bpf: Add bpf_ktime_get_coarse_ns helper

The helper uses CLOCK_MONOTONIC_COARSE source of time that is less
accurate but more performant.

We have a BPF CGROUP_SKB firewall that supports event logging through
bpf_perf_event_output(). Each event has a timestamp and currently we use
bpf_ktime_get_ns() for it. Use of bpf_ktime_get_coarse_ns() saves ~15-20
ns in time required for event logging.

bpf_ktime_get_ns():
EgressLogByRemoteEndpoint                              113.82ns    8.79M

bpf_ktime_get_coarse_ns():
EgressLogByRemoteEndpoint                               95.40ns   10.48M

Signed-off-by: Dmitrii Banshchikov <me@ubique.spb.ru>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20201117184549.257280-1-me@ubique.spb.ru

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 581b2a2e78eb71d0109a05efd43c92745ca6deeb..e1bcb6d7345cd05f0f7be78bd0917fc42651683a 100644 (file)
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1842,6 +1842,7 @@ extern const struct bpf_func_proto bpf_copy_from_user_proto;
 extern const struct bpf_func_proto bpf_snprintf_btf_proto;
 extern const struct bpf_func_proto bpf_per_cpu_ptr_proto;
 extern const struct bpf_func_proto bpf_this_cpu_ptr_proto;
+extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
        enum bpf_func_id func_id, const struct bpf_prog *prog);

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a52299b80b9d2cea8050a69af27971401a0cd12b..3ca6146f001ae1694ca3301111259c118b5afada 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3797,6 +3797,16 @@ union bpf_attr {
  *             is cleared if the flag is not specified.
  *     Return
  *             **-EINVAL** if invalid *flags* are passed, zero otherwise.
+ *
+ * u64 bpf_ktime_get_coarse_ns(void)
+ *     Description
+ *             Return a coarse-grained version of the time elapsed since
+ *             system boot, in nanoseconds. Does not include time the system
+ *             was suspended.
+ *
+ *             See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**)
+ *     Return
+ *             Current *ktime*.
  */
 #define __BPF_FUNC_MAPPER(FN)          \
        FN(unspec),                     \
@@ -3959,6 +3969,7 @@ union bpf_attr {
        FN(task_storage_delete),        \
        FN(get_current_task_btf),       \
        FN(bprm_opts_set),              \
+       FN(ktime_get_coarse_ns),        \
        /* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 55454d2278b17c84f1ceee9ba27688f6205afd62..ff55cbcfbab48516613559ac5f1a59774f93e2ed 100644 (file)
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2211,6 +2211,7 @@ const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
 const struct bpf_func_proto bpf_get_numa_node_id_proto __weak;
 const struct bpf_func_proto bpf_ktime_get_ns_proto __weak;
 const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak;
+const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto __weak;
 
 const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
 const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 25520f5eeaf687d836079b42ca159aeb977ae0c7..2c395deae279a2b63ec12b5f6db2ddff36e1805d 100644 (file)
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -167,6 +167,17 @@ const struct bpf_func_proto bpf_ktime_get_boot_ns_proto = {
        .ret_type       = RET_INTEGER,
 };
 
+BPF_CALL_0(bpf_ktime_get_coarse_ns)
+{
+       return ktime_get_coarse_ns();
+}
+
+const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto = {
+       .func           = bpf_ktime_get_coarse_ns,
+       .gpl_only       = false,
+       .ret_type       = RET_INTEGER,
+};
+
 BPF_CALL_0(bpf_get_current_pid_tgid)
 {
        struct task_struct *task = current;
@@ -685,6 +696,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
                return &bpf_ktime_get_ns_proto;
        case BPF_FUNC_ktime_get_boot_ns:
                return &bpf_ktime_get_boot_ns_proto;
+       case BPF_FUNC_ktime_get_coarse_ns:
+               return &bpf_ktime_get_coarse_ns_proto;
        case BPF_FUNC_ringbuf_output:
                return &bpf_ringbuf_output_proto;
        case BPF_FUNC_ringbuf_reserve:

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 02986c7b90eb04a6f4b03cc8c8c68910feb30923..d255bc9b2bfa316e6355d640bce73ed9421904e4 100644 (file)
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1280,6 +1280,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
                return &bpf_ktime_get_ns_proto;
        case BPF_FUNC_ktime_get_boot_ns:
                return &bpf_ktime_get_boot_ns_proto;
+       case BPF_FUNC_ktime_get_coarse_ns:
+               return &bpf_ktime_get_coarse_ns_proto;
        case BPF_FUNC_tail_call:
                return &bpf_tail_call_proto;
        case BPF_FUNC_get_current_pid_tgid:

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a52299b80b9d2cea8050a69af27971401a0cd12b..3ca6146f001ae1694ca3301111259c118b5afada 100644 (file)
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3797,6 +3797,16 @@ union bpf_attr {
  *             is cleared if the flag is not specified.
  *     Return
  *             **-EINVAL** if invalid *flags* are passed, zero otherwise.
+ *
+ * u64 bpf_ktime_get_coarse_ns(void)
+ *     Description
+ *             Return a coarse-grained version of the time elapsed since
+ *             system boot, in nanoseconds. Does not include time the system
+ *             was suspended.
+ *
+ *             See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**)
+ *     Return
+ *             Current *ktime*.
  */
 #define __BPF_FUNC_MAPPER(FN)          \
        FN(unspec),                     \
@@ -3959,6 +3969,7 @@ union bpf_attr {
        FN(task_storage_delete),        \
        FN(get_current_task_btf),       \
        FN(bprm_opts_set),              \
+       FN(ktime_get_coarse_ns),        \
        /* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper