From: Vineeth Remanan Pillai <vpillai@digitalocean.com>
To: Nishanth Aravamudan <naravamudan@digitalocean.com>,
Julien Desfossez <jdesfossez@digitalocean.com>,
Peter Zijlstra <peterz@infradead.org>,
Tim Chen <tim.c.chen@linux.intel.com>,
mingo@kernel.org, tglx@linutronix.de, pjt@google.com,
torvalds@linux-foundation.org
Cc: linux-kernel@vger.kernel.org, Dario Faggioli <dfaggioli@suse.com>,
fweisbec@gmail.com, keescook@chromium.org, kerrnel@google.com,
Phil Auld <pauld@redhat.com>, Aaron Lu <aaron.lwe@gmail.com>,
Aubrey Li <aubrey.intel@gmail.com>,
Valentin Schneider <valentin.schneider@arm.com>,
Mel Gorman <mgorman@techsingularity.net>,
Pawan Gupta <pawan.kumar.gupta@linux.intel.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Vineeth Remanan Pillai <vpillai@digitalocean.com>
Subject: [RFC PATCH v4 11/19] sched: Basic tracking of matching tasks
Date: Wed, 30 Oct 2019 18:33:24 +0000 [thread overview]
Message-ID: <ca8ef62d1eadc51a8d1056db5e1c38ecac09379e.1572437285.git.vpillai@digitalocean.com> (raw)
In-Reply-To: <cover.1572437285.git.vpillai@digitalocean.com>
In-Reply-To: <cover.1572437285.git.vpillai@digitalocean.com>
From: Peter Zijlstra <peterz@infradead.org>
Introduce task_struct::core_cookie as an opaque identifier for core
scheduling. When enabled; core scheduling will only allow matching
task to be on the core; where idle matches everything.
When task_struct::core_cookie is set (and core scheduling is enabled)
these tasks are indexed in a second RB-tree, first on cookie value
then on scheduling function, such that matching task selection always
finds the most elegible match.
NOTE: *shudder* at the overhead...
NOTE: *sigh*, a 3rd copy of the scheduling function; the alternative
is per class tracking of cookies and that just duplicates a lot of
stuff for no raisin (the 2nd copy lives in the rt-mutex PI code).
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Vineeth Remanan Pillai <vpillai@digitalocean.com>
Signed-off-by: Julien Desfossez <jdesfossez@digitalocean.com>
---
include/linux/sched.h | 8 ++-
kernel/sched/core.c | 146 ++++++++++++++++++++++++++++++++++++++++++
kernel/sched/fair.c | 46 -------------
kernel/sched/sched.h | 55 ++++++++++++++++
4 files changed, 208 insertions(+), 47 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9f51932bd543..d319219ea58f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -688,10 +688,16 @@ struct task_struct {
const struct sched_class *sched_class;
struct sched_entity se;
struct sched_rt_entity rt;
+ struct sched_dl_entity dl;
+
+#ifdef CONFIG_SCHED_CORE
+ struct rb_node core_node;
+ unsigned long core_cookie;
+#endif
+
#ifdef CONFIG_CGROUP_SCHED
struct task_group *sched_task_group;
#endif
- struct sched_dl_entity dl;
#ifdef CONFIG_UCLAMP_TASK
/* Clamp values requested for a scheduling entity */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0427cf610d6a..44dadbe9a2d0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -76,6 +76,141 @@ int sysctl_sched_rt_runtime = 950000;
DEFINE_STATIC_KEY_FALSE(__sched_core_enabled);
+/* kernel prio, less is more */
+static inline int __task_prio(struct task_struct *p)
+{
+ if (p->sched_class == &stop_sched_class) /* trumps deadline */
+ return -2;
+
+ if (rt_prio(p->prio)) /* includes deadline */
+ return p->prio; /* [-1, 99] */
+
+ if (p->sched_class == &idle_sched_class)
+ return MAX_RT_PRIO + NICE_WIDTH; /* 140 */
+
+ return MAX_RT_PRIO + MAX_NICE; /* 120, squash fair */
+}
+
+/*
+ * l(a,b)
+ * le(a,b) := !l(b,a)
+ * g(a,b) := l(b,a)
+ * ge(a,b) := !l(a,b)
+ */
+
+/* real prio, less is less */
+static inline bool prio_less(struct task_struct *a, struct task_struct *b)
+{
+
+ int pa = __task_prio(a), pb = __task_prio(b);
+
+ if (-pa < -pb)
+ return true;
+
+ if (-pb < -pa)
+ return false;
+
+ if (pa == -1) /* dl_prio() doesn't work because of stop_class above */
+ return !dl_time_before(a->dl.deadline, b->dl.deadline);
+
+ if (pa == MAX_RT_PRIO + MAX_NICE) { /* fair */
+ u64 vruntime = b->se.vruntime;
+
+ /*
+ * Normalize the vruntime if tasks are in different cpus.
+ */
+ if (task_cpu(a) != task_cpu(b)) {
+ vruntime -= task_cfs_rq(b)->min_vruntime;
+ vruntime += task_cfs_rq(a)->min_vruntime;
+ }
+
+ return !((s64)(a->se.vruntime - vruntime) <= 0);
+ }
+
+ return false;
+}
+
+static inline bool __sched_core_less(struct task_struct *a, struct task_struct *b)
+{
+ if (a->core_cookie < b->core_cookie)
+ return true;
+
+ if (a->core_cookie > b->core_cookie)
+ return false;
+
+ /* flip prio, so high prio is leftmost */
+ if (prio_less(b, a))
+ return true;
+
+ return false;
+}
+
+static void sched_core_enqueue(struct rq *rq, struct task_struct *p)
+{
+ struct rb_node *parent, **node;
+ struct task_struct *node_task;
+
+ rq->core->core_task_seq++;
+
+ if (!p->core_cookie)
+ return;
+
+ node = &rq->core_tree.rb_node;
+ parent = *node;
+
+ while (*node) {
+ node_task = container_of(*node, struct task_struct, core_node);
+ parent = *node;
+
+ if (__sched_core_less(p, node_task))
+ node = &parent->rb_left;
+ else
+ node = &parent->rb_right;
+ }
+
+ rb_link_node(&p->core_node, parent, node);
+ rb_insert_color(&p->core_node, &rq->core_tree);
+}
+
+static void sched_core_dequeue(struct rq *rq, struct task_struct *p)
+{
+ rq->core->core_task_seq++;
+
+ if (!p->core_cookie)
+ return;
+
+ rb_erase(&p->core_node, &rq->core_tree);
+}
+
+/*
+ * Find left-most (aka, highest priority) task matching @cookie.
+ */
+static struct task_struct *sched_core_find(struct rq *rq, unsigned long cookie)
+{
+ struct rb_node *node = rq->core_tree.rb_node;
+ struct task_struct *node_task, *match;
+
+ /*
+ * The idle task always matches any cookie!
+ */
+ match = idle_sched_class.pick_task(rq);
+
+ while (node) {
+ node_task = container_of(node, struct task_struct, core_node);
+
+ if (cookie < node_task->core_cookie) {
+ node = node->rb_left;
+ } else if (cookie > node_task->core_cookie) {
+ node = node->rb_right;
+ } else {
+ match = node_task;
+ node = node->rb_left;
+ }
+ }
+
+ return match;
+}
+
/*
* The static-key + stop-machine variable are needed such that:
*
@@ -134,6 +269,11 @@ void sched_core_put(void)
mutex_unlock(&sched_core_mutex);
}
+#else /* !CONFIG_SCHED_CORE */
+
+static inline void sched_core_enqueue(struct rq *rq, struct task_struct *p) { }
+static inline void sched_core_dequeue(struct rq *rq, struct task_struct *p) { }
+
#endif /* CONFIG_SCHED_CORE */
/*
@@ -1233,6 +1373,9 @@ static inline void init_uclamp(void) { }
static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
{
+ if (sched_core_enabled(rq))
+ sched_core_enqueue(rq, p);
+
if (!(flags & ENQUEUE_NOCLOCK))
update_rq_clock(rq);
@@ -1247,6 +1390,9 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
{
+ if (sched_core_enabled(rq))
+ sched_core_dequeue(rq, p);
+
if (!(flags & DEQUEUE_NOCLOCK))
update_rq_clock(rq);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cc78b334e1c3..e3b7e8ba1420 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -248,33 +248,11 @@ const struct sched_class fair_sched_class;
*/
#ifdef CONFIG_FAIR_GROUP_SCHED
-static inline struct task_struct *task_of(struct sched_entity *se)
-{
- SCHED_WARN_ON(!entity_is_task(se));
- return container_of(se, struct task_struct, se);
-}
/* Walk up scheduling entities hierarchy */
#define for_each_sched_entity(se) \
for (; se; se = se->parent)
-static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
-{
- return p->se.cfs_rq;
-}
-
-/* runqueue on which this entity is (to be) queued */
-static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
-{
- return se->cfs_rq;
-}
-
-/* runqueue "owned" by this group */
-static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
-{
- return grp->my_q;
-}
-
static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len)
{
if (!path)
@@ -435,33 +413,9 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
#else /* !CONFIG_FAIR_GROUP_SCHED */
-static inline struct task_struct *task_of(struct sched_entity *se)
-{
- return container_of(se, struct task_struct, se);
-}
-
#define for_each_sched_entity(se) \
for (; se; se = NULL)
-static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
-{
- return &task_rq(p)->cfs;
-}
-
-static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
-{
- struct task_struct *p = task_of(se);
- struct rq *rq = task_rq(p);
-
- return &rq->cfs;
-}
-
-/* runqueue "owned" by this group */
-static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
-{
- return NULL;
-}
-
static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len)
{
if (path)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 2ba68ab093ee..666b3bc2cfc2 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -996,6 +996,10 @@ struct rq {
/* per rq */
struct rq *core;
unsigned int core_enabled;
+ struct rb_root core_tree;
+
+ /* shared state */
+ unsigned int core_task_seq;
#endif
};
@@ -1075,6 +1079,57 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
#define raw_rq() raw_cpu_ptr(&runqueues)
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static inline struct task_struct *task_of(struct sched_entity *se)
+{
+ SCHED_WARN_ON(!entity_is_task(se));
+ return container_of(se, struct task_struct, se);
+}
+
+static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
+{
+ return p->se.cfs_rq;
+}
+
+/* runqueue on which this entity is (to be) queued */
+static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
+{
+ return se->cfs_rq;
+}
+
+/* runqueue "owned" by this group */
+static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
+{
+ return grp->my_q;
+}
+
+#else
+
+static inline struct task_struct *task_of(struct sched_entity *se)
+{
+ return container_of(se, struct task_struct, se);
+}
+
+static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
+{
+ return &task_rq(p)->cfs;
+}
+
+static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
+{
+ struct task_struct *p = task_of(se);
+ struct rq *rq = task_rq(p);
+
+ return &rq->cfs;
+}
+
+/* runqueue "owned" by this group */
+static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
+{
+ return NULL;
+}
+#endif
+
extern void update_rq_clock(struct rq *rq);
static inline u64 __rq_clock_broken(struct rq *rq)
--
2.17.1
next prev parent reply other threads:[~2019-10-30 18:34 UTC|newest]
Thread overview: 84+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-30 18:33 [RFC PATCH v4 00/19] Core scheduling v4 Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 01/19] stop_machine: Fix stop_cpus_in_progress ordering Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 02/19] sched: Fix kerneldoc comment for ia64_set_curr_task Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 03/19] sched: Wrap rq::lock access Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 04/19] sched/{rt,deadline}: Fix set_next_task vs pick_next_task Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 05/19] sched: Add task_struct pointer to sched_class::set_curr_task Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 06/19] sched/fair: Export newidle_balance() Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 07/19] sched: Allow put_prev_task() to drop rq->lock Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 08/19] sched: Rework pick_next_task() slow-path Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 09/19] sched: Introduce sched_class::pick_task() Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 10/19] sched: Core-wide rq->lock Vineeth Remanan Pillai
2019-10-30 18:33 ` Vineeth Remanan Pillai [this message]
2019-10-30 18:33 ` [RFC PATCH v4 12/19] sched: A quick and dirty cgroup tagging interface Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 13/19] sched: Add core wide task selection and scheduling Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 14/19] sched/fair: Add a few assertions Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 15/19] sched: Trivial forced-newidle balancer Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 16/19] sched: Debug bits Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 17/19] sched/fair: wrapper for cfs_rq->min_vruntime Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 18/19] sched/fair: core wide vruntime comparison Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 19/19] sched/fair : Wake up forced idle siblings if needed Vineeth Remanan Pillai
2019-10-31 11:42 ` [RFC PATCH v4 00/19] Core scheduling v4 Li, Aubrey
2019-11-01 11:33 ` Li, Aubrey
2019-11-08 3:20 ` Li, Aubrey
2019-10-31 18:42 ` Phil Auld
2019-11-01 14:03 ` Vineeth Remanan Pillai
2019-11-01 16:35 ` Greg Kerr
2019-11-01 18:07 ` Dario Faggioli
2019-11-12 1:45 ` Dario Faggioli
2019-11-13 17:16 ` Tim Chen
2020-01-02 2:28 ` Aubrey Li
2020-01-10 23:19 ` Tim Chen
2019-11-11 19:10 ` Tim Chen
2020-01-14 1:12 ` Tim Chen
2020-01-14 15:40 ` Vineeth Remanan Pillai
2020-01-15 3:43 ` Li, Aubrey
2020-01-15 19:33 ` Tim Chen
2020-01-16 1:45 ` Aubrey Li
2020-01-17 16:00 ` Vineeth Remanan Pillai
2020-01-22 18:04 ` Gruza, Agata
2020-01-28 2:40 ` Dario Faggioli
[not found] ` <CANaguZDDpzrzdTmvjXvCmV2c+wBt6mXWSz4Vn-LJ-onc_Oj=yw@mail.gmail.com>
2020-02-01 15:31 ` Dario Faggioli
2020-02-06 0:28 ` Tim Chen
2020-02-06 22:37 ` Julien Desfossez
2020-02-12 23:07 ` Julien Desfossez
2020-02-13 18:37 ` Tim Chen
2020-02-14 6:10 ` Aubrey Li
[not found] ` <CANaguZC40mDHfL1H_9AA7H8cyd028t9PQVRqQ3kB4ha8R7hhqg@mail.gmail.com>
2020-02-15 6:01 ` Aubrey Li
[not found] ` <CANaguZBj_x_2+9KwbHCQScsmraC_mHdQB6uRqMTYMmvhBYfv2Q@mail.gmail.com>
2020-02-21 23:20 ` Julien Desfossez
2020-03-17 0:55 ` Joel Fernandes
2020-03-17 19:07 ` Tim Chen
2020-03-17 20:18 ` Tim Chen
2020-03-18 1:10 ` Joel Fernandes
2020-03-17 21:17 ` Thomas Gleixner
2020-03-17 21:58 ` Tim Chen
2020-03-18 1:03 ` Joel Fernandes
2020-03-18 2:30 ` Joel Fernandes
2020-03-18 0:52 ` Joel Fernandes
2020-03-18 11:53 ` Thomas Gleixner
2020-03-19 1:54 ` Joel Fernandes
2020-02-25 3:44 ` Aaron Lu
2020-02-25 5:32 ` Aubrey Li
2020-02-25 7:34 ` Aaron Lu
2020-02-25 10:40 ` Aubrey Li
2020-02-25 11:21 ` Aaron Lu
2020-02-25 13:41 ` Aubrey Li
[not found] ` <CANaguZD205ccu1V_2W-QuMRrJA9SjJ5ng1do4NCdLy8NDKKrbA@mail.gmail.com>
2020-02-26 3:13 ` Aaron Lu
2020-02-26 7:21 ` Aubrey Li
[not found] ` <CANaguZDQZg-Z6aNpeLcjQ-cGm3X8CQOkZ_hnJNUyqDRM=yVDFQ@mail.gmail.com>
2020-02-27 4:45 ` Aubrey Li
2020-02-28 23:55 ` Tim Chen
2020-03-03 14:59 ` Li, Aubrey
2020-03-03 23:54 ` Li, Aubrey
2020-03-05 4:33 ` Aaron Lu
2020-03-05 6:10 ` Li, Aubrey
2020-03-05 8:52 ` Aaron Lu
2020-02-27 2:04 ` Aaron Lu
2020-02-27 14:10 ` Phil Auld
2020-02-27 14:37 ` Aubrey Li
2020-02-28 2:54 ` Aaron Lu
2020-03-05 13:45 ` Aubrey Li
2020-03-06 2:41 ` Aaron Lu
2020-03-06 18:06 ` Tim Chen
2020-03-06 18:33 ` Phil Auld
2020-03-06 21:44 ` Tim Chen
2020-03-07 3:13 ` Aaron Lu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=ca8ef62d1eadc51a8d1056db5e1c38ecac09379e.1572437285.git.vpillai@digitalocean.com \
--to=vpillai@digitalocean.com \
--cc=aaron.lwe@gmail.com \
--cc=aubrey.intel@gmail.com \
--cc=dfaggioli@suse.com \
--cc=fweisbec@gmail.com \
--cc=jdesfossez@digitalocean.com \
--cc=keescook@chromium.org \
--cc=kerrnel@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mgorman@techsingularity.net \
--cc=mingo@kernel.org \
--cc=naravamudan@digitalocean.com \
--cc=pauld@redhat.com \
--cc=pawan.kumar.gupta@linux.intel.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=pjt@google.com \
--cc=tglx@linutronix.de \
--cc=tim.c.chen@linux.intel.com \
--cc=torvalds@linux-foundation.org \
--cc=valentin.schneider@arm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).