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/bfq-iosched.h | 182 +++++++++++++++++++++++++++++++--------------
1 files changed, 126 insertions(+), 56 deletions(-)
diff --git a/kernel/block/bfq-iosched.h b/kernel/block/bfq-iosched.h
index ca98c98..2a4a6f4 100644
--- a/kernel/block/bfq-iosched.h
+++ b/kernel/block/bfq-iosched.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Header file for the BFQ I/O scheduler: data structures and
* prototypes of interface functions among BFQ components.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of the
- * License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
*/
#ifndef _BFQ_H
#define _BFQ_H
@@ -18,6 +9,8 @@
#include <linux/blktrace_api.h>
#include <linux/hrtimer.h>
#include <linux/blk-cgroup.h>
+
+#include "blk-cgroup-rwstat.h"
#define BFQ_IOPRIO_CLASSES 3
#define BFQ_CL_IDLE_TIMEOUT (HZ/5)
@@ -31,6 +24,8 @@
#define BFQ_WEIGHT_LEGACY_DFL 100
#define BFQ_DEFAULT_GRP_IOPRIO 0
#define BFQ_DEFAULT_GRP_CLASS IOPRIO_CLASS_BE
+
+#define MAX_PID_STR_LENGTH 12
/*
* Soft real-time applications are extremely more latency sensitive
@@ -89,7 +84,7 @@
* expiration. This peculiar definition allows for the following
* optimization, not yet exploited: while a given entity is still in
* service, we already know which is the best candidate for next
- * service among the other active entitities in the same parent
+ * service among the other active entities in the same parent
* entity. We can then quickly compare the timestamps of the
* in-service entity with those of such best candidate.
*
@@ -140,7 +135,7 @@
*
* Unless cgroups are used, the weight value is calculated from the
* ioprio to export the same interface as CFQ. When dealing with
- * ``well-behaved'' queues (i.e., queues that do not spend too much
+ * "well-behaved" queues (i.e., queues that do not spend too much
* time to consume their budget and have true sequential behavior, and
* when there are no external factors breaking anticipation) the
* relative weights at each level of the cgroups hierarchy should be
@@ -155,7 +150,7 @@
* Flag, true if the entity is on a tree (either the active or
* the idle one of its service_tree) or is in service.
*/
- bool on_st;
+ bool on_st_or_in_serv;
/* B-WF2Q+ start and finish timestamps [sectors/weight] */
u64 start, finish;
@@ -175,6 +170,9 @@
/* budget, used also to calculate F_i: F_i = S_i + @budget / @weight */
int budget;
+ /* device weight, if non-zero, it overrides the default weight of
+ * bfq_group_data */
+ int dev_weight;
/* weight of the queue */
int weight;
/* next weight if a change is in progress */
@@ -239,6 +237,13 @@
unsigned short ioprio, ioprio_class;
/* next ioprio and ioprio class if a change is in progress */
unsigned short new_ioprio, new_ioprio_class;
+
+ /* last total-service-time sample, see bfq_update_inject_limit() */
+ u64 last_serv_time_ns;
+ /* limit for request injection */
+ unsigned int inject_limit;
+ /* last time the inject limit has been decreased, in jiffies */
+ unsigned long decrease_time_jif;
/*
* Shared bfq_queue if queue is cooperating with one or more
@@ -357,29 +362,24 @@
/* max service rate measured so far */
u32 max_service_rate;
+
/*
- * Ratio between the service received by bfqq while it is in
- * service, and the cumulative service (of requests of other
- * queues) that may be injected while bfqq is empty but still
- * in service. To increase precision, the coefficient is
- * measured in tenths of unit. Here are some example of (1)
- * ratios, (2) resulting percentages of service injected
- * w.r.t. to the total service dispatched while bfqq is in
- * service, and (3) corresponding values of the coefficient:
- * 1 (50%) -> 10
- * 2 (33%) -> 20
- * 10 (9%) -> 100
- * 9.9 (9%) -> 99
- * 1.5 (40%) -> 15
- * 0.5 (66%) -> 5
- * 0.1 (90%) -> 1
- *
- * So, if the coefficient is lower than 10, then
- * injected service is more than bfqq service.
+ * Pointer to the waker queue for this queue, i.e., to the
+ * queue Q such that this queue happens to get new I/O right
+ * after some I/O request of Q is completed. For details, see
+ * the comments on the choice of the queue for injection in
+ * bfq_select_queue().
*/
- unsigned int inject_coeff;
- /* amount of service injected in current service slot */
- unsigned int injected_service;
+ struct bfq_queue *waker_bfqq;
+ /* node for woken_list, see below */
+ struct hlist_node woken_list_node;
+ /*
+ * Head of the list of the woken queues for this queue, i.e.,
+ * of the list of the queues for which this queue is a waker
+ * queue. This list is used to reset the waker_bfqq pointer in
+ * the woken queues when this queue exits.
+ */
+ struct hlist_head woken_list;
};
/**
@@ -419,6 +419,15 @@
bool was_in_burst_list;
/*
+ * Save the weight when a merge occurs, to be able
+ * to restore it in case of split. If the weight is not
+ * correctly resumed when the queue is recycled,
+ * then the weight of the recycled queue could differ
+ * from the weight of the original queue.
+ */
+ unsigned int saved_weight;
+
+ /*
* Similar to previous fields: save wr information.
*/
unsigned long saved_wr_coeff;
@@ -450,7 +459,7 @@
* weight-raised @bfq_queue (see the comments to the functions
* bfq_weights_tree_[add|remove] for further details).
*/
- struct rb_root queue_weights_tree;
+ struct rb_root_cached queue_weights_tree;
/*
* Number of groups with at least one descendant process that
@@ -501,16 +510,20 @@
unsigned int num_groups_with_pending_reqs;
/*
- * Number of bfq_queues containing requests (including the
- * queue in service, even if it is idling).
+ * Per-class (RT, BE, IDLE) number of bfq_queues containing
+ * requests (including the queue in service, even if it is
+ * idling).
*/
- int busy_queues;
+ unsigned int busy_queues[3];
/* number of weight-raised busy @bfq_queues */
int wr_busy_queues;
/* number of queued requests */
int queued;
/* number of requests dispatched and waiting for completion */
int rq_in_driver;
+
+ /* true if the device is non rotational and performs queueing */
+ bool nonrot_with_queueing;
/*
* Maximum number of requests in driver in the last
@@ -543,6 +556,29 @@
/* time of last request completion (ns) */
u64 last_completion;
+ /* bfqq owning the last completed rq */
+ struct bfq_queue *last_completed_rq_bfqq;
+
+ /* time of last transition from empty to non-empty (ns) */
+ u64 last_empty_occupied_ns;
+
+ /*
+ * Flag set to activate the sampling of the total service time
+ * of a just-arrived first I/O request (see
+ * bfq_update_inject_limit()). This will cause the setting of
+ * waited_rq when the request is finally dispatched.
+ */
+ bool wait_dispatch;
+ /*
+ * If set, then bfq_update_inject_limit() is invoked when
+ * waited_rq is eventually completed.
+ */
+ struct request *waited_rq;
+ /*
+ * True if some request has been injected during the last service hole.
+ */
+ bool rqs_injected;
+
/* time of first rq dispatch in current observation interval (ns) */
u64 first_dispatch;
/* time of last rq dispatch in current observation interval (ns) */
@@ -552,6 +588,7 @@
ktime_t last_budget_start;
/* beginning of the last idle slice */
ktime_t last_idling_start;
+ unsigned long last_idling_start_jiffies;
/* number of samples in current observation interval */
int peak_rate_samples;
@@ -732,7 +769,8 @@
* update
*/
BFQQF_coop, /* bfqq is shared */
- BFQQF_split_coop /* shared bfqq will be split */
+ BFQQF_split_coop, /* shared bfqq will be split */
+ BFQQF_has_waker /* bfqq has a waker queue */
};
#define BFQ_BFQQ_FNS(name) \
@@ -752,6 +790,7 @@
BFQ_BFQQ_FNS(coop);
BFQ_BFQQ_FNS(split_coop);
BFQ_BFQQ_FNS(softrt_update);
+BFQ_BFQQ_FNS(has_waker);
#undef BFQ_BFQQ_FNS
/* Expiration reasons. */
@@ -766,8 +805,16 @@
BFQQE_PREEMPTED /* preemption in progress */
};
+struct bfq_stat {
+ struct percpu_counter cpu_cnt;
+ atomic64_t aux_cnt;
+};
+
struct bfqg_stats {
-#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
+ /* basic stats */
+ struct blkg_rwstat bytes;
+ struct blkg_rwstat ios;
+#ifdef CONFIG_BFQ_CGROUP_DEBUG
/* number of ios merged */
struct blkg_rwstat merged;
/* total time spent on device in ns, may not be accurate w/ queueing */
@@ -777,25 +824,25 @@
/* number of IOs queued up */
struct blkg_rwstat queued;
/* total disk time and nr sectors dispatched by this group */
- struct blkg_stat time;
+ struct bfq_stat time;
/* sum of number of ios queued across all samples */
- struct blkg_stat avg_queue_size_sum;
+ struct bfq_stat avg_queue_size_sum;
/* count of samples taken for average */
- struct blkg_stat avg_queue_size_samples;
+ struct bfq_stat avg_queue_size_samples;
/* how many times this group has been removed from service tree */
- struct blkg_stat dequeue;
+ struct bfq_stat dequeue;
/* total time spent waiting for it to be assigned a timeslice. */
- struct blkg_stat group_wait_time;
+ struct bfq_stat group_wait_time;
/* time spent idling for this blkcg_gq */
- struct blkg_stat idle_time;
+ struct bfq_stat idle_time;
/* total time with empty current active q with other requests queued */
- struct blkg_stat empty_time;
+ struct bfq_stat empty_time;
/* fields after this shouldn't be cleared on stat reset */
u64 start_group_wait_time;
u64 start_idle_time;
u64 start_empty_time;
uint16_t flags;
-#endif /* CONFIG_BFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */
+#endif /* CONFIG_BFQ_CGROUP_DEBUG */
};
#ifdef CONFIG_BFQ_GROUP_IOSCHED
@@ -854,6 +901,8 @@
/* reference counter (see comments in bfq_bic_update_cgroup) */
int ref;
+ /* Is bfq_group still online? */
+ bool online;
struct bfq_entity entity;
struct bfq_sched_data sched_data;
@@ -874,6 +923,7 @@
#else
struct bfq_group {
+ struct bfq_entity entity;
struct bfq_sched_data sched_data;
struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
@@ -897,16 +947,18 @@
struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic);
void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq);
void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq,
- struct rb_root *root);
+ struct rb_root_cached *root);
void __bfq_weights_tree_remove(struct bfq_data *bfqd,
struct bfq_queue *bfqq,
- struct rb_root *root);
+ struct rb_root_cached *root);
void bfq_weights_tree_remove(struct bfq_data *bfqd,
struct bfq_queue *bfqq);
void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bool compensate, enum bfqq_expiration reason);
void bfq_put_queue(struct bfq_queue *bfqq);
+void bfq_put_cooperator(struct bfq_queue *bfqq);
void bfq_end_wr_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
+void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq);
void bfq_schedule_dispatch(struct bfq_data *bfqd);
void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
@@ -914,6 +966,7 @@
/* ---------------- cgroups-support interface ---------------- */
+void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq);
void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
unsigned int op);
void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op);
@@ -931,8 +984,7 @@
void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg);
void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio);
void bfq_end_wr_async(struct bfq_data *bfqd);
-struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
- struct blkcg *blkcg);
+struct bfq_group *bfq_bio_bfqg(struct bfq_data *bfqd, struct bio *bio);
struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node);
@@ -977,6 +1029,7 @@
struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq);
struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);
+unsigned int bfq_tot_busy_queues(struct bfq_data *bfqd);
struct bfq_service_tree *bfq_entity_service_tree(struct bfq_entity *entity);
struct bfq_entity *bfq_entity_of(struct rb_node *node);
unsigned short bfq_ioprio_to_weight(int ioprio);
@@ -1006,13 +1059,25 @@
/* --------------- end of interface of B-WF2Q+ ---------------- */
/* Logging facilities. */
+static inline void bfq_pid_to_str(int pid, char *str, int len)
+{
+ if (pid != -1)
+ snprintf(str, len, "%d", pid);
+ else
+ snprintf(str, len, "SHARED-");
+}
+
#ifdef CONFIG_BFQ_GROUP_IOSCHED
struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \
+ char pid_str[MAX_PID_STR_LENGTH]; \
+ if (likely(!blk_trace_note_message_enabled((bfqd)->queue))) \
+ break; \
+ bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH); \
blk_add_cgroup_trace_msg((bfqd)->queue, \
bfqg_to_blkg(bfqq_group(bfqq))->blkcg, \
- "bfq%d%c " fmt, (bfqq)->pid, \
+ "bfq%s%c " fmt, pid_str, \
bfq_bfqq_sync((bfqq)) ? 'S' : 'A', ##args); \
} while (0)
@@ -1023,10 +1088,15 @@
#else /* CONFIG_BFQ_GROUP_IOSCHED */
-#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) \
- blk_add_trace_msg((bfqd)->queue, "bfq%d%c " fmt, (bfqq)->pid, \
+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \
+ char pid_str[MAX_PID_STR_LENGTH]; \
+ if (likely(!blk_trace_note_message_enabled((bfqd)->queue))) \
+ break; \
+ bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH); \
+ blk_add_trace_msg((bfqd)->queue, "bfq%s%c " fmt, pid_str, \
bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \
- ##args)
+ ##args); \
+} while (0)
#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do {} while (0)
#endif /* CONFIG_BFQ_GROUP_IOSCHED */
--
Gitblit v1.6.2