From: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
When a process reduces its number of threads or clears bits in its CPU
affinity mask, the mm_cid allocation should eventually converge towards
smaller values.
However, the change introduced by:
commit 7e019dcc470f ("sched: Improve cache locality of RSEQ concurrency
IDs for intermittent workloads")
adds a per-mm/CPU recent_cid which is never unset unless a thread
migrates.
This is a tradeoff between:
A) Preserving cache locality after a transition from many threads to few
threads, or after reducing the hamming weight of the allowed CPU mask.
B) Making the mm_cid upper bounds wrt nr threads and allowed CPU mask
easy to document and understand.
C) Allowing applications to eventually react to mm_cid compaction after
reduction of the nr threads or allowed CPU mask, making the tracking
of mm_cid compaction easier by shrinking it back towards 0 or not.
D) Making sure applications that periodically reduce and then increase
again the nr threads or allowed CPU mask still benefit from good
cache locality with mm_cid.
Introduce the following changes:
* After shrinking the number of threads or reducing the number of
allowed CPUs, reduce the value of max_nr_cid so expansion of CID
allocation will preserve cache locality if the number of threads or
allowed CPUs increase again.
* Only re-use a recent_cid if it is within the max_nr_cid upper bound,
else find the first available CID.
Fixes: 7e019dcc470f ("sched: Improve cache locality of RSEQ concurrency IDs for intermittent workloads")
Cc: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Marco Elver <elver@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Tested-by: Gabriele Monaco <gmonaco@xxxxxxxxxx>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Signed-off-by: Gabriele Monaco <gmonaco@xxxxxxxxxx>
---
include/linux/mm_types.h | 7 ++++---
kernel/sched/sched.h | 25 ++++++++++++++++++++++---
2 files changed, 26 insertions(+), 6 deletions(-)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 7361a8f3ab68..d56948a74254 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -843,10 +843,11 @@ struct mm_struct {
*/
unsigned int nr_cpus_allowed;
/**
- * @max_nr_cid: Maximum number of concurrency IDs allocated.
+ * @max_nr_cid: Maximum number of allowed concurrency
+ * IDs allocated.
*
- * Track the highest number of concurrency IDs allocated for the
- * mm.
+ * Track the highest number of allowed concurrency IDs
+ * allocated for the mm.
*/
atomic_t max_nr_cid;
/**
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 76f5f53a645f..b50dcd908702 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3657,10 +3657,28 @@ static inline int __mm_cid_try_get(struct task_struct *t, struct mm_struct *mm)
{
struct cpumask *cidmask = mm_cidmask(mm);
struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
- int cid = __this_cpu_read(pcpu_cid->recent_cid);
+ int cid, max_nr_cid, allowed_max_nr_cid;
+ /*
+ * After shrinking the number of threads or reducing the number
+ * of allowed cpus, reduce the value of max_nr_cid so expansion
+ * of cid allocation will preserve cache locality if the number
+ * of threads or allowed cpus increase again.
+ */
+ max_nr_cid = atomic_read(&mm->max_nr_cid);
+ while ((allowed_max_nr_cid = min_t(int, READ_ONCE(mm->nr_cpus_allowed),
+ atomic_read(&mm->mm_users))),
+ max_nr_cid > allowed_max_nr_cid) {
+ /* atomic_try_cmpxchg loads previous mm->max_nr_cid into max_nr_cid. */
+ if (atomic_try_cmpxchg(&mm->max_nr_cid, &max_nr_cid, allowed_max_nr_cid)) {
+ max_nr_cid = allowed_max_nr_cid;
+ break;
+ }
+ }
/* Try to re-use recent cid. This improves cache locality. */
- if (!mm_cid_is_unset(cid) && !cpumask_test_and_set_cpu(cid, cidmask))
+ cid = __this_cpu_read(pcpu_cid->recent_cid);
+ if (!mm_cid_is_unset(cid) && cid < max_nr_cid &&
+ !cpumask_test_and_set_cpu(cid, cidmask))
return cid;
/*
* Expand cid allocation if the maximum number of concurrency
@@ -3668,8 +3686,9 @@ static inline int __mm_cid_try_get(struct task_struct *t, struct mm_struct *mm)
* and number of threads. Expanding cid allocation as much as
* possible improves cache locality.
*/
- cid = atomic_read(&mm->max_nr_cid);
+ cid = max_nr_cid;
while (cid < READ_ONCE(mm->nr_cpus_allowed) && cid < atomic_read(&mm->mm_users)) {
+ /* atomic_try_cmpxchg loads previous mm->max_nr_cid into cid. */
if (!atomic_try_cmpxchg(&mm->max_nr_cid, &cid, cid + 1))
continue;
if (!cpumask_test_and_set_cpu(cid, cidmask))
--
2.47.1
