All of lore.kernel.org
 help / color / mirror / Atom feed
From: subhra mazumdar <subhra.mazumdar@oracle.com>
To: linux-kernel@vger.kernel.org
Cc: peterz@infradead.org, mingo@redhat.com, tglx@linutronix.de,
	steven.sistare@oracle.com, dhaval.giani@oracle.com,
	daniel.lezcano@linaro.org, vincent.guittot@linaro.org,
	viresh.kumar@linaro.org, tim.c.chen@linux.intel.com,
	mgorman@techsingularity.net, parth@linux.ibm.com,
	patrick.bellasi@arm.com
Subject: [RFC PATCH 6/9] x86/smpboot: Optimize cpumask_weight_sibling macro for x86
Date: Fri, 30 Aug 2019 10:49:41 -0700	[thread overview]
Message-ID: <20190830174944.21741-7-subhra.mazumdar@oracle.com> (raw)
In-Reply-To: <20190830174944.21741-1-subhra.mazumdar@oracle.com>

Use per-CPU variable for cpumask_weight_sibling macro in case of x86 for
fast lookup in select_idle_cpu. This avoids reading multiple cache lines
in case of systems with large numbers of CPUs where bitmask can span
multiple cache lines. Even if bitmask spans only one cache line this avoids
looping through it to find the number of bits and gets it in O(1).

Signed-off-by: subhra mazumdar <subhra.mazumdar@oracle.com>
---
 arch/x86/include/asm/smp.h      |  1 +
 arch/x86/include/asm/topology.h |  1 +
 arch/x86/kernel/smpboot.c       | 17 ++++++++++++++++-
 3 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index da545df..1e90cbd 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -22,6 +22,7 @@ extern int smp_num_siblings;
 extern unsigned int num_processors;
 
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
+DECLARE_PER_CPU_READ_MOSTLY(unsigned int, cpumask_weight_sibling);
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
 /* cpus sharing the last level cache: */
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 453cf38..dd19c71 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -111,6 +111,7 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
 #ifdef CONFIG_SMP
 #define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
 #define topology_sibling_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
+#define topology_sibling_weight(cpu)	(per_cpu(cpumask_weight_sibling, cpu))
 
 extern unsigned int __max_logical_packages;
 #define topology_max_packages()			(__max_logical_packages)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 362dd89..57ad88d 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -85,6 +85,9 @@
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 
+/* representing number of HT siblings of each CPU */
+DEFINE_PER_CPU_READ_MOSTLY(unsigned int, cpumask_weight_sibling);
+
 /* representing HT and core siblings of each logical CPU */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
@@ -520,6 +523,8 @@ void set_cpu_sibling_map(int cpu)
 
 	if (!has_mp) {
 		cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu));
+		per_cpu(cpumask_weight_sibling, cpu) =
+		    cpumask_weight(topology_sibling_cpumask(cpu));
 		cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
 		cpumask_set_cpu(cpu, topology_core_cpumask(cpu));
 		c->booted_cores = 1;
@@ -529,8 +534,13 @@ void set_cpu_sibling_map(int cpu)
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		o = &cpu_data(i);
 
-		if ((i == cpu) || (has_smt && match_smt(c, o)))
+		if ((i == cpu) || (has_smt && match_smt(c, o))) {
 			link_mask(topology_sibling_cpumask, cpu, i);
+			per_cpu(cpumask_weight_sibling, cpu) =
+			    cpumask_weight(topology_sibling_cpumask(cpu));
+			per_cpu(cpumask_weight_sibling, i) =
+			    cpumask_weight(topology_sibling_cpumask(i));
+		}
 
 		if ((i == cpu) || (has_mp && match_llc(c, o)))
 			link_mask(cpu_llc_shared_mask, cpu, i);
@@ -1173,6 +1183,8 @@ static __init void disable_smp(void)
 	else
 		physid_set_mask_of_physid(0, &phys_cpu_present_map);
 	cpumask_set_cpu(0, topology_sibling_cpumask(0));
+	per_cpu(cpumask_weight_sibling, 0) =
+	    cpumask_weight(topology_sibling_cpumask(0));
 	cpumask_set_cpu(0, topology_core_cpumask(0));
 }
 
@@ -1482,6 +1494,8 @@ static void remove_siblinginfo(int cpu)
 
 	for_each_cpu(sibling, topology_core_cpumask(cpu)) {
 		cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
+		per_cpu(cpumask_weight_sibling, sibling) =
+		    cpumask_weight(topology_sibling_cpumask(sibling));
 		/*/
 		 * last thread sibling in this cpu core going down
 		 */
@@ -1495,6 +1509,7 @@ static void remove_siblinginfo(int cpu)
 		cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
 	cpumask_clear(cpu_llc_shared_mask(cpu));
 	cpumask_clear(topology_sibling_cpumask(cpu));
+	per_cpu(cpumask_weight_sibling, cpu) = 0;
 	cpumask_clear(topology_core_cpumask(cpu));
 	c->cpu_core_id = 0;
 	c->booted_cores = 0;
-- 
2.9.3


  parent reply	other threads:[~2019-08-30 17:59 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-30 17:49 [RFC PATCH 0/9] Task latency-nice subhra mazumdar
2019-08-30 17:49 ` [RFC PATCH 1/9] sched,cgroup: Add interface for latency-nice subhra mazumdar
2019-09-04 17:32   ` Tim Chen
2019-09-05  6:15     ` Parth Shah
2019-09-05 10:11       ` Patrick Bellasi
2019-09-06 12:22         ` Parth Shah
2019-09-05  8:31   ` Peter Zijlstra
2019-09-05  9:45     ` Patrick Bellasi
2019-09-05 10:46       ` Peter Zijlstra
2019-09-05 11:13         ` Qais Yousef
2019-09-05 11:30           ` Peter Zijlstra
2019-09-05 11:40             ` Patrick Bellasi
2019-09-05 11:48               ` Peter Zijlstra
2019-09-05 13:32                 ` Qais Yousef
2019-09-05 11:47             ` Qais Yousef
2020-04-16  0:02               ` Joel Fernandes
2020-04-16 17:23                 ` Dietmar Eggemann
2020-04-18 16:01                   ` Joel Fernandes
2020-04-20 11:26                     ` Parth Shah
2020-04-20 19:14                       ` Joel Fernandes
2020-04-20 11:47                     ` Qais Yousef
2020-04-20 19:10                       ` Joel Fernandes
2019-09-05 11:30           ` Patrick Bellasi
2019-09-05 11:47             ` Peter Zijlstra
2019-09-05 11:18         ` Patrick Bellasi
2019-09-05 11:40           ` Peter Zijlstra
2019-09-05 11:46             ` Patrick Bellasi
2019-09-05 11:46           ` Valentin Schneider
2019-09-05 13:07             ` Patrick Bellasi
2019-09-05 14:48               ` Valentin Schneider
2019-09-06 12:45               ` Parth Shah
2019-09-06 14:13                 ` Valentin Schneider
2019-09-06 14:32                   ` Vincent Guittot
2019-09-06 17:10                   ` Parth Shah
2019-09-06 22:50                     ` Valentin Schneider
2019-09-06 12:31       ` Parth Shah
2019-09-05 10:05   ` Patrick Bellasi
2019-09-05 10:48     ` Peter Zijlstra
2019-08-30 17:49 ` [RFC PATCH 2/9] sched: add search limit as per latency-nice subhra mazumdar
2019-09-05  6:22   ` Parth Shah
2019-08-30 17:49 ` [RFC PATCH 3/9] sched: add sched feature to disable idle core search subhra mazumdar
2019-09-05 10:17   ` Patrick Bellasi
2019-09-05 22:02     ` Subhra Mazumdar
2019-08-30 17:49 ` [RFC PATCH 4/9] sched: SIS_CORE " subhra mazumdar
2019-09-05 10:19   ` Patrick Bellasi
2019-08-30 17:49 ` [RFC PATCH 5/9] sched: Define macro for number of CPUs in core subhra mazumdar
2019-08-30 17:49 ` subhra mazumdar [this message]
2019-08-30 17:49 ` [RFC PATCH 7/9] sched: search SMT before LLC domain subhra mazumdar
2019-09-05  9:31   ` Peter Zijlstra
2019-09-05 20:40     ` Subhra Mazumdar
2019-08-30 17:49 ` [RFC PATCH 8/9] sched: introduce per-cpu var next_cpu to track search limit subhra mazumdar
2019-08-30 17:49 ` [RFC PATCH 9/9] sched: rotate the cpu search window for better spread subhra mazumdar
2019-09-05  6:37   ` Parth Shah
2019-09-05  5:55 ` [RFC PATCH 0/9] Task latency-nice Parth Shah
2019-09-05 10:31 ` Patrick Bellasi

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=20190830174944.21741-7-subhra.mazumdar@oracle.com \
    --to=subhra.mazumdar@oracle.com \
    --cc=daniel.lezcano@linaro.org \
    --cc=dhaval.giani@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@techsingularity.net \
    --cc=mingo@redhat.com \
    --cc=parth@linux.ibm.com \
    --cc=patrick.bellasi@arm.com \
    --cc=peterz@infradead.org \
    --cc=steven.sistare@oracle.com \
    --cc=tglx@linutronix.de \
    --cc=tim.c.chen@linux.intel.com \
    --cc=vincent.guittot@linaro.org \
    --cc=viresh.kumar@linaro.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.