From: vpillai <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, 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>,
aubrey.li@linux.intel.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>,
Joel Fernandes <joelaf@google.com>,
joel@joelfernandes.org,
Vineeth Remanan Pillai <vpillai@digitalocean.com>
Subject: [RFC PATCH 05/13] sched: Basic tracking of matching tasks
Date: Wed, 4 Mar 2020 16:59:55 +0000 [thread overview]
Message-ID: <bffdea4543bdf829b3937f7e01f74845043b8c0d.1583332765.git.vpillai@digitalocean.com> (raw)
In-Reply-To: <cover.1583332764.git.vpillai@digitalocean.com>
In-Reply-To: <cover.1583332764.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 716ad1d8d95e..80ec54706282 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -680,10 +680,16 @@ 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 ba17ff8a8663..452ce5bb9321 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -77,6 +77,141 @@ 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:
*
@@ -135,6 +270,11 @@ 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 */
/*
@@ -1354,6 +1494,9 @@ 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);
@@ -1368,6 +1511,9 @@ 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 cffc59a8b481..d6c932e8d554 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -247,33 +247,11 @@ 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)
@@ -434,33 +412,9 @@ 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 a3941b2ee29e..a38ae770dfd6 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1004,6 +1004,10 @@ struct rq {
/* per rq */
struct rq *core;
unsigned int core_enabled;
+ struct rb_root core_tree;
+
+ /* shared state */
+ unsigned int core_task_seq;
#endif
};
@@ -1083,6 +1087,57 @@ 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:[~2020-03-04 17:00 UTC|newest]
Thread overview: 110+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-04 16:59 [RFC PATCH 00/13] Core scheduling v5 vpillai
2020-03-04 16:59 ` [RFC PATCH 01/13] sched: Wrap rq::lock access vpillai
2020-03-04 16:59 ` [RFC PATCH 02/13] sched: Introduce sched_class::pick_task() vpillai
2020-03-04 16:59 ` [RFC PATCH 03/13] sched: Core-wide rq->lock vpillai
2020-04-01 11:42 ` [PATCH] sched/arm64: store cpu topology before notify_cpu_starting Cheng Jian
2020-04-01 13:23 ` Valentin Schneider
2020-04-06 8:00 ` chengjian (D)
2020-04-09 9:59 ` Sudeep Holla
2020-04-09 10:32 ` Valentin Schneider
2020-04-09 11:08 ` Sudeep Holla
2020-04-09 17:54 ` Joel Fernandes
2020-04-10 13:49 ` chengjian (D)
2020-04-14 11:36 ` [RFC PATCH 03/13] sched: Core-wide rq->lock Peter Zijlstra
2020-04-14 21:35 ` Vineeth Remanan Pillai
2020-04-15 10:55 ` Peter Zijlstra
2020-04-14 14:32 ` Peter Zijlstra
2020-03-04 16:59 ` [RFC PATCH 04/13] sched/fair: Add a few assertions vpillai
2020-03-04 16:59 ` vpillai [this message]
2020-03-04 16:59 ` [RFC PATCH 06/13] sched: Update core scheduler queue when taking cpu online/offline vpillai
2020-03-04 16:59 ` [RFC PATCH 07/13] sched: Add core wide task selection and scheduling vpillai
2020-04-14 13:35 ` Peter Zijlstra
2020-04-16 23:32 ` Tim Chen
2020-04-17 10:57 ` Peter Zijlstra
2020-04-16 3:39 ` Chen Yu
2020-04-16 19:59 ` Vineeth Remanan Pillai
2020-04-17 11:18 ` Peter Zijlstra
2020-04-19 15:31 ` Chen Yu
2020-05-21 23:14 ` Joel Fernandes
2020-05-21 23:16 ` Joel Fernandes
2020-05-22 2:35 ` Joel Fernandes
2020-05-22 3:44 ` Aaron Lu
2020-05-22 20:13 ` Joel Fernandes
2020-03-04 16:59 ` [RFC PATCH 08/13] sched/fair: wrapper for cfs_rq->min_vruntime vpillai
2020-03-04 16:59 ` [RFC PATCH 09/13] sched/fair: core wide vruntime comparison vpillai
2020-04-14 13:56 ` Peter Zijlstra
2020-04-15 3:34 ` Aaron Lu
2020-04-15 4:07 ` Aaron Lu
2020-04-15 21:24 ` Vineeth Remanan Pillai
2020-04-17 9:40 ` Aaron Lu
2020-04-20 8:07 ` [PATCH updated] sched/fair: core wide cfs task priority comparison Aaron Lu
2020-04-20 22:26 ` Vineeth Remanan Pillai
2020-04-21 2:51 ` Aaron Lu
2020-04-24 14:24 ` [PATCH updated v2] " Aaron Lu
2020-05-06 14:35 ` Peter Zijlstra
2020-05-08 8:44 ` Aaron Lu
2020-05-08 9:09 ` Peter Zijlstra
2020-05-08 12:34 ` Aaron Lu
2020-05-14 13:02 ` Peter Zijlstra
2020-05-14 22:51 ` Vineeth Remanan Pillai
2020-05-15 10:38 ` Peter Zijlstra
2020-05-15 10:43 ` Peter Zijlstra
2020-05-15 14:24 ` Vineeth Remanan Pillai
2020-05-16 3:42 ` Aaron Lu
2020-05-22 9:40 ` Aaron Lu
2020-06-08 1:41 ` Ning, Hongyu
2020-03-04 17:00 ` [RFC PATCH 10/13] sched: Trivial forced-newidle balancer vpillai
2020-03-04 17:00 ` [RFC PATCH 11/13] sched: migration changes for core scheduling vpillai
2020-06-12 13:21 ` Joel Fernandes
2020-06-12 21:32 ` Vineeth Remanan Pillai
2020-06-13 2:25 ` Joel Fernandes
2020-06-13 18:59 ` Vineeth Remanan Pillai
2020-06-15 2:05 ` Li, Aubrey
2020-03-04 17:00 ` [RFC PATCH 12/13] sched: cgroup tagging interface " vpillai
2020-06-26 15:06 ` Vineeth Remanan Pillai
2020-03-04 17:00 ` [RFC PATCH 13/13] sched: Debug bits vpillai
2020-03-04 17:36 ` [RFC PATCH 00/13] Core scheduling v5 Tim Chen
2020-03-04 17:42 ` Vineeth Remanan Pillai
2020-04-14 14:21 ` Peter Zijlstra
2020-04-15 16:32 ` Joel Fernandes
2020-04-17 11:12 ` Peter Zijlstra
2020-04-17 12:35 ` Alexander Graf
2020-04-17 13:08 ` Peter Zijlstra
2020-04-18 2:25 ` Joel Fernandes
2020-05-09 14:35 ` Dario Faggioli
[not found] ` <38805656-2e2f-222a-c083-692f4b113313@linux.intel.com>
2020-05-09 3:39 ` Ning, Hongyu
2020-05-14 20:51 ` FW: " Gruza, Agata
2020-05-10 23:46 ` [PATCH RFC] Add support for core-wide protection of IRQ and softirq Joel Fernandes (Google)
2020-05-11 13:49 ` Peter Zijlstra
2020-05-11 14:54 ` Joel Fernandes
2020-05-20 22:26 ` [PATCH RFC] sched: Add a per-thread core scheduling interface Joel Fernandes (Google)
2020-05-21 4:09 ` [PATCH RFC] sched: Add a per-thread core scheduling interface(Internet mail) benbjiang(蒋彪)
2020-05-21 13:49 ` Joel Fernandes
2020-05-21 8:51 ` [PATCH RFC] sched: Add a per-thread core scheduling interface Peter Zijlstra
2020-05-21 13:47 ` Joel Fernandes
2020-05-21 20:20 ` Vineeth Remanan Pillai
2020-05-22 12:59 ` Peter Zijlstra
2020-05-22 21:35 ` Joel Fernandes
2020-05-24 14:00 ` Phil Auld
2020-05-28 14:51 ` Joel Fernandes
2020-05-28 17:01 ` Peter Zijlstra
2020-05-28 18:17 ` Phil Auld
2020-05-28 18:34 ` Phil Auld
2020-05-28 18:23 ` Joel Fernandes
2020-05-21 18:31 ` Linus Torvalds
2020-05-21 20:40 ` Joel Fernandes
2020-05-21 21:58 ` Jesse Barnes
2020-05-22 16:33 ` Linus Torvalds
2020-05-20 22:37 ` [PATCH RFC v2] Add support for core-wide protection of IRQ and softirq Joel Fernandes (Google)
2020-05-20 22:48 ` [PATCH RFC] sched: Use sched-RCU in core-scheduling balancing logic Joel Fernandes (Google)
2020-05-21 22:52 ` Paul E. McKenney
2020-05-22 1:26 ` Joel Fernandes
2020-06-25 20:12 ` [RFC PATCH 00/13] Core scheduling v5 Vineeth Remanan Pillai
2020-06-26 1:47 ` Joel Fernandes
2020-06-26 14:36 ` Vineeth Remanan Pillai
2020-06-26 15:10 ` Joel Fernandes
2020-06-26 15:12 ` Joel Fernandes
2020-06-27 16:21 ` Joel Fernandes
2020-06-30 14:11 ` Phil Auld
2020-06-29 12:33 ` Li, Aubrey
2020-06-29 19:41 ` Vineeth Remanan Pillai
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=bffdea4543bdf829b3937f7e01f74845043b8c0d.1583332765.git.vpillai@digitalocean.com \
--to=vpillai@digitalocean.com \
--cc=aaron.lwe@gmail.com \
--cc=aubrey.intel@gmail.com \
--cc=aubrey.li@linux.intel.com \
--cc=fweisbec@gmail.com \
--cc=jdesfossez@digitalocean.com \
--cc=joel@joelfernandes.org \
--cc=joelaf@google.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).