[PATCHv2] Fix KMALLOC_MAX_SIZE overflow during cpumask allocation

[PATCHv2] Fix KMALLOC_MAX_SIZE overflow during cpumask allocation

[Alex Thorlton]

When allocating space for load_balance_mask, in sched_init, when
CPUMASK_OFFSTACK is set, we've managed to spill over KMALLOC_MAX_SIZE on our
6144 core machine.  The patch below breaks up the allocations so that they don't
overflow the max alloc size.  It also allocates the masks on the the node from
which they'll most commonly be accessed, to minimize remote accesses on NUMA
machines.

v2 - Replace a missing #endif to fix some build issues on certain configs

Any input is appreciated!

- Alex

Signed-off-by: Alex Thorlton <athorlton@sgi.com>
Suggested-by: George Beshers <gbeshers@sgi.com>
Cc: George Beshers <gbeshers@sgi.com>
Cc: Russ Anderson <rja@sgi.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-kernel@vger.kernel.org

---
 kernel/sched/core.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b5797b7..80a753f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7113,9 +7113,6 @@ void __init sched_init(void)
 #ifdef CONFIG_RT_GROUP_SCHED
 	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
 #endif
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	alloc_size += num_possible_cpus() * cpumask_size();
-#endif
 	if (alloc_size) {
 		ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
 
@@ -7135,13 +7132,13 @@ void __init sched_init(void)
 		ptr += nr_cpu_ids * sizeof(void **);
 
 #endif /* CONFIG_RT_GROUP_SCHED */
+	}
 #ifdef CONFIG_CPUMASK_OFFSTACK
-		for_each_possible_cpu(i) {
-			per_cpu(load_balance_mask, i) = (void *)ptr;
-			ptr += cpumask_size();
-		}
-#endif /* CONFIG_CPUMASK_OFFSTACK */
+	for_each_possible_cpu(i) {
+		per_cpu(load_balance_mask, i) = (cpumask_var_t) kzalloc_node(
+			cpumask_size(), GFP_KERNEL, cpu_to_node(i));
 	}
+#endif /* CONFIG_CPUMASK_OFFSTACK */
 
 	init_rt_bandwidth(&def_rt_bandwidth,
 			global_rt_period(), global_rt_runtime());
-- 
1.8.2.1

[tip:sched/urgent] sched: Fix KMALLOC_MAX_SIZE overflow during cpumask allocation

[tip-bot for Alex Thorlton]

Commit-ID:  b74e6278fd6db5848163ccdc6e9d8eb6efdee9bd
Gitweb:     http://git.kernel.org/tip/b74e6278fd6db5848163ccdc6e9d8eb6efdee9bd
Author:     Alex Thorlton <athorlton@sgi.com>
AuthorDate: Thu, 18 Dec 2014 12:44:30 -0600
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 23 Dec 2014 11:43:48 +0100

sched: Fix KMALLOC_MAX_SIZE overflow during cpumask allocation

When allocating space for load_balance_mask, in sched_init, when
CPUMASK_OFFSTACK is set, we've managed to spill over
KMALLOC_MAX_SIZE on our 6144 core machine.  The patch below
breaks up the allocations so that they don't overflow the max
alloc size.  It also allocates the masks on the the node from
which they'll most commonly be accessed, to minimize remote
accesses on NUMA machines.

Suggested-by: George Beshers <gbeshers@sgi.com>
Signed-off-by: Alex Thorlton <athorlton@sgi.com>
Cc: George Beshers <gbeshers@sgi.com>
Cc: Russ Anderson <rja@sgi.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1418928270-148543-1-git-send-email-athorlton@sgi.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b5797b7..c0accc0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7113,9 +7113,6 @@ void __init sched_init(void)
 #ifdef CONFIG_RT_GROUP_SCHED
 	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
 #endif
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	alloc_size += num_possible_cpus() * cpumask_size();
-#endif
 	if (alloc_size) {
 		ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
 
@@ -7135,13 +7132,13 @@ void __init sched_init(void)
 		ptr += nr_cpu_ids * sizeof(void **);
 
 #endif /* CONFIG_RT_GROUP_SCHED */
+	}
 #ifdef CONFIG_CPUMASK_OFFSTACK
-		for_each_possible_cpu(i) {
-			per_cpu(load_balance_mask, i) = (void *)ptr;
-			ptr += cpumask_size();
-		}
-#endif /* CONFIG_CPUMASK_OFFSTACK */
+	for_each_possible_cpu(i) {
+		per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node(
+			cpumask_size(), GFP_KERNEL, cpu_to_node(i));
 	}
+#endif /* CONFIG_CPUMASK_OFFSTACK */
 
 	init_rt_bandwidth(&def_rt_bandwidth,
 			global_rt_period(), global_rt_runtime());