// SPDX-License-Identifier: GPL-2.0
/*
 * NVMe I/O command implementation.
 * Copyright (c) 2015-2016 HGST, a Western Digital Company.
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/blkdev.h>
#include <linux/module.h>
#include "nvmet.h"

void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
{
        const struct queue_limits *ql = &bdev_get_queue(bdev)->limits;
        /* Number of physical blocks per logical block. */
        const u32 ppl = ql->physical_block_size / ql->logical_block_size;
        /* Physical blocks per logical block, 0's based. */
        const __le16 ppl0b = to0based(ppl);

        /*
         * For NVMe 1.2 and later, bit 1 indicates that the fields NAWUN,
         * NAWUPF, and NACWU are defined for this namespace and should be
         * used by the host for this namespace instead of the AWUN, AWUPF,
         * and ACWU fields in the Identify Controller data structure. If
         * any of these fields are zero that means that the corresponding
         * field from the identify controller data structure should be used.
         */
        id->nsfeat |= 1 << 1;
        id->nawun = ppl0b;
        id->nawupf = ppl0b;
        id->nacwu = ppl0b;

        /*
         * Bit 4 indicates that the fields NPWG, NPWA, NPDG, NPDA, and
         * NOWS are defined for this namespace and should be used by
         * the host for I/O optimization.
         */
        id->nsfeat |= 1 << 4;
        /* NPWG = Namespace Preferred Write Granularity. 0's based */
        id->npwg = ppl0b;
        /* NPWA = Namespace Preferred Write Alignment. 0's based */
        id->npwa = id->npwg;
        /* NPDG = Namespace Preferred Deallocate Granularity. 0's based */
        id->npdg = to0based(ql->discard_granularity / ql->logical_block_size);
        /* NPDG = Namespace Preferred Deallocate Alignment */
        id->npda = id->npdg;
        /* NOWS = Namespace Optimal Write Size */
        id->nows = to0based(ql->io_opt / ql->logical_block_size);
}

int nvmet_bdev_ns_enable(struct nvmet_ns *ns)
{
        int ret;

        ns->bdev = blkdev_get_by_path(ns->device_path,
                        FMODE_READ | FMODE_WRITE, NULL);
        if (IS_ERR(ns->bdev)) {
                ret = PTR_ERR(ns->bdev);
                if (ret != -ENOTBLK) {
                        pr_err("failed to open block device %s: (%ld)\n",
                                        ns->device_path, PTR_ERR(ns->bdev));
                }
                ns->bdev = NULL;
                return ret;
        }
        ns->size = i_size_read(ns->bdev->bd_inode);
        ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev));
        return 0;
}

void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
{
        if (ns->bdev) {
                blkdev_put(ns->bdev, FMODE_WRITE | FMODE_READ);
                ns->bdev = NULL;
        }
}

static u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
{
        u16 status = NVME_SC_SUCCESS;

        if (likely(blk_sts == BLK_STS_OK))
                return status;
        /*
         * Right now there exists M : 1 mapping between block layer error
         * to the NVMe status code (see nvme_error_status()). For consistency,
         * when we reverse map we use most appropriate NVMe Status code from
         * the group of the NVMe staus codes used in the nvme_error_status().
         */
        switch (blk_sts) {
        case BLK_STS_NOSPC:
                status = NVME_SC_CAP_EXCEEDED | NVME_SC_DNR;
                req->error_loc = offsetof(struct nvme_rw_command, length);
                break;
        case BLK_STS_TARGET:
                status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
                req->error_loc = offsetof(struct nvme_rw_command, slba);
                break;
        case BLK_STS_NOTSUPP:
                req->error_loc = offsetof(struct nvme_common_command, opcode);
                switch (req->cmd->common.opcode) {
                case nvme_cmd_dsm:
                case nvme_cmd_write_zeroes:
                        status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR;
                        break;
                default:
                        status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
                }
                break;
        case BLK_STS_MEDIUM:
                status = NVME_SC_ACCESS_DENIED;
                req->error_loc = offsetof(struct nvme_rw_command, nsid);
                break;
        case BLK_STS_IOERR:
                /* fallthru */
        default:
                status = NVME_SC_INTERNAL | NVME_SC_DNR;
                req->error_loc = offsetof(struct nvme_common_command, opcode);
        }

        switch (req->cmd->common.opcode) {
        case nvme_cmd_read:
        case nvme_cmd_write:
                req->error_slba = le64_to_cpu(req->cmd->rw.slba);
                break;
        case nvme_cmd_write_zeroes:
                req->error_slba =
                        le64_to_cpu(req->cmd->write_zeroes.slba);
                break;
        default:
                req->error_slba = 0;
        }
        return status;
}

static void nvmet_bio_done(struct bio *bio)
{
        struct nvmet_req *req = bio->bi_private;

        nvmet_req_complete(req, blk_to_nvme_status(req, bio->bi_status));
        if (bio != &req->b.inline_bio)
                bio_put(bio);
}

static void nvmet_bdev_execute_rw(struct nvmet_req *req)
{
        int sg_cnt = req->sg_cnt;
        struct bio *bio;
        struct scatterlist *sg;
        sector_t sector;
        int op, op_flags = 0, i;

        if (!req->sg_cnt) {
                nvmet_req_complete(req, 0);
                return;
        }

        if (req->cmd->rw.opcode == nvme_cmd_write) {
                op = REQ_OP_WRITE;
                op_flags = REQ_SYNC | REQ_IDLE;
                if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA))
                        op_flags |= REQ_FUA;
        } else {
                op = REQ_OP_READ;
        }

        if (is_pci_p2pdma_page(sg_page(req->sg)))
                op_flags |= REQ_NOMERGE;

        sector = le64_to_cpu(req->cmd->rw.slba);
        sector <<= (req->ns->blksize_shift - 9);

        if (req->data_len <= NVMET_MAX_INLINE_DATA_LEN) {
                bio = &req->b.inline_bio;
                bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec));
        } else {
                bio = bio_alloc(GFP_KERNEL, min(sg_cnt, BIO_MAX_PAGES));
        }
        bio_set_dev(bio, req->ns->bdev);
        bio->bi_iter.bi_sector = sector;
        bio->bi_private = req;
        bio->bi_end_io = nvmet_bio_done;
        bio_set_op_attrs(bio, op, op_flags);

        for_each_sg(req->sg, sg, req->sg_cnt, i) {
                while (bio_add_page(bio, sg_page(sg), sg->length, sg->offset)
                                != sg->length) {
                        struct bio *prev = bio;

                        bio = bio_alloc(GFP_KERNEL, min(sg_cnt, BIO_MAX_PAGES));
                        bio_set_dev(bio, req->ns->bdev);
                        bio->bi_iter.bi_sector = sector;
                        bio_set_op_attrs(bio, op, op_flags);

                        bio_chain(bio, prev);
                        submit_bio(prev);
                }

                sector += sg->length >> 9;
                sg_cnt--;
        }

        submit_bio(bio);
}

static void nvmet_bdev_execute_flush(struct nvmet_req *req)
{
        struct bio *bio = &req->b.inline_bio;

        bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec));
        bio_set_dev(bio, req->ns->bdev);
        bio->bi_private = req;
        bio->bi_end_io = nvmet_bio_done;
        bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;

        submit_bio(bio);
}

u16 nvmet_bdev_flush(struct nvmet_req *req)
{
        if (blkdev_issue_flush(req->ns->bdev, GFP_KERNEL, NULL))
                return NVME_SC_INTERNAL | NVME_SC_DNR;
        return 0;
}

static u16 nvmet_bdev_discard_range(struct nvmet_req *req,
                struct nvme_dsm_range *range, struct bio **bio)
{
        struct nvmet_ns *ns = req->ns;
        int ret;

        ret = __blkdev_issue_discard(ns->bdev,
                        le64_to_cpu(range->slba) << (ns->blksize_shift - 9),
                        le32_to_cpu(range->nlb) << (ns->blksize_shift - 9),
                        GFP_KERNEL, 0, bio);
        if (ret && ret != -EOPNOTSUPP) {
                req->error_slba = le64_to_cpu(range->slba);
                return errno_to_nvme_status(req, ret);
        }
        return NVME_SC_SUCCESS;
}

static void nvmet_bdev_execute_discard(struct nvmet_req *req)
{
        struct nvme_dsm_range range;
        struct bio *bio = NULL;
        int i;
        u16 status;

        for (i = 0; i <= le32_to_cpu(req->cmd->dsm.nr); i++) {
                status = nvmet_copy_from_sgl(req, i * sizeof(range), &range,
                                sizeof(range));
                if (status)
                        break;

                status = nvmet_bdev_discard_range(req, &range, &bio);
                if (status)
                        break;
        }

        if (bio) {
                bio->bi_private = req;
                bio->bi_end_io = nvmet_bio_done;
                if (status) {
                        bio->bi_status = BLK_STS_IOERR;
                        bio_endio(bio);
                } else {
                        submit_bio(bio);
                }
        } else {
                nvmet_req_complete(req, status);
        }
}

static void nvmet_bdev_execute_dsm(struct nvmet_req *req)
{
        switch (le32_to_cpu(req->cmd->dsm.attributes)) {
        case NVME_DSMGMT_AD:
                nvmet_bdev_execute_discard(req);
                return;
        case NVME_DSMGMT_IDR:
        case NVME_DSMGMT_IDW:
        default:
                /* Not supported yet */
                nvmet_req_complete(req, 0);
                return;
        }
}

static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req)
{
        struct nvme_write_zeroes_cmd *write_zeroes = &req->cmd->write_zeroes;
        struct bio *bio = NULL;
        sector_t sector;
        sector_t nr_sector;
        int ret;

        sector = le64_to_cpu(write_zeroes->slba) <<
                (req->ns->blksize_shift - 9);
        nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) <<
                (req->ns->blksize_shift - 9));

        ret = __blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector,
                        GFP_KERNEL, &bio, 0);
        if (bio) {
                bio->bi_private = req;
                bio->bi_end_io = nvmet_bio_done;
                submit_bio(bio);
        } else {
                nvmet_req_complete(req, errno_to_nvme_status(req, ret));
        }
}

u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req)
{
        struct nvme_command *cmd = req->cmd;

        switch (cmd->common.opcode) {
        case nvme_cmd_read:
        case nvme_cmd_write:
                req->execute = nvmet_bdev_execute_rw;
                req->data_len = nvmet_rw_len(req);
                return 0;
        case nvme_cmd_flush:
                req->execute = nvmet_bdev_execute_flush;
                req->data_len = 0;
                return 0;
        case nvme_cmd_dsm:
                req->execute = nvmet_bdev_execute_dsm;
                req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) *
                        sizeof(struct nvme_dsm_range);
                return 0;
        case nvme_cmd_write_zeroes:
                req->execute = nvmet_bdev_execute_write_zeroes;
                req->data_len = 0;
                return 0;
        default:
                pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
                       req->sq->qid);
                req->error_loc = offsetof(struct nvme_common_command, opcode);
                return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
        }
}