linux-block.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ming Lei <ming.lei@redhat.com>
To: Bart Van Assche <bvanassche@acm.org>
Cc: Jens Axboe <axboe@kernel.dk>,
	linux-block@vger.kernel.org, John Garry <john.garry@huawei.com>,
	Hannes Reinecke <hare@suse.com>, Christoph Hellwig <hch@lst.de>,
	Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [PATCH V10 05/11] blk-mq: support rq filter callback when iterating rqs
Date: Sat, 9 May 2020 10:05:22 +0800	[thread overview]
Message-ID: <20200509020522.GA1392681@T590> (raw)
In-Reply-To: <51888b96-1e3b-9810-fb64-47a965b83711@acm.org>

On Fri, May 08, 2020 at 05:18:56PM -0700, Bart Van Assche wrote:
> On 2020-05-08 16:32, Bart Van Assche wrote:
> > On 2020-05-04 19:09, Ming Lei wrote:
> >> @@ -310,19 +313,30 @@ static void bt_tags_for_each(struct blk_mq_tags *tags, struct sbitmap_queue *bt,
> >>  /**
> >>   * blk_mq_all_tag_busy_iter - iterate over all started requests in a tag map
> >>   * @tags:	Tag map to iterate over.
> >> - * @fn:		Pointer to the function that will be called for each started
> >> - *		request. @fn will be called as follows: @fn(rq, @priv,
> >> - *		reserved) where rq is a pointer to a request. 'reserved'
> >> - *		indicates whether or not @rq is a reserved request. Return
> >> - *		true to continue iterating tags, false to stop.
> >> + * @fn:		Pointer to the function that will be called for each request
> >> + * 		when .busy_rq_fn(rq) returns true. @fn will be called as
> >> + * 		follows: @fn(rq, @priv, reserved) where rq is a pointer to a
> >> + * 		request. 'reserved' indicates whether or not @rq is a reserved
> >> + * 		request. Return true to continue iterating tags, false to stop.
> >> + * @busy_rq_fn: Pointer to the function that will be called for each request,
> >> + * 		@busy_rq_fn's type is same with @fn. Only when @busy_rq_fn(rq,
> >> + * 		@priv, reserved) returns true, @fn will be called on this rq.
> >>   * @priv:	Will be passed as second argument to @fn.
> >>   */
> >> -static void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags,
> >> -		busy_tag_iter_fn *fn, void *priv)
> >> +void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags,
> >> +		busy_tag_iter_fn *fn, busy_rq_iter_fn *busy_rq_fn,
> >> +		void *priv)
> >>  {
> > 
> > The name 'busy_rq_fn' is not ideal because it is named after one
> > specific use case, namely checking whether or not a request is busy (has
> > already been started). How about using the name 'pred_fn' ('pred' from
> > predicate because it controls whether the other function is called)?
> > Since only the context that passes 'fn' can know what data structure
> > 'priv' points to and since 'busy_rq_fn' is passed from another context,
> > can 'busy_rq_fn' even know what data 'priv' points at? Has it been
> > considered not to pass the 'priv' argument to 'busy_rq_fn'?
> 
> Thinking further about this, another possible approach is not to modify
> blk_mq_all_tag_busy_iter() at all and to introduce a new function that
> iterates over all requests instead of only over busy requests. I think
> that approach will result in easier to read code than patch 5/11 because
> each of these request iteration functions will only accept a single
> callback function pointer. Additionally, that approach will make the
> following function superfluous (from patch 7/11):
> 
> +static bool blk_mq_inflight_rq(struct request *rq, void *data,
> +			       bool reserved)
> +{
> +	return rq->tag >= 0;
> +}

Fine, then we can save one callback, how about the following way?

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 586c9d6e904a..5e9c743d887b 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -257,6 +257,7 @@ struct bt_tags_iter_data {
 	busy_tag_iter_fn *fn;
 	void *data;
 	bool reserved;
+	bool iterate_all;
 };
 
 static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
@@ -274,8 +275,10 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 	 * test and set the bit before assining ->rqs[].
 	 */
 	rq = tags->rqs[bitnr];
-	if (rq && blk_mq_request_started(rq))
-		return iter_data->fn(rq, iter_data->data, reserved);
+	if (rq) {
+		if (iter_data->iterate_all || blk_mq_request_started(rq))
+			return iter_data->fn(rq, iter_data->data, reserved);
+	}
 
 	return true;
 }
@@ -294,13 +297,15 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
  *		bitmap_tags member of struct blk_mq_tags.
  */
 static void bt_tags_for_each(struct blk_mq_tags *tags, struct sbitmap_queue *bt,
-			     busy_tag_iter_fn *fn, void *data, bool reserved)
+			     busy_tag_iter_fn *fn, void *data, bool reserved,
+			     bool iterate_all)
 {
 	struct bt_tags_iter_data iter_data = {
 		.tags = tags,
 		.fn = fn,
 		.data = data,
 		.reserved = reserved,
+		.iterate_all = iterate_all,
 	};
 
 	if (tags->rqs)
@@ -321,8 +326,30 @@ static void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags,
 		busy_tag_iter_fn *fn, void *priv)
 {
 	if (tags->nr_reserved_tags)
-		bt_tags_for_each(tags, &tags->breserved_tags, fn, priv, true);
-	bt_tags_for_each(tags, &tags->bitmap_tags, fn, priv, false);
+		bt_tags_for_each(tags, &tags->breserved_tags, fn, priv, true,
+				 false);
+	bt_tags_for_each(tags, &tags->bitmap_tags, fn, priv, false, false);
+}
+
+/**
+ * blk_mq_all_tag_iter - iterate over all requests in a tag map
+ * @tags:	Tag map to iterate over.
+ * @fn:		Pointer to the function that will be called for each
+ *		request. @fn will be called as follows: @fn(rq, @priv,
+ *		reserved) where rq is a pointer to a request. 'reserved'
+ *		indicates whether or not @rq is a reserved request. Return
+ *		true to continue iterating tags, false to stop.
+ * @priv:	Will be passed as second argument to @fn.
+ *
+ * It is the caller's responsility to check rq's state in @fn.
+ */
+void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
+		void *priv)
+{
+	if (tags->nr_reserved_tags)
+		bt_tags_for_each(tags, &tags->breserved_tags, fn, priv, true,
+				 true);
+	bt_tags_for_each(tags, &tags->bitmap_tags, fn, priv, false, true);
 }
 
 /**
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 2b8321efb682..d19546e8246b 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -34,6 +34,8 @@ extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 		void *priv);
+void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
+		void *priv);
 
 static inline struct sbq_wait_state *bt_wait_ptr(struct sbitmap_queue *bt,
 						 struct blk_mq_hw_ctx *hctx)


thanks,
Ming


  reply	other threads:[~2020-05-09  2:05 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-05  2:09 [PATCH V10 00/11] blk-mq: improvement CPU hotplug Ming Lei
2020-05-05  2:09 ` [PATCH V10 01/11] block: clone nr_integrity_segments and write_hint in blk_rq_prep_clone Ming Lei
2020-05-05  2:09 ` [PATCH V10 02/11] block: add helper for copying request Ming Lei
2020-05-05  2:09 ` [PATCH V10 03/11] blk-mq: mark blk_mq_get_driver_tag as static Ming Lei
2020-05-05  2:09 ` [PATCH V10 04/11] blk-mq: assign rq->tag in blk_mq_get_driver_tag Ming Lei
2020-05-05  2:09 ` [PATCH V10 05/11] blk-mq: support rq filter callback when iterating rqs Ming Lei
2020-05-08 23:32   ` Bart Van Assche
2020-05-09  0:18     ` Bart Van Assche
2020-05-09  2:05       ` Ming Lei [this message]
2020-05-09  3:08         ` Bart Van Assche
2020-05-09  3:52           ` Ming Lei
2020-05-05  2:09 ` [PATCH V10 06/11] blk-mq: prepare for draining IO when hctx's all CPUs are offline Ming Lei
2020-05-05  6:14   ` Hannes Reinecke
2020-05-08 23:26   ` Bart Van Assche
2020-05-09  2:09     ` Ming Lei
2020-05-09  3:11       ` Bart Van Assche
2020-05-09  3:56         ` Ming Lei
2020-05-05  2:09 ` [PATCH V10 07/11] blk-mq: stop to handle IO and drain IO before hctx becomes inactive Ming Lei
2020-05-08 23:39   ` Bart Van Assche
2020-05-09  2:20     ` Ming Lei
2020-05-09  3:24       ` Bart Van Assche
2020-05-09  4:10         ` Ming Lei
2020-05-09 14:18           ` Bart Van Assche
2020-05-11  1:45             ` Ming Lei
2020-05-11  3:20               ` Bart Van Assche
2020-05-11  3:48                 ` Ming Lei
2020-05-11 20:56                   ` Bart Van Assche
2020-05-12  1:25                     ` Ming Lei
2020-05-05  2:09 ` [PATCH V10 08/11] block: add blk_end_flush_machinery Ming Lei
2020-05-05  2:09 ` [PATCH V10 09/11] blk-mq: add blk_mq_hctx_handle_dead_cpu for handling cpu dead Ming Lei
2020-05-05  2:09 ` [PATCH V10 10/11] blk-mq: re-submit IO in case that hctx is inactive Ming Lei
2020-05-05  2:09 ` [PATCH V10 11/11] block: deactivate hctx when the hctx is actually inactive Ming Lei
2020-05-09 14:07   ` Bart Van Assche
2020-05-11  2:11     ` Ming Lei
2020-05-11  3:30       ` Bart Van Assche
2020-05-11  4:08         ` Ming Lei
2020-05-11 20:52           ` Bart Van Assche
2020-05-12  1:43             ` Ming Lei
2020-05-12  2:08             ` Ming Lei
2020-05-08 21:49 ` [PATCH V10 00/11] blk-mq: improvement CPU hotplug Ming Lei
2020-05-09  3:17   ` Jens Axboe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200509020522.GA1392681@T590 \
    --to=ming.lei@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=bvanassche@acm.org \
    --cc=hare@suse.com \
    --cc=hch@lst.de \
    --cc=john.garry@huawei.com \
    --cc=linux-block@vger.kernel.org \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).