[PATCH bpf-next 1/2] bpf: Add ability to pin bpf timer to calling CPU

[David Vernet <void@xxxxxxxxxxxxx>]

BPF supports creating high resolution timers using bpf_timer_* helper
functions. Currently, only the BPF_F_TIMER_ABS flag is supported, which
specifies that the timeout should be interpreted as absolute time. It
would also be useful to be able to pin that timer to a core. For
example, if you wanted to make a subset of cores run without timer
interrupts, and only have the timer be invoked on a single core.

This patch adds support for this with a new BPF_F_TIMER_CPU_PIN flag.
When specified, the HRTIMER_MODE_PINNED flag is passed to
hrtimer_start(). A subsequent patch will update selftests to validate.

Signed-off-by: David Vernet <void@xxxxxxxxxxxxx>
---
 include/uapi/linux/bpf.h       | 4 ++++
 kernel/bpf/helpers.c           | 5 ++++-
 tools/include/uapi/linux/bpf.h | 4 ++++
 3 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 70bfa997e896..a7d4a1a69f21 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5096,6 +5096,8 @@ union bpf_attr {
  *		**BPF_F_TIMER_ABS**
  *			Start the timer in absolute expire value instead of the
  *			default relative one.
+ *		**BPF_F_TIMER_CPU_PIN**
+ *			Timer will be pinned to the CPU of the caller.
  *
  *	Return
  *		0 on success.
@@ -7309,9 +7311,11 @@ struct bpf_core_relo {
  * Flags to control bpf_timer_start() behaviour.
  *     - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is
  *       relative to current time.
+ *     - BPF_F_TIMER_CPU_PIN: Timer will be pinned to the CPU of the caller.
  */
 enum {
 	BPF_F_TIMER_ABS = (1ULL << 0),
+	BPF_F_TIMER_CPU_PIN = (1ULL << 1),
 };
 
 /* BPF numbers iterator state */
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index dd1c69ee3375..d2840dd5b00d 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1272,7 +1272,7 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla
 
 	if (in_nmi())
 		return -EOPNOTSUPP;
-	if (flags > BPF_F_TIMER_ABS)
+	if (flags & ~(BPF_F_TIMER_ABS | BPF_F_TIMER_CPU_PIN))
 		return -EINVAL;
 	__bpf_spin_lock_irqsave(&timer->lock);
 	t = timer->timer;
@@ -1286,6 +1286,9 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla
 	else
 		mode = HRTIMER_MODE_REL_SOFT;
 
+	if (flags & BPF_F_TIMER_CPU_PIN)
+		mode |= HRTIMER_MODE_PINNED;
+
 	hrtimer_start(&t->timer, ns_to_ktime(nsecs), mode);
 out:
 	__bpf_spin_unlock_irqrestore(&timer->lock);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 70bfa997e896..a7d4a1a69f21 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5096,6 +5096,8 @@ union bpf_attr {
  *		**BPF_F_TIMER_ABS**
  *			Start the timer in absolute expire value instead of the
  *			default relative one.
+ *		**BPF_F_TIMER_CPU_PIN**
+ *			Timer will be pinned to the CPU of the caller.
  *
  *	Return
  *		0 on success.
@@ -7309,9 +7311,11 @@ struct bpf_core_relo {
  * Flags to control bpf_timer_start() behaviour.
  *     - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is
  *       relative to current time.
+ *     - BPF_F_TIMER_CPU_PIN: Timer will be pinned to the CPU of the caller.
  */
 enum {
 	BPF_F_TIMER_ABS = (1ULL << 0),
+	BPF_F_TIMER_CPU_PIN = (1ULL << 1),
 };
 
 /* BPF numbers iterator state */
-- 
2.41.0