linux/drivers/block/null_blk/null_blk.h
Max Gurtovoy cee1b21523 null_blk: add option for managing virtual boundary
This will enable changing the virtual boundary of null blk devices. For
now, null blk devices didn't have any restriction on the scatter/gather
elements received from the block layer. Add a module parameter and a
configfs option that will control the virtual boundary. This will
enable testing the efficiency of the block layer bounce buffer in case
a suitable application will send discontiguous IO to the given device.

Initial testing with patched FIO showed the following results (64 jobs,
128 iodepth, 1 nullb device):
IO size      READ (virt=false)   READ (virt=true)   Write (virt=false)  Write (virt=true)
----------  ------------------- -----------------  ------------------- -------------------
 1k            10.7M                8482k               10.8M              8471k
 2k            10.4M                8266k               10.4M              8271k
 4k            10.4M                8274k               10.3M              8226k
 8k            10.2M                8131k               9800k              7933k
 16k           9567k                7764k               8081k              6828k
 32k           8865k                7309k               5570k              5153k
 64k           7695k                6586k               2682k              2617k
 128k          5346k                5489k               1320k              1296k

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Link: https://lore.kernel.org/r/20210412095523.278632-1-mgurtovoy@nvidia.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-04-12 06:47:25 -06:00

164 lines
4.9 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __BLK_NULL_BLK_H
#define __BLK_NULL_BLK_H
#undef pr_fmt
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/blk-mq.h>
#include <linux/hrtimer.h>
#include <linux/configfs.h>
#include <linux/badblocks.h>
#include <linux/fault-inject.h>
#include <linux/spinlock.h>
#include <linux/mutex.h>
struct nullb_cmd {
struct request *rq;
struct bio *bio;
unsigned int tag;
blk_status_t error;
struct nullb_queue *nq;
struct hrtimer timer;
};
struct nullb_queue {
unsigned long *tag_map;
wait_queue_head_t wait;
unsigned int queue_depth;
struct nullb_device *dev;
unsigned int requeue_selection;
struct nullb_cmd *cmds;
};
struct nullb_zone {
/*
* Zone lock to prevent concurrent modification of a zone write
* pointer position and condition: with memory backing, a write
* command execution may sleep on memory allocation. For this case,
* use mutex as the zone lock. Otherwise, use the spinlock for
* locking the zone.
*/
union {
spinlock_t spinlock;
struct mutex mutex;
};
enum blk_zone_type type;
enum blk_zone_cond cond;
sector_t start;
sector_t wp;
unsigned int len;
unsigned int capacity;
};
struct nullb_device {
struct nullb *nullb;
struct config_item item;
struct radix_tree_root data; /* data stored in the disk */
struct radix_tree_root cache; /* disk cache data */
unsigned long flags; /* device flags */
unsigned int curr_cache;
struct badblocks badblocks;
unsigned int nr_zones;
unsigned int nr_zones_imp_open;
unsigned int nr_zones_exp_open;
unsigned int nr_zones_closed;
unsigned int imp_close_zone_no;
struct nullb_zone *zones;
sector_t zone_size_sects;
bool need_zone_res_mgmt;
spinlock_t zone_res_lock;
unsigned long size; /* device size in MB */
unsigned long completion_nsec; /* time in ns to complete a request */
unsigned long cache_size; /* disk cache size in MB */
unsigned long zone_size; /* zone size in MB if device is zoned */
unsigned long zone_capacity; /* zone capacity in MB if device is zoned */
unsigned int zone_nr_conv; /* number of conventional zones */
unsigned int zone_max_open; /* max number of open zones */
unsigned int zone_max_active; /* max number of active zones */
unsigned int submit_queues; /* number of submission queues */
unsigned int home_node; /* home node for the device */
unsigned int queue_mode; /* block interface */
unsigned int blocksize; /* block size */
unsigned int max_sectors; /* Max sectors per command */
unsigned int irqmode; /* IRQ completion handler */
unsigned int hw_queue_depth; /* queue depth */
unsigned int index; /* index of the disk, only valid with a disk */
unsigned int mbps; /* Bandwidth throttle cap (in MB/s) */
bool blocking; /* blocking blk-mq device */
bool use_per_node_hctx; /* use per-node allocation for hardware context */
bool power; /* power on/off the device */
bool memory_backed; /* if data is stored in memory */
bool discard; /* if support discard */
bool zoned; /* if device is zoned */
bool virt_boundary; /* virtual boundary on/off for the device */
};
struct nullb {
struct nullb_device *dev;
struct list_head list;
unsigned int index;
struct request_queue *q;
struct gendisk *disk;
struct blk_mq_tag_set *tag_set;
struct blk_mq_tag_set __tag_set;
unsigned int queue_depth;
atomic_long_t cur_bytes;
struct hrtimer bw_timer;
unsigned long cache_flush_pos;
spinlock_t lock;
struct nullb_queue *queues;
unsigned int nr_queues;
char disk_name[DISK_NAME_LEN];
};
blk_status_t null_handle_discard(struct nullb_device *dev, sector_t sector,
sector_t nr_sectors);
blk_status_t null_process_cmd(struct nullb_cmd *cmd,
enum req_opf op, sector_t sector,
unsigned int nr_sectors);
#ifdef CONFIG_BLK_DEV_ZONED
int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q);
int null_register_zoned_dev(struct nullb *nullb);
void null_free_zoned_dev(struct nullb_device *dev);
int null_report_zones(struct gendisk *disk, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data);
blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd,
enum req_opf op, sector_t sector,
sector_t nr_sectors);
size_t null_zone_valid_read_len(struct nullb *nullb,
sector_t sector, unsigned int len);
#else
static inline int null_init_zoned_dev(struct nullb_device *dev,
struct request_queue *q)
{
pr_err("CONFIG_BLK_DEV_ZONED not enabled\n");
return -EINVAL;
}
static inline int null_register_zoned_dev(struct nullb *nullb)
{
return -ENODEV;
}
static inline void null_free_zoned_dev(struct nullb_device *dev) {}
static inline blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd,
enum req_opf op, sector_t sector, sector_t nr_sectors)
{
return BLK_STS_NOTSUPP;
}
static inline size_t null_zone_valid_read_len(struct nullb *nullb,
sector_t sector,
unsigned int len)
{
return len;
}
#define null_report_zones NULL
#endif /* CONFIG_BLK_DEV_ZONED */
#endif /* __NULL_BLK_H */