[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <tip-7e5a2c1729f1612618ed236249a15bf15f309325@git.kernel.org>
Date: Fri, 8 May 2015 06:22:19 -0700
From: tip-bot for Jason Low <tipbot@...or.com>
To: linux-tip-commits@...r.kernel.org
Cc: bp@...en8.de, umgwanakikbuti@...il.com, hpa@...or.com,
torvalds@...ux-foundation.org, peterz@...radead.org,
rostedt@...dmis.org, paulmck@...ux.vnet.ibm.com,
waiman.long@...com, jason.low2@...com, preeti@...ux.vnet.ibm.com,
akpm@...ux-foundation.org, aswin@...com, oleg@...hat.com,
tglx@...utronix.de, mgorman@...e.de, linux-kernel@...r.kernel.org,
dave@...olabs.net, scott.norton@...com, mingo@...nel.org,
riel@...hat.com, fweisbec@...il.com
Subject: [tip:sched/core] sched/numa: Document usages of mm->numa_scan_seq
Commit-ID: 7e5a2c1729f1612618ed236249a15bf15f309325
Gitweb: http://git.kernel.org/tip/7e5a2c1729f1612618ed236249a15bf15f309325
Author: Jason Low <jason.low2@...com>
AuthorDate: Thu, 30 Apr 2015 17:28:14 -0700
Committer: Ingo Molnar <mingo@...nel.org>
CommitDate: Fri, 8 May 2015 12:13:13 +0200
sched/numa: Document usages of mm->numa_scan_seq
The p->mm->numa_scan_seq is accessed using READ_ONCE/WRITE_ONCE
and modified without exclusive access. It is not clear why it is
accessed this way. This patch provides some documentation on that.
Suggested-by: Ingo Molnar <mingo@...nel.org>
Signed-off-by: Jason Low <jason.low2@...com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Acked-by: Thomas Gleixner <tglx@...utronix.de>
Acked-by: Rik van Riel <riel@...hat.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: Aswin Chandramouleeswaran <aswin@...com>
Cc: Borislav Petkov <bp@...en8.de>
Cc: Davidlohr Bueso <dave@...olabs.net>
Cc: Frederic Weisbecker <fweisbec@...il.com>
Cc: H. Peter Anvin <hpa@...or.com>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: Mel Gorman <mgorman@...e.de>
Cc: Mike Galbraith <umgwanakikbuti@...il.com>
Cc: Oleg Nesterov <oleg@...hat.com>
Cc: Paul E. McKenney <paulmck@...ux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Preeti U Murthy <preeti@...ux.vnet.ibm.com>
Cc: Scott J Norton <scott.norton@...com>
Cc: Steven Rostedt <rostedt@...dmis.org>
Cc: Waiman Long <waiman.long@...com>
Link: http://lkml.kernel.org/r/1430440094.2475.61.camel@j-VirtualBox
Signed-off-by: Ingo Molnar <mingo@...nel.org>
---
kernel/sched/fair.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d6915a0..f18ddb7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1794,6 +1794,11 @@ static void task_numa_placement(struct task_struct *p)
u64 runtime, period;
spinlock_t *group_lock = NULL;
+ /*
+ * The p->mm->numa_scan_seq field gets updated without
+ * exclusive access. Use READ_ONCE() here to ensure
+ * that the field is read in a single access:
+ */
seq = READ_ONCE(p->mm->numa_scan_seq);
if (p->numa_scan_seq == seq)
return;
@@ -2107,6 +2112,14 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
static void reset_ptenuma_scan(struct task_struct *p)
{
+ /*
+ * We only did a read acquisition of the mmap sem, so
+ * p->mm->numa_scan_seq is written to without exclusive access
+ * and the update is not guaranteed to be atomic. That's not
+ * much of an issue though, since this is just used for
+ * statistical sampling. Use READ_ONCE/WRITE_ONCE, which are not
+ * expensive, to avoid any form of compiler optimizations:
+ */
WRITE_ONCE(p->mm->numa_scan_seq, READ_ONCE(p->mm->numa_scan_seq) + 1);
p->mm->numa_scan_offset = 0;
}
--
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/
Powered by blists - more mailing lists