall -o "$TMPDIR"/udp_sink "$TMPDIR"/udp_sink.c -lm || exit $ksft_fail +} + +setup_veth() { + log_info "Setting up veth pair with GRO" + setup_ns NS || exit $ksft_skip + ip link add "$VETH_A" type veth peer name "$VETH_B" || \ + { echo "Failed to create veth pair (need root?)"; exit $ksft_skip; } + ip link set "$VETH_B" netns "$NS" || \ + { echo "Failed to move veth to namespace"; exit $ksft_skip; } + + # Configure IPs + ip addr add "${IP_A}/24" dev "$VETH_A" + ip link set "$VETH_A" up + + ip -netns "$NS" addr add "${IP_B}/24" dev "$VETH_B" + ip -netns "$NS" link set "$VETH_B" up + + # Raise wmem_max so the flood tool's SO_SNDBUF takes effect. + # Default 212992 caps in-flight to ~93 packets (sk_wmem_alloc limit), + # which is less than the 256-entry ptr_ring and prevents backpressure. + ORIG_WMEM_MAX=$(sysctl -n net.core.wmem_max) + sysctl -qw net.core.wmem_max=1048576 + + # Enable GRO on both ends -- activates NAPI -- BQL code path + ethtool -K "$VETH_A" gro on 2>/dev/null || true + ip netns exec "$NS" ethtool -K "$VETH_B" gro on 2>/dev/null || true + + # Disable TSO so veth_skb_is_eligible_for_gro() returns true for all + # packets, ensuring every SKB takes the NAPI/ptr_ring path. With TSO + # enabled, only packets matching sock_wfree + GRO features are eligible; + # disabling TSO removes that filter unconditionally. + ethtool -K "$VETH_A" tso off gso off 2>/dev/null || true + ip netns exec "$NS" ethtool -K "$VETH_B" tso off gso off 2>/dev/null || true + + # Enable threaded NAPI -- this is critical: BQL backpressure (STACK_XOFF) + # only engages when producer and consumer run on separate CPUs. + # Without threaded NAPI, softirq completions happen too fast for BQL + # to build up enough in-flight bytes to trigger the limit. + if [ "$NORMAL_NAPI" -eq 0 ]; then + echo 1 > /sys/class/net/"$VETH_A"/threaded 2>/dev/null || true + ip netns exec "$NS" sh -c "echo 1 > /sys/class/net/$VETH_B/threaded" 2>/dev/null || true + log_info "Threaded NAPI enabled" + else + log_info "Using normal softirq NAPI (threaded NAPI disabled)" + fi +} + +install_qdisc() { + local qdisc="${1:-$QDISC}" + local opts="${2:-}" + # Add a qdisc -- veth defaults to noqueue, but BQL needs a qdisc + # because STACK_XOFF is checked by the qdisc layer. + # Note: qdisc_create() auto-fixes txqueuelen=0 on IFF_NO_QUEUE devices + # to DEFAULT_TX_QUEUE_LEN (commit 84c46dd86538). + log_info "Installing qdisc: $qdisc $opts" + tc qdisc replace dev "$VETH_A" root $qdisc $opts + ip netns exec "$NS" tc qdisc replace dev "$VETH_B" root $qdisc $opts +} + +remove_qdisc() { + log_info "Removing qdisc (reverting to noqueue)" + tc qdisc del dev "$VETH_A" root 2>/dev/null || true + ip netns exec "$NS" tc qdisc del dev "$VETH_B" root 2>/dev/null || true +} + +setup_iptables() { + # Bulk-load iptables rules in consumer namespace to slow NAPI processing. + # Many rules force per-packet linear rule traversal, increasing consumer + # overhead and BQL inflight bytes -- simulates realistic k8s-like workload. + if [ "$NRULES" -gt 0 ]; then + ip netns exec "$NS" bash -c ' + iptables-restore < <( + echo "*filter" + for n in $(seq 1 '"$NRULES"'); do + echo "-I INPUT -d '"$IP_B"'" + done + echo "COMMIT" + ) + ' 2>/dev/null || log_info "iptables not available, skipping rules" + log_info "Loaded $NRULES iptables rules in consumer NS" + fi +} + +check_bql_sysfs() { + BQL_DIR="/sys/class/net/${VETH_A}/queues/tx-0/byte_queue_limits" + if [ -d "$BQL_DIR" ]; then + log_info "BQL sysfs found: $BQL_DIR" + if [ "$BQL_DISABLE" -eq 1 ]; then + echo 1073741824 > "$BQL_DIR/limit_min" + log_info "BQL effectively disabled (limit_min=1G)" + fi + else + log_info "BQL sysfs absent (veth IFF_NO_QUEUE+lltx, DQL accounting still active)" + BQL_DIR="" + fi +} + +start_traffic() { + # Snapshot dmesg before test + DMESG_BEFORE=$(dmesg | wc -l) + + log_info "Starting UDP sink in namespace" + ip netns exec "$NS" "$TMPDIR"/udp_sink "$PORT" & + SINK_PID=$! + sleep 0.2 + + log_info "Starting ping to $IP_B (5/s) to measure latency under load" + ping -i 0.2 -w "$DURATION" "$IP_B" > "$TMPDIR"/ping.log 2>&1 & + PING_PID=$! + + log_info "Flooding ${PKT_SIZE}-byte UDP packets for ${DURATION}s" + "$TMPDIR"/udp_flood "$IP_B" "$PKT_SIZE" "$PORT" "$DURATION" & + FLOOD_PID=$! + + # Optional: start bpftrace napi_poll histogram (best-effort) + local bt_script="$(dirname -- "$0")/napi_poll_hist.bt" + if command -v bpftrace >/dev/null 2>&1 && [ -f "$bt_script" ]; then + bpftrace "$bt_script" > "$TMPDIR"/napi_poll.log 2>&1 & + BPFTRACE_PID=$! + log_info "bpftrace napi_poll histogram started (pid=$BPFTRACE_PID)" + fi +} + +stop_traffic() { + [ -n "$FLOOD_PID" ] && kill_process $FLOOD_PID + FLOOD_PID="" + [ -n "$SINK_PID" ] && kill_process $SINK_PID + SINK_PID="" + [ -n "$PING_PID" ] && kill_process $PING_PID + PING_PID="" + [ -n "$BPFTRACE_PID" ] && kill_process $BPFTRACE_PID + BPFTRACE_PID="" +} + +check_dmesg_bug() { + local bug_pattern='kernel BUG|BUG:|Oops:|dql_completed' + local warn_pattern='WARNING:|asks to queue packet|NETDEV WATCHDOG' + if dmesg | tail -n +$((DMESG_BEFORE + 1)) | \ + grep -qE "$bug_pattern"; then + dmesg | tail -n +$((DMESG_BEFORE + 1)) | \ + grep -B2 -A20 -E "$bug_pattern|$warn_pattern" + return 1 + fi + # Log new warnings since last check (don't repeat old ones) + local cur_lines + cur_lines=$(dmesg | wc -l) + if [ "$cur_lines" -gt "${DMESG_WARN_SEEN:-$DMESG_BEFORE}" ]; then + local new_warns + new_warns=$(dmesg | tail -n +$(("${DMESG_WARN_SEEN:-$DMESG_BEFORE}" + 1)) | \ + grep -E "$warn_pattern") || true + if [ -n "$new_warns" ]; then + local cnt + cnt=$(echo "$new_warns" | wc -l) + echo " WARN: $cnt new kernel warning(s):" + echo "$new_warns" | tail -5 + fi + fi + DMESG_WARN_SEEN=$cur_lines + return 0 +} + +print_periodic_stats() { + local elapsed="$1" + + # BQL stats and watchdog counter + WD_CNT=$(cat /sys/class/net/${VETH_A}/queues/tx-0/tx_timeout \ + 2>/dev/null) || WD_CNT="?" + if [ -n "$BQL_DIR" ] && [ -d "$BQL_DIR" ]; then + INFLIGHT=$(cat "$BQL_DIR/inflight" 2>/dev/null || echo "?") + LIMIT=$(cat "$BQL_DIR/limit" 2>/dev/null || echo "?") + echo " [${elapsed}s] BQL inflight=${INFLIGHT} limit=${LIMIT}" \ + "watchdog=${WD_CNT}" + else + echo " [${elapsed}s] watchdog=${WD_CNT} (no BQL sysfs)" + fi + + # Qdisc stats + JQ_FMT='"qdisc \(.kind) pkts=\(.packets) drops=\(.drops)' + JQ_FMT+=' requeues=\(.requeues) backlog=\(.backlog)' + JQ_FMT+=' qlen=\(.qlen) overlimits=\(.overlimits)"' + CUR_QPKTS=$(tc -j -s qdisc show dev "$VETH_A" root 2>/dev/null | + jq -r '.[0].packets // 0' 2>/dev/null) || CUR_QPKTS=0 + QSTATS=$(tc -j -s qdisc show dev "$VETH_A" root 2>/dev/null | + jq -r ".[0] | $JQ_FMT" 2>/dev/null) && + echo " [${elapsed}s] $QSTATS" || true + + # Consumer PPS and per-packet processing time + if [ "$PREV_QPKTS" -gt 0 ] 2>/dev/null; then + DELTA=$((CUR_QPKTS - PREV_QPKTS)) + PPS=$((DELTA / INTERVAL)) + if [ "$PPS" -gt 0 ]; then + PKT_MS=$(awk "BEGIN {printf \"%.3f\", 1000.0/$PPS}") + NAPI_MS=$(awk "BEGIN {printf \"%.1f\", 64000.0/$PPS}") + echo " [${elapsed}s] consumer: ${PPS} pps" \ + "(~${PKT_MS}ms/pkt, NAPI-64 cycle ~${NAPI_MS}ms)" + fi + fi + PREV_QPKTS=$CUR_QPKTS + + # softnet_stat: per-CPU tracking to detect same-CPU vs multi-CPU NAPI + # /proc/net/softnet_stat columns: processed, dropped, time_squeeze (hex, per-CPU) + local cpu=0 total_proc=0 total_sq=0 active_cpus="" + while read -r line; do + set -- $line + local cur_p=$((0x${1})) cur_sq=$((0x${3})) + if [ -f "$TMPDIR/softnet_cpu${cpu}" ]; then + read prev_p prev_sq < "$TMPDIR/softnet_cpu${cpu}" + local dp=$((cur_p - prev_p)) dsq=$((cur_sq - prev_sq)) + total_proc=$((total_proc + dp)) + total_sq=$((total_sq + dsq)) + [ "$dp" -gt 0 ] && active_cpus="${active_cpus} cpu${cpu}(+${dp})" + fi + echo "$cur_p $cur_sq" > "$TMPDIR/softnet_cpu${cpu}" + cpu=$((cpu + 1)) + done < /proc/net/softnet_stat + local n_active=$(echo $active_cpus | wc -w) + local cpu_mode="single-CPU" + [ "$n_active" -gt 1 ] && cpu_mode="multi-CPU(${n_active})" + if [ "$total_sq" -gt 0 ] && [ "$INTERVAL" -gt 0 ]; then + echo " [${elapsed}s] softnet: processed=${total_proc}" \ + "time_squeeze=${total_sq} (${total_sq}/${INTERVAL}s)" \ + "${cpu_mode}:${active_cpus}" + else + echo " [${elapsed}s] softnet: processed=${total_proc}" \ + "time_squeeze=${total_sq}" \ + "${cpu_mode}:${active_cpus}" + fi + + # napi_poll histogram (from bpftrace, if running) + if [ -n "$BPFTRACE_PID" ] && [ -f "$TMPDIR"/napi_poll.log ]; then + local napi_line + napi_line=$(grep '^napi_poll:' "$TMPDIR"/napi_poll.log | tail -1) + [ -n "$napi_line" ] && echo " [${elapsed}s] $napi_line" + fi + + # Ping RTT + PING_RTT=$(tail -1 "$TMPDIR"/ping.log 2>/dev/null | grep -oP 'time=\K[0-9.]+') && + echo " [${elapsed}s] ping RTT=${PING_RTT}ms" || true +} + +monitor_loop() { + ELAPSED=0 + INTERVAL=5 + PREV_QPKTS=0 + # Seed per-CPU softnet baselines + local cpu=0 + while read -r line; do + set -- $line + echo "$((0x${1})) $((0x${3}))" > "$TMPDIR/softnet_cpu${cpu}" + cpu=$((cpu + 1)) + done < /proc/net/softnet_stat + while kill -0 "$FLOOD_PID" 2>/dev/null; do + sleep "$INTERVAL" + ELAPSED=$((ELAPSED + INTERVAL)) + + if ! check_dmesg_bug; then + RET=$ksft_fail + retmsg="BUG_ON triggered in dql_completed at ${ELAPSED}s" + log_test "veth_bql" + exit $EXIT_STATUS + fi + + print_periodic_stats "$ELAPSED" + done + wait "$FLOOD_PID" || true + FLOOD_PID="" +} + +# Verify traffic is flowing by checking device tx_packets counter. +# Works for both qdisc and noqueue modes. +verify_traffic_flowing() { + local label="$1" + local prev_tx cur_tx + + # Skip check if flood producer already exited (not a stall) + if [ -n "$FLOOD_PID" ] && ! kill -0 "$FLOOD_PID" 2>/dev/null; then + log_info "$label flood producer exited (duration reached)" + return 0 + fi + + prev_tx=$(cat /sys/class/net/${VETH_A}/statistics/tx_packets \ + 2>/dev/null) || prev_tx=0 + sleep 0.5 + cur_tx=$(cat /sys/class/net/${VETH_A}/statistics/tx_packets \ + 2>/dev/null) || cur_tx=0 + if [ "$cur_tx" -gt "$prev_tx" ]; then + log_info "$label traffic flowing (tx: $prev_tx -> $cur_tx)" + return 0 + fi + log_info "$label traffic STALLED (tx: $prev_tx -> $cur_tx)" + return 1 +} + +collect_results() { + local test_name="${1:-veth_bql}" + + # Ping summary + wait "$PING_PID" 2>/dev/null || true + PING_PID="" + if [ -f "$TMPDIR"/ping.log ]; then + PING_LOSS=$(grep -o '[0-9.]*% packet loss' "$TMPDIR"/ping.log) && + log_info "Ping loss: $PING_LOSS" + PING_SUMMARY=$(tail -1 "$TMPDIR"/ping.log) + log_info "Ping summary: $PING_SUMMARY" + fi + + # Watchdog summary + WD_FINAL=$(cat /sys/class/net/${VETH_A}/queues/tx-0/tx_timeout \ + 2>/dev/null) || WD_FINAL=0 + if [ "$WD_FINAL" -gt 0 ] 2>/dev/null; then + log_info "Watchdog fired ${WD_FINAL} time(s)" + dmesg | tail -n +$((DMESG_BEFORE + 1)) | \ + grep -E 'NETDEV WATCHDOG|veth backpressure' || true + fi + + # Final dmesg check -- only upgrade to fail, never override existing fail + if ! check_dmesg_bug; then + RET=$ksft_fail + retmsg="BUG_ON triggered in dql_completed" + fi + log_test "$test_name" + exit $EXIT_STATUS +} + +# --- Test modes --- + +test_bql_stress() { + RET=$ksft_pass + compile_tools + setup_veth + install_qdisc "$QDISC" "$QDISC_OPTS" + setup_iptables + log_info "kernel: $(uname -r)" + check_bql_sysfs + start_traffic + monitor_loop + collect_results "veth_bql" +} + +# Test qdisc replacement under active traffic. Cycles through several +# qdiscs including a transition to noqueue (tc qdisc del) to verify +# that stale BQL state (STACK_XOFF) is properly reset during qdisc +# transitions. +test_qdisc_replace() { + local qdiscs=("sfq" "pfifo" "fq_codel") + local step=2 + local elapsed=0 + local idx + + RET=$ksft_pass + compile_tools + setup_veth + install_qdisc "$QDISC" "$QDISC_OPTS" + setup_iptables + log_info "kernel: $(uname -r)" + check_bql_sysfs + start_traffic + + while [ "$elapsed" -lt "$DURATION" ] && kill -0 "$FLOOD_PID" 2>/dev/null; do + sleep "$step" + elapsed=$((elapsed + step)) + + if ! check_dmesg_bug; then + RET=$ksft_fail + retmsg="BUG_ON during qdisc replacement at ${elapsed}s" + break + fi + + # Cycle: sfq -> pfifo -> fq_codel -> noqueue -> sfq -> ... + idx=$(( (elapsed / step - 1) % (${#qdiscs[@]} + 1) )) + if [ "$idx" -eq "${#qdiscs[@]}" ]; then + remove_qdisc + else + install_qdisc "${qdiscs[$idx]}" + fi + + # Print BQL and qdisc stats after each replacement + if [ -n "$BQL_DIR" ] && [ -d "$BQL_DIR" ]; then + local inflight limit limit_min limit_max holding + inflight=$(cat "$BQL_DIR/inflight" 2>/dev/null || echo "?") + limit=$(cat "$BQL_DIR/limit" 2>/dev/null || echo "?") + limit_min=$(cat "$BQL_DIR/limit_min" 2>/dev/null || echo "?") + limit_max=$(cat "$BQL_DIR/limit_max" 2>/dev/null || echo "?") + holding=$(cat "$BQL_DIR/holding_time" 2>/dev/null || echo "?") + echo " [${elapsed}s] BQL inflight=${inflight} limit=${limit}" \ + "limit_min=${limit_min} limit_max=${limit_max}" \ + "holding=${holding}" + fi + local cur_qdisc + cur_qdisc=$(tc qdisc show dev "$VETH_A" root 2>/dev/null | \ + awk '{print $2}') || cur_qdisc="none" + local txq_state + txq_state=$(cat /sys/class/net/${VETH_A}/queues/tx-0/tx_timeout \ + 2>/dev/null) || txq_state="?" + echo " [${elapsed}s] qdisc=${cur_qdisc} watchdog=${txq_state}" + + if ! verify_traffic_flowing "[${elapsed}s]"; then + RET=$ksft_fail + retmsg="Traffic stalled after qdisc replacement at ${elapsed}s" + break + fi + done + + stop_traffic + collect_results "veth_bql_qdisc_replace" +} + +# --- Main --- +if [ "$QDISC_REPLACE" -eq 1 ]; then + test_qdisc_replace +else + test_bql_stress +fi diff --git a/tools/testing/selftests/net/veth_bql_test_virtme.sh b/tools/testing/selftests/net/veth_bql_test_virtme.sh new file mode 100755 index 000000000000..b097e5670808 --- /dev/null +++ b/tools/testing/selftests/net/veth_bql_test_virtme.sh @@ -0,0 +1,124 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Launch veth BQL test inside virtme-ng +# +# Must be run from the kernel build tree root. +# +# Options: +# --verbose Show kernel console (vng boot messages) in real time. +# Useful for debugging kernel panics / BUG_ON crashes. +# All other options are forwarded to veth_bql_test.sh (see --help there). +# +# Examples: +# ./tools/testing/selftests/net/veth_bql_test_virtme.sh +# ./tools/testing/selftests/net/veth_bql_test_virtme.sh --duration 20 --nrules 1000 --qdisc fq_codel +# ./tools/testing/selftests/net/veth_bql_test_virtme.sh --qdisc fq_codel --bql-disable +# ./tools/testing/selftests/net/veth_bql_test_virtme.sh --verbose --qdisc-replace --duration 60 + +set -eu + +# Parse --verbose (consumed here, not forwarded to the inner test). +VERBOSE="" +INNER_ARGS=() +for arg in "$@"; do + if [ "$arg" = "--verbose" ]; then + VERBOSE="--verbose" + else + INNER_ARGS+=("$arg") + fi +done +TEST_ARGS=$(printf '%q ' "${INNER_ARGS[@]+${INNER_ARGS[@]}}") +TEST="tools/testing/selftests/net/veth_bql_test.sh" + +if [ ! -f "$TEST" ]; then + echo "ERROR: Run this from the kernel tree root" >&2 + echo " cd /path/to/kernel && $0" >&2 + exit 1 +fi + +# Verify .config has the options needed for virtme-ng and this test. +# Without these the VM silently stalls with no output. +KCONFIG=".config" +if [ ! -f "$KCONFIG" ]; then + echo "ERROR: No .config found -- build the kernel first" >&2 + exit 1 +fi + +MISSING="" +for opt in CONFIG_VIRTIO CONFIG_VIRTIO_PCI CONFIG_VIRTIO_NET \ + CONFIG_VIRTIO_CONSOLE CONFIG_NET_9P CONFIG_NET_9P_VIRTIO \ + CONFIG_9P_FS CONFIG_VETH CONFIG_BQL; do + if ! grep -q "^${opt}=[ym]" "$KCONFIG"; then + MISSING+=" $opt\n" + fi +done +if [ -n "$MISSING" ]; then + echo "ERROR: .config is missing options required by virtme-ng:" >&2 + echo -e "$MISSING" >&2 + echo "Consider: vng --kconfig (or make defconfig + enable above)" >&2 + exit 1 +fi + +TESTDIR="tools/testing/selftests/net" +TESTNAME="veth_bql_test.sh" +LOGFILE="veth_bql_test.log" +LOGPATH="$TESTDIR/$LOGFILE" +CONSOLELOG="veth_bql_console.log" +rm -f "$LOGPATH" "$CONSOLELOG" + +echo "Starting VM... test output in $LOGPATH, kernel console in $CONSOLELOG" +echo "(VM is booting, please wait ~30s)" + +# Always capture kernel console to a file via a second QEMU serial port. +# vng claims ttyS0 (mapped to /dev/null); --qemu-opts adds ttyS1 on COM2. +# earlycon registers COM2's I/O port (0x2f8) as a persistent console. +# (plain console=ttyS1 does NOT work: the 8250 driver registers once, +# ttyS0 wins, and ttyS1 is never picked up.) +# --verbose additionally shows kernel console in real time on the terminal. +SERIAL_CONSOLE="earlycon=uart8250,io,0x2f8,115200" +SERIAL_CONSOLE+=" console=uart8250,io,0x2f8,115200" +set +e +vng $VERBOSE --cpus 4 --memory 2G \ + --rwdir "$TESTDIR" \ + --append "panic=5 loglevel=4 $SERIAL_CONSOLE" \ + --qemu-opts="-serial file:$CONSOLELOG" \ + --exec "cd $TESTDIR && \ + ./$TESTNAME $TEST_ARGS 2>&1 | \ + tee $LOGFILE; echo EXIT_CODE=\$? >> $LOGFILE" +VNG_RC=$? +set -e + +echo "" +if [ "$VNG_RC" -ne 0 ]; then + echo "***********************************************************" + echo "* VM CRASHED -- kernel panic or BUG_ON (vng rc=$VNG_RC)" + echo "***********************************************************" + if [ -s "$CONSOLELOG" ] && \ + grep -qiE 'kernel BUG|BUG:|Oops:|panic|dql_completed' "$CONSOLELOG"; then + echo "" + echo "--- kernel backtrace ($CONSOLELOG) ---" + grep -iE -A30 'kernel BUG|BUG:|Oops:|panic|dql_completed' \ + "$CONSOLELOG" | head -50 + else + echo "" + echo "Re-run with --verbose to see the kernel backtrace:" + echo " $0 --verbose ${INNER_ARGS[*]}" + fi + exit 1 +elif [ ! -f "$LOGPATH" ]; then + echo "No log file found -- VM may have crashed before writing output" + exit 2 +else + echo "=== VM finished ===" +fi + +# Scan console log for unexpected kernel warnings (even on clean exit) +if [ -s "$CONSOLELOG" ]; then + WARN_PATTERN='kernel BUG|BUG:|Oops:|dql_completed|WARNING:|asks to queue packet|NETDEV WATCHDOG' + WARN_LINES=$(grep -cE "$WARN_PATTERN" "$CONSOLELOG" 2>/dev/null) || WARN_LINES=0 + if [ "$WARN_LINES" -gt 0 ]; then + echo "" + echo "*** kernel warnings in $CONSOLELOG ($WARN_LINES lines) ***" + grep -E "$WARN_PATTERN" "$CONSOLELOG" | head -20 + fi +fi -- 2.43.0