drivers/nvme/host/core.c

/*
 * NVM Express device driver
 * 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.
 */

#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/errno.h>
#include <linux/hdreg.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/pr.h>
#include <linux/ptrace.h>
#include <linux/nvme_ioctl.h>
#include <linux/t10-pi.h>
#include <scsi/sg.h>
#include <asm/unaligned.h>

#include "nvme.h"

DEFINE_SPINLOCK(dev_list_lock);

static void nvme_free_ns(struct kref *kref)
{
	struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref);

	if (ns->type == NVME_NS_LIGHTNVM)
		nvme_nvm_unregister(ns->queue, ns->disk->disk_name);

	spin_lock(&dev_list_lock);
	ns->disk->private_data = NULL;
	spin_unlock(&dev_list_lock);

	nvme_put_ctrl(ns->ctrl);
	put_disk(ns->disk);
	kfree(ns);
}

void nvme_put_ns(struct nvme_ns *ns)
{
	kref_put(&ns->kref, nvme_free_ns);
}

static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk)
{
	struct nvme_ns *ns;

	spin_lock(&dev_list_lock);
	ns = disk->private_data;
	if (ns && !kref_get_unless_zero(&ns->kref))
		ns = NULL;
	spin_unlock(&dev_list_lock);

	return ns;
}

struct request *nvme_alloc_request(struct request_queue *q,
		struct nvme_command *cmd, unsigned int flags)
{
	bool write = cmd->common.opcode & 1;
	struct request *req;

	req = blk_mq_alloc_request(q, write, flags);
	if (IS_ERR(req))
		return req;

	req->cmd_type = REQ_TYPE_DRV_PRIV;
	req->cmd_flags |= REQ_FAILFAST_DRIVER;
	req->__data_len = 0;
	req->__sector = (sector_t) -1;
	req->bio = req->biotail = NULL;

	req->cmd = (unsigned char *)cmd;
	req->cmd_len = sizeof(struct nvme_command);
	req->special = (void *)0;

	return req;
}

/*
 * Returns 0 on success.  If the result is negative, it's a Linux error code;
 * if the result is positive, it's an NVM Express status code
 */
int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
		void *buffer, unsigned bufflen, u32 *result, unsigned timeout)
{
	struct request *req;
	int ret;

	req = nvme_alloc_request(q, cmd, 0);
	if (IS_ERR(req))
		return PTR_ERR(req);

	req->timeout = timeout ? timeout : ADMIN_TIMEOUT;

	if (buffer && bufflen) {
		ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL);
		if (ret)
			goto out;
	}

	blk_execute_rq(req->q, NULL, req, 0);
	if (result)
		*result = (u32)(uintptr_t)req->special;
	ret = req->errors;
 out:
	blk_mq_free_request(req);
	return ret;
}

int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
		void *buffer, unsigned bufflen)
{
	return __nvme_submit_sync_cmd(q, cmd, buffer, bufflen, NULL, 0);
}

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)
{
	bool write = cmd->common.opcode & 1;
	struct nvme_ns *ns = q->queuedata;
	struct gendisk *disk = ns ? ns->disk : NULL;
	struct request *req;
	struct bio *bio = NULL;
	void *meta = NULL;
	int ret;

	req = nvme_alloc_request(q, cmd, 0);
	if (IS_ERR(req))
		return PTR_ERR(req);

	req->timeout = timeout ? timeout : ADMIN_TIMEOUT;

	if (ubuffer && bufflen) {
		ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen,
				GFP_KERNEL);
		if (ret)
			goto out;
		bio = req->bio;

		if (!disk)
			goto submit;
		bio->bi_bdev = bdget_disk(disk, 0);
		if (!bio->bi_bdev) {
			ret = -ENODEV;
			goto out_unmap;
		}

		if (meta_buffer) {
			struct bio_integrity_payload *bip;

			meta = kmalloc(meta_len, GFP_KERNEL);
			if (!meta) {
				ret = -ENOMEM;
				goto out_unmap;
			}

			if (write) {
				if (copy_from_user(meta, meta_buffer,
						meta_len)) {
					ret = -EFAULT;
					goto out_free_meta;
				}
			}

			bip = bio_integrity_alloc(bio, GFP_KERNEL, 1);
			if (!bip) {
				ret = -ENOMEM;
				goto out_free_meta;
			}

			bip->bip_iter.bi_size = meta_len;
			bip->bip_iter.bi_sector = meta_seed;

			ret = bio_integrity_add_page(bio, virt_to_page(meta),
					meta_len, offset_in_page(meta));
			if (ret != meta_len) {
				ret = -ENOMEM;
				goto out_free_meta;
			}
		}
	}
 submit:
	blk_execute_rq(req->q, disk, req, 0);
	ret = req->errors;
	if (result)
		*result = (u32)(uintptr_t)req->special;
	if (meta && !ret && !write) {
		if (copy_to_user(meta_buffer, meta, meta_len))
			ret = -EFAULT;
	}
 out_free_meta:
	kfree(meta);
 out_unmap:
	if (bio) {
		if (disk && bio->bi_bdev)
			bdput(bio->bi_bdev);
		blk_rq_unmap_user(bio);
	}
 out:
	blk_mq_free_request(req);
	return ret;
}

int nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
		void __user *ubuffer, unsigned bufflen, u32 *result,
		unsigned timeout)
{
	return __nvme_submit_user_cmd(q, cmd, ubuffer, bufflen, NULL, 0, 0,
			result, timeout);
}

int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
{
	struct nvme_command c = { };
	int error;

	/* gcc-4.4.4 (at least) has issues with initializers and anon unions */
	c.identify.opcode = nvme_admin_identify;
	c.identify.cns = cpu_to_le32(1);

	*id = kmalloc(sizeof(struct nvme_id_ctrl), GFP_KERNEL);
	if (!*id)
		return -ENOMEM;

	error = nvme_submit_sync_cmd(dev->admin_q, &c, *id,
			sizeof(struct nvme_id_ctrl));
	if (error)
		kfree(*id);
	return error;
}

int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid,
		struct nvme_id_ns **id)
{
	struct nvme_command c = { };
	int error;

	/* gcc-4.4.4 (at least) has issues with initializers and anon unions */
	c.identify.opcode = nvme_admin_identify,
	c.identify.nsid = cpu_to_le32(nsid),

	*id = kmalloc(sizeof(struct nvme_id_ns), GFP_KERNEL);
	if (!*id)
		return -ENOMEM;

	error = nvme_submit_sync_cmd(dev->admin_q, &c, *id,
			sizeof(struct nvme_id_ns));
	if (error)
		kfree(*id);
	return error;
}

int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid,
					dma_addr_t dma_addr, u32 *result)
{
	struct nvme_command c;

	memset(&c, 0, sizeof(c));
	c.features.opcode = nvme_admin_get_features;
	c.features.nsid = cpu_to_le32(nsid);
	c.features.prp1 = cpu_to_le64(dma_addr);
	c.features.fid = cpu_to_le32(fid);

	return __nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0, result, 0);
}

int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
					dma_addr_t dma_addr, u32 *result)
{
	struct nvme_command c;

	memset(&c, 0, sizeof(c));
	c.features.opcode = nvme_admin_set_features;
	c.features.prp1 = cpu_to_le64(dma_addr);
	c.features.fid = cpu_to_le32(fid);
	c.features.dword11 = cpu_to_le32(dword11);

	return __nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0, result, 0);
}

int nvme_get_log_page(struct nvme_ctrl *dev, struct nvme_smart_log **log)
{
	struct nvme_command c = { };
	int error;

	c.common.opcode = nvme_admin_get_log_page,
	c.common.nsid = cpu_to_le32(0xFFFFFFFF),
	c.common.cdw10[0] = cpu_to_le32(
			(((sizeof(struct nvme_smart_log) / 4) - 1) << 16) |
			 NVME_LOG_SMART),

	*log = kmalloc(sizeof(struct nvme_smart_log), GFP_KERNEL);
	if (!*log)
		return -ENOMEM;

	error = nvme_submit_sync_cmd(dev->admin_q, &c, *log,
			sizeof(struct nvme_smart_log));
	if (error)
		kfree(*log);
	return error;
}

static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
{
	struct nvme_user_io io;
	struct nvme_command c;
	unsigned length, meta_len;
	void __user *metadata;

	if (copy_from_user(&io, uio, sizeof(io)))
		return -EFAULT;

	switch (io.opcode) {
	case nvme_cmd_write:
	case nvme_cmd_read:
	case nvme_cmd_compare:
		break;
	default:
		return -EINVAL;
	}

	length = (io.nblocks + 1) << ns->lba_shift;
	meta_len = (io.nblocks + 1) * ns->ms;
	metadata = (void __user *)(uintptr_t)io.metadata;

	if (ns->ext) {
		length += meta_len;
		meta_len = 0;
	} else if (meta_len) {
		if ((io.metadata & 3) || !io.metadata)
			return -EINVAL;
	}

	memset(&c, 0, sizeof(c));
	c.rw.opcode = io.opcode;
	c.rw.flags = io.flags;
	c.rw.nsid = cpu_to_le32(ns->ns_id);
	c.rw.slba = cpu_to_le64(io.slba);
	c.rw.length = cpu_to_le16(io.nblocks);
	c.rw.control = cpu_to_le16(io.control);
	c.rw.dsmgmt = cpu_to_le32(io.dsmgmt);
	c.rw.reftag = cpu_to_le32(io.reftag);
	c.rw.apptag = cpu_to_le16(io.apptag);
	c.rw.appmask = cpu_to_le16(io.appmask);

	return __nvme_submit_user_cmd(ns->queue, &c,
			(void __user *)(uintptr_t)io.addr, length,
			metadata, meta_len, io.slba, NULL, 0);
}

int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
			struct nvme_passthru_cmd __user *ucmd)
{
	struct nvme_passthru_cmd cmd;
	struct nvme_command c;
	unsigned timeout = 0;
	int status;

	if (!capable(CAP_SYS_ADMIN))
		return -EACCES;
	if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
		return -EFAULT;

	memset(&c, 0, sizeof(c));
	c.common.opcode = cmd.opcode;
	c.common.flags = cmd.flags;
	c.common.nsid = cpu_to_le32(cmd.nsid);
	c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
	c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
	c.common.cdw10[0] = cpu_to_le32(cmd.cdw10);
	c.common.cdw10[1] = cpu_to_le32(cmd.cdw11);
	c.common.cdw10[2] = cpu_to_le32(cmd.cdw12);
	c.common.cdw10[3] = cpu_to_le32(cmd.cdw13);
	c.common.cdw10[4] = cpu_to_le32(cmd.cdw14);
	c.common.cdw10[5] = cpu_to_le32(cmd.cdw15);

	if (cmd.timeout_ms)
		timeout = msecs_to_jiffies(cmd.timeout_ms);

	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
			(void __user *)cmd.addr, cmd.data_len,
			&cmd.result, timeout);
	if (status >= 0) {
		if (put_user(cmd.result, &ucmd->result))
			return -EFAULT;
	}

	return status;
}

static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
		unsigned int cmd, unsigned long arg)
{
	struct nvme_ns *ns = bdev->bd_disk->private_data;

	switch (cmd) {
	case NVME_IOCTL_ID:
		force_successful_syscall_return();
		return ns->ns_id;
	case NVME_IOCTL_ADMIN_CMD:
		return nvme_user_cmd(ns->ctrl, NULL, (void __user *)arg);
	case NVME_IOCTL_IO_CMD:
		return nvme_user_cmd(ns->ctrl, ns, (void __user *)arg);
	case NVME_IOCTL_SUBMIT_IO:
		return nvme_submit_io(ns, (void __user *)arg);
	case SG_GET_VERSION_NUM:
		return nvme_sg_get_version_num((void __user *)arg);
	case SG_IO:
		return nvme_sg_io(ns, (void __user *)arg);
	default:
		return -ENOTTY;
	}
}

#ifdef CONFIG_COMPAT
static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
			unsigned int cmd, unsigned long arg)
{
	switch (cmd) {
	case SG_IO:
		return -ENOIOCTLCMD;
	}
	return nvme_ioctl(bdev, mode, cmd, arg);
}
#else
#define nvme_compat_ioctl	NULL
#endif

static int nvme_open(struct block_device *bdev, fmode_t mode)
{
	return nvme_get_ns_from_disk(bdev->bd_disk) ? 0 : -ENXIO;
}

static void nvme_release(struct gendisk *disk, fmode_t mode)
{
	nvme_put_ns(disk->private_data);
}

static int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
{
	/* some standard values */
	geo->heads = 1 << 6;
	geo->sectors = 1 << 5;
	geo->cylinders = get_capacity(bdev->bd_disk) >> 11;
	return 0;
}

#ifdef CONFIG_BLK_DEV_INTEGRITY
static void nvme_init_integrity(struct nvme_ns *ns)
{
	struct blk_integrity integrity;

	switch (ns->pi_type) {
	case NVME_NS_DPS_PI_TYPE3:
		integrity.profile = &t10_pi_type3_crc;
		break;
	case NVME_NS_DPS_PI_TYPE1:
	case NVME_NS_DPS_PI_TYPE2:
		integrity.profile = &t10_pi_type1_crc;
		break;
	default:
		integrity.profile = NULL;
		break;
	}
	integrity.tuple_size = ns->ms;
	blk_integrity_register(ns->disk, &integrity);
	blk_queue_max_integrity_segments(ns->queue, 1);
}
#else
static void nvme_init_integrity(struct nvme_ns *ns)
{
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */

static void nvme_config_discard(struct nvme_ns *ns)
{
	u32 logical_block_size = queue_logical_block_size(ns->queue);
	ns->queue->limits.discard_zeroes_data = 0;
	ns->queue->limits.discard_alignment = logical_block_size;
	ns->queue->limits.discard_granularity = logical_block_size;
	blk_queue_max_discard_sectors(ns->queue, 0xffffffff);
	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
}

int nvme_revalidate_disk(struct gendisk *disk)
{
	struct nvme_ns *ns = disk->private_data;
	struct nvme_id_ns *id;
	u8 lbaf, pi_type;
	u16 old_ms;
	unsigned short bs;

	if (nvme_identify_ns(ns->ctrl, ns->ns_id, &id)) {
		dev_warn(ns->ctrl->dev, "%s: Identify failure nvme%dn%d\n",
				__func__, ns->ctrl->instance, ns->ns_id);
		return -ENODEV;
	}
	if (id->ncap == 0) {
		kfree(id);
		return -ENODEV;
	}

	if (nvme_nvm_ns_supported(ns, id) && ns->type != NVME_NS_LIGHTNVM) {
		if (nvme_nvm_register(ns->queue, disk->disk_name)) {
			dev_warn(ns->ctrl->dev,
				"%s: LightNVM init failure\n", __func__);
			kfree(id);
			return -ENODEV;
		}
		ns->type = NVME_NS_LIGHTNVM;
	}

	old_ms = ns->ms;
	lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
	ns->lba_shift = id->lbaf[lbaf].ds;
	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
	ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);

	/*
	 * If identify namespace failed, use default 512 byte block size so
	 * block layer can use before failing read/write for 0 capacity.
	 */
	if (ns->lba_shift == 0)
		ns->lba_shift = 9;
	bs = 1 << ns->lba_shift;

	/* XXX: PI implementation requires metadata equal t10 pi tuple size */
	pi_type = ns->ms == sizeof(struct t10_pi_tuple) ?
					id->dps & NVME_NS_DPS_PI_MASK : 0;

	blk_mq_freeze_queue(disk->queue);
	if (blk_get_integrity(disk) && (ns->pi_type != pi_type ||
				ns->ms != old_ms ||
				bs != queue_logical_block_size(disk->queue) ||
				(ns->ms && ns->ext)))
		blk_integrity_unregister(disk);

	ns->pi_type = pi_type;
	blk_queue_logical_block_size(ns->queue, bs);

	if (ns->ms && !ns->ext)
		nvme_init_integrity(ns);

	if (ns->ms && !(ns->ms == 8 && ns->pi_type) && !blk_get_integrity(disk))
		set_capacity(disk, 0);
	else
		set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));

	if (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM)
		nvme_config_discard(ns);
	blk_mq_unfreeze_queue(disk->queue);

	kfree(id);
	return 0;
}

static char nvme_pr_type(enum pr_type type)
{
	switch (type) {
	case PR_WRITE_EXCLUSIVE:
		return 1;
	case PR_EXCLUSIVE_ACCESS:
		return 2;
	case PR_WRITE_EXCLUSIVE_REG_ONLY:
		return 3;
	case PR_EXCLUSIVE_ACCESS_REG_ONLY:
		return 4;
	case PR_WRITE_EXCLUSIVE_ALL_REGS:
		return 5;
	case PR_EXCLUSIVE_ACCESS_ALL_REGS:
		return 6;
	default:
		return 0;
	}
};

static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
				u64 key, u64 sa_key, u8 op)
{
	struct nvme_ns *ns = bdev->bd_disk->private_data;
	struct nvme_command c;
	u8 data[16] = { 0, };

	put_unaligned_le64(key, &data[0]);
	put_unaligned_le64(sa_key, &data[8]);

	memset(&c, 0, sizeof(c));
	c.common.opcode = op;
	c.common.nsid = cpu_to_le32(ns->ns_id);
	c.common.cdw10[0] = cpu_to_le32(cdw10);

	return nvme_submit_sync_cmd(ns->queue, &c, data, 16);
}

static int nvme_pr_register(struct block_device *bdev, u64 old,
		u64 new, unsigned flags)
{
	u32 cdw10;

	if (flags & ~PR_FL_IGNORE_KEY)
		return -EOPNOTSUPP;

	cdw10 = old ? 2 : 0;
	cdw10 |= (flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0;
	cdw10 |= (1 << 30) | (1 << 31); /* PTPL=1 */
	return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_register);
}

static int nvme_pr_reserve(struct block_device *bdev, u64 key,
		enum pr_type type, unsigned flags)
{
	u32 cdw10;

	if (flags & ~PR_FL_IGNORE_KEY)
		return -EOPNOTSUPP;

	cdw10 = nvme_pr_type(type) << 8;
	cdw10 |= ((flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0);
	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_acquire);
}

static int nvme_pr_preempt(struct block_device *bdev, u64 old, u64 new,
		enum pr_type type, bool abort)
{
	u32 cdw10 = nvme_pr_type(type) << 8 | abort ? 2 : 1;
	return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_acquire);
}

static int nvme_pr_clear(struct block_device *bdev, u64 key)
{
	u32 cdw10 = 1 | key ? 1 << 3 : 0;
	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_register);
}

static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
{
	u32 cdw10 = nvme_pr_type(type) << 8 | key ? 1 << 3 : 0;
	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
}

static const struct pr_ops nvme_pr_ops = {
	.pr_register	= nvme_pr_register,
	.pr_reserve	= nvme_pr_reserve,
	.pr_release	= nvme_pr_release,
	.pr_preempt	= nvme_pr_preempt,
	.pr_clear	= nvme_pr_clear,
};

const struct block_device_operations nvme_fops = {
	.owner		= THIS_MODULE,
	.ioctl		= nvme_ioctl,
	.compat_ioctl	= nvme_compat_ioctl,
	.open		= nvme_open,
	.release	= nvme_release,
	.getgeo		= nvme_getgeo,
	.revalidate_disk= nvme_revalidate_disk,
	.pr_ops		= &nvme_pr_ops,
};

static void nvme_free_ctrl(struct kref *kref)
{
	struct nvme_ctrl *ctrl = container_of(kref, struct nvme_ctrl, kref);

	ctrl->ops->free_ctrl(ctrl);
}

void nvme_put_ctrl(struct nvme_ctrl *ctrl)
{
	kref_put(&ctrl->kref, nvme_free_ctrl);
}