1
0
Fork 0

nvme: move chardev and sysfs interface to common code

For this we need to add a proper controller init routine and a list of
all controllers that is in addition to the list of PCIe controllers,
which stays in pci.c.  Note that we remove the sysfs device when the
last reference to a controller is dropped now - the old code would have
kept it around longer, which doesn't make much sense.

This requires a new ->reset_ctrl operation to implement controleller
resets, and a new ->write_reg32 operation that is required to implement
subsystem resets.  We also now store caches copied of the NVMe compliance
version and the flag if a controller is attached to a subsystem or not in
the generic controller structure now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
[Fixes for pr merge]
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
hifive-unleashed-5.1
Christoph Hellwig 2015-11-28 15:40:19 +01:00 committed by Jens Axboe
parent 5bae7f73d3
commit f3ca80fc11
4 changed files with 245 additions and 204 deletions

View File

@ -31,11 +31,19 @@
#include "nvme.h"
#define NVME_MINORS (1U << MINORBITS)
static int nvme_major;
module_param(nvme_major, int, 0);
static int nvme_char_major;
module_param(nvme_char_major, int, 0);
static LIST_HEAD(nvme_ctrl_list);
DEFINE_SPINLOCK(dev_list_lock);
static struct class *nvme_class;
static void nvme_free_ns(struct kref *kref)
{
struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref);
@ -367,7 +375,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
metadata, meta_len, io.slba, NULL, 0);
}
int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
struct nvme_passthru_cmd __user *ucmd)
{
struct nvme_passthru_cmd cmd;
@ -792,6 +800,12 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
u64 cap;
int ret, page_shift;
ret = ctrl->ops->reg_read32(ctrl, NVME_REG_VS, &ctrl->vs);
if (ret) {
dev_err(ctrl->dev, "Reading VS failed (%d)\n", ret);
return ret;
}
ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &cap);
if (ret) {
dev_err(ctrl->dev, "Reading CAP failed (%d)\n", ret);
@ -799,6 +813,9 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
}
page_shift = NVME_CAP_MPSMIN(cap) + 12;
if (ctrl->vs >= NVME_VS(1, 1))
ctrl->subsystem = NVME_CAP_NSSRC(cap);
ret = nvme_identify_ctrl(ctrl, &id);
if (ret) {
dev_err(ctrl->dev, "Identify Controller failed (%d)\n", ret);
@ -833,18 +850,85 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
return 0;
}
static void nvme_free_ctrl(struct kref *kref)
static int nvme_dev_open(struct inode *inode, struct file *file)
{
struct nvme_ctrl *ctrl = container_of(kref, struct nvme_ctrl, kref);
struct nvme_ctrl *ctrl;
int instance = iminor(inode);
int ret = -ENODEV;
ctrl->ops->free_ctrl(ctrl);
spin_lock(&dev_list_lock);
list_for_each_entry(ctrl, &nvme_ctrl_list, node) {
if (ctrl->instance != instance)
continue;
if (!ctrl->admin_q) {
ret = -EWOULDBLOCK;
break;
}
if (!kref_get_unless_zero(&ctrl->kref))
break;
file->private_data = ctrl;
ret = 0;
break;
}
spin_unlock(&dev_list_lock);
return ret;
}
void nvme_put_ctrl(struct nvme_ctrl *ctrl)
static int nvme_dev_release(struct inode *inode, struct file *file)
{
kref_put(&ctrl->kref, nvme_free_ctrl);
nvme_put_ctrl(file->private_data);
return 0;
}
static long nvme_dev_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
struct nvme_ctrl *ctrl = file->private_data;
void __user *argp = (void __user *)arg;
struct nvme_ns *ns;
switch (cmd) {
case NVME_IOCTL_ADMIN_CMD:
return nvme_user_cmd(ctrl, NULL, argp);
case NVME_IOCTL_IO_CMD:
if (list_empty(&ctrl->namespaces))
return -ENOTTY;
ns = list_first_entry(&ctrl->namespaces, struct nvme_ns, list);
return nvme_user_cmd(ctrl, ns, argp);
case NVME_IOCTL_RESET:
dev_warn(ctrl->dev, "resetting controller\n");
return ctrl->ops->reset_ctrl(ctrl);
case NVME_IOCTL_SUBSYS_RESET:
return nvme_reset_subsystem(ctrl);
default:
return -ENOTTY;
}
}
static const struct file_operations nvme_dev_fops = {
.owner = THIS_MODULE,
.open = nvme_dev_open,
.release = nvme_dev_release,
.unlocked_ioctl = nvme_dev_ioctl,
.compat_ioctl = nvme_dev_ioctl,
};
static ssize_t nvme_sysfs_reset(struct device *dev,
struct device_attribute *attr, const char *buf,
size_t count)
{
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
int ret;
ret = ctrl->ops->reset_ctrl(ctrl);
if (ret < 0)
return ret;
return count;
}
static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset);
static int ns_cmp(void *priv, struct list_head *a, struct list_head *b)
{
struct nvme_ns *nsa = container_of(a, struct nvme_ns, list);
@ -1009,6 +1093,104 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
nvme_ns_remove(ns);
}
static DEFINE_IDA(nvme_instance_ida);
static int nvme_set_instance(struct nvme_ctrl *ctrl)
{
int instance, error;
do {
if (!ida_pre_get(&nvme_instance_ida, GFP_KERNEL))
return -ENODEV;
spin_lock(&dev_list_lock);
error = ida_get_new(&nvme_instance_ida, &instance);
spin_unlock(&dev_list_lock);
} while (error == -EAGAIN);
if (error)
return -ENODEV;
ctrl->instance = instance;
return 0;
}
static void nvme_release_instance(struct nvme_ctrl *ctrl)
{
spin_lock(&dev_list_lock);
ida_remove(&nvme_instance_ida, ctrl->instance);
spin_unlock(&dev_list_lock);
}
static void nvme_free_ctrl(struct kref *kref)
{
struct nvme_ctrl *ctrl = container_of(kref, struct nvme_ctrl, kref);
spin_lock(&dev_list_lock);
list_del(&ctrl->node);
spin_unlock(&dev_list_lock);
put_device(ctrl->device);
nvme_release_instance(ctrl);
device_destroy(nvme_class, MKDEV(nvme_char_major, ctrl->instance));
ctrl->ops->free_ctrl(ctrl);
}
void nvme_put_ctrl(struct nvme_ctrl *ctrl)
{
kref_put(&ctrl->kref, nvme_free_ctrl);
}
/*
* Initialize a NVMe controller structures. This needs to be called during
* earliest initialization so that we have the initialized structured around
* during probing.
*/
int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
const struct nvme_ctrl_ops *ops, unsigned long quirks)
{
int ret;
INIT_LIST_HEAD(&ctrl->namespaces);
kref_init(&ctrl->kref);
ctrl->dev = dev;
ctrl->ops = ops;
ctrl->quirks = quirks;
ret = nvme_set_instance(ctrl);
if (ret)
goto out;
ctrl->device = device_create(nvme_class, ctrl->dev,
MKDEV(nvme_char_major, ctrl->instance),
dev, "nvme%d", ctrl->instance);
if (IS_ERR(ctrl->device)) {
ret = PTR_ERR(ctrl->device);
goto out_release_instance;
}
get_device(ctrl->device);
dev_set_drvdata(ctrl->device, ctrl);
ret = device_create_file(ctrl->device, &dev_attr_reset_controller);
if (ret)
goto out_put_device;
spin_lock(&dev_list_lock);
list_add_tail(&ctrl->node, &nvme_ctrl_list);
spin_unlock(&dev_list_lock);
return 0;
out_put_device:
put_device(ctrl->device);
device_destroy(nvme_class, MKDEV(nvme_char_major, ctrl->instance));
out_release_instance:
nvme_release_instance(ctrl);
out:
return ret;
}
int __init nvme_core_init(void)
{
int result;
@ -1019,10 +1201,31 @@ int __init nvme_core_init(void)
else if (result > 0)
nvme_major = result;
result = __register_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme",
&nvme_dev_fops);
if (result < 0)
goto unregister_blkdev;
else if (result > 0)
nvme_char_major = result;
nvme_class = class_create(THIS_MODULE, "nvme");
if (IS_ERR(nvme_class)) {
result = PTR_ERR(nvme_class);
goto unregister_chrdev;
}
return 0;
unregister_chrdev:
__unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
unregister_blkdev:
unregister_blkdev(nvme_major, "nvme");
return result;
}
void nvme_core_exit(void)
{
unregister_blkdev(nvme_major, "nvme");
class_destroy(nvme_class);
__unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
}

View File

@ -19,8 +19,6 @@
#include <linux/kref.h>
#include <linux/blk-mq.h>
struct nvme_passthru_cmd;
extern unsigned char nvme_io_timeout;
#define NVME_IO_TIMEOUT (nvme_io_timeout * HZ)
@ -56,6 +54,7 @@ struct nvme_ctrl {
struct blk_mq_tag_set *tagset;
struct list_head namespaces;
struct device *device; /* char device */
struct list_head node;
char name[12];
char serial[20];
@ -71,6 +70,8 @@ struct nvme_ctrl {
u16 abort_limit;
u8 event_limit;
u8 vwc;
u32 vs;
bool subsystem;
unsigned long quirks;
};
@ -100,6 +101,7 @@ struct nvme_ctrl_ops {
int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val);
int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
bool (*io_incapable)(struct nvme_ctrl *ctrl);
int (*reset_ctrl)(struct nvme_ctrl *ctrl);
void (*free_ctrl)(struct nvme_ctrl *ctrl);
};
@ -123,6 +125,13 @@ static inline bool nvme_io_incapable(struct nvme_ctrl *ctrl)
return val & NVME_CSTS_CFS;
}
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));
@ -194,6 +203,8 @@ static inline int nvme_error_status(u16 status)
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_put_ctrl(struct nvme_ctrl *ctrl);
int nvme_init_identify(struct nvme_ctrl *ctrl);
@ -224,9 +235,6 @@ int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
extern spinlock_t dev_list_lock;
int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
struct nvme_passthru_cmd __user *ucmd);
struct sg_io_hdr;
int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr);

View File

@ -38,15 +38,11 @@
#include <linux/slab.h>
#include <linux/t10-pi.h>
#include <linux/types.h>
#include <linux/pr.h>
#include <scsi/sg.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <asm/unaligned.h>
#include <uapi/linux/nvme_ioctl.h>
#include "nvme.h"
#define NVME_MINORS (1U << MINORBITS)
#define NVME_Q_DEPTH 1024
#define NVME_AQ_DEPTH 256
#define SQ_SIZE(depth) (depth * sizeof(struct nvme_command))
@ -64,9 +60,6 @@ unsigned char shutdown_timeout = 5;
module_param(shutdown_timeout, byte, 0644);
MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown");
static int nvme_char_major;
module_param(nvme_char_major, int, 0);
static int use_threaded_interrupts;
module_param(use_threaded_interrupts, int, 0);
@ -79,8 +72,6 @@ static struct task_struct *nvme_thread;
static struct workqueue_struct *nvme_workq;
static wait_queue_head_t nvme_kthread_wait;
static struct class *nvme_class;
struct nvme_dev;
struct nvme_queue;
struct nvme_iod;
@ -1505,15 +1496,6 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
return result;
}
static int nvme_subsys_reset(struct nvme_dev *dev)
{
if (!dev->subsystem)
return -ENOTTY;
writel(0x4E564D65, dev->bar + NVME_REG_NSSR); /* "NVMe" */
return 0;
}
static int nvme_kthread(void *data)
{
struct nvme_dev *dev, *next;
@ -2113,42 +2095,11 @@ static void nvme_release_prp_pools(struct nvme_dev *dev)
dma_pool_destroy(dev->prp_small_pool);
}
static DEFINE_IDA(nvme_instance_ida);
static int nvme_set_instance(struct nvme_dev *dev)
{
int instance, error;
do {
if (!ida_pre_get(&nvme_instance_ida, GFP_KERNEL))
return -ENODEV;
spin_lock(&dev_list_lock);
error = ida_get_new(&nvme_instance_ida, &instance);
spin_unlock(&dev_list_lock);
} while (error == -EAGAIN);
if (error)
return -ENODEV;
dev->ctrl.instance = instance;
return 0;
}
static void nvme_release_instance(struct nvme_dev *dev)
{
spin_lock(&dev_list_lock);
ida_remove(&nvme_instance_ida, dev->ctrl.instance);
spin_unlock(&dev_list_lock);
}
static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
{
struct nvme_dev *dev = to_nvme_dev(ctrl);
put_device(dev->dev);
put_device(ctrl->device);
nvme_release_instance(dev);
if (dev->tagset.tags)
blk_mq_free_tag_set(&dev->tagset);
if (dev->ctrl.admin_q)
@ -2158,69 +2109,6 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
kfree(dev);
}
static int nvme_dev_open(struct inode *inode, struct file *f)
{
struct nvme_dev *dev;
int instance = iminor(inode);
int ret = -ENODEV;
spin_lock(&dev_list_lock);
list_for_each_entry(dev, &dev_list, node) {
if (dev->ctrl.instance == instance) {
if (!dev->ctrl.admin_q) {
ret = -EWOULDBLOCK;
break;
}
if (!kref_get_unless_zero(&dev->ctrl.kref))
break;
f->private_data = dev;
ret = 0;
break;
}
}
spin_unlock(&dev_list_lock);
return ret;
}
static int nvme_dev_release(struct inode *inode, struct file *f)
{
struct nvme_dev *dev = f->private_data;
nvme_put_ctrl(&dev->ctrl);
return 0;
}
static long nvme_dev_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
{
struct nvme_dev *dev = f->private_data;
struct nvme_ns *ns;
switch (cmd) {
case NVME_IOCTL_ADMIN_CMD:
return nvme_user_cmd(&dev->ctrl, NULL, (void __user *)arg);
case NVME_IOCTL_IO_CMD:
if (list_empty(&dev->ctrl.namespaces))
return -ENOTTY;
ns = list_first_entry(&dev->ctrl.namespaces, struct nvme_ns, list);
return nvme_user_cmd(&dev->ctrl, ns, (void __user *)arg);
case NVME_IOCTL_RESET:
dev_warn(dev->dev, "resetting controller\n");
return nvme_reset(dev);
case NVME_IOCTL_SUBSYS_RESET:
return nvme_subsys_reset(dev);
default:
return -ENOTTY;
}
}
static const struct file_operations nvme_dev_fops = {
.owner = THIS_MODULE,
.open = nvme_dev_open,
.release = nvme_dev_release,
.unlocked_ioctl = nvme_dev_ioctl,
.compat_ioctl = nvme_dev_ioctl,
};
static void nvme_probe_work(struct work_struct *work)
{
struct nvme_dev *dev = container_of(work, struct nvme_dev, probe_work);
@ -2372,21 +2260,6 @@ static int nvme_reset(struct nvme_dev *dev)
return ret;
}
static ssize_t nvme_sysfs_reset(struct device *dev,
struct device_attribute *attr, const char *buf,
size_t count)
{
struct nvme_dev *ndev = dev_get_drvdata(dev);
int ret;
ret = nvme_reset(ndev);
if (ret < 0)
return ret;
return count;
}
static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset);
static int nvme_pci_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
{
*val = readl(to_nvme_dev(ctrl)->bar + off);
@ -2412,11 +2285,17 @@ static bool nvme_pci_io_incapable(struct nvme_ctrl *ctrl)
return !dev->bar || dev->online_queues < 2;
}
static int nvme_pci_reset_ctrl(struct nvme_ctrl *ctrl)
{
return nvme_reset(to_nvme_dev(ctrl));
}
static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
.reg_read32 = nvme_pci_reg_read32,
.reg_write32 = nvme_pci_reg_write32,
.reg_read64 = nvme_pci_reg_read64,
.io_incapable = nvme_pci_io_incapable,
.reset_ctrl = nvme_pci_reset_ctrl,
.free_ctrl = nvme_pci_free_ctrl,
};
@ -2441,51 +2320,28 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (!dev->queues)
goto free;
INIT_LIST_HEAD(&dev->ctrl.namespaces);
INIT_WORK(&dev->reset_work, nvme_reset_work);
dev->dev = get_device(&pdev->dev);
pci_set_drvdata(pdev, dev);
dev->ctrl.ops = &nvme_pci_ctrl_ops;
dev->ctrl.dev = dev->dev;
dev->ctrl.quirks = id->driver_data;
result = nvme_set_instance(dev);
if (result)
goto put_pci;
result = nvme_setup_prp_pools(dev);
if (result)
goto release;
kref_init(&dev->ctrl.kref);
dev->ctrl.device = device_create(nvme_class, &pdev->dev,
MKDEV(nvme_char_major, dev->ctrl.instance),
dev, "nvme%d", dev->ctrl.instance);
if (IS_ERR(dev->ctrl.device)) {
result = PTR_ERR(dev->ctrl.device);
goto release_pools;
}
get_device(dev->ctrl.device);
dev_set_drvdata(dev->ctrl.device, dev);
result = device_create_file(dev->ctrl.device, &dev_attr_reset_controller);
if (result)
goto put_dev;
INIT_LIST_HEAD(&dev->node);
INIT_WORK(&dev->scan_work, nvme_dev_scan);
INIT_WORK(&dev->probe_work, nvme_probe_work);
INIT_WORK(&dev->reset_work, nvme_reset_work);
result = nvme_setup_prp_pools(dev);
if (result)
goto put_pci;
result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
id->driver_data);
if (result)
goto release_pools;
schedule_work(&dev->probe_work);
return 0;
put_dev:
device_destroy(nvme_class, MKDEV(nvme_char_major, dev->ctrl.instance));
put_device(dev->ctrl.device);
release_pools:
nvme_release_prp_pools(dev);
release:
nvme_release_instance(dev);
put_pci:
put_device(dev->dev);
free:
@ -2523,11 +2379,9 @@ static void nvme_remove(struct pci_dev *pdev)
flush_work(&dev->probe_work);
flush_work(&dev->reset_work);
flush_work(&dev->scan_work);
device_remove_file(dev->ctrl.device, &dev_attr_reset_controller);
nvme_remove_namespaces(&dev->ctrl);
nvme_dev_shutdown(dev);
nvme_dev_remove_admin(dev);
device_destroy(nvme_class, MKDEV(nvme_char_major, dev->ctrl.instance));
nvme_free_queues(dev, 0);
nvme_release_cmb(dev);
nvme_release_prp_pools(dev);
@ -2610,29 +2464,12 @@ static int __init nvme_init(void)
if (result < 0)
goto kill_workq;
result = __register_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme",
&nvme_dev_fops);
if (result < 0)
goto unregister_blkdev;
else if (result > 0)
nvme_char_major = result;
nvme_class = class_create(THIS_MODULE, "nvme");
if (IS_ERR(nvme_class)) {
result = PTR_ERR(nvme_class);
goto unregister_chrdev;
}
result = pci_register_driver(&nvme_driver);
if (result)
goto destroy_class;
goto core_exit;
return 0;
destroy_class:
class_destroy(nvme_class);
unregister_chrdev:
__unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
unregister_blkdev:
core_exit:
nvme_core_exit();
kill_workq:
destroy_workqueue(nvme_workq);
@ -2644,8 +2481,6 @@ static void __exit nvme_exit(void)
pci_unregister_driver(&nvme_driver);
nvme_core_exit();
destroy_workqueue(nvme_workq);
class_destroy(nvme_class);
__unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
BUG_ON(nvme_thread && !IS_ERR(nvme_thread));
_nvme_check_size();
}

View File

@ -600,7 +600,7 @@ static int nvme_trans_unit_serial_page(struct nvme_ns *ns,
}
static int nvme_fill_device_id_eui64(struct nvme_ns *ns, struct sg_io_hdr *hdr,
u8 *inq_response, int alloc_len, u32 vs)
u8 *inq_response, int alloc_len)
{
struct nvme_id_ns *id_ns;
int nvme_sc, res;
@ -615,7 +615,7 @@ static int nvme_fill_device_id_eui64(struct nvme_ns *ns, struct sg_io_hdr *hdr,
eui = id_ns->eui64;
len = sizeof(id_ns->eui64);
if (vs >= NVME_VS(1, 2)) {
if (ns->ctrl->vs >= NVME_VS(1, 2)) {
if (bitmap_empty(eui, len * 8)) {
eui = id_ns->nguid;
len = sizeof(id_ns->nguid);
@ -687,14 +687,9 @@ static int nvme_trans_device_id_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
u8 *resp, int alloc_len)
{
int res;
u32 vs;
res = ns->ctrl->ops->reg_read32(ns->ctrl, NVME_REG_VS, &vs);
if (res)
return res;
if (vs >= NVME_VS(1, 1)) {
res = nvme_fill_device_id_eui64(ns, hdr, resp, alloc_len, vs);
if (ns->ctrl->vs >= NVME_VS(1, 1)) {
res = nvme_fill_device_id_eui64(ns, hdr, resp, alloc_len);
if (res != -EOPNOTSUPP)
return res;
}