123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510 |
- /*
- * Common Block IO controller cgroup interface
- *
- * Based on ideas and code from CFQ, CFS and BFQ:
- * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
- *
- * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
- * Paolo Valente <paolo.valente@unimore.it>
- *
- * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
- * Nauman Rafique <nauman@google.com>
- */
- #include <linux/ioprio.h>
- #include <linux/kdev_t.h>
- #include <linux/module.h>
- #include <linux/err.h>
- #include <linux/blkdev.h>
- #include <linux/slab.h>
- #include <linux/genhd.h>
- #include <linux/delay.h>
- #include <linux/atomic.h>
- #include "blk-cgroup.h"
- #include "blk.h"
- #define MAX_KEY_LEN 100
- static DEFINE_MUTEX(blkcg_pol_mutex);
- struct blkcg blkcg_root = { .cfq_weight = 2 * CFQ_WEIGHT_DEFAULT };
- EXPORT_SYMBOL_GPL(blkcg_root);
- static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
- static bool blkcg_policy_enabled(struct request_queue *q,
- const struct blkcg_policy *pol)
- {
- return pol && test_bit(pol->plid, q->blkcg_pols);
- }
- /**
- * blkg_free - free a blkg
- * @blkg: blkg to free
- *
- * Free @blkg which may be partially allocated.
- */
- static void blkg_free(struct blkcg_gq *blkg)
- {
- int i;
- if (!blkg)
- return;
- for (i = 0; i < BLKCG_MAX_POLS; i++) {
- struct blkcg_policy *pol = blkcg_policy[i];
- struct blkg_policy_data *pd = blkg->pd[i];
- if (!pd)
- continue;
- if (pol && pol->pd_exit_fn)
- pol->pd_exit_fn(blkg);
- kfree(pd);
- }
- blk_exit_rl(&blkg->rl);
- kfree(blkg);
- }
- /**
- * blkg_alloc - allocate a blkg
- * @blkcg: block cgroup the new blkg is associated with
- * @q: request_queue the new blkg is associated with
- * @gfp_mask: allocation mask to use
- *
- * Allocate a new blkg assocating @blkcg and @q.
- */
- static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
- gfp_t gfp_mask)
- {
- struct blkcg_gq *blkg;
- int i;
- /* alloc and init base part */
- blkg = kzalloc_node(sizeof(*blkg), gfp_mask, q->node);
- if (!blkg)
- return NULL;
- blkg->q = q;
- INIT_LIST_HEAD(&blkg->q_node);
- blkg->blkcg = blkcg;
- blkg->refcnt = 1;
- /* root blkg uses @q->root_rl, init rl only for !root blkgs */
- if (blkcg != &blkcg_root) {
- if (blk_init_rl(&blkg->rl, q, gfp_mask))
- goto err_free;
- blkg->rl.blkg = blkg;
- }
- for (i = 0; i < BLKCG_MAX_POLS; i++) {
- struct blkcg_policy *pol = blkcg_policy[i];
- struct blkg_policy_data *pd;
- if (!blkcg_policy_enabled(q, pol))
- continue;
- /* alloc per-policy data and attach it to blkg */
- pd = kzalloc_node(pol->pd_size, gfp_mask, q->node);
- if (!pd)
- goto err_free;
- blkg->pd[i] = pd;
- pd->blkg = blkg;
- /* invoke per-policy init */
- if (blkcg_policy_enabled(blkg->q, pol))
- pol->pd_init_fn(blkg);
- }
- return blkg;
- err_free:
- blkg_free(blkg);
- return NULL;
- }
- static struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg,
- struct request_queue *q)
- {
- struct blkcg_gq *blkg;
- blkg = rcu_dereference(blkcg->blkg_hint);
- if (blkg && blkg->q == q)
- return blkg;
- /*
- * Hint didn't match. Look up from the radix tree. Note that we
- * may not be holding queue_lock and thus are not sure whether
- * @blkg from blkg_tree has already been removed or not, so we
- * can't update hint to the lookup result. Leave it to the caller.
- */
- blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id);
- if (blkg && blkg->q == q)
- return blkg;
- return NULL;
- }
- /**
- * blkg_lookup - lookup blkg for the specified blkcg - q pair
- * @blkcg: blkcg of interest
- * @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.
- */
- 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);
- }
- EXPORT_SYMBOL_GPL(blkg_lookup);
- /*
- * If @new_blkg is %NULL, this function tries to allocate a new one as
- * necessary using %GFP_ATOMIC. @new_blkg is always consumed on return.
- */
- static struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg,
- struct request_queue *q,
- struct blkcg_gq *new_blkg)
- {
- struct blkcg_gq *blkg;
- int ret;
- WARN_ON_ONCE(!rcu_read_lock_held());
- lockdep_assert_held(q->queue_lock);
- /* lookup and update hint on success, see __blkg_lookup() for details */
- blkg = __blkg_lookup(blkcg, q);
- if (blkg) {
- rcu_assign_pointer(blkcg->blkg_hint, blkg);
- goto out_free;
- }
- /* blkg holds a reference to blkcg */
- if (!css_tryget(&blkcg->css)) {
- blkg = ERR_PTR(-EINVAL);
- goto out_free;
- }
- /* allocate */
- if (!new_blkg) {
- new_blkg = blkg_alloc(blkcg, q, GFP_ATOMIC);
- if (unlikely(!new_blkg)) {
- blkg = ERR_PTR(-ENOMEM);
- goto out_put;
- }
- }
- blkg = new_blkg;
- /* insert */
- spin_lock(&blkcg->lock);
- ret = radix_tree_insert(&blkcg->blkg_tree, q->id, blkg);
- if (likely(!ret)) {
- hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
- list_add(&blkg->q_node, &q->blkg_list);
- }
- spin_unlock(&blkcg->lock);
- if (!ret)
- return blkg;
- blkg = ERR_PTR(ret);
- out_put:
- css_put(&blkcg->css);
- out_free:
- blkg_free(new_blkg);
- return blkg;
- }
- struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
- struct request_queue *q)
- {
- /*
- * This could be the first entry point of blkcg implementation and
- * we shouldn't allow anything to go through for a bypassing queue.
- */
- if (unlikely(blk_queue_bypass(q)))
- return ERR_PTR(blk_queue_dying(q) ? -EINVAL : -EBUSY);
- return __blkg_lookup_create(blkcg, q, NULL);
- }
- EXPORT_SYMBOL_GPL(blkg_lookup_create);
- static void blkg_destroy(struct blkcg_gq *blkg)
- {
- struct blkcg *blkcg = blkg->blkcg;
- lockdep_assert_held(blkg->q->queue_lock);
- lockdep_assert_held(&blkcg->lock);
- /* Something wrong if we are trying to remove same group twice */
- WARN_ON_ONCE(list_empty(&blkg->q_node));
- WARN_ON_ONCE(hlist_unhashed(&blkg->blkcg_node));
- radix_tree_delete(&blkcg->blkg_tree, blkg->q->id);
- list_del_init(&blkg->q_node);
- hlist_del_init_rcu(&blkg->blkcg_node);
- /*
- * Both setting lookup hint to and clearing it from @blkg are done
- * under queue_lock. If it's not pointing to @blkg now, it never
- * will. Hint assignment itself can race safely.
- */
- if (rcu_dereference_raw(blkcg->blkg_hint) == blkg)
- rcu_assign_pointer(blkcg->blkg_hint, NULL);
- /*
- * Put the reference taken at the time of creation so that when all
- * queues are gone, group can be destroyed.
- */
- blkg_put(blkg);
- }
- /**
- * blkg_destroy_all - destroy all blkgs associated with a request_queue
- * @q: request_queue of interest
- *
- * Destroy all blkgs associated with @q.
- */
- static void blkg_destroy_all(struct request_queue *q)
- {
- struct blkcg_gq *blkg, *n;
- lockdep_assert_held(q->queue_lock);
- list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) {
- struct blkcg *blkcg = blkg->blkcg;
- spin_lock(&blkcg->lock);
- blkg_destroy(blkg);
- spin_unlock(&blkcg->lock);
- }
- /*
- * root blkg is destroyed. Just clear the pointer since
- * root_rl does not take reference on root blkg.
- */
- q->root_blkg = NULL;
- q->root_rl.blkg = NULL;
- }
- static void blkg_rcu_free(struct rcu_head *rcu_head)
- {
- blkg_free(container_of(rcu_head, struct blkcg_gq, rcu_head));
- }
- void __blkg_release(struct blkcg_gq *blkg)
- {
- /* release the extra blkcg reference this blkg has been holding */
- css_put(&blkg->blkcg->css);
- /*
- * A group is freed in rcu manner. But having an rcu lock does not
- * mean that one can access all the fields of blkg and assume these
- * are valid. For example, don't try to follow throtl_data and
- * request queue links.
- *
- * Having a reference to blkg under an rcu allows acess to only
- * values local to groups like group stats and group rate limits
- */
- call_rcu(&blkg->rcu_head, blkg_rcu_free);
- }
- EXPORT_SYMBOL_GPL(__blkg_release);
- /*
- * The next function used by blk_queue_for_each_rl(). It's a bit tricky
- * because the root blkg uses @q->root_rl instead of its own rl.
- */
- struct request_list *__blk_queue_next_rl(struct request_list *rl,
- struct request_queue *q)
- {
- struct list_head *ent;
- struct blkcg_gq *blkg;
- /*
- * Determine the current blkg list_head. The first entry is
- * root_rl which is off @q->blkg_list and mapped to the head.
- */
- if (rl == &q->root_rl) {
- ent = &q->blkg_list;
- /* There are no more block groups, hence no request lists */
- if (list_empty(ent))
- return NULL;
- } else {
- blkg = container_of(rl, struct blkcg_gq, rl);
- ent = &blkg->q_node;
- }
- /* walk to the next list_head, skip root blkcg */
- ent = ent->next;
- if (ent == &q->root_blkg->q_node)
- ent = ent->next;
- if (ent == &q->blkg_list)
- return NULL;
- blkg = container_of(ent, struct blkcg_gq, q_node);
- return &blkg->rl;
- }
- static int blkcg_reset_stats(struct cgroup *cgroup, struct cftype *cftype,
- u64 val)
- {
- struct blkcg *blkcg = cgroup_to_blkcg(cgroup);
- struct blkcg_gq *blkg;
- struct hlist_node *n;
- int i;
- mutex_lock(&blkcg_pol_mutex);
- spin_lock_irq(&blkcg->lock);
- /*
- * Note that stat reset is racy - it doesn't synchronize against
- * stat updates. This is a debug feature which shouldn't exist
- * anyway. If you get hit by a race, retry.
- */
- hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
- for (i = 0; i < BLKCG_MAX_POLS; i++) {
- struct blkcg_policy *pol = blkcg_policy[i];
- if (blkcg_policy_enabled(blkg->q, pol) &&
- pol->pd_reset_stats_fn)
- pol->pd_reset_stats_fn(blkg);
- }
- }
- spin_unlock_irq(&blkcg->lock);
- mutex_unlock(&blkcg_pol_mutex);
- return 0;
- }
- static const char *blkg_dev_name(struct blkcg_gq *blkg)
- {
- /* some drivers (floppy) instantiate a queue w/o disk registered */
- if (blkg->q->backing_dev_info.dev)
- return dev_name(blkg->q->backing_dev_info.dev);
- return NULL;
- }
- /**
- * blkcg_print_blkgs - helper for printing per-blkg data
- * @sf: seq_file to print to
- * @blkcg: blkcg of interest
- * @prfill: fill function to print out a blkg
- * @pol: policy in question
- * @data: data to be passed to @prfill
- * @show_total: to print out sum of prfill return values or not
- *
- * This function invokes @prfill on each blkg of @blkcg if pd for the
- * policy specified by @pol exists. @prfill is invoked with @sf, the
- * policy data and @data. If @show_total is %true, the sum of the return
- * values from @prfill is printed with "Total" label at the end.
- *
- * This is to be used to construct print functions for
- * cftype->read_seq_string method.
- */
- void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
- u64 (*prfill)(struct seq_file *,
- struct blkg_policy_data *, int),
- const struct blkcg_policy *pol, int data,
- bool show_total)
- {
- struct blkcg_gq *blkg;
- struct hlist_node *n;
- u64 total = 0;
- spin_lock_irq(&blkcg->lock);
- hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node)
- if (blkcg_policy_enabled(blkg->q, pol))
- total += prfill(sf, blkg->pd[pol->plid], data);
- spin_unlock_irq(&blkcg->lock);
- if (show_total)
- seq_printf(sf, "Total %llu\n", (unsigned long long)total);
- }
- EXPORT_SYMBOL_GPL(blkcg_print_blkgs);
- /**
- * __blkg_prfill_u64 - prfill helper for a single u64 value
- * @sf: seq_file to print to
- * @pd: policy private data of interest
- * @v: value to print
- *
- * Print @v to @sf for the device assocaited with @pd.
- */
- u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v)
- {
- const char *dname = blkg_dev_name(pd->blkg);
- if (!dname)
- return 0;
- seq_printf(sf, "%s %llu\n", dname, (unsigned long long)v);
- return v;
- }
- EXPORT_SYMBOL_GPL(__blkg_prfill_u64);
- /**
- * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat
- * @sf: seq_file to print to
- * @pd: policy private data of interest
- * @rwstat: rwstat to print
- *
- * Print @rwstat to @sf for the device assocaited with @pd.
- */
- u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
- const struct blkg_rwstat *rwstat)
- {
- static const char *rwstr[] = {
- [BLKG_RWSTAT_READ] = "Read",
- [BLKG_RWSTAT_WRITE] = "Write",
- [BLKG_RWSTAT_SYNC] = "Sync",
- [BLKG_RWSTAT_ASYNC] = "Async",
- };
- const char *dname = blkg_dev_name(pd->blkg);
- u64 v;
- int i;
- if (!dname)
- return 0;
- for (i = 0; i < BLKG_RWSTAT_NR; i++)
- seq_printf(sf, "%s %s %llu\n", dname, rwstr[i],
- (unsigned long long)rwstat->cnt[i]);
- v = rwstat->cnt[BLKG_RWSTAT_READ] + rwstat->cnt[BLKG_RWSTAT_WRITE];
- seq_printf(sf, "%s Total %llu\n", dname, (unsigned long long)v);
- return v;
- }
- /**
- * blkg_prfill_stat - prfill callback for blkg_stat
- * @sf: seq_file to print to
- * @pd: policy private data of interest
- * @off: offset to the blkg_stat in @pd
- *
- * prfill callback for printing a blkg_stat.
- */
- u64 blkg_prfill_stat(struct seq_file *sf, struct blkg_policy_data *pd, int off)
- {
- return __blkg_prfill_u64(sf, pd, blkg_stat_read((void *)pd + off));
- }
- EXPORT_SYMBOL_GPL(blkg_prfill_stat);
- /**
- * blkg_prfill_rwstat - prfill callback for blkg_rwstat
- * @sf: seq_file to print to
- * @pd: policy private data of interest
- * @off: offset to the blkg_rwstat in @pd
- *
- * prfill callback for printing a blkg_rwstat.
- */
- u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
- int off)
- {
- struct blkg_rwstat rwstat = blkg_rwstat_read((void *)pd + off);
|