summaryrefslogtreecommitdiffstats
path: root/kernel/async.c
diff options
context:
space:
mode:
authorAlexander Duyck <alexander.h.duyck@linux.intel.com>2019-01-22 10:39:31 -0800
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2019-01-31 14:20:54 +0100
commit6be9238e5cb64741ff95c3ae440b112753ad93de (patch)
tree9c4b599c9a69bfa534d053ad31ceea1d78d99eb1 /kernel/async.c
parent8204e0c1113d6b7f599bcd7ebfbfde72e76c102f (diff)
downloadlinux-6be9238e5cb64741ff95c3ae440b112753ad93de.tar.bz2
async: Add support for queueing on specific NUMA node
Introduce four new variants of the async_schedule_ functions that allow scheduling on a specific NUMA node. The first two functions are async_schedule_near and async_schedule_near_domain end up mapping to async_schedule and async_schedule_domain, but provide NUMA node specific functionality. They replace the original functions which were moved to inline function definitions that call the new functions while passing NUMA_NO_NODE. The second two functions are async_schedule_dev and async_schedule_dev_domain which provide NUMA specific functionality when passing a device as the data member and that device has a NUMA node other than NUMA_NO_NODE. The main motivation behind this is to address the need to be able to schedule device specific init work on specific NUMA nodes in order to improve performance of memory initialization. I have seen a significant improvement in initialziation time for persistent memory as a result of this approach. In the case of 3TB of memory on a single node the initialization time in the worst case went from 36s down to about 26s for a 10s improvement. As such the data shows a general benefit for affinitizing the async work to the node local to the device. Reviewed-by: Bart Van Assche <bvanassche@acm.org> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'kernel/async.c')
-rw-r--r--kernel/async.c53
1 files changed, 29 insertions, 24 deletions
diff --git a/kernel/async.c b/kernel/async.c
index a893d6170944..f6bd0d9885e1 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -149,7 +149,25 @@ static void async_run_entry_fn(struct work_struct *work)
wake_up(&async_done);
}
-static async_cookie_t __async_schedule(async_func_t func, void *data, struct async_domain *domain)
+/**
+ * async_schedule_node_domain - NUMA specific version of async_schedule_domain
+ * @func: function to execute asynchronously
+ * @data: data pointer to pass to the function
+ * @node: NUMA node that we want to schedule this on or close to
+ * @domain: the domain
+ *
+ * Returns an async_cookie_t that may be used for checkpointing later.
+ * @domain may be used in the async_synchronize_*_domain() functions to
+ * wait within a certain synchronization domain rather than globally.
+ *
+ * Note: This function may be called from atomic or non-atomic contexts.
+ *
+ * The node requested will be honored on a best effort basis. If the node
+ * has no CPUs associated with it then the work is distributed among all
+ * available CPUs.
+ */
+async_cookie_t async_schedule_node_domain(async_func_t func, void *data,
+ int node, struct async_domain *domain)
{
struct async_entry *entry;
unsigned long flags;
@@ -195,43 +213,30 @@ static async_cookie_t __async_schedule(async_func_t func, void *data, struct asy
current->flags |= PF_USED_ASYNC;
/* schedule for execution */
- queue_work(system_unbound_wq, &entry->work);
+ queue_work_node(node, system_unbound_wq, &entry->work);
return newcookie;
}
+EXPORT_SYMBOL_GPL(async_schedule_node_domain);
/**
- * async_schedule - schedule a function for asynchronous execution
+ * async_schedule_node - NUMA specific version of async_schedule
* @func: function to execute asynchronously
* @data: data pointer to pass to the function
+ * @node: NUMA node that we want to schedule this on or close to
*
* Returns an async_cookie_t that may be used for checkpointing later.
* Note: This function may be called from atomic or non-atomic contexts.
- */
-async_cookie_t async_schedule(async_func_t func, void *data)
-{
- return __async_schedule(func, data, &async_dfl_domain);
-}
-EXPORT_SYMBOL_GPL(async_schedule);
-
-/**
- * async_schedule_domain - schedule a function for asynchronous execution within a certain domain
- * @func: function to execute asynchronously
- * @data: data pointer to pass to the function
- * @domain: the domain
*
- * Returns an async_cookie_t that may be used for checkpointing later.
- * @domain may be used in the async_synchronize_*_domain() functions to
- * wait within a certain synchronization domain rather than globally. A
- * synchronization domain is specified via @domain. Note: This function
- * may be called from atomic or non-atomic contexts.
+ * The node requested will be honored on a best effort basis. If the node
+ * has no CPUs associated with it then the work is distributed among all
+ * available CPUs.
*/
-async_cookie_t async_schedule_domain(async_func_t func, void *data,
- struct async_domain *domain)
+async_cookie_t async_schedule_node(async_func_t func, void *data, int node)
{
- return __async_schedule(func, data, domain);
+ return async_schedule_node_domain(func, data, node, &async_dfl_domain);
}
-EXPORT_SYMBOL_GPL(async_schedule_domain);
+EXPORT_SYMBOL_GPL(async_schedule_node);
/**
* async_synchronize_full - synchronize all asynchronous function calls