From 01573e231f18eb2d99162747186f59511f56b64d Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 08 Dec 2023 10:40:48 +0000
Subject: [PATCH] 移去rt
---
kernel/include/linux/blk-cgroup.h | 600 ++++++++++++++++-------------------------------------------
1 files changed, 163 insertions(+), 437 deletions(-)
diff --git a/kernel/include/linux/blk-cgroup.h b/kernel/include/linux/blk-cgroup.h
index 6d766a1..7c86f5c 100644
--- a/kernel/include/linux/blk-cgroup.h
+++ b/kernel/include/linux/blk-cgroup.h
@@ -15,12 +15,18 @@
*/
#include <linux/cgroup.h>
+#include <linux/percpu.h>
#include <linux/percpu_counter.h>
+#include <linux/u64_stats_sync.h>
#include <linux/seq_file.h>
#include <linux/radix-tree.h>
#include <linux/blkdev.h>
#include <linux/atomic.h>
#include <linux/kthread.h>
+#include <linux/fs.h>
+#ifndef __GENKSYMS__
+#include <linux/blk-mq.h>
+#endif
/* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */
#define BLKG_STAT_CPU_BATCH (INT_MAX / 2)
@@ -30,15 +36,12 @@
#ifdef CONFIG_BLK_CGROUP
-enum blkg_rwstat_type {
- BLKG_RWSTAT_READ,
- BLKG_RWSTAT_WRITE,
- BLKG_RWSTAT_SYNC,
- BLKG_RWSTAT_ASYNC,
- BLKG_RWSTAT_DISCARD,
+enum blkg_iostat_type {
+ BLKG_IOSTAT_READ,
+ BLKG_IOSTAT_WRITE,
+ BLKG_IOSTAT_DISCARD,
- BLKG_RWSTAT_NR,
- BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,
+ BLKG_IOSTAT_NR,
};
struct blkcg_gq;
@@ -46,6 +49,7 @@
struct blkcg {
struct cgroup_subsys_state css;
spinlock_t lock;
+ refcount_t online_pin;
struct radix_tree_root blkg_tree;
struct blkcg_gq __rcu *blkg_hint;
@@ -56,23 +60,18 @@
struct list_head all_blkcgs_node;
#ifdef CONFIG_CGROUP_WRITEBACK
struct list_head cgwb_list;
- refcount_t cgwb_refcnt;
#endif
};
-/*
- * blkg_[rw]stat->aux_cnt is excluded for local stats but included for
- * recursive. Used to carry stats of dead children, and, for blkg_rwstat,
- * to carry result values from read and sum operations.
- */
-struct blkg_stat {
- struct percpu_counter cpu_cnt;
- atomic64_t aux_cnt;
+struct blkg_iostat {
+ u64 bytes[BLKG_IOSTAT_NR];
+ u64 ios[BLKG_IOSTAT_NR];
};
-struct blkg_rwstat {
- struct percpu_counter cpu_cnt[BLKG_RWSTAT_NR];
- atomic64_t aux_cnt[BLKG_RWSTAT_NR];
+struct blkg_iostat_set {
+ struct u64_stats_sync sync;
+ struct blkg_iostat cur;
+ struct blkg_iostat last;
};
/*
@@ -113,43 +112,39 @@
struct hlist_node blkcg_node;
struct blkcg *blkcg;
- /*
- * Each blkg gets congested separately and the congestion state is
- * propagated to the matching bdi_writeback_congested.
- */
- struct bdi_writeback_congested *wb_congested;
-
/* all non-root blkcg_gq's are guaranteed to have access to parent */
struct blkcg_gq *parent;
- /* request allocation list for this blkcg-q pair */
- struct request_list rl;
-
/* reference count */
- atomic_t refcnt;
+ struct percpu_ref refcnt;
/* is this blkg online? protected by both blkcg and q locks */
bool online;
- struct blkg_rwstat stat_bytes;
- struct blkg_rwstat stat_ios;
+ struct blkg_iostat_set __percpu *iostat_cpu;
+ struct blkg_iostat_set iostat;
struct blkg_policy_data *pd[BLKCG_MAX_POLS];
- struct rcu_head rcu_head;
+ spinlock_t async_bio_lock;
+ struct bio_list async_bios;
+ struct work_struct async_bio_work;
atomic_t use_delay;
atomic64_t delay_nsec;
atomic64_t delay_start;
u64 last_delay;
int last_use;
+
+ struct rcu_head rcu_head;
};
typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp);
typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd);
typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd);
typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd);
-typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp, int node);
+typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp,
+ struct request_queue *q, struct blkcg *blkcg);
typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd);
typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd);
typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd);
@@ -181,13 +176,11 @@
extern struct blkcg blkcg_root;
extern struct cgroup_subsys_state * const blkcg_root_css;
+extern bool blkcg_debug_stats;
struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
struct request_queue *q, bool update_hint);
-struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
- struct request_queue *q);
int blkcg_init_queue(struct request_queue *q);
-void blkcg_drain_queue(struct request_queue *q);
void blkcg_exit_queue(struct request_queue *q);
/* Blkio controller policy registration */
@@ -205,20 +198,6 @@
const struct blkcg_policy *pol, int data,
bool show_total);
u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v);
-u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
- const struct blkg_rwstat *rwstat);
-u64 blkg_prfill_stat(struct seq_file *sf, struct blkg_policy_data *pd, int off);
-u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
- int off);
-int blkg_print_stat_bytes(struct seq_file *sf, void *v);
-int blkg_print_stat_ios(struct seq_file *sf, void *v);
-int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v);
-int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v);
-
-u64 blkg_stat_recursive_sum(struct blkcg_gq *blkg,
- struct blkcg_policy *pol, int off);
-struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkcg_gq *blkg,
- struct blkcg_policy *pol, int off);
struct blkg_conf_ctx {
struct gendisk *disk;
@@ -226,26 +205,67 @@
char *body;
};
+struct gendisk *blkcg_conf_get_disk(char **inputp);
int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
char *input, struct blkg_conf_ctx *ctx);
void blkg_conf_finish(struct blkg_conf_ctx *ctx);
+/**
+ * blkcg_css - find the current css
+ *
+ * Find the css associated with either the kthread or the current task.
+ * This may return a dying css, so it is up to the caller to use tryget logic
+ * to confirm it is alive and well.
+ */
+static inline struct cgroup_subsys_state *blkcg_css(void)
+{
+ struct cgroup_subsys_state *css;
+
+ css = kthread_blkcg();
+ if (css)
+ return css;
+ return task_css(current, io_cgrp_id);
+}
static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css)
{
return css ? container_of(css, struct blkcg, css) : NULL;
}
+/**
+ * __bio_blkcg - internal, inconsistent version to get blkcg
+ *
+ * DO NOT USE.
+ * This function is inconsistent and consequently is dangerous to use. The
+ * first part of the function returns a blkcg where a reference is owned by the
+ * bio. This means it does not need to be rcu protected as it cannot go away
+ * with the bio owning a reference to it. However, the latter potentially gets
+ * it from task_css(). This can race against task migration and the cgroup
+ * dying. It is also semantically different as it must be called rcu protected
+ * and is susceptible to failure when trying to get a reference to it.
+ * Therefore, it is not ok to assume that *_get() will always succeed on the
+ * blkcg returned here.
+ */
+static inline struct blkcg *__bio_blkcg(struct bio *bio)
+{
+ if (bio && bio->bi_blkg)
+ return bio->bi_blkg->blkcg;
+ return css_to_blkcg(blkcg_css());
+}
+
+/**
+ * bio_blkcg - grab the blkcg associated with a bio
+ * @bio: target bio
+ *
+ * This returns the blkcg associated with a bio, %NULL if not associated.
+ * Callers are expected to either handle %NULL or know association has been
+ * done prior to calling this.
+ */
static inline struct blkcg *bio_blkcg(struct bio *bio)
{
- struct cgroup_subsys_state *css;
-
- if (bio && bio->bi_css)
- return css_to_blkcg(bio->bi_css);
- css = kthread_blkcg();
- if (css)
- return css_to_blkcg(css);
- return css_to_blkcg(task_css(current, io_cgrp_id));
+ if (bio && bio->bi_blkg)
+ return bio->bi_blkg->blkcg;
+ return NULL;
}
static inline bool blk_cgroup_congested(void)
@@ -328,16 +348,12 @@
* @q: request_queue of interest
*
* Lookup blkg for the @blkcg - @q pair. This function should be called
- * under RCU read lock and is guaranteed to return %NULL if @q is bypassing
- * - see blk_queue_bypass_start() for details.
+ * under RCU read lock.
*/
static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
struct request_queue *q)
{
WARN_ON_ONCE(!rcu_read_lock_held());
-
- if (unlikely(blk_queue_bypass(q)))
- return NULL;
return __blkg_lookup(blkcg, q, false);
}
@@ -389,46 +405,37 @@
extern void blkcg_destroy_blkgs(struct blkcg *blkcg);
-#ifdef CONFIG_CGROUP_WRITEBACK
-
/**
- * blkcg_cgwb_get - get a reference for blkcg->cgwb_list
+ * blkcg_pin_online - pin online state
* @blkcg: blkcg of interest
*
- * This is used to track the number of active wb's related to a blkcg.
+ * While pinned, a blkcg is kept online. This is primarily used to
+ * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline
+ * while an associated cgwb is still active.
*/
-static inline void blkcg_cgwb_get(struct blkcg *blkcg)
+static inline void blkcg_pin_online(struct blkcg *blkcg)
{
- refcount_inc(&blkcg->cgwb_refcnt);
+ refcount_inc(&blkcg->online_pin);
}
/**
- * blkcg_cgwb_put - put a reference for @blkcg->cgwb_list
+ * blkcg_unpin_online - unpin online state
* @blkcg: blkcg of interest
*
- * This is used to track the number of active wb's related to a blkcg.
- * When this count goes to zero, all active wb has finished so the
+ * This is primarily used to impedance-match blkg and cgwb lifetimes so
+ * that blkg doesn't go offline while an associated cgwb is still active.
+ * When this count goes to zero, all active cgwbs have finished so the
* blkcg can continue destruction by calling blkcg_destroy_blkgs().
- * This work may occur in cgwb_release_workfn() on the cgwb_release
- * workqueue.
*/
-static inline void blkcg_cgwb_put(struct blkcg *blkcg)
+static inline void blkcg_unpin_online(struct blkcg *blkcg)
{
- if (refcount_dec_and_test(&blkcg->cgwb_refcnt))
+ do {
+ if (!refcount_dec_and_test(&blkcg->online_pin))
+ break;
blkcg_destroy_blkgs(blkcg);
+ blkcg = blkcg_parent(blkcg);
+ } while (blkcg);
}
-
-#else
-
-static inline void blkcg_cgwb_get(struct blkcg *blkcg) { }
-
-static inline void blkcg_cgwb_put(struct blkcg *blkcg)
-{
- /* wb isn't being accounted, so trigger destruction right away */
- blkcg_destroy_blkgs(blkcg);
-}
-
-#endif
/**
* blkg_path - format cgroup path of blkg
@@ -451,26 +458,20 @@
*/
static inline void blkg_get(struct blkcg_gq *blkg)
{
- WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0);
- atomic_inc(&blkg->refcnt);
+ percpu_ref_get(&blkg->refcnt);
}
/**
- * blkg_try_get - try and get a blkg reference
+ * blkg_tryget - try and get a blkg reference
* @blkg: blkg to get
*
* This is for use when doing an RCU lookup of the blkg. We may be in the midst
* of freeing this blkg, so we can only use it if the refcnt is not zero.
*/
-static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg)
+static inline bool blkg_tryget(struct blkcg_gq *blkg)
{
- if (atomic_inc_not_zero(&blkg->refcnt))
- return blkg;
- return NULL;
+ return blkg && percpu_ref_tryget(&blkg->refcnt);
}
-
-
-void __blkg_release_rcu(struct rcu_head *rcu);
/**
* blkg_put - put a blkg reference
@@ -478,9 +479,7 @@
*/
static inline void blkg_put(struct blkcg_gq *blkg)
{
- WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0);
- if (atomic_dec_and_test(&blkg->refcnt))
- call_rcu(&blkg->rcu_head, __blkg_release_rcu);
+ percpu_ref_put(&blkg->refcnt);
}
/**
@@ -515,331 +514,25 @@
if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \
(p_blkg)->q, false)))
-/**
- * blk_get_rl - get request_list to use
- * @q: request_queue of interest
- * @bio: bio which will be attached to the allocated request (may be %NULL)
- *
- * The caller wants to allocate a request from @q to use for @bio. Find
- * the request_list to use and obtain a reference on it. Should be called
- * under queue_lock. This function is guaranteed to return non-%NULL
- * request_list.
- */
-static inline struct request_list *blk_get_rl(struct request_queue *q,
- struct bio *bio)
+bool __blkcg_punt_bio_submit(struct bio *bio);
+
+static inline bool blkcg_punt_bio_submit(struct bio *bio)
{
- struct blkcg *blkcg;
- struct blkcg_gq *blkg;
-
- rcu_read_lock();
-
- blkcg = bio_blkcg(bio);
-
- /* bypass blkg lookup and use @q->root_rl directly for root */
- if (blkcg == &blkcg_root)
- goto root_rl;
-
- /*
- * Try to use blkg->rl. blkg lookup may fail under memory pressure
- * or if either the blkcg or queue is going away. Fall back to
- * root_rl in such cases.
- */
- blkg = blkg_lookup(blkcg, q);
- if (unlikely(!blkg))
- goto root_rl;
-
- blkg_get(blkg);
- rcu_read_unlock();
- return &blkg->rl;
-root_rl:
- rcu_read_unlock();
- return &q->root_rl;
-}
-
-/**
- * blk_put_rl - put request_list
- * @rl: request_list to put
- *
- * Put the reference acquired by blk_get_rl(). Should be called under
- * queue_lock.
- */
-static inline void blk_put_rl(struct request_list *rl)
-{
- if (rl->blkg->blkcg != &blkcg_root)
- blkg_put(rl->blkg);
-}
-
-/**
- * blk_rq_set_rl - associate a request with a request_list
- * @rq: request of interest
- * @rl: target request_list
- *
- * Associate @rq with @rl so that accounting and freeing can know the
- * request_list @rq came from.
- */
-static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl)
-{
- rq->rl = rl;
-}
-
-/**
- * blk_rq_rl - return the request_list a request came from
- * @rq: request of interest
- *
- * Return the request_list @rq is allocated from.
- */
-static inline struct request_list *blk_rq_rl(struct request *rq)
-{
- return rq->rl;
-}
-
-struct request_list *__blk_queue_next_rl(struct request_list *rl,
- struct request_queue *q);
-/**
- * blk_queue_for_each_rl - iterate through all request_lists of a request_queue
- *
- * Should be used under queue_lock.
- */
-#define blk_queue_for_each_rl(rl, q) \
- for ((rl) = &(q)->root_rl; (rl); (rl) = __blk_queue_next_rl((rl), (q)))
-
-static inline int blkg_stat_init(struct blkg_stat *stat, gfp_t gfp)
-{
- int ret;
-
- ret = percpu_counter_init(&stat->cpu_cnt, 0, gfp);
- if (ret)
- return ret;
-
- atomic64_set(&stat->aux_cnt, 0);
- return 0;
-}
-
-static inline void blkg_stat_exit(struct blkg_stat *stat)
-{
- percpu_counter_destroy(&stat->cpu_cnt);
-}
-
-/**
- * blkg_stat_add - add a value to a blkg_stat
- * @stat: target blkg_stat
- * @val: value to add
- *
- * Add @val to @stat. The caller must ensure that IRQ on the same CPU
- * don't re-enter this function for the same counter.
- */
-static inline void blkg_stat_add(struct blkg_stat *stat, uint64_t val)
-{
- percpu_counter_add_batch(&stat->cpu_cnt, val, BLKG_STAT_CPU_BATCH);
-}
-
-/**
- * blkg_stat_read - read the current value of a blkg_stat
- * @stat: blkg_stat to read
- */
-static inline uint64_t blkg_stat_read(struct blkg_stat *stat)
-{
- return percpu_counter_sum_positive(&stat->cpu_cnt);
-}
-
-/**
- * blkg_stat_reset - reset a blkg_stat
- * @stat: blkg_stat to reset
- */
-static inline void blkg_stat_reset(struct blkg_stat *stat)
-{
- percpu_counter_set(&stat->cpu_cnt, 0);
- atomic64_set(&stat->aux_cnt, 0);
-}
-
-/**
- * blkg_stat_add_aux - add a blkg_stat into another's aux count
- * @to: the destination blkg_stat
- * @from: the source
- *
- * Add @from's count including the aux one to @to's aux count.
- */
-static inline void blkg_stat_add_aux(struct blkg_stat *to,
- struct blkg_stat *from)
-{
- atomic64_add(blkg_stat_read(from) + atomic64_read(&from->aux_cnt),
- &to->aux_cnt);
-}
-
-static inline int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp)
-{
- int i, ret;
-
- for (i = 0; i < BLKG_RWSTAT_NR; i++) {
- ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp);
- if (ret) {
- while (--i >= 0)
- percpu_counter_destroy(&rwstat->cpu_cnt[i]);
- return ret;
- }
- atomic64_set(&rwstat->aux_cnt[i], 0);
- }
- return 0;
-}
-
-static inline void blkg_rwstat_exit(struct blkg_rwstat *rwstat)
-{
- int i;
-
- for (i = 0; i < BLKG_RWSTAT_NR; i++)
- percpu_counter_destroy(&rwstat->cpu_cnt[i]);
-}
-
-/**
- * blkg_rwstat_add - add a value to a blkg_rwstat
- * @rwstat: target blkg_rwstat
- * @op: REQ_OP and flags
- * @val: value to add
- *
- * Add @val to @rwstat. The counters are chosen according to @rw. The
- * caller is responsible for synchronizing calls to this function.
- */
-static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
- unsigned int op, uint64_t val)
-{
- struct percpu_counter *cnt;
-
- if (op_is_discard(op))
- cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD];
- else if (op_is_write(op))
- cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE];
+ if (bio->bi_opf & REQ_CGROUP_PUNT)
+ return __blkcg_punt_bio_submit(bio);
else
- cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ];
-
- percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);
-
- if (op_is_sync(op))
- cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC];
- else
- cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC];
-
- percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);
+ return false;
}
-/**
- * blkg_rwstat_read - read the current values of a blkg_rwstat
- * @rwstat: blkg_rwstat to read
- *
- * Read the current snapshot of @rwstat and return it in the aux counts.
- */
-static inline struct blkg_rwstat blkg_rwstat_read(struct blkg_rwstat *rwstat)
+static inline void blkcg_bio_issue_init(struct bio *bio)
{
- struct blkg_rwstat result;
- int i;
-
- for (i = 0; i < BLKG_RWSTAT_NR; i++)
- atomic64_set(&result.aux_cnt[i],
- percpu_counter_sum_positive(&rwstat->cpu_cnt[i]));
- return result;
-}
-
-/**
- * blkg_rwstat_total - read the total count of a blkg_rwstat
- * @rwstat: blkg_rwstat to read
- *
- * Return the total count of @rwstat regardless of the IO direction. This
- * function can be called without synchronization and takes care of u64
- * atomicity.
- */
-static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat)
-{
- struct blkg_rwstat tmp = blkg_rwstat_read(rwstat);
-
- return atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_READ]) +
- atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_WRITE]);
-}
-
-/**
- * blkg_rwstat_reset - reset a blkg_rwstat
- * @rwstat: blkg_rwstat to reset
- */
-static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat)
-{
- int i;
-
- for (i = 0; i < BLKG_RWSTAT_NR; i++) {
- percpu_counter_set(&rwstat->cpu_cnt[i], 0);
- atomic64_set(&rwstat->aux_cnt[i], 0);
- }
-}
-
-/**
- * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count
- * @to: the destination blkg_rwstat
- * @from: the source
- *
- * Add @from's count including the aux one to @to's aux count.
- */
-static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to,
- struct blkg_rwstat *from)
-{
- u64 sum[BLKG_RWSTAT_NR];
- int i;
-
- for (i = 0; i < BLKG_RWSTAT_NR; i++)
- sum[i] = percpu_counter_sum_positive(&from->cpu_cnt[i]);
-
- for (i = 0; i < BLKG_RWSTAT_NR; i++)
- atomic64_add(sum[i] + atomic64_read(&from->aux_cnt[i]),
- &to->aux_cnt[i]);
-}
-
-#ifdef CONFIG_BLK_DEV_THROTTLING
-extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
- struct bio *bio);
-#else
-static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
- struct bio *bio) { return false; }
-#endif
-
-static inline bool blkcg_bio_issue_check(struct request_queue *q,
- struct bio *bio)
-{
- struct blkcg *blkcg;
- struct blkcg_gq *blkg;
- bool throtl = false;
-
- rcu_read_lock();
- blkcg = bio_blkcg(bio);
-
- /* associate blkcg if bio hasn't attached one */
- bio_associate_blkcg(bio, &blkcg->css);
-
- blkg = blkg_lookup(blkcg, q);
- if (unlikely(!blkg)) {
- spin_lock_irq(q->queue_lock);
- blkg = blkg_lookup_create(blkcg, q);
- if (IS_ERR(blkg))
- blkg = NULL;
- spin_unlock_irq(q->queue_lock);
- }
-
- throtl = blk_throtl_bio(q, blkg, bio);
-
- if (!throtl) {
- blkg = blkg ?: q->root_blkg;
- /*
- * If the bio is flagged with BIO_QUEUE_ENTERED it means this
- * is a split bio and we would have already accounted for the
- * size of the bio.
- */
- if (!bio_flagged(bio, BIO_QUEUE_ENTERED))
- blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf,
- bio->bi_iter.bi_size);
- blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1);
- }
-
- rcu_read_unlock();
- return !throtl;
+ bio_issue_init(&bio->bi_issue, bio_sectors(bio));
}
static inline void blkcg_use_delay(struct blkcg_gq *blkg)
{
+ if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0))
+ return;
if (atomic_add_return(1, &blkg->use_delay) == 1)
atomic_inc(&blkg->blkcg->css.cgroup->congestion_count);
}
@@ -848,6 +541,8 @@
{
int old = atomic_read(&blkg->use_delay);
+ if (WARN_ON_ONCE(old < 0))
+ return 0;
if (old == 0)
return 0;
@@ -872,22 +567,57 @@
return 1;
}
+/**
+ * blkcg_set_delay - Enable allocator delay mechanism with the specified delay amount
+ * @blkg: target blkg
+ * @delay: delay duration in nsecs
+ *
+ * When enabled with this function, the delay is not decayed and must be
+ * explicitly cleared with blkcg_clear_delay(). Must not be mixed with
+ * blkcg_[un]use_delay() and blkcg_add_delay() usages.
+ */
+static inline void blkcg_set_delay(struct blkcg_gq *blkg, u64 delay)
+{
+ int old = atomic_read(&blkg->use_delay);
+
+ /* We only want 1 person setting the congestion count for this blkg. */
+ if (!old && atomic_cmpxchg(&blkg->use_delay, old, -1) == old)
+ atomic_inc(&blkg->blkcg->css.cgroup->congestion_count);
+
+ atomic64_set(&blkg->delay_nsec, delay);
+}
+
+/**
+ * blkcg_clear_delay - Disable allocator delay mechanism
+ * @blkg: target blkg
+ *
+ * Disable use_delay mechanism. See blkcg_set_delay().
+ */
static inline void blkcg_clear_delay(struct blkcg_gq *blkg)
{
int old = atomic_read(&blkg->use_delay);
- if (!old)
- return;
+
/* We only want 1 person clearing the congestion count for this blkg. */
- while (old) {
- int cur = atomic_cmpxchg(&blkg->use_delay, old, 0);
- if (cur == old) {
- atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
- break;
- }
- old = cur;
- }
+ if (old && atomic_cmpxchg(&blkg->use_delay, old, 0) == old)
+ atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
}
+/**
+ * blk_cgroup_mergeable - Determine whether to allow or disallow merges
+ * @rq: request to merge into
+ * @bio: bio to merge
+ *
+ * @bio and @rq should belong to the same cgroup and their issue_as_root should
+ * match. The latter is necessary as we don't want to throttle e.g. a metadata
+ * update because it happens to be next to a regular IO.
+ */
+static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio)
+{
+ return rq->bio->bi_blkg == bio->bi_blkg &&
+ bio_issue_as_root_blkg(rq->bio) == bio_issue_as_root_blkg(bio);
+}
+
+void blk_cgroup_bio_start(struct bio *bio);
void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta);
void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay);
void blkcg_maybe_throttle_current(void);
@@ -921,7 +651,6 @@
static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q)
{ return NULL; }
static inline int blkcg_init_queue(struct request_queue *q) { return 0; }
-static inline void blkcg_drain_queue(struct request_queue *q) { }
static inline void blkcg_exit_queue(struct request_queue *q) { }
static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; }
static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { }
@@ -930,6 +659,7 @@
static inline void blkcg_deactivate_policy(struct request_queue *q,
const struct blkcg_policy *pol) { }
+static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; }
static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; }
static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
@@ -939,14 +669,10 @@
static inline void blkg_get(struct blkcg_gq *blkg) { }
static inline void blkg_put(struct blkcg_gq *blkg) { }
-static inline struct request_list *blk_get_rl(struct request_queue *q,
- struct bio *bio) { return &q->root_rl; }
-static inline void blk_put_rl(struct request_list *rl) { }
-static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) { }
-static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q->root_rl; }
-
-static inline bool blkcg_bio_issue_check(struct request_queue *q,
- struct bio *bio) { return true; }
+static inline bool blkcg_punt_bio_submit(struct bio *bio) { return false; }
+static inline void blkcg_bio_issue_init(struct bio *bio) { }
+static inline void blk_cgroup_bio_start(struct bio *bio) { }
+static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio) { return true; }
#define blk_queue_for_each_rl(rl, q) \
for ((rl) = &(q)->root_rl; (rl); (rl) = NULL)
--
Gitblit v1.6.2