On 6/21/24 23:58, Leonardo Bras wrote:
Some places in the kernel implement a parallel programming strategy
consisting on local_locks() for most of the work, and some rare remote
operations are scheduled on target cpu. This keeps cache bouncing low since
cacheline tends to be mostly local, and avoids the cost of locks in non-RT
kernels, even though the very few remote operations will be expensive due
to scheduling overhead.
On the other hand, for RT workloads this can represent a problem: getting
an important workload scheduled out to deal with some unrelated task is
sure to introduce unexpected deadline misses.
It's interesting, though, that local_lock()s in RT kernels become
spinlock(). We can make use of those to avoid scheduling work on a remote
cpu by directly updating another cpu's per_cpu structure, while holding
it's spinlock().
In order to do that, it's necessary to introduce a new set of functions to
make it possible to get another cpu's per-cpu "local" lock (qpw_{un,}lock*)
and also the corresponding queue_percpu_work_on() and flush_percpu_work()
helpers to run the remote work.
On non-RT kernels, no changes are expected, as every one of the introduced
helpers work the exactly same as the current implementation:
qpw_{un,}lock*() -> local_{un,}lock*() (ignores cpu parameter)
queue_percpu_work_on() -> queue_work_on()
flush_percpu_work() -> flush_work()
For RT kernels, though, qpw_{un,}lock*() will use the extra cpu parameter
to select the correct per-cpu structure to work on, and acquire the
spinlock for that cpu.
queue_percpu_work_on() will just call the requested function in the current
cpu, which will operate in another cpu's per-cpu object. Since the
local_locks() become spinlock()s in PREEMPT_RT, we are safe doing that.
flush_percpu_work() then becomes a no-op since no work is actually
scheduled on a remote cpu.
Some minimal code rework is needed in order to make this mechanism work:
The calls for local_{un,}lock*() on the functions that are currently
scheduled on remote cpus need to be replaced by qpw_{un,}lock_n*(), so in
RT kernels they can reference a different cpu. It's also necessary to use a
qpw_struct instead of a work_struct, but it just contains a work struct
and, in PREEMPT_RT, the target cpu.
This should have almost no impact on non-RT kernels: few this_cpu_ptr()
will become per_cpu_ptr(,smp_processor_id()).
On RT kernels, this should improve performance and reduce latency by
removing scheduling noise.
Signed-off-by: Leonardo Bras <leobras@xxxxxxxxxx>
---
include/linux/qpw.h | 88 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 88 insertions(+)
create mode 100644 include/linux/qpw.h
diff --git a/include/linux/qpw.h b/include/linux/qpw.h
new file mode 100644
index 000000000000..ea2686a01e5e
--- /dev/null
+++ b/include/linux/qpw.h
@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_QPW_H
+#define _LINUX_QPW_H
+
+#include "linux/local_lock.h"
+#include "linux/workqueue.h"
+
+#ifndef CONFIG_PREEMPT_RT
+
+struct qpw_struct {
+ struct work_struct work;
+};
+
+#define qpw_lock(lock, cpu) \
+ local_lock(lock)
+
+#define qpw_unlock(lock, cpu) \
+ local_unlock(lock)
+
+#define qpw_lock_irqsave(lock, flags, cpu) \
+ local_lock_irqsave(lock, flags)
+
+#define qpw_unlock_irqrestore(lock, flags, cpu) \
+ local_unlock_irqrestore(lock, flags)
+
+#define queue_percpu_work_on(c, wq, qpw) \
+ queue_work_on(c, wq, &(qpw)->work)
+
+#define flush_percpu_work(qpw) \
+ flush_work(&(qpw)->work)
+
+#define qpw_get_cpu(qpw) \
+ smp_processor_id()
+
+#define INIT_QPW(qpw, func, c) \
+ INIT_WORK(&(qpw)->work, (func))
+
+#else /* !CONFIG_PREEMPT_RT */
+
+struct qpw_struct {
+ struct work_struct work;
+ int cpu;
+};
+
+#define qpw_lock(__lock, cpu) \
+ do { \
+ migrate_disable(); \
+ spin_lock(per_cpu_ptr((__lock), cpu)); \
+ } while (0)
+
+#define qpw_unlock(__lock, cpu) \
+ do { \
+ spin_unlock(per_cpu_ptr((__lock), cpu)); \
+ migrate_enable(); \
+ } while (0)
Why there is a migrate_disable/enable() call in qpw_lock/unlock()? The
rt_spin_lock/unlock() calls have already include a
migrate_disable/enable() pair.
+
+#define qpw_lock_irqsave(lock, flags, cpu) \
+ do { \
+ typecheck(unsigned long, flags); \
+ flags = 0; \
+ qpw_lock(lock, cpu); \
+ } while (0)
+
+#define qpw_unlock_irqrestore(lock, flags, cpu) \
+ qpw_unlock(lock, cpu)
+
+#define queue_percpu_work_on(c, wq, qpw) \
+ do { \
+ struct qpw_struct *__qpw = (qpw); \
+ WARN_ON((c) != __qpw->cpu); \
+ __qpw->work.func(&__qpw->work); \
+ } while (0)
+
+#define flush_percpu_work(qpw) \
+ do {} while (0)
+
+#define qpw_get_cpu(w) \
+ container_of((w), struct qpw_struct, work)->cpu
+
+#define INIT_QPW(qpw, func, c) \
+ do { \
+ struct qpw_struct *__qpw = (qpw); \
+ INIT_WORK(&__qpw->work, (func)); \
+ __qpw->cpu = (c); \
+ } while (0)
+
+#endif /* CONFIG_PREEMPT_RT */
+#endif /* LINUX_QPW_H */
You may also consider adding a documentation file about the
qpw_lock/unlock() calls.
Cheers,
Longman
