linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Andreas Herrmann <andreas.herrmann3@amd.com>
To: Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@elte.hu>
Cc: linux-kernel@vger.kernel.org
Subject: [PATCH 4/15] sched: Define per CPU variables and cpu_to_group function for MN domain
Date: Thu, 20 Aug 2009 15:35:39 +0200	[thread overview]
Message-ID: <20090820133539.GS29327@alberich.amd.com> (raw)
In-Reply-To: <20090820131243.GO29327@alberich.amd.com>


Additionally fixup cpu_to_phys_group() in case of CONFIG_SCHED_MN=y.

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
---
 kernel/sched.c |   32 +++++++++++++++++++++++++++-----
 1 files changed, 27 insertions(+), 5 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 9990c3a..d85985d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -8255,9 +8255,27 @@ cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
 #ifdef CONFIG_SCHED_MC
 static DEFINE_PER_CPU(struct static_sched_domain, core_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
-#endif /* CONFIG_SCHED_MC */
 
-#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
+/*
+ * multi-node sched-domains:
+ */
+#ifdef CONFIG_SCHED_MN
+static DEFINE_PER_CPU(struct static_sched_domain, cpu_node_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpu_node);
+
+static int cpu_to_cpu_node_group(int cpu, const struct cpumask *cpu_map,
+                                 struct sched_group **sg, struct cpumask *mask)
+{
+        int group;
+        cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
+        group = cpumask_first(mask);
+        if (sg)
+                *sg = &per_cpu(sched_group_cpu_node, group).sg;
+        return group;
+}
+#endif /* CONFIG_SCHED_MN */
+
+#ifdef CONFIG_SCHED_SMT
 static int
 cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
 		  struct sched_group **sg, struct cpumask *mask)
@@ -8270,7 +8288,7 @@ cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
 		*sg = &per_cpu(sched_group_core, group).sg;
 	return group;
 }
-#elif defined(CONFIG_SCHED_MC)
+#else
 static int
 cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
 		  struct sched_group **sg, struct cpumask *unused)
@@ -8279,7 +8297,8 @@ cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
 		*sg = &per_cpu(sched_group_core, cpu).sg;
 	return cpu;
 }
-#endif
+#endif /* CONFIG_SCHED_SMT */
+#endif /* CONFIG_SCHED_MC */
 
 static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);
@@ -8289,7 +8308,10 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
 		  struct sched_group **sg, struct cpumask *mask)
 {
 	int group;
-#ifdef CONFIG_SCHED_MC
+#ifdef CONFIG_SCHED_MN
+	cpumask_and(mask, topology_cpu_node_cpumask(cpu), cpu_map);
+	group = cpumask_first(mask);
+#elif CONFIG_SCHED_MC
 	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
 	group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
-- 
1.6.0.4




  parent reply	other threads:[~2009-08-20 13:35 UTC|newest]

Thread overview: 64+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-08-20 13:12 [RFC][PATCH 0/15] sched: Fix scheduling for multi-node processors Andreas Herrmann
2009-08-20 13:15 ` [PATCH 1/15] x86, sched: Add config option for multi-node CPU scheduling Andreas Herrmann
2009-08-21 13:50   ` Valdis.Kletnieks
2009-08-24  8:49     ` Andreas Herrmann
2009-08-20 13:34 ` [PATCH 2/15] sched, x86: Provide initializer for MN scheduling domain, define MN level Andreas Herrmann
2009-08-20 13:34 ` [PATCH 3/15] sched: Add cpumask to be used when building MN domain Andreas Herrmann
2009-08-20 13:35 ` Andreas Herrmann [this message]
2009-08-20 13:36 ` [PATCH 5/15] sched: Add function to build MN sched domain Andreas Herrmann
2009-08-20 13:37 ` [PATCH 6/15] sched: Add support for MN domain in build_sched_groups Andreas Herrmann
2009-08-20 13:38 ` [PATCH 7/15] sched: Activate build of MN domains Andreas Herrmann
2009-08-20 13:39 ` [PATCH 8/15] sched: Add parameter sched_mn_power_savings to control MN domain sched policy Andreas Herrmann
2009-08-24 14:56   ` Peter Zijlstra
2009-08-24 15:32     ` Vaidyanathan Srinivasan
2009-08-24 15:45       ` Peter Zijlstra
2009-08-25  7:52         ` Andreas Herrmann
2009-08-25  7:50       ` Andreas Herrmann
2009-08-25  6:24     ` Andreas Herrmann
2009-08-25  6:41       ` Peter Zijlstra
2009-08-25  8:38         ` Andreas Herrmann
2009-08-26  9:30   ` Gautham R Shenoy
2009-08-27 12:47     ` Andreas Herrmann
2009-08-20 13:40 ` [PATCH 9/15] sched: Check sched_mn_power_savings when setting flags for CPU and MN domains Andreas Herrmann
2009-08-24 14:57   ` Peter Zijlstra
2009-08-25  9:34     ` Gautham R Shenoy
2009-08-26 10:01   ` Gautham R Shenoy
2009-08-20 13:41 ` [PATCH 10/15] sched: Check for sched_mn_power_savings when doing load balancing Andreas Herrmann
2009-08-24 15:03   ` Peter Zijlstra
2009-08-24 15:40     ` Vaidyanathan Srinivasan
2009-08-25  8:00       ` Andreas Herrmann
2009-08-20 13:41 ` [PATCH 11/15] sched: Pass unlimited __cpu_power information to upper domain level groups Andreas Herrmann
2009-08-24 15:21   ` Peter Zijlstra
2009-08-24 16:44     ` Balbir Singh
2009-08-24 17:26       ` Peter Zijlstra
2009-08-24 18:19         ` Balbir Singh
2009-08-25  7:11           ` Peter Zijlstra
2009-08-25  8:04             ` Balbir Singh
2009-08-25  8:30               ` Peter Zijlstra
2009-08-25  8:51     ` Andreas Herrmann
2009-08-20 13:42 ` [PATCH 12/15] sched: Allow NODE domain to be parent of MC instead of CPU domain Andreas Herrmann
2009-08-24 15:32   ` Peter Zijlstra
2009-08-25  8:55     ` Andreas Herrmann
2009-08-20 13:43 ` [PATCH 13/15] sched: Detect child domain of NUMA (aka NODE) domain Andreas Herrmann
2009-08-24 15:34   ` Peter Zijlstra
2009-08-25  9:13     ` Andreas Herrmann
2009-08-20 13:45 ` [PATCH 14/15] sched: Conditionally limit __cpu_power when child sched domain has type NODE Andreas Herrmann
2009-08-24 15:35   ` Peter Zijlstra
2009-08-25  9:19     ` Andreas Herrmann
2009-08-20 13:46 ` [PATCH 15/15] x86: Fix cpu_coregroup_mask to return correct cpumask on multi-node processors Andreas Herrmann
2009-08-24 15:36   ` Peter Zijlstra
2009-08-24 18:21     ` Ingo Molnar
2009-08-25 10:13       ` Andreas Herrmann
2009-08-25 10:36         ` Ingo Molnar
2009-08-27 13:18           ` Andreas Herrmann
2009-08-25  9:31     ` Andreas Herrmann
2009-08-25  9:55       ` Peter Zijlstra
2009-08-25 10:20         ` Ingo Molnar
2009-08-25 10:24         ` Andreas Herrmann
2009-08-25 10:28           ` Ingo Molnar
2009-08-25 10:35           ` Peter Zijlstra
2009-08-27 15:42             ` Andreas Herrmann
2009-08-27 15:25         ` Andreas Herrmann
2009-08-28 10:39           ` Peter Zijlstra
2009-08-28 12:03             ` Andreas Herrmann
2009-08-28 12:50               ` Peter Zijlstra

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=20090820133539.GS29327@alberich.amd.com \
    --to=andreas.herrmann3@amd.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=peterz@infradead.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 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).