Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2025-01-01 07:42:07 +00:00
Code Issues Packages Projects Releases Wiki Activity
8ee82bda23
linux/drivers/mmc/core/queue.c
Adrian Hunter 1e8e55b670 mmc: block: Add CQE support 
Add CQE support to the block driver, including:
    - optionally using DCMD for flush requests
    - "manually" issuing discard requests
    - issuing read / write requests to the CQE
    - supporting block-layer timeouts
    - handling recovery
    - supporting re-tuning

CQE offers 25% - 50% better random multi-threaded I/O.  There is a slight
(e.g. 2%) drop in sequential read speed but no observable change to sequential
write.

CQE automatically sends the commands to complete requests.  However it only
supports reads / writes and so-called "direct commands" (DCMD).  Furthermore
DCMD is limited to one command at a time, but discards require 3 commands.
That makes issuing discards through CQE very awkward, but some CQE's don't
support DCMD anyway.  So for discards, the existing non-CQE approach is
taken, where the mmc core code issues the 3 commands one at a time i.e.
mmc_erase(). Where DCMD is used, is for issuing flushes.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Tested-by: Linus Walleij <linus.walleij@linaro.org>
2017-12-11 12:44:34 +01:00

733 lines
17 KiB
C
Raw Blame History

/*
* Copyright (C) 2003 Russell King, All Rights Reserved.
* Copyright 2006-2007 Pierre Ossman
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
*/
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/blkdev.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/scatterlist.h>
#include <linux/dma-mapping.h>
#include <linux/mmc/card.h>
#include <linux/mmc/host.h>
#include "queue.h"
#include "block.h"
#include "core.h"
#include "card.h"
#include "host.h"
/*
* Prepare a MMC request. This just filters out odd stuff.
*/
static int mmc_prep_request(struct request_queue *q, struct request *req)
{
struct mmc_queue *mq = q->queuedata;
if (mq && mmc_card_removed(mq->card))
return BLKPREP_KILL;
req->rq_flags |= RQF_DONTPREP;
req_to_mmc_queue_req(req)->retries = 0;
return BLKPREP_OK;
}
static inline bool mmc_cqe_dcmd_busy(struct mmc_queue *mq)
{
/* Allow only 1 DCMD at a time */
return mq->in_flight[MMC_ISSUE_DCMD];
}
void mmc_cqe_check_busy(struct mmc_queue *mq)
{
if ((mq->cqe_busy & MMC_CQE_DCMD_BUSY) && !mmc_cqe_dcmd_busy(mq))
mq->cqe_busy &= ~MMC_CQE_DCMD_BUSY;
mq->cqe_busy &= ~MMC_CQE_QUEUE_FULL;
}
static inline bool mmc_cqe_can_dcmd(struct mmc_host *host)
{
return host->caps2 & MMC_CAP2_CQE_DCMD;
}
enum mmc_issue_type mmc_cqe_issue_type(struct mmc_host *host,
struct request *req)
{
switch (req_op(req)) {
case REQ_OP_DRV_IN:
case REQ_OP_DRV_OUT:
case REQ_OP_DISCARD:
case REQ_OP_SECURE_ERASE:
return MMC_ISSUE_SYNC;
case REQ_OP_FLUSH:
return mmc_cqe_can_dcmd(host) ? MMC_ISSUE_DCMD : MMC_ISSUE_SYNC;
default:
return MMC_ISSUE_ASYNC;
}
}
enum mmc_issue_type mmc_issue_type(struct mmc_queue *mq, struct request *req)
{
struct mmc_host *host = mq->card->host;
if (mq->use_cqe)
return mmc_cqe_issue_type(host, req);
if (req_op(req) == REQ_OP_READ || req_op(req) == REQ_OP_WRITE)
return MMC_ISSUE_ASYNC;
return MMC_ISSUE_SYNC;
}
static void __mmc_cqe_recovery_notifier(struct mmc_queue *mq)
{
if (!mq->recovery_needed) {
mq->recovery_needed = true;
schedule_work(&mq->recovery_work);
}
}
void mmc_cqe_recovery_notifier(struct mmc_request *mrq)
{
struct mmc_queue_req *mqrq = container_of(mrq, struct mmc_queue_req,
brq.mrq);
struct request *req = mmc_queue_req_to_req(mqrq);
struct request_queue *q = req->q;
struct mmc_queue *mq = q->queuedata;
unsigned long flags;
spin_lock_irqsave(q->queue_lock, flags);
__mmc_cqe_recovery_notifier(mq);
spin_unlock_irqrestore(q->queue_lock, flags);
}
static enum blk_eh_timer_return mmc_cqe_timed_out(struct request *req)
{
struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
struct mmc_request *mrq = &mqrq->brq.mrq;
struct mmc_queue *mq = req->q->queuedata;
struct mmc_host *host = mq->card->host;
enum mmc_issue_type issue_type = mmc_issue_type(mq, req);
bool recovery_needed = false;
switch (issue_type) {
case MMC_ISSUE_ASYNC:
case MMC_ISSUE_DCMD:
if (host->cqe_ops->cqe_timeout(host, mrq, &recovery_needed)) {
if (recovery_needed)
__mmc_cqe_recovery_notifier(mq);
return BLK_EH_RESET_TIMER;
}
/* No timeout */
return BLK_EH_HANDLED;
default:
/* Timeout is handled by mmc core */
return BLK_EH_RESET_TIMER;
}
}
static enum blk_eh_timer_return mmc_mq_timed_out(struct request *req,
bool reserved)
{
struct request_queue *q = req->q;
struct mmc_queue *mq = q->queuedata;
unsigned long flags;
int ret;
spin_lock_irqsave(q->queue_lock, flags);
if (mq->recovery_needed || !mq->use_cqe)
ret = BLK_EH_RESET_TIMER;
else
ret = mmc_cqe_timed_out(req);
spin_unlock_irqrestore(q->queue_lock, flags);
return ret;
}
static void mmc_mq_recovery_handler(struct work_struct *work)
{
struct mmc_queue *mq = container_of(work, struct mmc_queue,
recovery_work);
struct request_queue *q = mq->queue;
mmc_get_card(mq->card, &mq->ctx);
mq->in_recovery = true;
mmc_blk_cqe_recovery(mq);
mq->in_recovery = false;
spin_lock_irq(q->queue_lock);
mq->recovery_needed = false;
spin_unlock_irq(q->queue_lock);
mmc_put_card(mq->card, &mq->ctx);
blk_mq_run_hw_queues(q, true);
}
static int mmc_queue_thread(void *d)
{
struct mmc_queue *mq = d;
struct request_queue *q = mq->queue;
struct mmc_context_info *cntx = &mq->card->host->context_info;
current->flags |= PF_MEMALLOC;
down(&mq->thread_sem);
do {
struct request *req;
spin_lock_irq(q->queue_lock);
set_current_state(TASK_INTERRUPTIBLE);
req = blk_fetch_request(q);
mq->asleep = false;
cntx->is_waiting_last_req = false;
cntx->is_new_req = false;
if (!req) {
/*
* Dispatch queue is empty so set flags for
* mmc_request_fn() to wake us up.
*/
if (mq->qcnt)
cntx->is_waiting_last_req = true;
else
mq->asleep = true;
}
spin_unlock_irq(q->queue_lock);
if (req || mq->qcnt) {
set_current_state(TASK_RUNNING);
mmc_blk_issue_rq(mq, req);
cond_resched();
} else {
if (kthread_should_stop()) {
set_current_state(TASK_RUNNING);
break;
}
up(&mq->thread_sem);
schedule();
down(&mq->thread_sem);
}
} while (1);
up(&mq->thread_sem);
return 0;
}
/*
* Generic MMC request handler. This is called for any queue on a
* particular host. When the host is not busy, we look for a request
* on any queue on this host, and attempt to issue it. This may
* not be the queue we were asked to process.
*/
static void mmc_request_fn(struct request_queue *q)
{
struct mmc_queue *mq = q->queuedata;
struct request *req;
struct mmc_context_info *cntx;
if (!mq) {
while ((req = blk_fetch_request(q)) != NULL) {
req->rq_flags |= RQF_QUIET;
__blk_end_request_all(req, BLK_STS_IOERR);
}
return;
}
cntx = &mq->card->host->context_info;
if (cntx->is_waiting_last_req) {
cntx->is_new_req = true;
wake_up_interruptible(&cntx->wait);
}
if (mq->asleep)
wake_up_process(mq->thread);
}
static struct scatterlist *mmc_alloc_sg(int sg_len, gfp_t gfp)
{
struct scatterlist *sg;
sg = kmalloc_array(sg_len, sizeof(*sg), gfp);
if (sg)
sg_init_table(sg, sg_len);
return sg;
}
static void mmc_queue_setup_discard(struct request_queue *q,
struct mmc_card *card)
{
unsigned max_discard;
max_discard = mmc_calc_max_discard(card);
if (!max_discard)
return;
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
blk_queue_max_discard_sectors(q, max_discard);
q->limits.discard_granularity = card->pref_erase << 9;
/* granularity must not be greater than max. discard */
if (card->pref_erase > max_discard)
q->limits.discard_granularity = 0;
if (mmc_can_secure_erase_trim(card))
queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, q);
}
/**
* mmc_init_request() - initialize the MMC-specific per-request data
* @q: the request queue
* @req: the request
* @gfp: memory allocation policy
*/
static int __mmc_init_request(struct mmc_queue *mq, struct request *req,
gfp_t gfp)
{
struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req);
struct mmc_card *card = mq->card;
struct mmc_host *host = card->host;
mq_rq->sg = mmc_alloc_sg(host->max_segs, gfp);
if (!mq_rq->sg)
return -ENOMEM;
return 0;
}
static int mmc_init_request(struct request_queue *q, struct request *req,
gfp_t gfp)
{
return __mmc_init_request(q->queuedata, req, gfp);
}
static void mmc_exit_request(struct request_queue *q, struct request *req)
{
struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req);
kfree(mq_rq->sg);
mq_rq->sg = NULL;
}
static int mmc_mq_init_request(struct blk_mq_tag_set *set, struct request *req,
unsigned int hctx_idx, unsigned int numa_node)
{
return __mmc_init_request(set->driver_data, req, GFP_KERNEL);
}
static void mmc_mq_exit_request(struct blk_mq_tag_set *set, struct request *req,
unsigned int hctx_idx)
{
struct mmc_queue *mq = set->driver_data;
mmc_exit_request(mq->queue, req);
}
/*
* We use BLK_MQ_F_BLOCKING and have only 1 hardware queue, which means requests
* will not be dispatched in parallel.
*/
static blk_status_t mmc_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
struct request *req = bd->rq;
struct request_queue *q = req->q;
struct mmc_queue *mq = q->queuedata;
struct mmc_card *card = mq->card;
struct mmc_host *host = card->host;
enum mmc_issue_type issue_type;
enum mmc_issued issued;
bool get_card, cqe_retune_ok;
int ret;
if (mmc_card_removed(mq->card)) {
req->rq_flags |= RQF_QUIET;
return BLK_STS_IOERR;
}
issue_type = mmc_issue_type(mq, req);
spin_lock_irq(q->queue_lock);
if (mq->recovery_needed) {
spin_unlock_irq(q->queue_lock);
return BLK_STS_RESOURCE;
}
switch (issue_type) {
case MMC_ISSUE_DCMD:
if (mmc_cqe_dcmd_busy(mq)) {
mq->cqe_busy |= MMC_CQE_DCMD_BUSY;
spin_unlock_irq(q->queue_lock);
return BLK_STS_RESOURCE;
}
break;
case MMC_ISSUE_ASYNC:
break;
default:
/*
* Timeouts are handled by mmc core, and we don't have a host
* API to abort requests, so we can't handle the timeout anyway.
* However, when the timeout happens, blk_mq_complete_request()
* no longer works (to stop the request disappearing under us).
* To avoid racing with that, set a large timeout.
*/
req->timeout = 600 * HZ;
break;
}
mq->in_flight[issue_type] += 1;
get_card = (mmc_tot_in_flight(mq) == 1);
cqe_retune_ok = (mmc_cqe_qcnt(mq) == 1);
spin_unlock_irq(q->queue_lock);
if (!(req->rq_flags & RQF_DONTPREP)) {
req_to_mmc_queue_req(req)->retries = 0;
req->rq_flags |= RQF_DONTPREP;
}
if (get_card)
mmc_get_card(card, &mq->ctx);
if (mq->use_cqe) {
host->retune_now = host->need_retune && cqe_retune_ok &&
!host->hold_retune;
}
blk_mq_start_request(req);
issued = mmc_blk_mq_issue_rq(mq, req);
switch (issued) {
case MMC_REQ_BUSY:
ret = BLK_STS_RESOURCE;
break;
case MMC_REQ_FAILED_TO_START:
ret = BLK_STS_IOERR;
break;
default:
ret = BLK_STS_OK;
break;
}
if (issued != MMC_REQ_STARTED) {
bool put_card = false;
spin_lock_irq(q->queue_lock);
mq->in_flight[issue_type] -= 1;
if (mmc_tot_in_flight(mq) == 0)
put_card = true;
spin_unlock_irq(q->queue_lock);
if (put_card)
mmc_put_card(card, &mq->ctx);
}
return ret;
}
static const struct blk_mq_ops mmc_mq_ops = {
.queue_rq = mmc_mq_queue_rq,
.init_request = mmc_mq_init_request,
.exit_request = mmc_mq_exit_request,
.complete = mmc_blk_mq_complete,
.timeout = mmc_mq_timed_out,
};
static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)
{
struct mmc_host *host = card->host;
u64 limit = BLK_BOUNCE_HIGH;
if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask)
limit = (u64)dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT;
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mq->queue);
queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, mq->queue);
if (mmc_can_erase(card))
mmc_queue_setup_discard(mq->queue, card);
blk_queue_bounce_limit(mq->queue, limit);
blk_queue_max_hw_sectors(mq->queue,
min(host->max_blk_count, host->max_req_size / 512));
blk_queue_max_segments(mq->queue, host->max_segs);
blk_queue_max_segment_size(mq->queue, host->max_seg_size);
/* Initialize thread_sem even if it is not used */
sema_init(&mq->thread_sem, 1);
INIT_WORK(&mq->recovery_work, mmc_mq_recovery_handler);
INIT_WORK(&mq->complete_work, mmc_blk_mq_complete_work);
mutex_init(&mq->complete_lock);
init_waitqueue_head(&mq->wait);
}
static int mmc_mq_init_queue(struct mmc_queue *mq, int q_depth,
const struct blk_mq_ops *mq_ops, spinlock_t *lock)
{
int ret;
memset(&mq->tag_set, 0, sizeof(mq->tag_set));
mq->tag_set.ops = mq_ops;
mq->tag_set.queue_depth = q_depth;
mq->tag_set.numa_node = NUMA_NO_NODE;
mq->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE |
BLK_MQ_F_BLOCKING;
mq->tag_set.nr_hw_queues = 1;
mq->tag_set.cmd_size = sizeof(struct mmc_queue_req);
mq->tag_set.driver_data = mq;
ret = blk_mq_alloc_tag_set(&mq->tag_set);
if (ret)
return ret;
mq->queue = blk_mq_init_queue(&mq->tag_set);
if (IS_ERR(mq->queue)) {
ret = PTR_ERR(mq->queue);
goto free_tag_set;
}
mq->queue->queue_lock = lock;
mq->queue->queuedata = mq;
return 0;
free_tag_set:
blk_mq_free_tag_set(&mq->tag_set);
return ret;
}
/* Set queue depth to get a reasonable value for q->nr_requests */
#define MMC_QUEUE_DEPTH 64
static int mmc_mq_init(struct mmc_queue *mq, struct mmc_card *card,
spinlock_t *lock)
{
struct mmc_host *host = card->host;
int q_depth;
int ret;
/*
* The queue depth for CQE must match the hardware because the request
* tag is used to index the hardware queue.
*/
if (mq->use_cqe)
q_depth = min_t(int, card->ext_csd.cmdq_depth, host->cqe_qdepth);
else
q_depth = MMC_QUEUE_DEPTH;
ret = mmc_mq_init_queue(mq, q_depth, &mmc_mq_ops, lock);
if (ret)
return ret;
blk_queue_rq_timeout(mq->queue, 60 * HZ);
mmc_setup_queue(mq, card);
return 0;
}
/**
* mmc_init_queue - initialise a queue structure.
* @mq: mmc queue
* @card: mmc card to attach this queue
* @lock: queue lock
* @subname: partition subname
*
* Initialise a MMC card request queue.
*/
int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
spinlock_t *lock, const char *subname)
{
struct mmc_host *host = card->host;
int ret = -ENOMEM;
mq->card = card;
mq->use_cqe = host->cqe_enabled;
if (mq->use_cqe || mmc_host_use_blk_mq(host))
return mmc_mq_init(mq, card, lock);
mq->queue = blk_alloc_queue(GFP_KERNEL);
if (!mq->queue)
return -ENOMEM;
mq->queue->queue_lock = lock;
mq->queue->request_fn = mmc_request_fn;
mq->queue->init_rq_fn = mmc_init_request;
mq->queue->exit_rq_fn = mmc_exit_request;
mq->queue->cmd_size = sizeof(struct mmc_queue_req);
mq->queue->queuedata = mq;
mq->qcnt = 0;
ret = blk_init_allocated_queue(mq->queue);
if (ret) {
blk_cleanup_queue(mq->queue);
return ret;
}
blk_queue_prep_rq(mq->queue, mmc_prep_request);
mmc_setup_queue(mq, card);
mq->thread = kthread_run(mmc_queue_thread, mq, "mmcqd/%d%s",
host->index, subname ? subname : "");
if (IS_ERR(mq->thread)) {
ret = PTR_ERR(mq->thread);
goto cleanup_queue;
}
return 0;
cleanup_queue:
blk_cleanup_queue(mq->queue);
return ret;
}
static void mmc_mq_queue_suspend(struct mmc_queue *mq)
{
blk_mq_quiesce_queue(mq->queue);
/*
* The host remains claimed while there are outstanding requests, so
* simply claiming and releasing here ensures there are none.
*/
mmc_claim_host(mq->card->host);
mmc_release_host(mq->card->host);
}
static void mmc_mq_queue_resume(struct mmc_queue *mq)
{
blk_mq_unquiesce_queue(mq->queue);
}
static void __mmc_queue_suspend(struct mmc_queue *mq)
{
struct request_queue *q = mq->queue;
unsigned long flags;
if (!mq->suspended) {
mq->suspended |= true;
spin_lock_irqsave(q->queue_lock, flags);
blk_stop_queue(q);
spin_unlock_irqrestore(q->queue_lock, flags);
down(&mq->thread_sem);
}
}
static void __mmc_queue_resume(struct mmc_queue *mq)
{
struct request_queue *q = mq->queue;
unsigned long flags;
if (mq->suspended) {
mq->suspended = false;
up(&mq->thread_sem);
spin_lock_irqsave(q->queue_lock, flags);
blk_start_queue(q);
spin_unlock_irqrestore(q->queue_lock, flags);
}
}
void mmc_cleanup_queue(struct mmc_queue *mq)
{
struct request_queue *q = mq->queue;
unsigned long flags;
if (q->mq_ops) {
/*
* The legacy code handled the possibility of being suspended,
* so do that here too.
*/
if (blk_queue_quiesced(q))
blk_mq_unquiesce_queue(q);
goto out_cleanup;
}
/* Make sure the queue isn't suspended, as that will deadlock */
mmc_queue_resume(mq);
/* Then terminate our worker thread */
kthread_stop(mq->thread);
/* Empty the queue */
spin_lock_irqsave(q->queue_lock, flags);
q->queuedata = NULL;
blk_start_queue(q);
spin_unlock_irqrestore(q->queue_lock, flags);
out_cleanup:
blk_cleanup_queue(q);
/*
* A request can be completed before the next request, potentially
* leaving a complete_work with nothing to do. Such a work item might
* still be queued at this point. Flush it.
*/
flush_work(&mq->complete_work);
mq->card = NULL;
}
/**
* mmc_queue_suspend - suspend a MMC request queue
* @mq: MMC queue to suspend
*
* Stop the block request queue, and wait for our thread to
* complete any outstanding requests. This ensures that we
* won't suspend while a request is being processed.
*/
void mmc_queue_suspend(struct mmc_queue *mq)
{
struct request_queue *q = mq->queue;
if (q->mq_ops)
mmc_mq_queue_suspend(mq);
else
__mmc_queue_suspend(mq);
}
/**
* mmc_queue_resume - resume a previously suspended MMC request queue
* @mq: MMC queue to resume
*/
void mmc_queue_resume(struct mmc_queue *mq)
{
struct request_queue *q = mq->queue;
if (q->mq_ops)
mmc_mq_queue_resume(mq);
else
__mmc_queue_resume(mq);
}
/*
* Prepare the sg list(s) to be handed of to the host driver
*/
unsigned int mmc_queue_map_sg(struct mmc_queue *mq, struct mmc_queue_req *mqrq)
{
struct request *req = mmc_queue_req_to_req(mqrq);
return blk_rq_map_sg(mq->queue, req, mqrq->sg);
}
Reference in New Issue View Git Blame Copy Permalink