Re: [PATCH v2] mmc: core: Add support for idle time BKOPS

[Jaehoon Chung <jh80.chung@samsung.com>]

Hi Maya, 

I tested with dw-mmc controller.
It's look good to me.

Tested-by: Jaehoon Chung <jh80.chung@samsung.com>

On 11/07/2012 01:28 PM, merez@codeaurora.org wrote:
> Hi Jaehoon,
> 
> Any update on this patch review and testing?
> 
> Thanks,
> Maya
> On Mon, October 15, 2012 11:53 pm, Jaehoon Chung wrote:
>> Hi Maya,
>>
>> I'm testing with your patch..but i need to have the more time for testing.
>> In now, it looks good to me. Thank you for working the idle bkops.
>>
>> Best Regards,
>> Jaehoon Chung
>>
>>> ---
>>> diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
>>> index 172a768..ed040d5 100644
>>> --- a/drivers/mmc/card/block.c
>>> +++ b/drivers/mmc/card/block.c
>>> @@ -827,6 +827,9 @@ static int mmc_blk_issue_discard_rq(struct mmc_queue
>>> *mq, struct request *req)
>>>  	from = blk_rq_pos(req);
>>>  	nr = blk_rq_sectors(req);
>>>
>>> +	if (card->ext_csd.bkops_en)
>>> +		card->bkops_info.sectors_changed += blk_rq_sectors(req);
>> using nr?
>>> +
>>>  	if (mmc_can_discard(card))
>>>  		arg = MMC_DISCARD_ARG;
>>>  	else if (mmc_can_trim(card))
>>> @@ -1268,6 +1271,9 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue
>>> *mq, struct request *rqc)
>>>  	if (!rqc && !mq->mqrq_prev->req)
>>>  		return 0;
>>>
>>> +	if (rqc && (card->ext_csd.bkops_en) && (rq_data_dir(rqc) == WRITE))
>>> +			card->bkops_info.sectors_changed += blk_rq_sectors(rqc);
>> Fix the indent.
>>> +
>>>  	do {
>>>  		if (rqc) {
>>>  			/*
>>> diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
>>> index e360a97..e96f5cf 100644
>>> --- a/drivers/mmc/card/queue.c
>>> +++ b/drivers/mmc/card/queue.c
>>> @@ -51,6 +51,7 @@ static int mmc_queue_thread(void *d)
>>>  {
>>>  	struct mmc_queue *mq = d;
>>>  	struct request_queue *q = mq->queue;
>>> +	struct mmc_card *card = mq->card;
>>>
>>>  	current->flags |= PF_MEMALLOC;
>>>
>>> @@ -66,6 +67,17 @@ static int mmc_queue_thread(void *d)
>>>  		spin_unlock_irq(q->queue_lock);
>>>
>>>  		if (req || mq->mqrq_prev->req) {
>>> +			/*
>>> +			 * If this is the first request, BKOPs might be in
>>> +			 * progress and needs to be stopped before issuing the
>>> +			 * request
>>> +			 */
>>> +			if (card->ext_csd.bkops_en &&
>>> +			    card->bkops_info.started_delayed_bkops) {
>>> +				card->bkops_info.started_delayed_bkops = false;
>>> +				mmc_stop_bkops(card);
>> if mmc_stop_bkops is failed..?
>>> +			}
>>> +
>>>  			set_current_state(TASK_RUNNING);
>>>  			mq->issue_fn(mq, req);
>>>  		} else {
>>> @@ -73,6 +85,7 @@ static int mmc_queue_thread(void *d)
>>>  				set_current_state(TASK_RUNNING);
>>>  				break;
>>>  			}
>>> +			mmc_start_delayed_bkops(card);
>>>  			up(&mq->thread_sem);
>>>  			schedule();
>>>  			down(&mq->thread_sem);
>>> diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
>>> index 6612163..fd8783d 100644
>>> --- a/drivers/mmc/core/core.c
>>> +++ b/drivers/mmc/core/core.c
>>> @@ -253,9 +253,42 @@ mmc_start_request(struct mmc_host *host, struct
>>> mmc_request *mrq)
>>>  }
>>>
>>>  /**
>>> + * mmc_start_delayed_bkops() - Start a delayed work to check for
>>> + *      the need of non urgent BKOPS
>>> + *
>>> + * @card: MMC card to start BKOPS on
>>> + */
>>> +void mmc_start_delayed_bkops(struct mmc_card *card)
>>> +{
>>> +	if (!card || !card->ext_csd.bkops_en || mmc_card_doing_bkops(card))
>>> +		return;
>>> +
>>> +	if (card->bkops_info.sectors_changed <
>>> +	    BKOPS_MIN_SECTORS_TO_QUEUE_DELAYED_WORK)
>>> +		return;
>>> +
>>> +	pr_debug("%s: %s: queueing delayed_bkops_work\n",
>>> +		 mmc_hostname(card->host), __func__);
>>> +
>>> +	card->bkops_info.sectors_changed = 0;
>>> +
>>> +	/*
>>> +	 * cancel_delayed_bkops_work will prevent a race condition between
>>> +	 * fetching a request by the mmcqd and the delayed work, in case
>>> +	 * it was removed from the queue work but not started yet
>>> +	 */
>>> +	card->bkops_info.cancel_delayed_work = false;
>>> +	card->bkops_info.started_delayed_bkops = true;
>>> +	queue_delayed_work(system_nrt_wq, &card->bkops_info.dw,
>>> +			   msecs_to_jiffies(
>>> +				   card->bkops_info.delay_ms));
>>> +}
>>> +EXPORT_SYMBOL(mmc_start_delayed_bkops);
>>> +
>>> +/**
>>>   *	mmc_start_bkops - start BKOPS for supported cards
>>>   *	@card: MMC card to start BKOPS
>>> - *	@form_exception: A flag to indicate if this function was
>>> + *	@from_exception: A flag to indicate if this function was
>>>   *			 called due to an exception raised by the card
>>>   *
>>>   *	Start background operations whenever requested.
>>> @@ -269,25 +302,47 @@ void mmc_start_bkops(struct mmc_card *card, bool
>>> from_exception)
>>>  	bool use_busy_signal;
>>>
>>>  	BUG_ON(!card);
>>> -
>>> -	if (!card->ext_csd.bkops_en || mmc_card_doing_bkops(card))
>>> +	if (!card->ext_csd.bkops_en)
>>>  		return;
>>>
>>> +	mmc_claim_host(card->host);
>>> +
>>> +	if ((card->bkops_info.cancel_delayed_work) && !from_exception) {
>>> +		pr_debug("%s: %s: cancel_delayed_work was set, exit\n",
>>> +			 mmc_hostname(card->host), __func__);
>>> +		card->bkops_info.cancel_delayed_work = false;
>>> +		goto out;
>>> +	}
>>> +
>>> +	if (mmc_card_doing_bkops(card)) {
>>> +		pr_debug("%s: %s: already doing bkops, exit\n",
>>> +			 mmc_hostname(card->host), __func__);
>>> +		goto out;
>>> +	}
>>> +
>>>  	err = mmc_read_bkops_status(card);
>>>  	if (err) {
>>>  		pr_err("%s: Failed to read bkops status: %d\n",
>>>  		       mmc_hostname(card->host), err);
>>> -		return;
>>> +		goto out;
>>>  	}
>>>
>>>  	if (!card->ext_csd.raw_bkops_status)
>>> -		return;
>>> +		goto out;
>>> +
>>> +	pr_info("%s: %s: card->ext_csd.raw_bkops_status = 0x%x\n",
>>> +		mmc_hostname(card->host), __func__,
>>> +		card->ext_csd.raw_bkops_status);
>>>
>>> +	/*
>>> +	 * If the function was called due to exception but there is no need
>>> +	 * for urgent BKOPS, BKOPs will be performed by the delayed BKOPs
>>> +	 * work, before going to suspend
>>> +	 */
>>>  	if (card->ext_csd.raw_bkops_status < EXT_CSD_BKOPS_LEVEL_2 &&
>>>  	    from_exception)
>>> -		return;
>>> +		goto out;
>>>
>>> -	mmc_claim_host(card->host);
>>>  	if (card->ext_csd.raw_bkops_status >= EXT_CSD_BKOPS_LEVEL_2) {
>>>  		timeout = MMC_BKOPS_MAX_TIMEOUT;
>>>  		use_busy_signal = true;
>>> @@ -309,13 +364,108 @@ void mmc_start_bkops(struct mmc_card *card, bool
>>> from_exception)
>>>  	 * bkops executed synchronously, otherwise
>>>  	 * the operation is in progress
>>>  	 */
>>> -	if (!use_busy_signal)
>>> +	if (!use_busy_signal) {
>>>  		mmc_card_set_doing_bkops(card);
>>> +		pr_debug("%s: %s: starting the polling thread\n",
>>> +			 mmc_hostname(card->host), __func__);
>>> +		queue_work(system_nrt_wq,
>>> +			   &card->bkops_info.poll_for_completion);
>>> +	}
>>> +
>>>  out:
>>>  	mmc_release_host(card->host);
>>>  }
>>>  EXPORT_SYMBOL(mmc_start_bkops);
>>>
>>> +/**
>>> + * mmc_bkops_completion_polling() - Poll on the card status to
>>> + * wait for the non-blocking BKOPS completion
>>> + * @work:	The completion polling work
>>> + *
>>> + * The on-going reading of the card status will prevent the card
>>> + * from getting into suspend while it is in the middle of
>>> + * performing BKOPS.
>>> + * Since the non blocking BKOPS can be interrupted by a fetched
>>> + * request we also check IF mmc_card_doing_bkops in each
>>> + * iteration.
>>> + */
>>> +void mmc_bkops_completion_polling(struct work_struct *work)
>>> +{
>>> +	struct mmc_card *card = container_of(work, struct mmc_card,
>>> +			bkops_info.poll_for_completion);
>>> +	unsigned long timeout_jiffies = jiffies +
>>> +		msecs_to_jiffies(BKOPS_COMPLETION_POLLING_TIMEOUT_MS);
>>> +	u32 status;
>>> +	int err;
>>> +
>>> +	/*
>>> +	 * Wait for the BKOPs to complete. Keep reading the status to prevent
>>> +	 * the host from getting into suspend
>>> +	 */
>>> +	do {
>>> +		mmc_claim_host(card->host);
>>> +
>>> +		if (!mmc_card_doing_bkops(card))
>>> +			goto out;
>>> +
>>> +		err = mmc_send_status(card, &status);
>>> +		if (err) {
>>> +			pr_err("%s: error %d requesting status\n",
>>> +			       mmc_hostname(card->host), err);
>>> +			goto out;
>>> +		}
>>> +
>>> +		/*
>>> +		 * Some cards mishandle the status bits, so make sure to check
>>> +		 * both the busy indication and the card state.
>>> +		 */
>>> +		if ((status & R1_READY_FOR_DATA) &&
>>> +		    (R1_CURRENT_STATE(status) != R1_STATE_PRG)) {
>>> +			pr_debug("%s: %s: completed BKOPs, exit polling\n",
>>> +				 mmc_hostname(card->host), __func__);
>>> +			mmc_card_clr_doing_bkops(card);
>>> +			card->bkops_info.started_delayed_bkops = false;
>>> +			goto out;
>>> +		}
>>> +
>>> +		mmc_release_host(card->host);
>>> +
>>> +		/*
>>> +		 * Sleep before checking the card status again to allow the
>>> +		 * card to complete the BKOPs operation
>>> +		 */
>>> +		msleep(BKOPS_COMPLETION_POLLING_INTERVAL_MS);
>>> +	} while (time_before(jiffies, timeout_jiffies));
>>> +
>>> +	pr_err("%s: %s: exit polling due to timeout\n",
>>> +	       mmc_hostname(card->host), __func__);
>>> +
>>> +	return;
>>> +out:
>>> +	mmc_release_host(card->host);
>>> +}
>>> +
>>> +/**
>>> + * mmc_start_idle_time_bkops() - check if a non urgent BKOPS is
>>> + * needed
>>> + * @work:	The idle time BKOPS work
>>> + */
>>> +void mmc_start_idle_time_bkops(struct work_struct *work)
>>> +{
>>> +	struct mmc_card *card = container_of(work, struct mmc_card,
>>> +			bkops_info.dw.work);
>>> +
>>> +	/*
>>> +	 * Prevent a race condition between mmc_stop_bkops and the delayed
>>> +	 * BKOPS work in case the delayed work is executed on another CPU
>>> +	 */
>>> +	if (card->bkops_info.cancel_delayed_work)
>>> +		return;
>>> +
>>> +	mmc_start_bkops(card, false);
>>> +}
>>> +EXPORT_SYMBOL(mmc_start_idle_time_bkops);
>>> +
>>>  static void mmc_wait_done(struct mmc_request *mrq)
>>>  {
>>>  	complete(&mrq->completion);
>>> @@ -582,6 +732,19 @@ int mmc_stop_bkops(struct mmc_card *card)
>>>  	int err = 0;
>>>
>>>  	BUG_ON(!card);
>>> +
>>> +	mmc_claim_host(card->host);
>>> +
>>> +	/*
>>> +	 * Notify the delayed work to be cancelled, in case it was already
>>> +	 * removed from the queue, but was not started yet
>>> +	 */
>>> +	card->bkops_info.cancel_delayed_work = true;
>>> +	if (delayed_work_pending(&card->bkops_info.dw))
>>> +		cancel_delayed_work_sync(&card->bkops_info.dw);
>>> +	if (!mmc_card_doing_bkops(card))
>>> +		goto out;
>>> +
>>>  	err = mmc_interrupt_hpi(card);
>>>
>>>  	/*
>>> @@ -593,6 +756,8 @@ int mmc_stop_bkops(struct mmc_card *card)
>>>  		err = 0;
>>>  	}
>>>
>>> +out:
>>> +	mmc_release_host(card->host);
>>>  	return err;
>>>  }
>>>  EXPORT_SYMBOL(mmc_stop_bkops);
>>> @@ -2566,15 +2731,13 @@ int mmc_pm_notify(struct notifier_block
>>> *notify_block,
>>>  	switch (mode) {
>>>  	case PM_HIBERNATION_PREPARE:
>>>  	case PM_SUSPEND_PREPARE:
>>> -		if (host->card && mmc_card_mmc(host->card) &&
>>> -		    mmc_card_doing_bkops(host->card)) {
>>> +		if (host->card && mmc_card_mmc(host->card)) {
>>>  			err = mmc_stop_bkops(host->card);
>>>  			if (err) {
>>>  				pr_err("%s: didn't stop bkops\n",
>>>  					mmc_hostname(host));
>>>  				return err;
>>>  			}
>>> -			mmc_card_clr_doing_bkops(host->card);
>>>  		}
>>>
>>>  		spin_lock_irqsave(&host->lock, flags);
>>> diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
>>> index 7509de1..f8ff640 100644
>>> --- a/drivers/mmc/core/mmc.c
>>> +++ b/drivers/mmc/core/mmc.c
>>> @@ -1258,6 +1258,30 @@ static int mmc_init_card(struct mmc_host *host,
>>> u32 ocr,
>>>  		}
>>>  	}
>>>
>>> +	if (!oldcard) {
>>> +		if (card->ext_csd.bkops_en) {
>>> +			INIT_DELAYED_WORK(&card->bkops_info.dw,
>>> +					  mmc_start_idle_time_bkops);
>>> +			INIT_WORK(&card->bkops_info.poll_for_completion,
>>> +				  mmc_bkops_completion_polling);
>>> +
>>> +			/*
>>> +			 * Calculate the time to start the BKOPs checking.
>>> +			 * The idle time of the host controller should be taken
>>> +			 * into account in order to prevent a race condition
>>> +			 * before starting BKOPs and going into suspend.
>>> +			 * If the host controller didn't set its idle time,
>>> +			 * a default value is used.
>>> +			 */
>>> +			card->bkops_info.delay_ms = MMC_IDLE_BKOPS_TIME_MS;
>>> +			if (card->bkops_info.host_suspend_tout_ms)
>>> +				card->bkops_info.delay_ms = min(
>>> +					card->bkops_info.delay_ms,
>>> +				      card->bkops_info.host_suspend_tout_ms/2);
>>> +
>>> +		}
>>> +	}
>>> +
>>>  	if (!oldcard)
>>>  		host->card = card;
>>>
>>> diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
>>> index 78cc3be..0e4d55a 100644
>>> --- a/include/linux/mmc/card.h
>>> +++ b/include/linux/mmc/card.h
>>> @@ -207,6 +207,48 @@ struct mmc_part {
>>>  #define MMC_BLK_DATA_AREA_GP	(1<<2)
>>>  };
>>>
>>> +/**
>>> + * struct mmc_bkops_info - BKOPS data
>>> + * @dw:	Idle time bkops delayed work
>>> + * @host_suspend_tout_ms:	The host controller idle time,
>>> + * before getting into suspend
>>> + * @delay_ms:	The time to start the BKOPS
>>> + *        delayed work once MMC thread is idle
>>> + * @poll_for_completion:	Poll on BKOPS completion
>>> + * @cancel_delayed_work: A flag to indicate if the delayed work
>>> + *        should be cancelled
>>> + * @started_delayed_bkops:  A flag to indicate if the delayed
>>> + *        work was scheduled
>>> + * @sectors_changed:  number of  sectors written or
>>> + *       discard since the last idle BKOPS were scheduled
>>> + */
>>> +struct mmc_bkops_info {
>>> +	struct delayed_work	dw;
>>> +	unsigned int		host_suspend_tout_ms;
>>> +	unsigned int		delay_ms;
>>> +/*
>>> + * A default time for checking the need for non urgent BKOPS once mmcqd
>>> + * is idle.
>>> + */
>>> +#define MMC_IDLE_BKOPS_TIME_MS 2000
>>> +	struct work_struct	poll_for_completion;
>>> +/* Polling timeout and interval for waiting on non-blocking BKOPs
>>> completion */
>>> +#define BKOPS_COMPLETION_POLLING_TIMEOUT_MS 10000 /* in ms */
>>> +#define BKOPS_COMPLETION_POLLING_INTERVAL_MS 1000 /* in ms */
>>> +	bool			cancel_delayed_work;
>>> +	bool			started_delayed_bkops;
>>> +	unsigned int		sectors_changed;
>>> +/*
>>> + * Since canceling the delayed work might have significant effect on
>>> the
>>> + * performance of small requests we won't queue the delayed work every
>>> time
>>> + * mmcqd thread is idle.
>>> + * The delayed work for idle BKOPS will be scheduled only after a
>>> significant
>>> + * amount of write or discard data.
>>> + * 100MB is chosen based on benchmark tests.
>>> + */
>>> +#define BKOPS_MIN_SECTORS_TO_QUEUE_DELAYED_WORK 204800 /* 100MB */
>>> +};
>>> +
>>>  /*
>>>   * MMC device
>>>   */
>>> @@ -281,6 +323,8 @@ struct mmc_card {
>>>  	struct dentry		*debugfs_root;
>>>  	struct mmc_part	part[MMC_NUM_PHY_PARTITION]; /* physical partitions */
>>>  	unsigned int    nr_parts;
>>> +
>>> +	struct mmc_bkops_info	bkops_info;
>>>  };
>>>
>>>  /*
>>> diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
>>> index 9b9cdaf..665d345 100644
>>> --- a/include/linux/mmc/core.h
>>> +++ b/include/linux/mmc/core.h
>>> @@ -145,6 +145,9 @@ extern int mmc_app_cmd(struct mmc_host *, struct
>>> mmc_card *);
>>>  extern int mmc_wait_for_app_cmd(struct mmc_host *, struct mmc_card *,
>>>  	struct mmc_command *, int);
>>>  extern void mmc_start_bkops(struct mmc_card *card, bool
>>> from_exception);
>>> +extern void mmc_start_delayed_bkops(struct mmc_card *card);
>>> +extern void mmc_start_idle_time_bkops(struct work_struct *work);
>>> +extern void mmc_bkops_completion_polling(struct work_struct *work);
>>>  extern int __mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int,
>>> bool);
>>>  extern int mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int);
>>>
>>>
>>
>>
> 
>