path: root/kernel/fork.c
diff options
authorAndi Kleen <ak@linux.intel.com>2016-05-23 16:24:05 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-05-23 17:04:14 -0700
commit725fc629ff2545b061407305ae51016c9f928fce (patch)
treed9b5ace469a064da5439bd6c96d1e714df85bab2 /kernel/fork.c
parent5c8ccefdf46c5f87d87b694c7fbc04941c2c99a5 (diff)
kernek/fork.c: allocate idle task for a CPU always on its local node
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@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@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'kernel/fork.c')
1 files changed, 9 insertions, 6 deletions
diff --git a/kernel/fork.c b/kernel/fork.c
index 103d78fd8f75..e67d7b773348 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -340,13 +340,14 @@ 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;
@@ -1276,7 +1277,8 @@ 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;
@@ -1328,7 +1330,7 @@ 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;
@@ -1706,7 +1708,8 @@ 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(task, cpu);
@@ -1751,7 +1754,7 @@ 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.