Context |
Check |
Description |
bpf/vmtest-bpf-next-PR |
fail
|
PR summary
|
netdev/series_format |
success
|
Single patches do not need cover letters
|
netdev/tree_selection |
success
|
Clearly marked for net-next, async
|
netdev/ynl |
success
|
Generated files up to date;
no warnings/errors;
no diff in generated;
|
netdev/fixes_present |
success
|
Fixes tag not required for -next series
|
netdev/header_inline |
success
|
No static functions without inline keyword in header files
|
netdev/build_32bit |
success
|
Errors and warnings before: 932 this patch: 932
|
netdev/build_tools |
success
|
Errors and warnings before: 0 this patch: 0
|
netdev/cc_maintainers |
warning
|
15 maintainers not CCed: kpsingh@kernel.org john.fastabend@gmail.com andrii@kernel.org shuah@kernel.org jolsa@kernel.org eddyz87@gmail.com yonghong.song@linux.dev song@kernel.org daniel@iogearbox.net linux-kselftest@vger.kernel.org martin.lau@linux.dev mykolal@fb.com ast@kernel.org haoluo@google.com sdf@google.com
|
netdev/build_clang |
success
|
Errors and warnings before: 938 this patch: 938
|
netdev/verify_signedoff |
success
|
Signed-off-by tag matches author and committer
|
netdev/deprecated_api |
success
|
None detected
|
netdev/check_selftest |
success
|
No net selftest shell script
|
netdev/verify_fixes |
success
|
No Fixes tag
|
netdev/build_allmodconfig_warn |
success
|
Errors and warnings before: 944 this patch: 944
|
netdev/checkpatch |
warning
|
CHECK: Alignment should match open parenthesis
CHECK: Lines should not end with a '('
CHECK: Please don't use multiple blank lines
CHECK: spaces preferred around that '<<' (ctx:VxV)
WARNING: added, moved or deleted file(s), does MAINTAINERS need updating?
WARNING: line length of 81 exceeds 80 columns
WARNING: line length of 83 exceeds 80 columns
WARNING: line length of 84 exceeds 80 columns
WARNING: line length of 85 exceeds 80 columns
WARNING: line length of 88 exceeds 80 columns
WARNING: line length of 89 exceeds 80 columns
WARNING: line length of 92 exceeds 80 columns
WARNING: line length of 99 exceeds 80 columns
WARNING: min() should probably be min_t(__u64, rate, sk->sk_max_pacing_rate)
|
netdev/build_clang_rust |
success
|
No Rust files in patch. Skipping build
|
netdev/kdoc |
success
|
Errors and warnings before: 0 this patch: 0
|
netdev/source_inline |
success
|
Was 0 now: 0
|
bpf/vmtest-bpf-next-VM_Test-3 |
success
|
Logs for Validate matrix.py
|
bpf/vmtest-bpf-next-VM_Test-1 |
success
|
Logs for ShellCheck
|
bpf/vmtest-bpf-next-VM_Test-0 |
success
|
Logs for Lint
|
bpf/vmtest-bpf-next-VM_Test-2 |
success
|
Logs for Unittests
|
bpf/vmtest-bpf-next-VM_Test-5 |
success
|
Logs for aarch64-gcc / build-release
|
bpf/vmtest-bpf-next-VM_Test-12 |
success
|
Logs for s390x-gcc / build-release
|
bpf/vmtest-bpf-next-VM_Test-11 |
success
|
Logs for s390x-gcc / build / build for s390x with gcc
|
bpf/vmtest-bpf-next-VM_Test-4 |
success
|
Logs for aarch64-gcc / build / build for aarch64 with gcc
|
bpf/vmtest-bpf-next-VM_Test-9 |
success
|
Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
|
bpf/vmtest-bpf-next-VM_Test-17 |
success
|
Logs for s390x-gcc / veristat
|
bpf/vmtest-bpf-next-VM_Test-18 |
success
|
Logs for set-matrix
|
bpf/vmtest-bpf-next-VM_Test-10 |
success
|
Logs for aarch64-gcc / veristat
|
bpf/vmtest-bpf-next-VM_Test-29 |
success
|
Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17 and -O2 optimization
|
bpf/vmtest-bpf-next-VM_Test-20 |
success
|
Logs for x86_64-gcc / build-release
|
bpf/vmtest-bpf-next-VM_Test-36 |
success
|
Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18 and -O2 optimization
|
bpf/vmtest-bpf-next-VM_Test-28 |
success
|
Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
|
bpf/vmtest-bpf-next-VM_Test-42 |
success
|
Logs for x86_64-llvm-18 / veristat
|
bpf/vmtest-bpf-next-VM_Test-35 |
success
|
Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
|
bpf/vmtest-bpf-next-VM_Test-8 |
fail
|
Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
|
bpf/vmtest-bpf-next-VM_Test-13 |
success
|
Logs for s390x-gcc / test (test_maps, false, 360) / test_maps on s390x with gcc
|
bpf/vmtest-bpf-next-VM_Test-16 |
success
|
Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
|
bpf/vmtest-bpf-next-VM_Test-19 |
success
|
Logs for x86_64-gcc / build / build for x86_64 with gcc
|
bpf/vmtest-bpf-next-VM_Test-7 |
fail
|
Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
|
bpf/vmtest-bpf-next-VM_Test-6 |
success
|
Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
|
bpf/vmtest-bpf-next-VM_Test-26 |
success
|
Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
|
bpf/vmtest-bpf-next-VM_Test-34 |
success
|
Logs for x86_64-llvm-17 / veristat
|
bpf/vmtest-bpf-next-VM_Test-25 |
success
|
Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
|
bpf/vmtest-bpf-next-VM_Test-14 |
fail
|
Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc
|
bpf/vmtest-bpf-next-VM_Test-27 |
fail
|
Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
|
bpf/vmtest-bpf-next-VM_Test-32 |
fail
|
Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
|
bpf/vmtest-bpf-next-VM_Test-33 |
success
|
Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
|
bpf/vmtest-bpf-next-VM_Test-31 |
fail
|
Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
|
bpf/vmtest-bpf-next-VM_Test-30 |
success
|
Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
|
bpf/vmtest-bpf-next-VM_Test-24 |
success
|
Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
|
bpf/vmtest-bpf-next-VM_Test-37 |
success
|
Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
|
bpf/vmtest-bpf-next-VM_Test-21 |
success
|
Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
|
bpf/vmtest-bpf-next-VM_Test-22 |
fail
|
Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
|
bpf/vmtest-bpf-next-VM_Test-23 |
fail
|
Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
|
bpf/vmtest-bpf-next-VM_Test-15 |
fail
|
Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc
|
bpf/vmtest-bpf-next-VM_Test-40 |
fail
|
Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18
|
bpf/vmtest-bpf-next-VM_Test-39 |
fail
|
Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
|
bpf/vmtest-bpf-next-VM_Test-38 |
fail
|
Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
|
bpf/vmtest-bpf-next-VM_Test-41 |
success
|
Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18
|
@@ -21,6 +21,15 @@ BPF_PROG(name, args)
#endif
#define tcp_jiffies32 ((__u32)bpf_jiffies64())
+#define TCP_INFINITE_SSTHRESH 0x7fffffff
+
+#define FLAG_DATA_ACKED 0x04 /* This ACK acknowledged new data. */
+#define FLAG_SYN_ACKED 0x10 /* This ACK acknowledged SYN. */
+#define FLAG_DATA_SACKED 0x20 /* New SACK. */
+#define FLAG_SND_UNA_ADVANCED \
+ 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */
+#define FLAG_ACKED (FLAG_DATA_ACKED | FLAG_SYN_ACKED)
+#define FLAG_FORWARD_PROGRESS (FLAG_ACKED | FLAG_DATA_SACKED)
struct sock_common {
unsigned char skc_state;
@@ -37,6 +46,7 @@ struct sock {
struct sock_common __sk_common;
#define sk_state __sk_common.skc_state
unsigned long sk_pacing_rate;
+ unsigned long sk_max_pacing_rate;
__u32 sk_pacing_status; /* see enum sk_pacing */
} __attribute__((preserve_access_index));
@@ -86,6 +96,19 @@ struct tcp_sock {
__u32 prior_cwnd;
__u64 tcp_mstamp; /* most recent packet received/sent */
bool is_mptcp;
+ __u32 snd_cwnd_stamp;
+ __u32 mss_cache; /* Cached effective mss, not including SACKS */
+ __u32 high_seq; /* snd_nxt at onset of congestion */
+ __u32 packets_out; /* Packets which are "in flight" */
+ __u32 srtt_us; /* smoothed round trip time << 3 in usecs */
+ __u32 retrans_out; /* Retransmitted packets out */
+ __u32 lost_out; /* Lost packets */
+ __u32 sacked_out; /* SACK'd packets */
+ __u32 prr_delivered; /* Number of newly delivered packets to
+ * receiver in Recovery.
+ */
+ __u32 prr_out; /* Total number of pkts sent during Recovery. */
+ __u32 reordering; /* Packet reordering metric. */
} __attribute__((preserve_access_index));
static __always_inline struct inet_connection_sock *inet_csk(const struct sock *sk)
new file mode 100644
@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/* WARNING: This implementation is NOT the same as the tcp_cubic.c.
+ * The purpose is mainly to show use cases of the new arguments in
+ * cong_control.
+ */
+
+#include <linux/bpf.h>
+#include <linux/stddef.h>
+#include <linux/tcp.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+extern void cubictcp_init(struct sock *sk) __ksym;
+extern void cubictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event)
+ __ksym;
+ extern __u32 cubictcp_recalc_ssthresh(struct sock *sk) __ksym;
+ extern void cubictcp_state(struct sock *sk, __u8 new_state) __ksym;
+ extern __u32 tcp_reno_undo_cwnd(struct sock *sk) __ksym;
+extern void cubictcp_acked(struct sock *sk, const struct ack_sample *sample)
+ __ksym;
+ extern void cubictcp_cong_avoid(struct sock *sk, __u32 ack, __u32 acked) __ksym;
+
+
+void BPF_STRUCT_OPS(bpf_cubic_init, struct sock *sk)
+{
+ cubictcp_init(sk);
+}
+
+void BPF_STRUCT_OPS(bpf_cubic_cwnd_event, struct sock *sk, enum tcp_ca_event event)
+{
+ cubictcp_cwnd_event(sk, event);
+}
+
+#define USEC_PER_SEC 1000000UL
+#define TCP_PACING_SS_RATIO (200)
+#define TCP_PACING_CA_RATIO (120)
+#define TCP_REORDERING (12)
+#define likely(x) (__builtin_expect(!!(x), 1))
+
+static __always_inline __u64 div64_u64(__u64 dividend, __u64 divisor)
+{
+ return dividend / divisor;
+}
+
+static void tcp_update_pacing_rate(struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ __u64 rate;
+
+ /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */
+ rate = (__u64)tp->mss_cache * ((USEC_PER_SEC / 100) << 3);
+
+ /* current rate is (cwnd * mss) / srtt
+ * In Slow Start [1], set sk_pacing_rate to 200 % the current rate.
+ * In Congestion Avoidance phase, set it to 120 % the current rate.
+ *
+ * [1] : Normal Slow Start condition is (tp->snd_cwnd < tp->snd_ssthresh)
+ * If snd_cwnd >= (tp->snd_ssthresh / 2), we are approaching
+ * end of slow start and should slow down.
+ */
+ if (tp->snd_cwnd < tp->snd_ssthresh / 2)
+ rate *= TCP_PACING_SS_RATIO;
+ else
+ rate *= TCP_PACING_CA_RATIO;
+
+ rate *= max(tp->snd_cwnd, tp->packets_out);
+
+ if (likely(tp->srtt_us))
+ rate = div64_u64(rate, (__u64)tp->srtt_us);
+
+ sk->sk_pacing_rate = min(rate, (__u64)sk->sk_max_pacing_rate);
+}
+
+static __always_inline void tcp_cwnd_reduction(
+ struct sock *sk,
+ int newly_acked_sacked,
+ int newly_lost,
+ int flag) {
+ struct tcp_sock *tp = tcp_sk(sk);
+ int sndcnt = 0;
+ __u32 pkts_in_flight = tp->packets_out - (tp->sacked_out + tp->lost_out) + tp->retrans_out;
+ int delta = tp->snd_ssthresh - pkts_in_flight;
+
+ if (newly_acked_sacked <= 0 || !tp->prior_cwnd)
+ return;
+
+ __u32 prr_delivered = tp->prr_delivered + newly_acked_sacked;
+
+ if (delta < 0) {
+ __u64 dividend =
+ (__u64)tp->snd_ssthresh * prr_delivered + tp->prior_cwnd - 1;
+ sndcnt = (__u32)div64_u64(dividend, (__u64)tp->prior_cwnd) - tp->prr_out;
+ } else {
+ sndcnt = max(prr_delivered - tp->prr_out, newly_acked_sacked);
+ if (flag & FLAG_SND_UNA_ADVANCED && !newly_lost)
+ sndcnt++;
+ sndcnt = min(delta, sndcnt);
+ }
+ /* Force a fast retransmit upon entering fast recovery */
+ sndcnt = max(sndcnt, (tp->prr_out ? 0 : 1));
+ tp->snd_cwnd = pkts_in_flight + sndcnt;
+}
+
+/* Decide wheather to run the increase function of congestion control. */
+static __always_inline bool tcp_may_raise_cwnd(
+ const struct sock *sk,
+ const int flag) {
+ if (tcp_sk(sk)->reordering > TCP_REORDERING)
+ return flag & FLAG_FORWARD_PROGRESS;
+
+ return flag & FLAG_DATA_ACKED;
+}
+
+void BPF_STRUCT_OPS(bpf_cubic_cong_control, struct sock *sk, __u32 ack, int flag,
+ const struct rate_sample *rs)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (((1<<TCP_CA_CWR) | (1<<TCP_CA_Recovery)) &
+ (1 << inet_csk(sk)->icsk_ca_state)) {
+ /* Reduce cwnd if state mandates */
+ tcp_cwnd_reduction(sk, rs->acked_sacked, rs->losses, flag);
+
+ if (!before(tp->snd_una, tp->high_seq)) {
+ /* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */
+ if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH &&
+ inet_csk(sk)->icsk_ca_state == TCP_CA_CWR) {
+ tp->snd_cwnd = tp->snd_ssthresh;
+ tp->snd_cwnd_stamp = tcp_jiffies32;
+ }
+ // __cwnd_event(sk, CA_EVENT_COMPLETE_CWR);
+ }
+ } else if (tcp_may_raise_cwnd(sk, flag)) {
+ /* Advance cwnd if state allows */
+ cubictcp_cong_avoid(sk, ack, rs->acked_sacked);
+ tp->snd_cwnd_stamp = tcp_jiffies32;
+ }
+
+ tcp_update_pacing_rate(sk);
+}
+
+__u32 BPF_STRUCT_OPS(bpf_cubic_recalc_ssthresh, struct sock *sk)
+{
+ return cubictcp_recalc_ssthresh(sk);
+}
+
+void BPF_STRUCT_OPS(bpf_cubic_state, struct sock *sk, __u8 new_state)
+{
+ cubictcp_state(sk, new_state);
+}
+
+void BPF_STRUCT_OPS(bpf_cubic_acked, struct sock *sk,
+ const struct ack_sample *sample)
+{
+ cubictcp_acked(sk, sample);
+}
+
+__u32 BPF_STRUCT_OPS(bpf_cubic_undo_cwnd, struct sock *sk)
+{
+ return tcp_reno_undo_cwnd(sk);
+}
+
+
+SEC(".struct_ops")
+struct tcp_congestion_ops cubic = {
+ .init = (void *)bpf_cubic_init,
+ .ssthresh = (void *)bpf_cubic_recalc_ssthresh,
+ .cong_control = (void *)bpf_cubic_cong_control,
+ .set_state = (void *)bpf_cubic_state,
+ .undo_cwnd = (void *)bpf_cubic_undo_cwnd,
+ .cwnd_event = (void *)bpf_cubic_cwnd_event,
+ .pkts_acked = (void *)bpf_cubic_acked,
+ .name = "bpf_cubic",
+};
This patch adds a selftest to show the usage of the new arguments in cong_control. For simplicity's sake, the testing example reuses cubic's kernel functions. Signed-off-by: Miao Xu <miaxu@meta.com> --- tools/testing/selftests/bpf/bpf_tcp_helpers.h | 23 +++ .../bpf/progs/bpf_cubic_cong_control.c | 176 ++++++++++++++++++ 2 files changed, 199 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/bpf_cubic_cong_control.c