Star64_linux/drivers/mmc/card/queue.c
Linus Torvalds 36869cb93d Merge branch 'for-4.10/block' of git://git.kernel.dk/linux-block
Pull block layer updates from Jens Axboe:
 "This is the main block pull request this series. Contrary to previous
  release, I've kept the core and driver changes in the same branch. We
  always ended up having dependencies between the two for obvious
  reasons, so makes more sense to keep them together. That said, I'll
  probably try and keep more topical branches going forward, especially
  for cycles that end up being as busy as this one.

  The major parts of this pull request is:

   - Improved support for O_DIRECT on block devices, with a small
     private implementation instead of using the pig that is
     fs/direct-io.c. From Christoph.

   - Request completion tracking in a scalable fashion. This is utilized
     by two components in this pull, the new hybrid polling and the
     writeback queue throttling code.

   - Improved support for polling with O_DIRECT, adding a hybrid mode
     that combines pure polling with an initial sleep. From me.

   - Support for automatic throttling of writeback queues on the block
     side. This uses feedback from the device completion latencies to
     scale the queue on the block side up or down. From me.

   - Support from SMR drives in the block layer and for SD. From Hannes
     and Shaun.

   - Multi-connection support for nbd. From Josef.

   - Cleanup of request and bio flags, so we have a clear split between
     which are bio (or rq) private, and which ones are shared. From
     Christoph.

   - A set of patches from Bart, that improve how we handle queue
     stopping and starting in blk-mq.

   - Support for WRITE_ZEROES from Chaitanya.

   - Lightnvm updates from Javier/Matias.

   - Supoort for FC for the nvme-over-fabrics code. From James Smart.

   - A bunch of fixes from a whole slew of people, too many to name
     here"

* 'for-4.10/block' of git://git.kernel.dk/linux-block: (182 commits)
  blk-stat: fix a few cases of missing batch flushing
  blk-flush: run the queue when inserting blk-mq flush
  elevator: make the rqhash helpers exported
  blk-mq: abstract out blk_mq_dispatch_rq_list() helper
  blk-mq: add blk_mq_start_stopped_hw_queue()
  block: improve handling of the magic discard payload
  blk-wbt: don't throttle discard or write zeroes
  nbd: use dev_err_ratelimited in io path
  nbd: reset the setup task for NBD_CLEAR_SOCK
  nvme-fabrics: Add FC LLDD loopback driver to test FC-NVME
  nvme-fabrics: Add target support for FC transport
  nvme-fabrics: Add host support for FC transport
  nvme-fabrics: Add FC transport LLDD api definitions
  nvme-fabrics: Add FC transport FC-NVME definitions
  nvme-fabrics: Add FC transport error codes to nvme.h
  Add type 0x28 NVME type code to scsi fc headers
  nvme-fabrics: patch target code in prep for FC transport support
  nvme-fabrics: set sqe.command_id in core not transports
  parser: add u64 number parser
  nvme-rdma: align to generic ib_event logging helper
  ...
2016-12-13 10:19:16 -08:00

491 lines
11 KiB
C

/*
* linux/drivers/mmc/card/queue.c
*
* 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"
#define MMC_QUEUE_BOUNCESZ 65536
/*
* 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;
/*
* We only like normal block requests and discards.
*/
if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD &&
req_op(req) != REQ_OP_SECURE_ERASE) {
blk_dump_rq_flags(req, "MMC bad request");
return BLKPREP_KILL;
}
if (mq && (mmc_card_removed(mq->card) || mmc_access_rpmb(mq)))
return BLKPREP_KILL;
req->rq_flags |= RQF_DONTPREP;
return BLKPREP_OK;
}
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 = NULL;
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->mqrq_prev->req)
cntx->is_waiting_last_req = true;
else
mq->asleep = true;
}
mq->mqrq_cur->req = req;
spin_unlock_irq(q->queue_lock);
if (req || mq->mqrq_prev->req) {
bool req_is_special = mmc_req_is_special(req);
set_current_state(TASK_RUNNING);
mmc_blk_issue_rq(mq, req);
cond_resched();
if (mq->flags & MMC_QUEUE_NEW_REQUEST) {
mq->flags &= ~MMC_QUEUE_NEW_REQUEST;
continue; /* fetch again */
}
/*
* Current request becomes previous request
* and vice versa.
* In case of special requests, current request
* has been finished. Do not assign it to previous
* request.
*/
if (req_is_special)
mq->mqrq_cur->req = NULL;
mq->mqrq_prev->brq.mrq.data = NULL;
mq->mqrq_prev->req = NULL;
swap(mq->mqrq_prev, mq->mqrq_cur);
} 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, -EIO);
}
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, int *err)
{
struct scatterlist *sg;
sg = kmalloc(sizeof(struct scatterlist)*sg_len, GFP_KERNEL);
if (!sg)
*err = -ENOMEM;
else {
*err = 0;
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);
if (card->erased_byte == 0 && !mmc_can_discard(card))
q->limits.discard_zeroes_data = 1;
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);
}
#ifdef CONFIG_MMC_BLOCK_BOUNCE
static bool mmc_queue_alloc_bounce_bufs(struct mmc_queue *mq,
unsigned int bouncesz)
{
int i;
for (i = 0; i < mq->qdepth; i++) {
mq->mqrq[i].bounce_buf = kmalloc(bouncesz, GFP_KERNEL);
if (!mq->mqrq[i].bounce_buf)
goto out_err;
}
return true;
out_err:
while (--i >= 0) {
kfree(mq->mqrq[i].bounce_buf);
mq->mqrq[i].bounce_buf = NULL;
}
pr_warn("%s: unable to allocate bounce buffers\n",
mmc_card_name(mq->card));
return false;
}
static int mmc_queue_alloc_bounce_sgs(struct mmc_queue *mq,
unsigned int bouncesz)
{
int i, ret;
for (i = 0; i < mq->qdepth; i++) {
mq->mqrq[i].sg = mmc_alloc_sg(1, &ret);
if (ret)
return ret;
mq->mqrq[i].bounce_sg = mmc_alloc_sg(bouncesz / 512, &ret);
if (ret)
return ret;
}
return 0;
}
#endif
static int mmc_queue_alloc_sgs(struct mmc_queue *mq, int max_segs)
{
int i, ret;
for (i = 0; i < mq->qdepth; i++) {
mq->mqrq[i].sg = mmc_alloc_sg(max_segs, &ret);
if (ret)
return ret;
}
return 0;
}
static void mmc_queue_req_free_bufs(struct mmc_queue_req *mqrq)
{
kfree(mqrq->bounce_sg);
mqrq->bounce_sg = NULL;
kfree(mqrq->sg);
mqrq->sg = NULL;
kfree(mqrq->bounce_buf);
mqrq->bounce_buf = NULL;
}
static void mmc_queue_reqs_free_bufs(struct mmc_queue *mq)
{
int i;
for (i = 0; i < mq->qdepth; i++)
mmc_queue_req_free_bufs(&mq->mqrq[i]);
}
/**
* 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;
u64 limit = BLK_BOUNCE_HIGH;
bool bounce = false;
int ret = -ENOMEM;
if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask)
limit = (u64)dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT;
mq->card = card;
mq->queue = blk_init_queue(mmc_request_fn, lock);
if (!mq->queue)
return -ENOMEM;
mq->qdepth = 2;
mq->mqrq = kcalloc(mq->qdepth, sizeof(struct mmc_queue_req),
GFP_KERNEL);
if (!mq->mqrq)
goto blk_cleanup;
mq->mqrq_cur = &mq->mqrq[0];
mq->mqrq_prev = &mq->mqrq[1];
mq->queue->queuedata = mq;
blk_queue_prep_rq(mq->queue, mmc_prep_request);
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);
#ifdef CONFIG_MMC_BLOCK_BOUNCE
if (host->max_segs == 1) {
unsigned int bouncesz;
bouncesz = MMC_QUEUE_BOUNCESZ;
if (bouncesz > host->max_req_size)
bouncesz = host->max_req_size;
if (bouncesz > host->max_seg_size)
bouncesz = host->max_seg_size;
if (bouncesz > (host->max_blk_count * 512))
bouncesz = host->max_blk_count * 512;
if (bouncesz > 512 &&
mmc_queue_alloc_bounce_bufs(mq, bouncesz)) {
blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_ANY);
blk_queue_max_hw_sectors(mq->queue, bouncesz / 512);
blk_queue_max_segments(mq->queue, bouncesz / 512);
blk_queue_max_segment_size(mq->queue, bouncesz);
ret = mmc_queue_alloc_bounce_sgs(mq, bouncesz);
if (ret)
goto cleanup_queue;
bounce = true;
}
}
#endif
if (!bounce) {
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);
ret = mmc_queue_alloc_sgs(mq, host->max_segs);
if (ret)
goto cleanup_queue;
}
sema_init(&mq->thread_sem, 1);
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:
mmc_queue_reqs_free_bufs(mq);
kfree(mq->mqrq);
mq->mqrq = NULL;
blk_cleanup:
blk_cleanup_queue(mq->queue);
return ret;
}
void mmc_cleanup_queue(struct mmc_queue *mq)
{
struct request_queue *q = mq->queue;
unsigned long flags;
/* 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);
mmc_queue_reqs_free_bufs(mq);
kfree(mq->mqrq);
mq->mqrq = NULL;
mq->card = NULL;
}
EXPORT_SYMBOL(mmc_cleanup_queue);
/**
* 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;
unsigned long flags;
if (!(mq->flags & MMC_QUEUE_SUSPENDED)) {
mq->flags |= MMC_QUEUE_SUSPENDED;
spin_lock_irqsave(q->queue_lock, flags);
blk_stop_queue(q);
spin_unlock_irqrestore(q->queue_lock, flags);
down(&mq->thread_sem);
}
}
/**
* 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;
unsigned long flags;
if (mq->flags & MMC_QUEUE_SUSPENDED) {
mq->flags &= ~MMC_QUEUE_SUSPENDED;
up(&mq->thread_sem);
spin_lock_irqsave(q->queue_lock, flags);
blk_start_queue(q);
spin_unlock_irqrestore(q->queue_lock, flags);
}
}
/*
* 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)
{
unsigned int sg_len;
size_t buflen;
struct scatterlist *sg;
int i;
if (!mqrq->bounce_buf)
return blk_rq_map_sg(mq->queue, mqrq->req, mqrq->sg);
sg_len = blk_rq_map_sg(mq->queue, mqrq->req, mqrq->bounce_sg);
mqrq->bounce_sg_len = sg_len;
buflen = 0;
for_each_sg(mqrq->bounce_sg, sg, sg_len, i)
buflen += sg->length;
sg_init_one(mqrq->sg, mqrq->bounce_buf, buflen);
return 1;
}
/*
* If writing, bounce the data to the buffer before the request
* is sent to the host driver
*/
void mmc_queue_bounce_pre(struct mmc_queue_req *mqrq)
{
if (!mqrq->bounce_buf)
return;
if (rq_data_dir(mqrq->req) != WRITE)
return;
sg_copy_to_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len,
mqrq->bounce_buf, mqrq->sg[0].length);
}
/*
* If reading, bounce the data from the buffer after the request
* has been handled by the host driver
*/
void mmc_queue_bounce_post(struct mmc_queue_req *mqrq)
{
if (!mqrq->bounce_buf)
return;
if (rq_data_dir(mqrq->req) != READ)
return;
sg_copy_from_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len,
mqrq->bounce_buf, mqrq->sg[0].length);
}