[PATCH Xenial SRU] kernek/fork.c: allocate idle task for a CPU always on its local node

[Tim Gardner]

From: Andi Kleen <ak at linux.intel.com>

BugLink: http://bugs.launchpad.net/bugs/1585850

Linux preallocates the task structs of the idle tasks for all possible
CPUs.  This currently means they all end up on node 0.  This also implies
that the cache line of MWAIT, which is around the flags field in the task
struct, are all located in node 0.

We see a noticeable performance improvement on Knights Landing CPUs when
the cache lines used for MWAIT are located in the local nodes of the CPUs
using them.  I would expect this to give a (likely slight) improvement on
other systems too.

The patch implements placing the idle task in the node of its CPUs, by
passing the right target node to copy_process()

[akpm at linux-foundation.org: use NUMA_NO_NODE, not a bare -1]
Link: http://lkml.kernel.org/r/1463492694-15833-1-git-send-email-andi@firstfloor.org
Signed-off-by: Andi Kleen <ak at linux.intel.com>
Cc: Thomas Gleixner <tglx at linutronix.de>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>

(cherry picked from linux-next commit b97773886a6864fcac4039f8a12ed5177c2218ba)
Signed-off-by: Tim Gardner <tim.gardner at canonical.com>
---
 kernel/fork.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index 004131b..27b4f2f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -336,13 +336,14 @@ void set_task_stack_end_magic(struct task_struct *tsk)
 	*stackend = STACK_END_MAGIC;	/* for overflow detection */
 }
 
-static struct task_struct *dup_task_struct(struct task_struct *orig)
+static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 {
 	struct task_struct *tsk;
 	struct thread_info *ti;
-	int node = tsk_fork_get_node(orig);
 	int err;
 
+	if (node == NUMA_NO_NODE)
+		node = tsk_fork_get_node(orig);
 	tsk = alloc_task_struct_node(node);
 	if (!tsk)
 		return NULL;
@@ -1251,7 +1252,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 					int __user *child_tidptr,
 					struct pid *pid,
 					int trace,
-					unsigned long tls)
+					unsigned long tls,
+					int node)
 {
 	int retval;
 	struct task_struct *p;
@@ -1308,7 +1310,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto fork_out;
 
 	retval = -ENOMEM;
-	p = dup_task_struct(current);
+	p = dup_task_struct(current, node);
 	if (!p)
 		goto fork_out;
 
@@ -1684,7 +1686,8 @@ static inline void init_idle_pids(struct pid_link *links)
 struct task_struct *fork_idle(int cpu)
 {
 	struct task_struct *task;
-	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0);
+	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0,
+			    cpu_to_node(cpu));
 	if (!IS_ERR(task)) {
 		init_idle_pids(task->pids);
 		init_idle(task, cpu);
@@ -1729,7 +1732,7 @@ long _do_fork(unsigned long clone_flags,
 	}
 
 	p = copy_process(clone_flags, stack_start, stack_size,
-			 child_tidptr, NULL, trace, tls);
+			 child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
 	/*
 	 * Do this prior waking up the new thread - the thread pointer
 	 * might get invalid after that point, if the thread exits quickly.
-- 
1.9.1