linux-kernel - [PATCH] Avoid mask based num_possible_cpus and num_online

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Mon, 23 Jan 2012 18:34:15 -0800
From:	Venkatesh Pallipadi <venki@...gle.com>
To:	KOSAKI Motohiro <kosaki.motohiro@...il.com>,
	"Srivatsa S. Bhat" <srivatsa.bhat@...ux.vnet.ibm.com>
Cc:	Andrew Morton <akpm@...ux-foundation.org>,
	KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>,
	Mike Travis <travis@....com>,
	"Paul E. McKenney" <paul.mckenney@...aro.org>,
	"Rafael J. Wysocki" <rjw@...k.pl>,
	Paul Gortmaker <paul.gortmaker@...driver.com>,
	linux-kernel@...r.kernel.org,
	Venkatesh Pallipadi <venki@...gle.com>
Subject: [PATCH] Avoid mask based num_possible_cpus and num_online_cpus -v3

Kernel's notion of possible cpus (from include/linux/cpumask.h)
 *     cpu_possible_mask- has bit 'cpu' set iff cpu is populatable

 *  The cpu_possible_mask is fixed at boot time, as the set of CPU id's
 *  that it is possible might ever be plugged in at anytime during the
 *  life of that system boot.

 #define num_possible_cpus()     cpumask_weight(cpu_possible_mask)

and on x86 cpumask_weight() calls hweight64 and hweight64 (on older kernels
and systems with !X86_FEATURE_POPCNT) or a popcnt based alternative.

i.e, We needlessly go through this mask based calculation everytime
num_possible_cpus() is called.

The problem is there with cpu_online_mask() as well, which is fixed value at
boot time in !CONFIG_HOTPLUG_CPU case and should not change that often even
in HOTPLUG case.

Though most of the callers of these two routines are init time (with few
exceptions of runtime calls), it is cleaner to use variables
and not go through this repeated mask based calculation.

Signed-off-by: Venkatesh Pallipadi <venki@...gle.com>
---
 arch/x86/kernel/smpboot.c |    2 +-
 include/linux/cpumask.h   |   10 ++++++++--
 kernel/cpu.c              |    5 +++++
 kernel/smp.c              |    4 ++++
 4 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 66d250c..f87fcde 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -947,7 +947,7 @@ static int __init smp_sanity_check(unsigned max_cpus)
 			nr++;
 		}
 
-		nr_cpu_ids = 8;
+		setup_nr_cpu_ids();
 	}
 #endif
 
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 4f7a632..ac3113b 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -23,10 +23,14 @@ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
 
 #if NR_CPUS == 1
 #define nr_cpu_ids		1
+#define nr_possible_cpus	1
 #else
 extern int nr_cpu_ids;
+extern int nr_possible_cpus;
 #endif
 
+extern int nr_online_cpus;
+
 #ifdef CONFIG_CPUMASK_OFFSTACK
 /* Assuming NR_CPUS is huge, a runtime limit is more efficient.  Also,
  * not all bits may be allocated. */
@@ -81,8 +85,10 @@ extern const struct cpumask *const cpu_present_mask;
 extern const struct cpumask *const cpu_active_mask;
 
 #if NR_CPUS > 1
-#define num_online_cpus()	cpumask_weight(cpu_online_mask)
-#define num_possible_cpus()	cpumask_weight(cpu_possible_mask)
+
+#define num_online_cpus()	(nr_online_cpus)
+#define num_possible_cpus()	(nr_possible_cpus)
+
 #define num_present_cpus()	cpumask_weight(cpu_present_mask)
 #define num_active_cpus()	cpumask_weight(cpu_active_mask)
 #define cpu_online(cpu)		cpumask_test_cpu((cpu), cpu_online_mask)
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 2060c6e..f179baa 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -622,6 +622,9 @@ static DECLARE_BITMAP(cpu_active_bits, CONFIG_NR_CPUS) __read_mostly;
 const struct cpumask *const cpu_active_mask = to_cpumask(cpu_active_bits);
 EXPORT_SYMBOL(cpu_active_mask);
 
+int nr_online_cpus __read_mostly;
+EXPORT_SYMBOL(nr_online_cpus);
+
 void set_cpu_possible(unsigned int cpu, bool possible)
 {
 	if (possible)
@@ -644,6 +647,8 @@ void set_cpu_online(unsigned int cpu, bool online)
 		cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits));
 	else
 		cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits));
+
+	nr_online_cpus = cpumask_weight(cpu_online_mask);
 }
 
 void set_cpu_active(unsigned int cpu, bool active)
diff --git a/kernel/smp.c b/kernel/smp.c
index db197d6..106e519 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -658,10 +658,14 @@ early_param("maxcpus", maxcpus);
 int nr_cpu_ids __read_mostly = NR_CPUS;
 EXPORT_SYMBOL(nr_cpu_ids);
 
+int nr_possible_cpus __read_mostly = NR_CPUS;
+EXPORT_SYMBOL(nr_possible_cpus);
+
 /* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */
 void __init setup_nr_cpu_ids(void)
 {
 	nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1;
+	nr_possible_cpus = cpumask_weight(cpu_possible_mask);
 }
 
 /* Called by boot processor to activate the rest. */
-- 
1.7.7.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/