OpenCloudOS-Kernel/include/linux/nvme.h

180 lines
5.1 KiB
C
Raw Normal View History

/*
* Definitions for the NVM Express interface
* 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 _LINUX_NVME_H
#define _LINUX_NVME_H
#include <uapi/linux/nvme.h>
#include <linux/pci.h>
#include <linux/miscdevice.h>
#include <linux/kref.h>
NVMe: Convert to blk-mq This converts the NVMe driver to a blk-mq request-based driver. The NVMe driver is currently bio-based and implements queue logic within itself. By using blk-mq, a lot of these responsibilities can be moved and simplified. The patch is divided into the following blocks: * Per-command data and cmdid have been moved into the struct request field. The cmdid_data can be retrieved using blk_mq_rq_to_pdu() and id maintenance are now handled by blk-mq through the rq->tag field. * The logic for splitting bio's has been moved into the blk-mq layer. The driver instead notifies the block layer about limited gap support in SG lists. * blk-mq handles timeouts and is reimplemented within nvme_timeout(). This both includes abort handling and command cancelation. * Assignment of nvme queues to CPUs are replaced with the blk-mq version. The current blk-mq strategy is to assign the number of mapped queues and CPUs to provide synergy, while the nvme driver assign as many nvme hw queues as possible. This can be implemented in blk-mq if needed. * NVMe queues are merged with the tags structure of blk-mq. * blk-mq takes care of setup/teardown of nvme queues and guards invalid accesses. Therefore, RCU-usage for nvme queues can be removed. * IO tracing and accounting are handled by blk-mq and therefore removed. * Queue suspension logic is replaced with the logic from the block layer. Contributions in this patch from: Sam Bradshaw <sbradshaw@micron.com> Jens Axboe <axboe@fb.com> Keith Busch <keith.busch@intel.com> Robert Nelson <rlnelson@google.com> Acked-by: Keith Busch <keith.busch@intel.com> Acked-by: Jens Axboe <axboe@fb.com> Updated for new ->queue_rq() prototype. Signed-off-by: Jens Axboe <axboe@fb.com>
2014-11-04 23:20:14 +08:00
#include <linux/blk-mq.h>
struct nvme_bar {
__u64 cap; /* Controller Capabilities */
__u32 vs; /* Version */
__u32 intms; /* Interrupt Mask Set */
__u32 intmc; /* Interrupt Mask Clear */
__u32 cc; /* Controller Configuration */
__u32 rsvd1; /* Reserved */
__u32 csts; /* Controller Status */
__u32 rsvd2; /* Reserved */
__u32 aqa; /* Admin Queue Attributes */
__u64 asq; /* Admin SQ Base Address */
__u64 acq; /* Admin CQ Base Address */
};
#define NVME_CAP_MQES(cap) ((cap) & 0xffff)
#define NVME_CAP_TIMEOUT(cap) (((cap) >> 24) & 0xff)
#define NVME_CAP_STRIDE(cap) (((cap) >> 32) & 0xf)
#define NVME_CAP_MPSMIN(cap) (((cap) >> 48) & 0xf)
#define NVME_CAP_MPSMAX(cap) (((cap) >> 52) & 0xf)
enum {
NVME_CC_ENABLE = 1 << 0,
NVME_CC_CSS_NVM = 0 << 4,
NVME_CC_MPS_SHIFT = 7,
NVME_CC_ARB_RR = 0 << 11,
NVME_CC_ARB_WRRU = 1 << 11,
NVME_CC_ARB_VS = 7 << 11,
NVME_CC_SHN_NONE = 0 << 14,
NVME_CC_SHN_NORMAL = 1 << 14,
NVME_CC_SHN_ABRUPT = 2 << 14,
NVME_CC_SHN_MASK = 3 << 14,
NVME_CC_IOSQES = 6 << 16,
NVME_CC_IOCQES = 4 << 20,
NVME_CSTS_RDY = 1 << 0,
NVME_CSTS_CFS = 1 << 1,
NVME_CSTS_SHST_NORMAL = 0 << 2,
NVME_CSTS_SHST_OCCUR = 1 << 2,
NVME_CSTS_SHST_CMPLT = 2 << 2,
NVME_CSTS_SHST_MASK = 3 << 2,
};
extern unsigned char nvme_io_timeout;
#define NVME_IO_TIMEOUT (nvme_io_timeout * HZ)
/*
* Represents an NVM Express device. Each nvme_dev is a PCI function.
*/
struct nvme_dev {
struct list_head node;
NVMe: Convert to blk-mq This converts the NVMe driver to a blk-mq request-based driver. The NVMe driver is currently bio-based and implements queue logic within itself. By using blk-mq, a lot of these responsibilities can be moved and simplified. The patch is divided into the following blocks: * Per-command data and cmdid have been moved into the struct request field. The cmdid_data can be retrieved using blk_mq_rq_to_pdu() and id maintenance are now handled by blk-mq through the rq->tag field. * The logic for splitting bio's has been moved into the blk-mq layer. The driver instead notifies the block layer about limited gap support in SG lists. * blk-mq handles timeouts and is reimplemented within nvme_timeout(). This both includes abort handling and command cancelation. * Assignment of nvme queues to CPUs are replaced with the blk-mq version. The current blk-mq strategy is to assign the number of mapped queues and CPUs to provide synergy, while the nvme driver assign as many nvme hw queues as possible. This can be implemented in blk-mq if needed. * NVMe queues are merged with the tags structure of blk-mq. * blk-mq takes care of setup/teardown of nvme queues and guards invalid accesses. Therefore, RCU-usage for nvme queues can be removed. * IO tracing and accounting are handled by blk-mq and therefore removed. * Queue suspension logic is replaced with the logic from the block layer. Contributions in this patch from: Sam Bradshaw <sbradshaw@micron.com> Jens Axboe <axboe@fb.com> Keith Busch <keith.busch@intel.com> Robert Nelson <rlnelson@google.com> Acked-by: Keith Busch <keith.busch@intel.com> Acked-by: Jens Axboe <axboe@fb.com> Updated for new ->queue_rq() prototype. Signed-off-by: Jens Axboe <axboe@fb.com>
2014-11-04 23:20:14 +08:00
struct nvme_queue **queues;
struct request_queue *admin_q;
struct blk_mq_tag_set tagset;
struct blk_mq_tag_set admin_tagset;
u32 __iomem *dbs;
struct pci_dev *pci_dev;
struct dma_pool *prp_page_pool;
struct dma_pool *prp_small_pool;
int instance;
unsigned queue_count;
unsigned online_queues;
unsigned max_qid;
int q_depth;
u32 db_stride;
u32 ctrl_config;
struct msix_entry *entry;
struct nvme_bar __iomem *bar;
struct list_head namespaces;
struct kref kref;
struct miscdevice miscdev;
work_func_t reset_workfn;
struct work_struct reset_work;
char name[12];
char serial[20];
char model[40];
char firmware_rev[8];
u32 max_hw_sectors;
u32 stripe_size;
u32 page_size;
u16 oncs;
u16 abort_limit;
u8 event_limit;
u8 vwc;
u8 initialized;
};
/*
* An NVM Express namespace is equivalent to a SCSI LUN
*/
struct nvme_ns {
struct list_head list;
struct nvme_dev *dev;
struct request_queue *queue;
struct gendisk *disk;
unsigned ns_id;
int lba_shift;
int ms;
NVMe: Metadata format support Adds support for NVMe metadata formats and exposes block devices for all namespaces regardless of their format. Namespace formats that are unusable will have disk capacity set to 0, but a handle to the block device is created to simplify device management. A namespace is not usable when the format requires host interleave block and metadata in single buffer, has no provisioned storage, or has better data but failed to register with blk integrity. The namespace has to be scanned in two phases to support separate metadata formats. The first establishes the sector size and capacity prior to invoking add_disk. If metadata is required, the capacity will be temporarilly set to 0 until it can be revalidated and registered with the integrity extenstions after add_disk completes. The driver relies on the integrity extensions to provide the metadata buffer. NVMe requires this be a single physically contiguous region, so only one integrity segment is allowed per command. If the metadata is used for T10 PI, the driver provides mappings to save and restore the reftag physical block translation. The driver provides no-op functions for generate and verify if metadata is not used for protection information. This way the setup is always provided by the block layer. If a request does not supply a required metadata buffer, the command is failed with bad address. This could only happen if a user manually disables verify/generate on such a disk. The only exception to where this is okay is if the controller is capable of stripping/generating the metadata, which is possible on some types of formats. The metadata scatter gather list now occupies the spot in the nvme_iod that used to be used to link retryable IOD's, but we don't do that anymore, so the field was unused. Signed-off-by: Keith Busch <keith.busch@intel.com>
2015-02-20 04:39:03 +08:00
int pi_type;
u64 mode_select_num_blocks;
u32 mode_select_block_len;
};
/*
* The nvme_iod describes the data in an I/O, including the list of PRP
* entries. You can't see it in this data structure because C doesn't let
* me express that. Use nvme_alloc_iod to ensure there's enough space
* allocated to store the PRP list.
*/
struct nvme_iod {
unsigned long private; /* For the use of the submitter of the I/O */
int npages; /* In the PRP list. 0 means small pool in use */
int offset; /* Of PRP list */
int nents; /* Used in scatterlist */
int length; /* Of data, in bytes */
dma_addr_t first_dma;
NVMe: Metadata format support Adds support for NVMe metadata formats and exposes block devices for all namespaces regardless of their format. Namespace formats that are unusable will have disk capacity set to 0, but a handle to the block device is created to simplify device management. A namespace is not usable when the format requires host interleave block and metadata in single buffer, has no provisioned storage, or has better data but failed to register with blk integrity. The namespace has to be scanned in two phases to support separate metadata formats. The first establishes the sector size and capacity prior to invoking add_disk. If metadata is required, the capacity will be temporarilly set to 0 until it can be revalidated and registered with the integrity extenstions after add_disk completes. The driver relies on the integrity extensions to provide the metadata buffer. NVMe requires this be a single physically contiguous region, so only one integrity segment is allowed per command. If the metadata is used for T10 PI, the driver provides mappings to save and restore the reftag physical block translation. The driver provides no-op functions for generate and verify if metadata is not used for protection information. This way the setup is always provided by the block layer. If a request does not supply a required metadata buffer, the command is failed with bad address. This could only happen if a user manually disables verify/generate on such a disk. The only exception to where this is okay is if the controller is capable of stripping/generating the metadata, which is possible on some types of formats. The metadata scatter gather list now occupies the spot in the nvme_iod that used to be used to link retryable IOD's, but we don't do that anymore, so the field was unused. Signed-off-by: Keith Busch <keith.busch@intel.com>
2015-02-20 04:39:03 +08:00
struct scatterlist meta_sg[1]; /* metadata requires single contiguous buffer */
struct scatterlist sg[0];
};
static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector)
{
return (sector >> (ns->lba_shift - 9));
}
/**
* nvme_free_iod - frees an nvme_iod
* @dev: The device that the I/O was submitted to
* @iod: The memory to free
*/
void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod);
NVMe: Convert to blk-mq This converts the NVMe driver to a blk-mq request-based driver. The NVMe driver is currently bio-based and implements queue logic within itself. By using blk-mq, a lot of these responsibilities can be moved and simplified. The patch is divided into the following blocks: * Per-command data and cmdid have been moved into the struct request field. The cmdid_data can be retrieved using blk_mq_rq_to_pdu() and id maintenance are now handled by blk-mq through the rq->tag field. * The logic for splitting bio's has been moved into the blk-mq layer. The driver instead notifies the block layer about limited gap support in SG lists. * blk-mq handles timeouts and is reimplemented within nvme_timeout(). This both includes abort handling and command cancelation. * Assignment of nvme queues to CPUs are replaced with the blk-mq version. The current blk-mq strategy is to assign the number of mapped queues and CPUs to provide synergy, while the nvme driver assign as many nvme hw queues as possible. This can be implemented in blk-mq if needed. * NVMe queues are merged with the tags structure of blk-mq. * blk-mq takes care of setup/teardown of nvme queues and guards invalid accesses. Therefore, RCU-usage for nvme queues can be removed. * IO tracing and accounting are handled by blk-mq and therefore removed. * Queue suspension logic is replaced with the logic from the block layer. Contributions in this patch from: Sam Bradshaw <sbradshaw@micron.com> Jens Axboe <axboe@fb.com> Keith Busch <keith.busch@intel.com> Robert Nelson <rlnelson@google.com> Acked-by: Keith Busch <keith.busch@intel.com> Acked-by: Jens Axboe <axboe@fb.com> Updated for new ->queue_rq() prototype. Signed-off-by: Jens Axboe <axboe@fb.com>
2014-11-04 23:20:14 +08:00
int nvme_setup_prps(struct nvme_dev *, struct nvme_iod *, int, gfp_t);
struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
unsigned long addr, unsigned length);
void nvme_unmap_user_pages(struct nvme_dev *dev, int write,
struct nvme_iod *iod);
NVMe: Convert to blk-mq This converts the NVMe driver to a blk-mq request-based driver. The NVMe driver is currently bio-based and implements queue logic within itself. By using blk-mq, a lot of these responsibilities can be moved and simplified. The patch is divided into the following blocks: * Per-command data and cmdid have been moved into the struct request field. The cmdid_data can be retrieved using blk_mq_rq_to_pdu() and id maintenance are now handled by blk-mq through the rq->tag field. * The logic for splitting bio's has been moved into the blk-mq layer. The driver instead notifies the block layer about limited gap support in SG lists. * blk-mq handles timeouts and is reimplemented within nvme_timeout(). This both includes abort handling and command cancelation. * Assignment of nvme queues to CPUs are replaced with the blk-mq version. The current blk-mq strategy is to assign the number of mapped queues and CPUs to provide synergy, while the nvme driver assign as many nvme hw queues as possible. This can be implemented in blk-mq if needed. * NVMe queues are merged with the tags structure of blk-mq. * blk-mq takes care of setup/teardown of nvme queues and guards invalid accesses. Therefore, RCU-usage for nvme queues can be removed. * IO tracing and accounting are handled by blk-mq and therefore removed. * Queue suspension logic is replaced with the logic from the block layer. Contributions in this patch from: Sam Bradshaw <sbradshaw@micron.com> Jens Axboe <axboe@fb.com> Keith Busch <keith.busch@intel.com> Robert Nelson <rlnelson@google.com> Acked-by: Keith Busch <keith.busch@intel.com> Acked-by: Jens Axboe <axboe@fb.com> Updated for new ->queue_rq() prototype. Signed-off-by: Jens Axboe <axboe@fb.com>
2014-11-04 23:20:14 +08:00
int nvme_submit_io_cmd(struct nvme_dev *, struct nvme_ns *,
struct nvme_command *, u32 *);
int nvme_submit_flush_data(struct nvme_queue *nvmeq, struct nvme_ns *ns);
int nvme_submit_admin_cmd(struct nvme_dev *, struct nvme_command *,
u32 *result);
int nvme_identify(struct nvme_dev *, unsigned nsid, unsigned cns,
dma_addr_t dma_addr);
int nvme_get_features(struct nvme_dev *dev, unsigned fid, unsigned nsid,
dma_addr_t dma_addr, u32 *result);
int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11,
dma_addr_t dma_addr, u32 *result);
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);
#endif /* _LINUX_NVME_H */