bpf: Add support for absolute value BPF timers

Add a new flag BPF_F_TIMER_ABS that can be passed to bpf_timer_start()
to start an absolute value timer instead of the default relative value.
This makes the timer expire at an exact point in time, instead of a time
with latencies induced by both the BPF and timer subsystems.

Suggested-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Tero Kristo <tero.kristo@linux.intel.com>
Link: https://lore.kernel.org/r/20230302114614.2985072-2-tero.kristo@linux.intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c969930..976b194 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4969,6 +4969,12 @@ union bpf_attr {
  *             different maps if key/value layout matches across maps.
  *             Every bpf_timer_set_callback() can have different callback_fn.
  *
+ *             *flags* can be one of:
+ *
+ *             **BPF_F_TIMER_ABS**
+ *                     Start the timer in absolute expire value instead of the
+ *                     default relative one.
+ *
  *     Return
  *             0 on success.
  *             **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier
@@ -7097,4 +7103,13 @@ struct bpf_core_relo {
        enum bpf_core_relo_kind kind;
 };
 
+/*
+ * Flags to control bpf_timer_start() behaviour.
+ *     - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is
+ *       relative to current time.
+ */
+enum {
+       BPF_F_TIMER_ABS = (1ULL << 0),
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 6fc0d6c..12f12e8 100644 (file)
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1264,10 +1264,11 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla
 {
        struct bpf_hrtimer *t;
        int ret = 0;
+       enum hrtimer_mode mode;
 
        if (in_nmi())
                return -EOPNOTSUPP;
-       if (flags)
+       if (flags > BPF_F_TIMER_ABS)
                return -EINVAL;
        __bpf_spin_lock_irqsave(&timer->lock);
        t = timer->timer;
@@ -1275,7 +1276,13 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla
                ret = -EINVAL;
                goto out;
        }
-       hrtimer_start(&t->timer, ns_to_ktime(nsecs), HRTIMER_MODE_REL_SOFT);
+
+       if (flags & BPF_F_TIMER_ABS)
+               mode = HRTIMER_MODE_ABS_SOFT;
+       else
+               mode = HRTIMER_MODE_REL_SOFT;
+
+       hrtimer_start(&t->timer, ns_to_ktime(nsecs), mode);
 out:
        __bpf_spin_unlock_irqrestore(&timer->lock);
        return ret;

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index c969930..976b194 100644 (file)
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4969,6 +4969,12 @@ union bpf_attr {
  *             different maps if key/value layout matches across maps.
  *             Every bpf_timer_set_callback() can have different callback_fn.
  *
+ *             *flags* can be one of:
+ *
+ *             **BPF_F_TIMER_ABS**
+ *                     Start the timer in absolute expire value instead of the
+ *                     default relative one.
+ *
  *     Return
  *             0 on success.
  *             **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier
@@ -7097,4 +7103,13 @@ struct bpf_core_relo {
        enum bpf_core_relo_kind kind;
 };
 
+/*
+ * Flags to control bpf_timer_start() behaviour.
+ *     - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is
+ *       relative to current time.
+ */
+enum {
+       BPF_F_TIMER_ABS = (1ULL << 0),
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */