[PATCH 2/2] blk-mq: don't handle TAG_SHARED in restart

[Ming Lei]

Now restart is used in the following cases, and TAG_SHARED is for
SCSI only.

1) .get_budget() returns BLK_STS_RESOURCE
- if resource in target/host level isn't satistifed, this SCSI device
will be added in shost->starved_list, and the whole queue will be rerun
(via SCSI's built-in RESTART) in scsi_end_request() after any request
initiated from this host/targe is completed. Forget to mention, host level
resource is always respected by blk-mq before running .queue_rq().

- the same is true if resource in the queue level isn't satisfied.

- if there isn't outstanding request on this queue, then SCSI's RESTART
can't work(blk-mq's can't work too), and the queue will be run after
SCSI_QUEUE_DELAY, and finally all starved sdevs will be handled by SCSI's
RESTART when this request is finished

2) scsi_dispatch_cmd() returns BLK_STS_RESOURCE
- if there isn't onprogressing request on this queue, the queue
will be run after SCSI_QUEUE_DELAY

- otherwise, SCSI's RESTART covers the rerun.

3) blk_mq_get_driver_tag() failed
- BLK_MQ_S_TAG_WAITING covers the cross-queue RESTART for driver
allocation.

In one word, SCSI's built-in RESTART is enough to cover itself.
So we don't need to pay special attention to TAG_SHARED wrt. restart.

Signed-off-by: Ming Lei 
---
 block/blk-mq-sched.c | 78 +++-
 1 file changed, 4 insertions(+), 74 deletions(-)

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index df8581bb0a37..daab27feb653 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -68,25 +68,17 @@ static void blk_mq_sched_mark_restart_hctx(struct 
blk_mq_hw_ctx *hctx)
set_bit(BLK_MQ_S_SCHED_RESTART, >state);
 }
 
-static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
+void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
 {
if (!test_bit(BLK_MQ_S_SCHED_RESTART, >state))
-   return false;
-
-   if (hctx->flags & BLK_MQ_F_TAG_SHARED) {
-   struct request_queue *q = hctx->queue;
+   return;
 
-   if (test_and_clear_bit(BLK_MQ_S_SCHED_RESTART, >state))
-   atomic_dec(>shared_hctx_restart);
-   } else
-   clear_bit(BLK_MQ_S_SCHED_RESTART, >state);
+   clear_bit(BLK_MQ_S_SCHED_RESTART, >state);
 
if (blk_mq_hctx_has_pending(hctx)) {
blk_mq_run_hw_queue(hctx, true);
-   return true;
+   return;
}
-
-   return false;
 }
 
 /* return true if hctx need to run again */
@@ -385,68 +377,6 @@ static bool blk_mq_sched_bypass_insert(struct 
blk_mq_hw_ctx *hctx,
return true;
 }
 
-/**
- * list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list
- * @pos:loop cursor.
- * @skip:   the list element that will not be examined. Iteration starts at
- *  @skip->next.
- * @head:   head of the list to examine. This list must have at least one
- *  element, namely @skip.
- * @member: name of the list_head structure within typeof(*pos).
- */
-#define list_for_each_entry_rcu_rr(pos, skip, head, member)\
-   for ((pos) = (skip);\
-(pos = (pos)->member.next != (head) ? list_entry_rcu(  \
-   (pos)->member.next, typeof(*pos), member) : \
- list_entry_rcu((pos)->member.next->next, typeof(*pos), member)), \
-(pos) != (skip); )
-
-/*
- * Called after a driver tag has been freed to check whether a hctx needs to
- * be restarted. Restarts @hctx if its tag set is not shared. Restarts hardware
- * queues in a round-robin fashion if the tag set of @hctx is shared with other
- * hardware queues.
- */
-void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx)
-{
-   struct blk_mq_tags *const tags = hctx->tags;
-   struct blk_mq_tag_set *const set = hctx->queue->tag_set;
-   struct request_queue *const queue = hctx->queue, *q;
-   struct blk_mq_hw_ctx *hctx2;
-   unsigned int i, j;
-
-   if (set->flags & BLK_MQ_F_TAG_SHARED) {
-   /*
-* If this is 0, then we know that no hardware queues
-* have RESTART marked. We're done.
-*/
-   if (!atomic_read(>shared_hctx_restart))
-   return;
-
-   rcu_read_lock();
-   list_for_each_entry_rcu_rr(q, queue, >tag_list,
-  tag_set_list) {
-   queue_for_each_hw_ctx(q, hctx2, i)
-   if (hctx2->tags == tags &&
-   blk_mq_sched_restart_hctx(hctx2))
-   goto done;
-   }
-   j = hctx->queue_num + 1;
-   for (i = 0; i < queue->nr_hw_queues; i++, j++) {
-   if (j == queue->nr_hw_queues)
-   j = 0;
-   hctx2 = 

[PATCH 2/2] blk-mq: don't handle TAG_SHARED in restart

[Ming Lei]

Now restart is used in the following cases, and TAG_SHARED is for
SCSI only.

1) .get_budget() returns BLK_STS_RESOURCE
- if resource in target/host level isn't satistifed, this SCSI device
will be added in shost->starved_list, and the whole queue will be rerun
(via SCSI's built-in RESTART) in scsi_end_request() after any request
initiated from this host/targe is completed. Forget to mention, host level
resource is always respected by blk-mq before running .queue_rq().

- the same is true if resource in the queue level isn't satisfied.

- if there isn't outstanding request on this queue, then SCSI's RESTART
can't work(blk-mq's can't work too), and the queue will be run after
SCSI_QUEUE_DELAY, and finally all starved sdevs will be handled by SCSI's
RESTART when this request is finished

2) scsi_dispatch_cmd() returns BLK_STS_RESOURCE
- if there isn't onprogressing request on this queue, the queue
will be run after SCSI_QUEUE_DELAY

- otherwise, SCSI's RESTART covers the rerun.

3) blk_mq_get_driver_tag() failed
- BLK_MQ_S_TAG_WAITING covers the cross-queue RESTART for driver
allocation.

In one word, SCSI's built-in RESTART is enough to cover itself.
So we don't need to pay special attention to TAG_SHARED wrt. restart.

Signed-off-by: Ming Lei 
---
 block/blk-mq-sched.c | 78 +++-
 1 file changed, 4 insertions(+), 74 deletions(-)

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index df8581bb0a37..daab27feb653 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -68,25 +68,17 @@ static void blk_mq_sched_mark_restart_hctx(struct 
blk_mq_hw_ctx *hctx)
set_bit(BLK_MQ_S_SCHED_RESTART, >state);
 }
 
-static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
+void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
 {
if (!test_bit(BLK_MQ_S_SCHED_RESTART, >state))
-   return false;
-
-   if (hctx->flags & BLK_MQ_F_TAG_SHARED) {
-   struct request_queue *q = hctx->queue;
+   return;
 
-   if (test_and_clear_bit(BLK_MQ_S_SCHED_RESTART, >state))
-   atomic_dec(>shared_hctx_restart);
-   } else
-   clear_bit(BLK_MQ_S_SCHED_RESTART, >state);
+   clear_bit(BLK_MQ_S_SCHED_RESTART, >state);
 
if (blk_mq_hctx_has_pending(hctx)) {
blk_mq_run_hw_queue(hctx, true);
-   return true;
+   return;
}
-
-   return false;
 }
 
 /* return true if hctx need to run again */
@@ -385,68 +377,6 @@ static bool blk_mq_sched_bypass_insert(struct 
blk_mq_hw_ctx *hctx,
return true;
 }
 
-/**
- * list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list
- * @pos:loop cursor.
- * @skip:   the list element that will not be examined. Iteration starts at
- *  @skip->next.
- * @head:   head of the list to examine. This list must have at least one
- *  element, namely @skip.
- * @member: name of the list_head structure within typeof(*pos).
- */
-#define list_for_each_entry_rcu_rr(pos, skip, head, member)\
-   for ((pos) = (skip);\
-(pos = (pos)->member.next != (head) ? list_entry_rcu(  \
-   (pos)->member.next, typeof(*pos), member) : \
- list_entry_rcu((pos)->member.next->next, typeof(*pos), member)), \
-(pos) != (skip); )
-
-/*
- * Called after a driver tag has been freed to check whether a hctx needs to
- * be restarted. Restarts @hctx if its tag set is not shared. Restarts hardware
- * queues in a round-robin fashion if the tag set of @hctx is shared with other
- * hardware queues.
- */
-void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx)
-{
-   struct blk_mq_tags *const tags = hctx->tags;
-   struct blk_mq_tag_set *const set = hctx->queue->tag_set;
-   struct request_queue *const queue = hctx->queue, *q;
-   struct blk_mq_hw_ctx *hctx2;
-   unsigned int i, j;
-
-   if (set->flags & BLK_MQ_F_TAG_SHARED) {
-   /*
-* If this is 0, then we know that no hardware queues
-* have RESTART marked. We're done.
-*/
-   if (!atomic_read(>shared_hctx_restart))
-   return;
-
-   rcu_read_lock();
-   list_for_each_entry_rcu_rr(q, queue, >tag_list,
-  tag_set_list) {
-   queue_for_each_hw_ctx(q, hctx2, i)
-   if (hctx2->tags == tags &&
-   blk_mq_sched_restart_hctx(hctx2))
-   goto done;
-   }
-   j = hctx->queue_num + 1;
-   for (i = 0; i < queue->nr_hw_queues; i++, j++) {
-   if (j == queue->nr_hw_queues)
-   j = 0;
-   hctx2 =