linux/drivers/nvme/host/nvme.h
Linus Torvalds 694752922b Merge branch 'for-4.12/block' of git://git.kernel.dk/linux-block
Pull block layer updates from Jens Axboe:

 - Add BFQ IO scheduler under the new blk-mq scheduling framework. BFQ
   was initially a fork of CFQ, but subsequently changed to implement
   fairness based on B-WF2Q+, a modified variant of WF2Q. BFQ is meant
   to be used on desktop type single drives, providing good fairness.
   From Paolo.

 - Add Kyber IO scheduler. This is a full multiqueue aware scheduler,
   using a scalable token based algorithm that throttles IO based on
   live completion IO stats, similary to blk-wbt. From Omar.

 - A series from Jan, moving users to separately allocated backing
   devices. This continues the work of separating backing device life
   times, solving various problems with hot removal.

 - A series of updates for lightnvm, mostly from Javier. Includes a
   'pblk' target that exposes an open channel SSD as a physical block
   device.

 - A series of fixes and improvements for nbd from Josef.

 - A series from Omar, removing queue sharing between devices on mostly
   legacy drivers. This helps us clean up other bits, if we know that a
   queue only has a single device backing. This has been overdue for
   more than a decade.

 - Fixes for the blk-stats, and improvements to unify the stats and user
   windows. This both improves blk-wbt, and enables other users to
   register a need to receive IO stats for a device. From Omar.

 - blk-throttle improvements from Shaohua. This provides a scalable
   framework for implementing scalable priotization - particularly for
   blk-mq, but applicable to any type of block device. The interface is
   marked experimental for now.

 - Bucketized IO stats for IO polling from Stephen Bates. This improves
   efficiency of polled workloads in the presence of mixed block size
   IO.

 - A few fixes for opal, from Scott.

 - A few pulls for NVMe, including a lot of fixes for NVMe-over-fabrics.
   From a variety of folks, mostly Sagi and James Smart.

 - A series from Bart, improving our exposed info and capabilities from
   the blk-mq debugfs support.

 - A series from Christoph, cleaning up how handle WRITE_ZEROES.

 - A series from Christoph, cleaning up the block layer handling of how
   we track errors in a request. On top of being a nice cleanup, it also
   shrinks the size of struct request a bit.

 - Removal of mg_disk and hd (sorry Linus) by Christoph. The former was
   never used by platforms, and the latter has outlived it's usefulness.

 - Various little bug fixes and cleanups from a wide variety of folks.

* 'for-4.12/block' of git://git.kernel.dk/linux-block: (329 commits)
  block: hide badblocks attribute by default
  blk-mq: unify hctx delay_work and run_work
  block: add kblock_mod_delayed_work_on()
  blk-mq: unify hctx delayed_run_work and run_work
  nbd: fix use after free on module unload
  MAINTAINERS: bfq: Add Paolo as maintainer for the BFQ I/O scheduler
  blk-mq-sched: alloate reserved tags out of normal pool
  mtip32xx: use runtime tag to initialize command header
  scsi: Implement blk_mq_ops.show_rq()
  blk-mq: Add blk_mq_ops.show_rq()
  blk-mq: Show operation, cmd_flags and rq_flags names
  blk-mq: Make blk_flags_show() callers append a newline character
  blk-mq: Move the "state" debugfs attribute one level down
  blk-mq: Unregister debugfs attributes earlier
  blk-mq: Only unregister hctxs for which registration succeeded
  blk-mq-debugfs: Rename functions for registering and unregistering the mq directory
  blk-mq: Let blk_mq_debugfs_register() look up the queue name
  blk-mq: Register <dev>/queue/mq after having registered <dev>/queue
  ide-pm: always pass 0 error to ide_complete_rq in ide_do_devset
  ide-pm: always pass 0 error to __blk_end_request_all
  ..
2017-05-01 10:39:57 -07:00

369 lines
9.9 KiB
C

/*
* Copyright (c) 2011-2014, Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope 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 _NVME_H
#define _NVME_H
#include <linux/nvme.h>
#include <linux/pci.h>
#include <linux/kref.h>
#include <linux/blk-mq.h>
#include <linux/lightnvm.h>
#include <linux/sed-opal.h>
extern unsigned char nvme_io_timeout;
#define NVME_IO_TIMEOUT (nvme_io_timeout * HZ)
extern unsigned char admin_timeout;
#define ADMIN_TIMEOUT (admin_timeout * HZ)
extern unsigned char shutdown_timeout;
#define SHUTDOWN_TIMEOUT (shutdown_timeout * HZ)
#define NVME_DEFAULT_KATO 5
#define NVME_KATO_GRACE 10
enum {
NVME_NS_LBA = 0,
NVME_NS_LIGHTNVM = 1,
};
/*
* List of workarounds for devices that required behavior not specified in
* the standard.
*/
enum nvme_quirks {
/*
* Prefers I/O aligned to a stripe size specified in a vendor
* specific Identify field.
*/
NVME_QUIRK_STRIPE_SIZE = (1 << 0),
/*
* The controller doesn't handle Identify value others than 0 or 1
* correctly.
*/
NVME_QUIRK_IDENTIFY_CNS = (1 << 1),
/*
* The controller deterministically returns O's on reads to
* logical blocks that deallocate was called on.
*/
NVME_QUIRK_DEALLOCATE_ZEROES = (1 << 2),
/*
* The controller needs a delay before starts checking the device
* readiness, which is done by reading the NVME_CSTS_RDY bit.
*/
NVME_QUIRK_DELAY_BEFORE_CHK_RDY = (1 << 3),
/*
* APST should not be used.
*/
NVME_QUIRK_NO_APST = (1 << 4),
/*
* The deepest sleep state should not be used.
*/
NVME_QUIRK_NO_DEEPEST_PS = (1 << 5),
};
/*
* Common request structure for NVMe passthrough. All drivers must have
* this structure as the first member of their request-private data.
*/
struct nvme_request {
struct nvme_command *cmd;
union nvme_result result;
u8 retries;
u8 flags;
u16 status;
};
enum {
NVME_REQ_CANCELLED = (1 << 0),
};
static inline struct nvme_request *nvme_req(struct request *req)
{
return blk_mq_rq_to_pdu(req);
}
/* The below value is the specific amount of delay needed before checking
* readiness in case of the PCI_DEVICE(0x1c58, 0x0003), which needs the
* NVME_QUIRK_DELAY_BEFORE_CHK_RDY quirk enabled. The value (in ms) was
* found empirically.
*/
#define NVME_QUIRK_DELAY_AMOUNT 2000
enum nvme_ctrl_state {
NVME_CTRL_NEW,
NVME_CTRL_LIVE,
NVME_CTRL_RESETTING,
NVME_CTRL_RECONNECTING,
NVME_CTRL_DELETING,
NVME_CTRL_DEAD,
};
struct nvme_ctrl {
enum nvme_ctrl_state state;
bool identified;
spinlock_t lock;
const struct nvme_ctrl_ops *ops;
struct request_queue *admin_q;
struct request_queue *connect_q;
struct device *dev;
struct kref kref;
int instance;
struct blk_mq_tag_set *tagset;
struct list_head namespaces;
struct mutex namespaces_mutex;
struct device *device; /* char device */
struct list_head node;
struct ida ns_ida;
struct opal_dev *opal_dev;
char name[12];
char serial[20];
char model[40];
char firmware_rev[8];
u16 cntlid;
u32 ctrl_config;
u32 page_size;
u32 max_hw_sectors;
u16 oncs;
u16 vid;
u16 oacs;
atomic_t abort_limit;
u8 event_limit;
u8 vwc;
u32 vs;
u32 sgls;
u16 kas;
u8 npss;
u8 apsta;
unsigned int kato;
bool subsystem;
unsigned long quirks;
struct nvme_id_power_state psd[32];
struct work_struct scan_work;
struct work_struct async_event_work;
struct delayed_work ka_work;
/* Power saving configuration */
u64 ps_max_latency_us;
/* Fabrics only */
u16 sqsize;
u32 ioccsz;
u32 iorcsz;
u16 icdoff;
u16 maxcmd;
struct nvmf_ctrl_options *opts;
};
/*
* An NVM Express namespace is equivalent to a SCSI LUN
*/
struct nvme_ns {
struct list_head list;
struct nvme_ctrl *ctrl;
struct request_queue *queue;
struct gendisk *disk;
struct nvm_dev *ndev;
struct kref kref;
int instance;
u8 eui[8];
u8 uuid[16];
unsigned ns_id;
int lba_shift;
u16 ms;
bool ext;
u8 pi_type;
unsigned long flags;
#define NVME_NS_REMOVING 0
#define NVME_NS_DEAD 1
u64 mode_select_num_blocks;
u32 mode_select_block_len;
};
struct nvme_ctrl_ops {
const char *name;
struct module *module;
bool is_fabrics;
int (*reg_read32)(struct nvme_ctrl *ctrl, u32 off, u32 *val);
int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val);
int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
int (*reset_ctrl)(struct nvme_ctrl *ctrl);
void (*free_ctrl)(struct nvme_ctrl *ctrl);
void (*submit_async_event)(struct nvme_ctrl *ctrl, int aer_idx);
int (*delete_ctrl)(struct nvme_ctrl *ctrl);
const char *(*get_subsysnqn)(struct nvme_ctrl *ctrl);
int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
};
static inline bool nvme_ctrl_ready(struct nvme_ctrl *ctrl)
{
u32 val = 0;
if (ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &val))
return false;
return val & NVME_CSTS_RDY;
}
static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl)
{
if (!ctrl->subsystem)
return -ENOTTY;
return ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, 0x4E564D65);
}
static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector)
{
return (sector >> (ns->lba_shift - 9));
}
static inline void nvme_cleanup_cmd(struct request *req)
{
if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
kfree(page_address(req->special_vec.bv_page) +
req->special_vec.bv_offset);
}
}
static inline void nvme_end_request(struct request *req, __le16 status,
union nvme_result result)
{
struct nvme_request *rq = nvme_req(req);
rq->status = le16_to_cpu(status) >> 1;
rq->result = result;
blk_mq_complete_request(req);
}
void nvme_complete_rq(struct request *req);
void nvme_cancel_request(struct request *req, void *data, bool reserved);
bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
enum nvme_ctrl_state new_state);
int nvme_disable_ctrl(struct nvme_ctrl *ctrl, u64 cap);
int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap);
int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl);
int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
const struct nvme_ctrl_ops *ops, unsigned long quirks);
void nvme_uninit_ctrl(struct nvme_ctrl *ctrl);
void nvme_put_ctrl(struct nvme_ctrl *ctrl);
int nvme_init_identify(struct nvme_ctrl *ctrl);
void nvme_queue_scan(struct nvme_ctrl *ctrl);
void nvme_remove_namespaces(struct nvme_ctrl *ctrl);
int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
bool send);
#define NVME_NR_AERS 1
void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
union nvme_result *res);
void nvme_queue_async_events(struct nvme_ctrl *ctrl);
void nvme_stop_queues(struct nvme_ctrl *ctrl);
void nvme_start_queues(struct nvme_ctrl *ctrl);
void nvme_kill_queues(struct nvme_ctrl *ctrl);
void nvme_unfreeze(struct nvme_ctrl *ctrl);
void nvme_wait_freeze(struct nvme_ctrl *ctrl);
void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
void nvme_start_freeze(struct nvme_ctrl *ctrl);
#define NVME_QID_ANY -1
struct request *nvme_alloc_request(struct request_queue *q,
struct nvme_command *cmd, unsigned int flags, int qid);
int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
struct nvme_command *cmd);
int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
void *buf, unsigned bufflen);
int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
union nvme_result *result, void *buffer, unsigned bufflen,
unsigned timeout, int qid, int at_head, int flags);
int nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
void __user *ubuffer, unsigned bufflen, u32 *result,
unsigned timeout);
int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
void __user *ubuffer, unsigned bufflen,
void __user *meta_buffer, unsigned meta_len, u32 meta_seed,
u32 *result, unsigned timeout);
int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id);
int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid,
struct nvme_id_ns **id);
int nvme_get_log_page(struct nvme_ctrl *dev, struct nvme_smart_log **log);
int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid,
void *buffer, size_t buflen, u32 *result);
int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
void *buffer, size_t buflen, u32 *result);
int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count);
void nvme_start_keep_alive(struct nvme_ctrl *ctrl);
void nvme_stop_keep_alive(struct nvme_ctrl *ctrl);
struct sg_io_hdr;
int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr);
int nvme_sg_io32(struct nvme_ns *ns, unsigned long arg);
int nvme_sg_get_version_num(int __user *ip);
#ifdef CONFIG_NVM
int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id);
int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node);
void nvme_nvm_unregister(struct nvme_ns *ns);
int nvme_nvm_register_sysfs(struct nvme_ns *ns);
void nvme_nvm_unregister_sysfs(struct nvme_ns *ns);
int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd, unsigned long arg);
#else
static inline int nvme_nvm_register(struct nvme_ns *ns, char *disk_name,
int node)
{
return 0;
}
static inline void nvme_nvm_unregister(struct nvme_ns *ns) {};
static inline int nvme_nvm_register_sysfs(struct nvme_ns *ns)
{
return 0;
}
static inline void nvme_nvm_unregister_sysfs(struct nvme_ns *ns) {};
static inline int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id)
{
return 0;
}
static inline int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd,
unsigned long arg)
{
return -ENOTTY;
}
#endif /* CONFIG_NVM */
static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
{
return dev_to_disk(dev)->private_data;
}
int __init nvme_core_init(void);
void nvme_core_exit(void);
#endif /* _NVME_H */