CTCaer/switch-l4t-kernel-4.9
1
0
Fork 0
mirror of https://github.com/CTCaer/switch-l4t-kernel-4.9.git synced 2024-11-26 21:31:18 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

blk-mq: Create hctx for each present CPU

Browse Source 
Currently we only create hctx for online CPUs, which can lead to a lot
of churn due to frequent soft offline / online operations.  Instead
allocate one for each present CPU to avoid this and dramatically simplify
the code.

Bug 2090405

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Cc: Keith Busch <keith.busch@intel.com>
Cc: linux-block@vger.kernel.org
Cc: linux-nvme@lists.infradead.org
Link: http://lkml.kernel.org/r/20170626102058.10200-3-hch@lst.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
(cherry-picked from commit 4b855ad37194f7bdbb200ce7a1c7051fecb56a08 in dev-kernel-4.14)
(vigneshr, resolved merge conflicts)
Change-Id: I88b3f6d8122caebc7e3cdd1f0c3ffa9fc60141f7
Signed-off-by: Vignesh Radhakrishnan <vigneshr@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1740887
Reviewed-by: Alexander Van Brunt <avanbrunt@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
This commit is contained in:
Vignesh Radhakrishnan 2018-06-04 17:45:17 -07:00 committed by mobile promotions
parent b32b6b3a7d
commit 67a095c6fe
3 changed files with 11 additions and 119 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

124
block/blk-mq.c
View File

@ -31,9 +31,6 @@
#include "blk-mq.h"
#include "blk-mq-tag.h"
static DEFINE_MUTEX(all_q_mutex);
static LIST_HEAD(all_q_list);
/*
* Check if any of the ctx's have pending work in this hardware queue
*/
@ -1723,8 +1720,8 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
INIT_LIST_HEAD(&__ctx->rq_list);
__ctx->queue = q;
/* If the cpu isn't online, the cpu is mapped to first hctx */
if (!cpu_online(i))
/* If the cpu isn't present, the cpu is mapped to first hctx */
if (!cpu_present(i))
continue;
hctx = blk_mq_map_queue(q, i);
@ -1738,8 +1735,7 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
}
}
static void blk_mq_map_swqueue(struct request_queue *q,
const struct cpumask *online_mask)
static void blk_mq_map_swqueue(struct request_queue *q)
{
unsigned int i;
struct blk_mq_hw_ctx *hctx;
@ -1757,12 +1753,11 @@ static void blk_mq_map_swqueue(struct request_queue *q,
}
/*
* Map software to hardware queues
* Map software to hardware queues.
*
* If the cpu isn't present, the cpu is mapped to first hctx.
*/
for_each_possible_cpu(i) {
/* If the cpu isn't online, the cpu is mapped to first hctx */
if (!cpumask_test_cpu(i, online_mask))
continue;
for_each_present_cpu(i) {
ctx = per_cpu_ptr(q->queue_ctx, i);
hctx = blk_mq_map_queue(q, i);
@ -2029,15 +2024,8 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
blk_mq_init_cpu_queues(q, set->nr_hw_queues);
get_online_cpus();
mutex_lock(&all_q_mutex);
list_add_tail(&q->all_q_node, &all_q_list);
blk_mq_add_queue_tag_set(set, q);
blk_mq_map_swqueue(q, cpu_online_mask);
mutex_unlock(&all_q_mutex);
put_online_cpus();
blk_mq_map_swqueue(q);
return q;
@ -2055,10 +2043,6 @@ void blk_mq_free_queue(struct request_queue *q)
{
struct blk_mq_tag_set *set = q->tag_set;
mutex_lock(&all_q_mutex);
list_del_init(&q->all_q_node);
mutex_unlock(&all_q_mutex);
blk_mq_del_queue_tag_set(q);
blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
@ -2066,8 +2050,7 @@ void blk_mq_free_queue(struct request_queue *q)
}
/* Basically redo blk_mq_init_queue with queue frozen */
static void blk_mq_queue_reinit(struct request_queue *q,
const struct cpumask *online_mask)
static void blk_mq_queue_reinit(struct request_queue *q)
{
WARN_ON_ONCE(!atomic_read(&q->mq_freeze_depth));
@ -2079,82 +2062,11 @@ static void blk_mq_queue_reinit(struct request_queue *q,
* involves free and re-allocate memory, worthy doing?)
*/
blk_mq_map_swqueue(q, online_mask);
blk_mq_map_swqueue(q);
blk_mq_sysfs_register(q);
}
/*
* New online cpumask which is going to be set in this hotplug event.
* Declare this cpumasks as global as cpu-hotplug operation is invoked
* one-by-one and dynamically allocating this could result in a failure.
*/
static struct cpumask cpuhp_online_new;
static void blk_mq_queue_reinit_work(void)
{
struct request_queue *q;
mutex_lock(&all_q_mutex);
/*
* We need to freeze and reinit all existing queues. Freezing
* involves synchronous wait for an RCU grace period and doing it
* one by one may take a long time. Start freezing all queues in
* one swoop and then wait for the completions so that freezing can
* take place in parallel.
*/
list_for_each_entry(q, &all_q_list, all_q_node)
blk_mq_freeze_queue_start(q);
list_for_each_entry(q, &all_q_list, all_q_node) {
blk_mq_freeze_queue_wait(q);
/*
* timeout handler can't touch hw queue during the
* reinitialization
*/
del_timer_sync(&q->timeout);
}
list_for_each_entry(q, &all_q_list, all_q_node)
blk_mq_queue_reinit(q, &cpuhp_online_new);
list_for_each_entry(q, &all_q_list, all_q_node)
blk_mq_unfreeze_queue(q);
mutex_unlock(&all_q_mutex);
}
static int blk_mq_queue_reinit_dead(unsigned int cpu)
{
cpumask_copy(&cpuhp_online_new, cpu_online_mask);
blk_mq_queue_reinit_work();
return 0;
}
/*
* Before hotadded cpu starts handling requests, new mappings must be
* established. Otherwise, these requests in hw queue might never be
* dispatched.
*
* For example, there is a single hw queue (hctx) and two CPU queues (ctx0
* for CPU0, and ctx1 for CPU1).
*
* Now CPU1 is just onlined and a request is inserted into ctx1->rq_list
* and set bit0 in pending bitmap as ctx1->index_hw is still zero.
*
* And then while running hw queue, flush_busy_ctxs() finds bit0 is set in
* pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list.
* But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list
* is ignored.
*/
static int blk_mq_queue_reinit_prepare(unsigned int cpu)
{
cpumask_copy(&cpuhp_online_new, cpu_online_mask);
cpumask_set_cpu(cpu, &cpuhp_online_new);
blk_mq_queue_reinit_work();
return 0;
}
static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
{
int i;
@ -2351,7 +2263,7 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
else
blk_queue_make_request(q, blk_sq_make_request);
blk_mq_queue_reinit(q, cpu_online_mask);
blk_mq_queue_reinit(q);
}
list_for_each_entry(q, &set->tag_list, tag_set_list)
@ -2359,24 +2271,10 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
}
EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
void blk_mq_disable_hotplug(void)
{
mutex_lock(&all_q_mutex);
}
void blk_mq_enable_hotplug(void)
{
mutex_unlock(&all_q_mutex);
}
static int __init blk_mq_init(void)
{
cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL,
blk_mq_hctx_notify_dead);
cpuhp_setup_state_nocalls(CPUHP_BLK_MQ_PREPARE, "block/mq:prepare",
blk_mq_queue_reinit_prepare,
blk_mq_queue_reinit_dead);
return 0;
}
subsys_initcall(blk_mq_init);

5
block/blk-mq.h
View File

@ -29,11 +29,6 @@ void blk_mq_free_queue(struct request_queue *q);
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
void blk_mq_wake_waiters(struct request_queue *q);
/*
* CPU hotplug helpers
*/
void blk_mq_enable_hotplug(void);
void blk_mq_disable_hotplug(void);
/*
* CPU -> queue mappings

1
include/linux/cpuhotplug.h
View File

@ -47,7 +47,6 @@ enum cpuhp_state {
CPUHP_NOTIFY_PREPARE,
CPUHP_ARM_SHMOBILE_SCU_PREPARE,
CPUHP_SH_SH3X_PREPARE,
CPUHP_BLK_MQ_PREPARE,
CPUHP_TIMERS_PREPARE,
CPUHP_NOTF_ERR_INJ_PREPARE,
CPUHP_MIPS_SOC_PREPARE,