e2c5923c34
Pull core block layer updates from Jens Axboe: "This is the main pull request for block storage for 4.15-rc1. Nothing out of the ordinary in here, and no API changes or anything like that. Just various new features for drivers, core changes, etc. In particular, this pull request contains: - A patch series from Bart, closing the whole on blk/scsi-mq queue quescing. - A series from Christoph, building towards hidden gendisks (for multipath) and ability to move bio chains around. - NVMe - Support for native multipath for NVMe (Christoph). - Userspace notifications for AENs (Keith). - Command side-effects support (Keith). - SGL support (Chaitanya Kulkarni) - FC fixes and improvements (James Smart) - Lots of fixes and tweaks (Various) - bcache - New maintainer (Michael Lyle) - Writeback control improvements (Michael) - Various fixes (Coly, Elena, Eric, Liang, et al) - lightnvm updates, mostly centered around the pblk interface (Javier, Hans, and Rakesh). - Removal of unused bio/bvec kmap atomic interfaces (me, Christoph) - Writeback series that fix the much discussed hundreds of millions of sync-all units. This goes all the way, as discussed previously (me). - Fix for missing wakeup on writeback timer adjustments (Yafang Shao). - Fix laptop mode on blk-mq (me). - {mq,name} tupple lookup for IO schedulers, allowing us to have alias names. This means you can use 'deadline' on both !mq and on mq (where it's called mq-deadline). (me). - blktrace race fix, oopsing on sg load (me). - blk-mq optimizations (me). - Obscure waitqueue race fix for kyber (Omar). - NBD fixes (Josef). - Disable writeback throttling by default on bfq, like we do on cfq (Luca Miccio). - Series from Ming that enable us to treat flush requests on blk-mq like any other request. This is a really nice cleanup. - Series from Ming that improves merging on blk-mq with schedulers, getting us closer to flipping the switch on scsi-mq again. - BFQ updates (Paolo). - blk-mq atomic flags memory ordering fixes (Peter Z). - Loop cgroup support (Shaohua). - Lots of minor fixes from lots of different folks, both for core and driver code" * 'for-4.15/block' of git://git.kernel.dk/linux-block: (294 commits) nvme: fix visibility of "uuid" ns attribute blk-mq: fixup some comment typos and lengths ide: ide-atapi: fix compile error with defining macro DEBUG blk-mq: improve tag waiting setup for non-shared tags brd: remove unused brd_mutex blk-mq: only run the hardware queue if IO is pending block: avoid null pointer dereference on null disk fs: guard_bio_eod() needs to consider partitions xtensa/simdisk: fix compile error nvme: expose subsys attribute to sysfs nvme: create 'slaves' and 'holders' entries for hidden controllers block: create 'slaves' and 'holders' entries for hidden gendisks nvme: also expose the namespace identification sysfs files for mpath nodes nvme: implement multipath access to nvme subsystems nvme: track shared namespaces nvme: introduce a nvme_ns_ids structure nvme: track subsystems block, nvme: Introduce blk_mq_req_flags_t block, scsi: Make SCSI quiesce and resume work reliably block: Add the QUEUE_FLAG_PREEMPT_ONLY request queue flag ...
292 lines
8.2 KiB
C
292 lines
8.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __LINUX_BACKING_DEV_DEFS_H
|
|
#define __LINUX_BACKING_DEV_DEFS_H
|
|
|
|
#include <linux/list.h>
|
|
#include <linux/radix-tree.h>
|
|
#include <linux/rbtree.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/percpu_counter.h>
|
|
#include <linux/percpu-refcount.h>
|
|
#include <linux/flex_proportions.h>
|
|
#include <linux/timer.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/kref.h>
|
|
|
|
struct page;
|
|
struct device;
|
|
struct dentry;
|
|
|
|
/*
|
|
* Bits in bdi_writeback.state
|
|
*/
|
|
enum wb_state {
|
|
WB_registered, /* bdi_register() was done */
|
|
WB_shutting_down, /* wb_shutdown() in progress */
|
|
WB_writeback_running, /* Writeback is in progress */
|
|
WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */
|
|
WB_start_all, /* nr_pages == 0 (all) work pending */
|
|
};
|
|
|
|
enum wb_congested_state {
|
|
WB_async_congested, /* The async (write) queue is getting full */
|
|
WB_sync_congested, /* The sync queue is getting full */
|
|
};
|
|
|
|
typedef int (congested_fn)(void *, int);
|
|
|
|
enum wb_stat_item {
|
|
WB_RECLAIMABLE,
|
|
WB_WRITEBACK,
|
|
WB_DIRTIED,
|
|
WB_WRITTEN,
|
|
NR_WB_STAT_ITEMS
|
|
};
|
|
|
|
#define WB_STAT_BATCH (8*(1+ilog2(nr_cpu_ids)))
|
|
|
|
/*
|
|
* why some writeback work was initiated
|
|
*/
|
|
enum wb_reason {
|
|
WB_REASON_BACKGROUND,
|
|
WB_REASON_VMSCAN,
|
|
WB_REASON_SYNC,
|
|
WB_REASON_PERIODIC,
|
|
WB_REASON_LAPTOP_TIMER,
|
|
WB_REASON_FREE_MORE_MEM,
|
|
WB_REASON_FS_FREE_SPACE,
|
|
/*
|
|
* There is no bdi forker thread any more and works are done
|
|
* by emergency worker, however, this is TPs userland visible
|
|
* and we'll be exposing exactly the same information,
|
|
* so it has a mismatch name.
|
|
*/
|
|
WB_REASON_FORKER_THREAD,
|
|
|
|
WB_REASON_MAX,
|
|
};
|
|
|
|
/*
|
|
* For cgroup writeback, multiple wb's may map to the same blkcg. Those
|
|
* wb's can operate mostly independently but should share the congested
|
|
* state. To facilitate such sharing, the congested state is tracked using
|
|
* the following struct which is created on demand, indexed by blkcg ID on
|
|
* its bdi, and refcounted.
|
|
*/
|
|
struct bdi_writeback_congested {
|
|
unsigned long state; /* WB_[a]sync_congested flags */
|
|
atomic_t refcnt; /* nr of attached wb's and blkg */
|
|
|
|
#ifdef CONFIG_CGROUP_WRITEBACK
|
|
struct backing_dev_info *__bdi; /* the associated bdi, set to NULL
|
|
* on bdi unregistration. For memcg-wb
|
|
* internal use only! */
|
|
int blkcg_id; /* ID of the associated blkcg */
|
|
struct rb_node rb_node; /* on bdi->cgwb_congestion_tree */
|
|
#endif
|
|
};
|
|
|
|
/*
|
|
* Each wb (bdi_writeback) can perform writeback operations, is measured
|
|
* and throttled, independently. Without cgroup writeback, each bdi
|
|
* (bdi_writeback) is served by its embedded bdi->wb.
|
|
*
|
|
* On the default hierarchy, blkcg implicitly enables memcg. This allows
|
|
* using memcg's page ownership for attributing writeback IOs, and every
|
|
* memcg - blkcg combination can be served by its own wb by assigning a
|
|
* dedicated wb to each memcg, which enables isolation across different
|
|
* cgroups and propagation of IO back pressure down from the IO layer upto
|
|
* the tasks which are generating the dirty pages to be written back.
|
|
*
|
|
* A cgroup wb is indexed on its bdi by the ID of the associated memcg,
|
|
* refcounted with the number of inodes attached to it, and pins the memcg
|
|
* and the corresponding blkcg. As the corresponding blkcg for a memcg may
|
|
* change as blkcg is disabled and enabled higher up in the hierarchy, a wb
|
|
* is tested for blkcg after lookup and removed from index on mismatch so
|
|
* that a new wb for the combination can be created.
|
|
*/
|
|
struct bdi_writeback {
|
|
struct backing_dev_info *bdi; /* our parent bdi */
|
|
|
|
unsigned long state; /* Always use atomic bitops on this */
|
|
unsigned long last_old_flush; /* last old data flush */
|
|
|
|
struct list_head b_dirty; /* dirty inodes */
|
|
struct list_head b_io; /* parked for writeback */
|
|
struct list_head b_more_io; /* parked for more writeback */
|
|
struct list_head b_dirty_time; /* time stamps are dirty */
|
|
spinlock_t list_lock; /* protects the b_* lists */
|
|
|
|
struct percpu_counter stat[NR_WB_STAT_ITEMS];
|
|
|
|
struct bdi_writeback_congested *congested;
|
|
|
|
unsigned long bw_time_stamp; /* last time write bw is updated */
|
|
unsigned long dirtied_stamp;
|
|
unsigned long written_stamp; /* pages written at bw_time_stamp */
|
|
unsigned long write_bandwidth; /* the estimated write bandwidth */
|
|
unsigned long avg_write_bandwidth; /* further smoothed write bw, > 0 */
|
|
|
|
/*
|
|
* The base dirty throttle rate, re-calculated on every 200ms.
|
|
* All the bdi tasks' dirty rate will be curbed under it.
|
|
* @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit
|
|
* in small steps and is much more smooth/stable than the latter.
|
|
*/
|
|
unsigned long dirty_ratelimit;
|
|
unsigned long balanced_dirty_ratelimit;
|
|
|
|
struct fprop_local_percpu completions;
|
|
int dirty_exceeded;
|
|
enum wb_reason start_all_reason;
|
|
|
|
spinlock_t work_lock; /* protects work_list & dwork scheduling */
|
|
struct list_head work_list;
|
|
struct delayed_work dwork; /* work item used for writeback */
|
|
|
|
unsigned long dirty_sleep; /* last wait */
|
|
|
|
struct list_head bdi_node; /* anchored at bdi->wb_list */
|
|
|
|
#ifdef CONFIG_CGROUP_WRITEBACK
|
|
struct percpu_ref refcnt; /* used only for !root wb's */
|
|
struct fprop_local_percpu memcg_completions;
|
|
struct cgroup_subsys_state *memcg_css; /* the associated memcg */
|
|
struct cgroup_subsys_state *blkcg_css; /* and blkcg */
|
|
struct list_head memcg_node; /* anchored at memcg->cgwb_list */
|
|
struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */
|
|
|
|
union {
|
|
struct work_struct release_work;
|
|
struct rcu_head rcu;
|
|
};
|
|
#endif
|
|
};
|
|
|
|
struct backing_dev_info {
|
|
struct list_head bdi_list;
|
|
unsigned long ra_pages; /* max readahead in PAGE_SIZE units */
|
|
unsigned long io_pages; /* max allowed IO size */
|
|
congested_fn *congested_fn; /* Function pointer if device is md/dm */
|
|
void *congested_data; /* Pointer to aux data for congested func */
|
|
|
|
const char *name;
|
|
|
|
struct kref refcnt; /* Reference counter for the structure */
|
|
unsigned int capabilities; /* Device capabilities */
|
|
unsigned int min_ratio;
|
|
unsigned int max_ratio, max_prop_frac;
|
|
|
|
/*
|
|
* Sum of avg_write_bw of wbs with dirty inodes. > 0 if there are
|
|
* any dirty wbs, which is depended upon by bdi_has_dirty().
|
|
*/
|
|
atomic_long_t tot_write_bandwidth;
|
|
|
|
struct bdi_writeback wb; /* the root writeback info for this bdi */
|
|
struct list_head wb_list; /* list of all wbs */
|
|
#ifdef CONFIG_CGROUP_WRITEBACK
|
|
struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
|
|
struct rb_root cgwb_congested_tree; /* their congested states */
|
|
#else
|
|
struct bdi_writeback_congested *wb_congested;
|
|
#endif
|
|
wait_queue_head_t wb_waitq;
|
|
|
|
struct device *dev;
|
|
struct device *owner;
|
|
|
|
struct timer_list laptop_mode_wb_timer;
|
|
|
|
#ifdef CONFIG_DEBUG_FS
|
|
struct dentry *debug_dir;
|
|
struct dentry *debug_stats;
|
|
#endif
|
|
};
|
|
|
|
enum {
|
|
BLK_RW_ASYNC = 0,
|
|
BLK_RW_SYNC = 1,
|
|
};
|
|
|
|
void clear_wb_congested(struct bdi_writeback_congested *congested, int sync);
|
|
void set_wb_congested(struct bdi_writeback_congested *congested, int sync);
|
|
|
|
static inline void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
|
|
{
|
|
clear_wb_congested(bdi->wb.congested, sync);
|
|
}
|
|
|
|
static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync)
|
|
{
|
|
set_wb_congested(bdi->wb.congested, sync);
|
|
}
|
|
|
|
#ifdef CONFIG_CGROUP_WRITEBACK
|
|
|
|
/**
|
|
* wb_tryget - try to increment a wb's refcount
|
|
* @wb: bdi_writeback to get
|
|
*/
|
|
static inline bool wb_tryget(struct bdi_writeback *wb)
|
|
{
|
|
if (wb != &wb->bdi->wb)
|
|
return percpu_ref_tryget(&wb->refcnt);
|
|
return true;
|
|
}
|
|
|
|
/**
|
|
* wb_get - increment a wb's refcount
|
|
* @wb: bdi_writeback to get
|
|
*/
|
|
static inline void wb_get(struct bdi_writeback *wb)
|
|
{
|
|
if (wb != &wb->bdi->wb)
|
|
percpu_ref_get(&wb->refcnt);
|
|
}
|
|
|
|
/**
|
|
* wb_put - decrement a wb's refcount
|
|
* @wb: bdi_writeback to put
|
|
*/
|
|
static inline void wb_put(struct bdi_writeback *wb)
|
|
{
|
|
if (wb != &wb->bdi->wb)
|
|
percpu_ref_put(&wb->refcnt);
|
|
}
|
|
|
|
/**
|
|
* wb_dying - is a wb dying?
|
|
* @wb: bdi_writeback of interest
|
|
*
|
|
* Returns whether @wb is unlinked and being drained.
|
|
*/
|
|
static inline bool wb_dying(struct bdi_writeback *wb)
|
|
{
|
|
return percpu_ref_is_dying(&wb->refcnt);
|
|
}
|
|
|
|
#else /* CONFIG_CGROUP_WRITEBACK */
|
|
|
|
static inline bool wb_tryget(struct bdi_writeback *wb)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline void wb_get(struct bdi_writeback *wb)
|
|
{
|
|
}
|
|
|
|
static inline void wb_put(struct bdi_writeback *wb)
|
|
{
|
|
}
|
|
|
|
static inline bool wb_dying(struct bdi_writeback *wb)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
#endif /* CONFIG_CGROUP_WRITEBACK */
|
|
|
|
#endif /* __LINUX_BACKING_DEV_DEFS_H */
|