From: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
To: "Peter Zijlstra (Intel)" <peterz@infradead.org>,
Juri Lelli <juri.lelli@redhat.com>,
Vincent Guittot <vincent.guittot@linaro.org>
Cc: Ricardo Neri <ricardo.neri@intel.com>,
"Ravi V. Shankar" <ravi.v.shankar@intel.com>,
Ben Segall <bsegall@google.com>,
Daniel Bristot de Oliveira <bristot@redhat.com>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
Len Brown <len.brown@intel.com>, Mel Gorman <mgorman@suse.de>,
"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>,
Steven Rostedt <rostedt@goodmis.org>,
Tim Chen <tim.c.chen@linux.intel.com>,
Valentin Schneider <vschneid@redhat.com>,
Lukasz Luba <lukasz.luba@arm.com>,
Ionela Voinescu <ionela.voinescu@arm.com>,
Zhao Liu <zhao1.liu@intel.com>,
"Yuan, Perry" <Perry.Yuan@amd.com>,
x86@kernel.org,
"Joel Fernandes (Google)" <joel@joelfernandes.org>,
linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org,
Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Subject: [PATCH v4 00/24] sched: Introduce classes of tasks for load balance
Date: Mon, 12 Jun 2023 21:23:58 -0700 [thread overview]
Message-ID: <20230613042422.5344-1-ricardo.neri-calderon@linux.intel.com> (raw)
Hi,
This is the fourth version of this patchset. Previous versions can be found
here [1], here [2], and here[3]. For brevity, I did not include the cover
letter from the original posting. You can read it here [1].
This patchset depends on a separate patchset to handle better asym_packing
between SMT cores [4]. This patchset was recently merged into the tip tree.
For your convenience, you can retrieve this patchset from [5], and is based
on the master branch of the tip tree as on 12th June 2023.
Changes since v3:
Vincent highlighted the issue of using the current tasks of runqueues to
collect IPCC statistics. Since these are the last tasks to be pulled during
load balance, the proposed tie breakers would have little effect. Instead,
I have reworked the collection of IPCC statistics to look at the back of
the runqueues. This makes the IPCC scores more useful, as these are the
first tasks to be pulled during load balance.
Rafael argued that the HFI driver should not handle tasks directly. I have
reworked the code to let the HFI driver read the classification result.
A new sched_ipcc.c file under arch/x86 is in charge or handling tasks and
postprocess classification.
Rafael also raised concerns about the need for a memory barrier to order
reads and writes of the cached IPCC scores that the scheduler can access
without holding the HFI lock. I decided to use a seqcount. The seqcount
provides store-release and load-acquire semantics, ensuring proper
ordering of reads and writes of the cached IPCC scores. It also provides a
compiler barrier. A CPU memory barrier is not needed.
Zhao noticed that there is a new CPUID_7_1_EAX leaf and using cpuid_bits[]
in scattered.c is not needed. I fixed it.
lkp@intel.com found a build break due to a misplaced definition of
MSR_IA32_HW_FEEDBACK_CHAR. I moved the definition to patch 13.
Updated patches: 6, 10, 13, 14, 15, 17, 21, 22
New patches: none
Unchanged patches: 1, 2, 3, 4, 5, 7, 8, 9, 11, 12, 16, 18, 19, 20, 23, 24
Thanks in advance for your kind feedback!
BR,
Ricardo
[1]. https://lore.kernel.org/lkml/20220909231205.14009-1-ricardo.neri-calderon@linux.intel.com/
[2]. https://lore.kernel.org/lkml/20221128132100.30253-1-ricardo.neri-calderon@linux.intel.com/
[3]. https://lore.kernel.org/all/20230207051105.11575-1-ricardo.neri-calderon@linux.intel.com/
[4]. https://lore.kernel.org/all/20230406203148.19182-1-ricardo.neri-calderon@linux.intel.com/
[5]. https://github.com/ricardon/tip/tree/rneri/ipc_classes_v4
Ricardo Neri (24):
sched/task_struct: Introduce IPC classes of tasks
sched: Add interfaces for IPC classes
sched/core: Initialize the IPC class of a new task
sched/core: Add user_tick as argument to scheduler_tick()
sched/core: Update the IPC class of the current task
sched/fair: Collect load-balancing stats for IPC classes
sched/fair: Compute IPC class scores for load balancing
sched/fair: Use IPCC stats to break ties between asym_packing sched
groups
sched/fair: Use IPCC stats to break ties between fully_busy SMT groups
sched/fair: Use IPCC scores to select a busiest runqueue
thermal: intel: hfi: Introduce Intel Thread Director classes
x86/cpufeatures: Add the Intel Thread Director feature definitions
x86/sched: Update the IPC class of the current task
thermal: intel: hfi: Store per-CPU IPCC scores
thermal: intel: hfi: Report the IPC class score of a CPU
thermal: intel: hfi: Define a default class for unclassified tasks
thermal: intel: hfi: Enable the Intel Thread Director
sched/task_struct: Add helpers for IPC classification
sched/core: Initialize helpers of task classification
sched/fair: Introduce sched_smt_siblings_idle()
x86/sched/ipcc: Implement model-specific checks for task
classification
x86/cpufeatures: Add feature bit for HRESET
x86/hreset: Configure history reset
x86/process: Reset hardware history in context switch
arch/x86/include/asm/cpufeatures.h | 2 +
arch/x86/include/asm/disabled-features.h | 8 +-
arch/x86/include/asm/hreset.h | 30 +++
arch/x86/include/asm/msr-index.h | 5 +
arch/x86/include/asm/topology.h | 15 ++
arch/x86/kernel/Makefile | 2 +
arch/x86/kernel/cpu/common.c | 30 ++-
arch/x86/kernel/cpu/cpuid-deps.c | 1 +
arch/x86/kernel/process_32.c | 3 +
arch/x86/kernel/process_64.c | 3 +
arch/x86/kernel/sched_ipcc.c | 93 +++++++
drivers/thermal/intel/Kconfig | 1 +
drivers/thermal/intel/intel_hfi.c | 219 +++++++++++++++-
include/linux/sched.h | 24 +-
include/linux/sched/topology.h | 6 +
init/Kconfig | 12 +
kernel/sched/core.c | 10 +-
kernel/sched/fair.c | 316 ++++++++++++++++++++++-
kernel/sched/sched.h | 66 +++++
kernel/sched/topology.c | 9 +
kernel/time/timer.c | 2 +-
21 files changed, 840 insertions(+), 17 deletions(-)
create mode 100644 arch/x86/include/asm/hreset.h
create mode 100644 arch/x86/kernel/sched_ipcc.c
--
2.25.1
next reply other threads:[~2023-06-13 4:21 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-13 4:23 Ricardo Neri [this message]
2023-06-13 4:23 ` [PATCH v4 01/24] sched/task_struct: Introduce IPC classes of tasks Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 02/24] sched: Add interfaces for IPC classes Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 03/24] sched/core: Initialize the IPC class of a new task Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 04/24] sched/core: Add user_tick as argument to scheduler_tick() Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 05/24] sched/core: Update the IPC class of the current task Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 06/24] sched/fair: Collect load-balancing stats for IPC classes Ricardo Neri
2023-06-14 0:29 ` Ricardo Neri
2023-06-22 9:01 ` Ionela Voinescu
2023-06-24 0:01 ` Ricardo Neri
2023-06-26 19:52 ` Tim Chen
2023-07-06 23:40 ` Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 07/24] sched/fair: Compute IPC class scores for load balancing Ricardo Neri
2023-06-22 9:02 ` Ionela Voinescu
2023-06-25 20:11 ` Ricardo Neri
2023-06-26 21:01 ` Tim Chen
2023-07-06 23:48 ` Ricardo Neri
2023-06-27 15:19 ` Ionela Voinescu
2023-06-13 4:24 ` [PATCH v4 08/24] sched/fair: Use IPCC stats to break ties between asym_packing sched groups Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 09/24] sched/fair: Use IPCC stats to break ties between fully_busy SMT groups Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 10/24] sched/fair: Use IPCC scores to select a busiest runqueue Ricardo Neri
2023-06-22 9:03 ` Ionela Voinescu
2023-06-24 0:25 ` Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 11/24] thermal: intel: hfi: Introduce Intel Thread Director classes Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 12/24] x86/cpufeatures: Add the Intel Thread Director feature definitions Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 13/24] x86/sched: Update the IPC class of the current task Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 14/24] thermal: intel: hfi: Store per-CPU IPCC scores Ricardo Neri
2023-06-29 18:53 ` Rafael J. Wysocki
2023-07-06 23:23 ` Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 15/24] thermal: intel: hfi: Report the IPC class score of a CPU Ricardo Neri
2023-06-29 18:56 ` Rafael J. Wysocki
2023-07-06 23:10 ` Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 16/24] thermal: intel: hfi: Define a default class for unclassified tasks Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 17/24] thermal: intel: hfi: Enable the Intel Thread Director Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 18/24] sched/task_struct: Add helpers for IPC classification Ricardo Neri
2023-06-22 10:20 ` Ionela Voinescu
2023-06-25 20:23 ` Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 19/24] sched/core: Initialize helpers of task classification Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 20/24] sched/fair: Introduce sched_smt_siblings_idle() Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 21/24] x86/sched/ipcc: Implement model-specific checks for task classification Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 22/24] x86/cpufeatures: Add feature bit for HRESET Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 23/24] x86/hreset: Configure history reset Ricardo Neri
2023-06-13 4:24 ` [PATCH v4 24/24] x86/process: Reset hardware history in context switch Ricardo Neri
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=20230613042422.5344-1-ricardo.neri-calderon@linux.intel.com \
--to=ricardo.neri-calderon@linux.intel.com \
--cc=Perry.Yuan@amd.com \
--cc=bristot@redhat.com \
--cc=bsegall@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=ionela.voinescu@arm.com \
--cc=joel@joelfernandes.org \
--cc=juri.lelli@redhat.com \
--cc=len.brown@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=lukasz.luba@arm.com \
--cc=mgorman@suse.de \
--cc=peterz@infradead.org \
--cc=rafael.j.wysocki@intel.com \
--cc=ravi.v.shankar@intel.com \
--cc=ricardo.neri@intel.com \
--cc=rostedt@goodmis.org \
--cc=srinivas.pandruvada@linux.intel.com \
--cc=tim.c.chen@linux.intel.com \
--cc=vincent.guittot@linaro.org \
--cc=vschneid@redhat.com \
--cc=x86@kernel.org \
--cc=zhao1.liu@intel.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
all inboxes | Powered by JetHome®