From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/block/blk-mq.h | 232 +++++++++++++++++++++++++++++++++++++++++++--------------
1 files changed, 173 insertions(+), 59 deletions(-)
diff --git a/kernel/block/blk-mq.h b/kernel/block/blk-mq.h
index 5a96c97..d533ab5 100644
--- a/kernel/block/blk-mq.h
+++ b/kernel/block/blk-mq.h
@@ -7,17 +7,23 @@
struct blk_mq_tag_set;
+struct blk_mq_ctxs {
+ struct kobject kobj;
+ struct blk_mq_ctx __percpu *queue_ctx;
+};
+
/**
* struct blk_mq_ctx - State for a software queue facing the submitting CPUs
*/
struct blk_mq_ctx {
struct {
spinlock_t lock;
- struct list_head rq_list;
- } ____cacheline_aligned_in_smp;
+ struct list_head rq_lists[HCTX_MAX_TYPES];
+ } ____cacheline_aligned_in_smp;
unsigned int cpu;
- unsigned int index_hw;
+ unsigned short index_hw[HCTX_MAX_TYPES];
+ struct blk_mq_hw_ctx *hctxs[HCTX_MAX_TYPES];
/* incremented at dispatch time */
unsigned long rq_dispatched[2];
@@ -27,29 +33,35 @@
unsigned long ____cacheline_aligned_in_smp rq_completed[2];
struct request_queue *queue;
+ struct blk_mq_ctxs *ctxs;
struct kobject kobj;
+
+ ANDROID_OEM_DATA_ARRAY(1, 2);
} ____cacheline_aligned_in_smp;
-void blk_mq_freeze_queue(struct request_queue *q);
void blk_mq_exit_queue(struct request_queue *q);
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
void blk_mq_wake_waiters(struct request_queue *q);
-bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool);
+bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *,
+ unsigned int);
+void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
+ bool kick_requeue_list);
void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
-bool blk_mq_get_driver_tag(struct request *rq);
struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
struct blk_mq_ctx *start);
+void blk_mq_put_rq_ref(struct request *rq);
/*
* Internal helpers for allocating/freeing the request map
*/
void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
unsigned int hctx_idx);
-void blk_mq_free_rq_map(struct blk_mq_tags *tags);
+void blk_mq_free_rq_map(struct blk_mq_tags *tags, unsigned int flags);
struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
unsigned int hctx_idx,
unsigned int nr_tags,
- unsigned int reserved_tags);
+ unsigned int reserved_tags,
+ unsigned int flags);
int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
unsigned int hctx_idx, unsigned int depth);
@@ -58,24 +70,55 @@
*/
void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
bool at_head);
-void blk_mq_request_bypass_insert(struct request *rq, bool run_queue);
+void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
+ bool run_queue);
void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
struct list_head *list);
/* Used by blk_insert_cloned_request() to issue request directly */
-blk_status_t blk_mq_request_issue_directly(struct request *rq);
+blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last);
void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
struct list_head *list);
/*
* CPU -> queue mappings
*/
-extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int);
+extern int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int);
-static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
- int cpu)
+/*
+ * blk_mq_map_queue_type() - map (hctx_type,cpu) to hardware queue
+ * @q: request queue
+ * @type: the hctx type index
+ * @cpu: CPU
+ */
+static inline struct blk_mq_hw_ctx *blk_mq_map_queue_type(struct request_queue *q,
+ enum hctx_type type,
+ unsigned int cpu)
{
- return q->queue_hw_ctx[q->mq_map[cpu]];
+ return q->queue_hw_ctx[q->tag_set->map[type].mq_map[cpu]];
+}
+
+/*
+ * blk_mq_map_queue() - map (cmd_flags,type) to hardware queue
+ * @q: request queue
+ * @flags: request command flags
+ * @cpu: cpu ctx
+ */
+static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
+ unsigned int flags,
+ struct blk_mq_ctx *ctx)
+{
+ enum hctx_type type = HCTX_TYPE_DEFAULT;
+
+ /*
+ * The caller ensure that if REQ_HIPRI, poll must be enabled.
+ */
+ if (flags & REQ_HIPRI)
+ type = HCTX_TYPE_POLL;
+ else if ((flags & REQ_OP_MASK) == REQ_OP_READ)
+ type = HCTX_TYPE_READ;
+
+ return ctx->hctxs[type];
}
/*
@@ -89,15 +132,6 @@
extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
void blk_mq_release(struct request_queue *q);
-
-/**
- * blk_mq_rq_state() - read the current MQ_RQ_* state of a request
- * @rq: target request.
- */
-static inline enum mq_rq_state blk_mq_rq_state(struct request *rq)
-{
- return READ_ONCE(rq->state);
-}
static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
unsigned int cpu)
@@ -113,12 +147,7 @@
*/
static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q)
{
- return __blk_mq_get_ctx(q, get_cpu_light());
-}
-
-static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx)
-{
- put_cpu_light();
+ return __blk_mq_get_ctx(q, raw_smp_processor_id());
}
struct blk_mq_alloc_data {
@@ -126,15 +155,21 @@
struct request_queue *q;
blk_mq_req_flags_t flags;
unsigned int shallow_depth;
+ unsigned int cmd_flags;
/* input & output parameter */
struct blk_mq_ctx *ctx;
struct blk_mq_hw_ctx *hctx;
};
+static inline bool blk_mq_is_sbitmap_shared(unsigned int flags)
+{
+ return flags & BLK_MQ_F_TAG_HCTX_SHARED;
+}
+
static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
{
- if (data->flags & BLK_MQ_REQ_INTERNAL)
+ if (data->q->elevator)
return data->hctx->sched_tags;
return data->hctx->tags;
@@ -150,66 +185,145 @@
return hctx->nr_ctx && hctx->tags;
}
-void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
- unsigned int inflight[2]);
+unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part);
void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
unsigned int inflight[2]);
-static inline void blk_mq_put_dispatch_budget(struct blk_mq_hw_ctx *hctx)
+static inline void blk_mq_put_dispatch_budget(struct request_queue *q)
{
- struct request_queue *q = hctx->queue;
-
if (q->mq_ops->put_budget)
- q->mq_ops->put_budget(hctx);
+ q->mq_ops->put_budget(q);
}
-static inline bool blk_mq_get_dispatch_budget(struct blk_mq_hw_ctx *hctx)
+static inline bool blk_mq_get_dispatch_budget(struct request_queue *q)
{
- struct request_queue *q = hctx->queue;
-
if (q->mq_ops->get_budget)
- return q->mq_ops->get_budget(hctx);
+ return q->mq_ops->get_budget(q);
return true;
}
+static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+ if (blk_mq_is_sbitmap_shared(hctx->flags))
+ atomic_inc(&hctx->queue->nr_active_requests_shared_sbitmap);
+ else
+ atomic_inc(&hctx->nr_active);
+}
+
+static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+ if (blk_mq_is_sbitmap_shared(hctx->flags))
+ atomic_dec(&hctx->queue->nr_active_requests_shared_sbitmap);
+ else
+ atomic_dec(&hctx->nr_active);
+}
+
+static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+ if (blk_mq_is_sbitmap_shared(hctx->flags))
+ return atomic_read(&hctx->queue->nr_active_requests_shared_sbitmap);
+ return atomic_read(&hctx->nr_active);
+}
static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
- blk_mq_put_tag(hctx, hctx->tags, rq->mq_ctx, rq->tag);
- rq->tag = -1;
+ blk_mq_put_tag(hctx->tags, rq->mq_ctx, rq->tag);
+ rq->tag = BLK_MQ_NO_TAG;
if (rq->rq_flags & RQF_MQ_INFLIGHT) {
rq->rq_flags &= ~RQF_MQ_INFLIGHT;
- atomic_dec(&hctx->nr_active);
+ __blk_mq_dec_active_requests(hctx);
}
-}
-
-static inline void blk_mq_put_driver_tag_hctx(struct blk_mq_hw_ctx *hctx,
- struct request *rq)
-{
- if (rq->tag == -1 || rq->internal_tag == -1)
- return;
-
- __blk_mq_put_driver_tag(hctx, rq);
}
static inline void blk_mq_put_driver_tag(struct request *rq)
{
- struct blk_mq_hw_ctx *hctx;
-
- if (rq->tag == -1 || rq->internal_tag == -1)
+ if (rq->tag == BLK_MQ_NO_TAG || rq->internal_tag == BLK_MQ_NO_TAG)
return;
- hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu);
- __blk_mq_put_driver_tag(hctx, rq);
+ __blk_mq_put_driver_tag(rq->mq_hctx, rq);
}
-static inline void blk_mq_clear_mq_map(struct blk_mq_tag_set *set)
+static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap)
{
int cpu;
for_each_possible_cpu(cpu)
- set->mq_map[cpu] = 0;
+ qmap->mq_map[cpu] = 0;
}
+/*
+ * blk_mq_plug() - Get caller context plug
+ * @q: request queue
+ * @bio : the bio being submitted by the caller context
+ *
+ * Plugging, by design, may delay the insertion of BIOs into the elevator in
+ * order to increase BIO merging opportunities. This however can cause BIO
+ * insertion order to change from the order in which submit_bio() is being
+ * executed in the case of multiple contexts concurrently issuing BIOs to a
+ * device, even if these context are synchronized to tightly control BIO issuing
+ * order. While this is not a problem with regular block devices, this ordering
+ * change can cause write BIO failures with zoned block devices as these
+ * require sequential write patterns to zones. Prevent this from happening by
+ * ignoring the plug state of a BIO issuing context if the target request queue
+ * is for a zoned block device and the BIO to plug is a write operation.
+ *
+ * Return current->plug if the bio can be plugged and NULL otherwise
+ */
+static inline struct blk_plug *blk_mq_plug(struct request_queue *q,
+ struct bio *bio)
+{
+ /*
+ * For regular block devices or read operations, use the context plug
+ * which may be NULL if blk_start_plug() was not executed.
+ */
+ if (!blk_queue_is_zoned(q) || !op_is_write(bio_op(bio)))
+ return current->plug;
+
+ /* Zoned block device write operation case: do not plug the BIO */
+ return NULL;
+}
+
+/*
+ * For shared tag users, we track the number of currently active users
+ * and attempt to provide a fair share of the tag depth for each of them.
+ */
+static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
+ struct sbitmap_queue *bt)
+{
+ unsigned int depth, users;
+
+ if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
+ return true;
+
+ /*
+ * Don't try dividing an ant
+ */
+ if (bt->sb.depth == 1)
+ return true;
+
+ if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+ struct request_queue *q = hctx->queue;
+ struct blk_mq_tag_set *set = q->tag_set;
+
+ if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags))
+ return true;
+ users = atomic_read(&set->active_queues_shared_sbitmap);
+ } else {
+ if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
+ return true;
+ users = atomic_read(&hctx->tags->active_queues);
+ }
+
+ if (!users)
+ return true;
+
+ /*
+ * Allow at least some tags
+ */
+ depth = max((bt->sb.depth + users - 1) / users, 4U);
+ return __blk_mq_active_requests(hctx) < depth;
+}
+
+
#endif
--
Gitblit v1.6.2