[PATCH 1/4] nvme: move driver into subdirectory
J Freyensee
james_p_freyensee at linux.intel.com
Sat Sep 26 18:35:10 PDT 2015
>From 16d464da995bb698a5045ac434d6c2f1efc5a346 Mon Sep 17 00:00:00 2001
From: Jay Sternberg <jay.e.sternberg at intel.com>
Date: Fri, 25 Sep 2015 10:14:17 -0700
Subject: [PATCH 1/4] nvme: move driver into subdirectory
Signed-off-by: Jay Sternberg <jay.e.sternberg at intel.com>
---
drivers/block/Kconfig | 11 +-
drivers/block/Makefile | 3 +-
drivers/block/nvme-core.c | 3395 -----------------------------------
--------
drivers/block/nvme-scsi.c | 2556 --------------------------------
drivers/block/nvme/Kconfig | 10 +
drivers/block/nvme/Makefile | 3 +
drivers/block/nvme/core.c | 3395
+++++++++++++++++++++++++++++++++++++++++++
drivers/block/nvme/scsi.c | 2556 ++++++++++++++++++++++++++++++++
8 files changed, 5966 insertions(+), 5963 deletions(-)
delete mode 100644 drivers/block/nvme-core.c
delete mode 100644 drivers/block/nvme-scsi.c
create mode 100644 drivers/block/nvme/Kconfig
create mode 100644 drivers/block/nvme/Makefile
create mode 100644 drivers/block/nvme/core.c
create mode 100644 drivers/block/nvme/scsi.c
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 1b8094d..fda69ca 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -310,16 +310,7 @@ config BLK_DEV_NBD
If unsure, say N.
-config BLK_DEV_NVME
- tristate "NVM Express block device"
- depends on PCI
- ---help---
- The NVM Express driver is for solid state drives directly
- connected to the PCI or PCI Express bus. If you know you
- don't have one of these, it is safe to answer N.
-
- To compile this driver as a module, choose M here: the
- module will be called nvme.
+source "drivers/block/nvme/Kconfig"
config BLK_DEV_SKD
tristate "STEC S1120 Block Driver"
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index 02b688d..b96a474 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -22,7 +22,7 @@ obj-$(CONFIG_XILINX_SYSACE) += xsysace.o
obj-$(CONFIG_CDROM_PKTCDVD) += pktcdvd.o
obj-$(CONFIG_MG_DISK) += mg_disk.o
obj-$(CONFIG_SUNVDC) += sunvdc.o
-obj-$(CONFIG_BLK_DEV_NVME) += nvme.o
+obj-$(CONFIG_BLK_DEV_NVME) += nvme/
obj-$(CONFIG_BLK_DEV_SKD) += skd.o
obj-$(CONFIG_BLK_DEV_OSD) += osdblk.o
@@ -44,6 +44,5 @@ obj-$(CONFIG_BLK_DEV_RSXX) += rsxx/
obj-$(CONFIG_BLK_DEV_NULL_BLK) += null_blk.o
obj-$(CONFIG_ZRAM) += zram/
-nvme-y := nvme-core.o nvme-scsi.o
skd-y := skd_main.o
swim_mod-y := swim.o swim_asm.o
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
deleted file mode 100644
index b97fc3f..0000000
--- a/drivers/block/nvme-core.c
+++ /dev/null
@@ -1,3395 +0,0 @@
-/*
- * 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/nvme.h>
-#include <linux/bitops.h>
-#include <linux/blkdev.h>
-#include <linux/blk-mq.h>
-#include <linux/cpu.h>
-#include <linux/delay.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/genhd.h>
-#include <linux/hdreg.h>
-#include <linux/idr.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/kdev_t.h>
-#include <linux/kthread.h>
-#include <linux/kernel.h>
-#include <linux/list_sort.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/pci.h>
-#include <linux/poison.h>
-#include <linux/ptrace.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/t10-pi.h>
-#include <linux/types.h>
-#include <scsi/sg.h>
-#include <asm-generic/io-64-nonatomic-lo-hi.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))
-#define CQ_SIZE(depth) (depth * sizeof(struct
nvme_completion))
-#define ADMIN_TIMEOUT (admin_timeout * HZ)
-#define SHUTDOWN_TIMEOUT (shutdown_timeout * HZ)
-
-static unsigned char admin_timeout = 60;
-module_param(admin_timeout, byte, 0644);
-MODULE_PARM_DESC(admin_timeout, "timeout in seconds for admin
commands");
-
-unsigned char nvme_io_timeout = 30;
-module_param_named(io_timeout, nvme_io_timeout, byte, 0644);
-MODULE_PARM_DESC(io_timeout, "timeout in seconds for I/O");
-
-static 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_major;
-module_param(nvme_major, int, 0);
-
-static int nvme_char_major;
-module_param(nvme_char_major, int, 0);
-
-static int use_threaded_interrupts;
-module_param(use_threaded_interrupts, int, 0);
-
-static bool use_cmb_sqes = true;
-module_param(use_cmb_sqes, bool, 0644);
-MODULE_PARM_DESC(use_cmb_sqes, "use controller's memory buffer for I/O
SQes");
-
-static DEFINE_SPINLOCK(dev_list_lock);
-static LIST_HEAD(dev_list);
-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;
-
-static void nvme_reset_failed_dev(struct work_struct *ws);
-static int nvme_reset(struct nvme_dev *dev);
-static int nvme_process_cq(struct nvme_queue *nvmeq);
-
-struct async_cmd_info {
- struct kthread_work work;
- struct kthread_worker *worker;
- struct request *req;
- u32 result;
- int status;
- void *ctx;
-};
-
-/*
- * An NVM Express queue. Each device has at least two (one for admin
- * commands and one for I/O commands).
- */
-struct nvme_queue {
- struct device *q_dmadev;
- struct nvme_dev *dev;
- char irqname[24]; /* nvme4294967295-65535\0 */
- spinlock_t q_lock;
- struct nvme_command *sq_cmds;
- struct nvme_command __iomem *sq_cmds_io;
- volatile struct nvme_completion *cqes;
- struct blk_mq_tags **tags;
- dma_addr_t sq_dma_addr;
- dma_addr_t cq_dma_addr;
- u32 __iomem *q_db;
- u16 q_depth;
- s16 cq_vector;
- u16 sq_head;
- u16 sq_tail;
- u16 cq_head;
- u16 qid;
- u8 cq_phase;
- u8 cqe_seen;
- struct async_cmd_info cmdinfo;
-};
-
-/*
- * Check we didin't inadvertently grow the command struct
- */
-static inline void _nvme_check_size(void)
-{
- BUILD_BUG_ON(sizeof(struct nvme_rw_command) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_create_cq) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_create_sq) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_features) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != 4096);
- BUILD_BUG_ON(sizeof(struct nvme_id_ns) != 4096);
- BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
-}
-
-typedef void (*nvme_completion_fn)(struct nvme_queue *, void *,
- struct nvme_completion
*);
-
-struct nvme_cmd_info {
- nvme_completion_fn fn;
- void *ctx;
- int aborted;
- struct nvme_queue *nvmeq;
- struct nvme_iod iod[0];
-};
-
-/*
- * Max size of iod being embedded in the request payload
- */
-#define NVME_INT_PAGES 2
-#define NVME_INT_BYTES(dev) (NVME_INT_PAGES * (dev)->page_size)
-#define NVME_INT_MASK 0x01
-
-/*
- * Will slightly overestimate the number of pages needed. This is OK
- * as it only leads to a small amount of wasted memory for the
lifetime of
- * the I/O.
- */
-static int nvme_npages(unsigned size, struct nvme_dev *dev)
-{
- unsigned nprps = DIV_ROUND_UP(size + dev->page_size, dev
->page_size);
- return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8);
-}
-
-static unsigned int nvme_cmd_size(struct nvme_dev *dev)
-{
- unsigned int ret = sizeof(struct nvme_cmd_info);
-
- ret += sizeof(struct nvme_iod);
- ret += sizeof(__le64 *) * nvme_npages(NVME_INT_BYTES(dev),
dev);
- ret += sizeof(struct scatterlist) * NVME_INT_PAGES;
-
- return ret;
-}
-
-static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void
*data,
- unsigned int hctx_idx)
-{
- struct nvme_dev *dev = data;
- struct nvme_queue *nvmeq = dev->queues[0];
-
- WARN_ON(hctx_idx != 0);
- WARN_ON(dev->admin_tagset.tags[0] != hctx->tags);
- WARN_ON(nvmeq->tags);
-
- hctx->driver_data = nvmeq;
- nvmeq->tags = &dev->admin_tagset.tags[0];
- return 0;
-}
-
-static void nvme_admin_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned
int hctx_idx)
-{
- struct nvme_queue *nvmeq = hctx->driver_data;
-
- nvmeq->tags = NULL;
-}
-
-static int nvme_admin_init_request(void *data, struct request *req,
- unsigned int hctx_idx, unsigned int
rq_idx,
- unsigned int numa_node)
-{
- struct nvme_dev *dev = data;
- struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
- struct nvme_queue *nvmeq = dev->queues[0];
-
- BUG_ON(!nvmeq);
- cmd->nvmeq = nvmeq;
- return 0;
-}
-
-static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
- unsigned int hctx_idx)
-{
- struct nvme_dev *dev = data;
- struct nvme_queue *nvmeq = dev->queues[hctx_idx + 1];
-
- if (!nvmeq->tags)
- nvmeq->tags = &dev->tagset.tags[hctx_idx];
-
- WARN_ON(dev->tagset.tags[hctx_idx] != hctx->tags);
- hctx->driver_data = nvmeq;
- return 0;
-}
-
-static int nvme_init_request(void *data, struct request *req,
- unsigned int hctx_idx, unsigned int
rq_idx,
- unsigned int numa_node)
-{
- struct nvme_dev *dev = data;
- struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
- struct nvme_queue *nvmeq = dev->queues[hctx_idx + 1];
-
- BUG_ON(!nvmeq);
- cmd->nvmeq = nvmeq;
- return 0;
-}
-
-static void nvme_set_info(struct nvme_cmd_info *cmd, void *ctx,
- nvme_completion_fn handler)
-{
- cmd->fn = handler;
- cmd->ctx = ctx;
- cmd->aborted = 0;
- blk_mq_start_request(blk_mq_rq_from_pdu(cmd));
-}
-
-static void *iod_get_private(struct nvme_iod *iod)
-{
- return (void *) (iod->private & ~0x1UL);
-}
-
-/*
- * If bit 0 is set, the iod is embedded in the request payload.
- */
-static bool iod_should_kfree(struct nvme_iod *iod)
-{
- return (iod->private & NVME_INT_MASK) == 0;
-}
-
-/* Special values must be less than 0x1000 */
-#define CMD_CTX_BASE ((void *)POISON_POINTER_DELTA)
-#define CMD_CTX_CANCELLED (0x30C + CMD_CTX_BASE)
-#define CMD_CTX_COMPLETED (0x310 + CMD_CTX_BASE)
-#define CMD_CTX_INVALID (0x314 + CMD_CTX_BASE)
-
-static void special_completion(struct nvme_queue *nvmeq, void *ctx,
- struct nvme_completion
*cqe)
-{
- if (ctx == CMD_CTX_CANCELLED)
- return;
- if (ctx == CMD_CTX_COMPLETED) {
- dev_warn(nvmeq->q_dmadev,
- "completed id %d twice on queue %d\n",
- cqe->command_id, le16_to_cpup(&cqe
->sq_id));
- return;
- }
- if (ctx == CMD_CTX_INVALID) {
- dev_warn(nvmeq->q_dmadev,
- "invalid id %d completed on queue
%d\n",
- cqe->command_id, le16_to_cpup(&cqe
->sq_id));
- return;
- }
- dev_warn(nvmeq->q_dmadev, "Unknown special completion %p\n",
ctx);
-}
-
-static void *cancel_cmd_info(struct nvme_cmd_info *cmd,
nvme_completion_fn *fn)
-{
- void *ctx;
-
- if (fn)
- *fn = cmd->fn;
- ctx = cmd->ctx;
- cmd->fn = special_completion;
- cmd->ctx = CMD_CTX_CANCELLED;
- return ctx;
-}
-
-static void async_req_completion(struct nvme_queue *nvmeq, void *ctx,
- struct nvme_completion
*cqe)
-{
- u32 result = le32_to_cpup(&cqe->result);
- u16 status = le16_to_cpup(&cqe->status) >> 1;
-
- if (status == NVME_SC_SUCCESS || status == NVME_SC_ABORT_REQ)
- ++nvmeq->dev->event_limit;
- if (status != NVME_SC_SUCCESS)
- return;
-
- switch (result & 0xff07) {
- case NVME_AER_NOTICE_NS_CHANGED:
- dev_info(nvmeq->q_dmadev, "rescanning\n");
- schedule_work(&nvmeq->dev->scan_work);
- default:
- dev_warn(nvmeq->q_dmadev, "async event result %08x\n",
result);
- }
-}
-
-static void abort_completion(struct nvme_queue *nvmeq, void *ctx,
- struct nvme_completion
*cqe)
-{
- struct request *req = ctx;
-
- u16 status = le16_to_cpup(&cqe->status) >> 1;
- u32 result = le32_to_cpup(&cqe->result);
-
- blk_mq_free_request(req);
-
- dev_warn(nvmeq->q_dmadev, "Abort status:%x result:%x", status,
result);
- ++nvmeq->dev->abort_limit;
-}
-
-static void async_completion(struct nvme_queue *nvmeq, void *ctx,
- struct nvme_completion
*cqe)
-{
- struct async_cmd_info *cmdinfo = ctx;
- cmdinfo->result = le32_to_cpup(&cqe->result);
- cmdinfo->status = le16_to_cpup(&cqe->status) >> 1;
- queue_kthread_work(cmdinfo->worker, &cmdinfo->work);
- blk_mq_free_request(cmdinfo->req);
-}
-
-static inline struct nvme_cmd_info *get_cmd_from_tag(struct nvme_queue
*nvmeq,
- unsigned int tag)
-{
- struct request *req = blk_mq_tag_to_rq(*nvmeq->tags, tag);
-
- return blk_mq_rq_to_pdu(req);
-}
-
-/*
- * Called with local interrupts disabled and the q_lock held. May not
sleep.
- */
-static void *nvme_finish_cmd(struct nvme_queue *nvmeq, int tag,
- nvme_completion_fn
*fn)
-{
- struct nvme_cmd_info *cmd = get_cmd_from_tag(nvmeq, tag);
- void *ctx;
- if (tag >= nvmeq->q_depth) {
- *fn = special_completion;
- return CMD_CTX_INVALID;
- }
- if (fn)
- *fn = cmd->fn;
- ctx = cmd->ctx;
- cmd->fn = special_completion;
- cmd->ctx = CMD_CTX_COMPLETED;
- return ctx;
-}
-
-/**
- * nvme_submit_cmd() - Copy a command into a queue and ring the
doorbell
- * @nvmeq: The queue to use
- * @cmd: The command to send
- *
- * Safe to use from interrupt context
- */
-static void __nvme_submit_cmd(struct nvme_queue *nvmeq,
- struct nvme_command
*cmd)
-{
- u16 tail = nvmeq->sq_tail;
-
- if (nvmeq->sq_cmds_io)
- memcpy_toio(&nvmeq->sq_cmds_io[tail], cmd,
sizeof(*cmd));
- else
- memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
-
- if (++tail == nvmeq->q_depth)
- tail = 0;
- writel(tail, nvmeq->q_db);
- nvmeq->sq_tail = tail;
-}
-
-static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct
nvme_command *cmd)
-{
- unsigned long flags;
- spin_lock_irqsave(&nvmeq->q_lock, flags);
- __nvme_submit_cmd(nvmeq, cmd);
- spin_unlock_irqrestore(&nvmeq->q_lock, flags);
-}
-
-static __le64 **iod_list(struct nvme_iod *iod)
-{
- return ((void *)iod) + iod->offset;
-}
-
-static inline void iod_init(struct nvme_iod *iod, unsigned nbytes,
- unsigned nseg, unsigned long private)
-{
- iod->private = private;
- iod->offset = offsetof(struct nvme_iod, sg[nseg]);
- iod->npages = -1;
- iod->length = nbytes;
- iod->nents = 0;
-}
-
-static struct nvme_iod *
-__nvme_alloc_iod(unsigned nseg, unsigned bytes, struct nvme_dev *dev,
- unsigned long priv, gfp_t gfp)
-{
- struct nvme_iod *iod = kmalloc(sizeof(struct nvme_iod) +
- sizeof(__le64 *) * nvme_npages(bytes,
dev) +
- sizeof(struct scatterlist) * nseg,
gfp);
-
- if (iod)
- iod_init(iod, bytes, nseg, priv);
-
- return iod;
-}
-
-static struct nvme_iod *nvme_alloc_iod(struct request *rq, struct
nvme_dev *dev,
- gfp_t gfp)
-{
- unsigned size = !(rq->cmd_flags & REQ_DISCARD) ?
blk_rq_bytes(rq) :
- sizeof(struct
nvme_dsm_range);
- struct nvme_iod *iod;
-
- if (rq->nr_phys_segments <= NVME_INT_PAGES &&
- size <= NVME_INT_BYTES(dev)) {
- struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(rq);
-
- iod = cmd->iod;
- iod_init(iod, size, rq->nr_phys_segments,
- (unsigned long) rq | NVME_INT_MASK);
- return iod;
- }
-
- return __nvme_alloc_iod(rq->nr_phys_segments, size, dev,
- (unsigned long) rq, gfp);
-}
-
-static void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
-{
- const int last_prp = dev->page_size / 8 - 1;
- int i;
- __le64 **list = iod_list(iod);
- dma_addr_t prp_dma = iod->first_dma;
-
- if (iod->npages == 0)
- dma_pool_free(dev->prp_small_pool, list[0], prp_dma);
- for (i = 0; i < iod->npages; i++) {
- __le64 *prp_list = list[i];
- dma_addr_t next_prp_dma =
le64_to_cpu(prp_list[last_prp]);
- dma_pool_free(dev->prp_page_pool, prp_list, prp_dma);
- prp_dma = next_prp_dma;
- }
-
- if (iod_should_kfree(iod))
- kfree(iod);
-}
-
-static int nvme_error_status(u16 status)
-{
- switch (status & 0x7ff) {
- case NVME_SC_SUCCESS:
- return 0;
- case NVME_SC_CAP_EXCEEDED:
- return -ENOSPC;
- default:
- return -EIO;
- }
-}
-
-#ifdef CONFIG_BLK_DEV_INTEGRITY
-static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
- if (be32_to_cpu(pi->ref_tag) == v)
- pi->ref_tag = cpu_to_be32(p);
-}
-
-static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
- if (be32_to_cpu(pi->ref_tag) == p)
- pi->ref_tag = cpu_to_be32(v);
-}
-
-/**
- * nvme_dif_remap - remaps ref tags to bip seed and physical lba
- *
- * The virtual start sector is the one that was originally submitted
by the
- * block layer. Due to partitioning, MD/DM cloning, etc. the
actual physical
- * start sector may be different. Remap protection information to
match the
- * physical LBA on writes, and back to the original seed on reads.
- *
- * Type 0 and 3 do not have a ref tag, so no remapping required.
- */
-static void nvme_dif_remap(struct request *req,
- void (*dif_swap)(u32 p, u32 v, struct
t10_pi_tuple *pi))
-{
- struct nvme_ns *ns = req->rq_disk->private_data;
- struct bio_integrity_payload *bip;
- struct t10_pi_tuple *pi;
- void *p, *pmap;
- u32 i, nlb, ts, phys, virt;
-
- if (!ns->pi_type || ns->pi_type == NVME_NS_DPS_PI_TYPE3)
- return;
-
- bip = bio_integrity(req->bio);
- if (!bip)
- return;
-
- pmap = kmap_atomic(bip->bip_vec->bv_page) + bip->bip_vec
->bv_offset;
-
- p = pmap;
- virt = bip_get_seed(bip);
- phys = nvme_block_nr(ns, blk_rq_pos(req));
- nlb = (blk_rq_bytes(req) >> ns->lba_shift);
- ts = ns->disk->integrity->tuple_size;
-
- for (i = 0; i < nlb; i++, virt++, phys++) {
- pi = (struct t10_pi_tuple *)p;
- dif_swap(phys, virt, pi);
- p += ts;
- }
- kunmap_atomic(pmap);
-}
-
-static int nvme_noop_verify(struct blk_integrity_iter *iter)
-{
- return 0;
-}
-
-static int nvme_noop_generate(struct blk_integrity_iter *iter)
-{
- return 0;
-}
-
-struct blk_integrity nvme_meta_noop = {
- .name = "NVME_META_NOOP",
- .generate_fn = nvme_noop_generate,
- .verify_fn = nvme_noop_verify,
-};
-
-static void nvme_init_integrity(struct nvme_ns *ns)
-{
- struct blk_integrity integrity;
-
- switch (ns->pi_type) {
- case NVME_NS_DPS_PI_TYPE3:
- integrity = t10_pi_type3_crc;
- break;
- case NVME_NS_DPS_PI_TYPE1:
- case NVME_NS_DPS_PI_TYPE2:
- integrity = t10_pi_type1_crc;
- break;
- default:
- integrity = nvme_meta_noop;
- break;
- }
- integrity.tuple_size = ns->ms;
- blk_integrity_register(ns->disk, &integrity);
- blk_queue_max_integrity_segments(ns->queue, 1);
-}
-#else /* CONFIG_BLK_DEV_INTEGRITY */
-static void nvme_dif_remap(struct request *req,
- void (*dif_swap)(u32 p, u32 v, struct
t10_pi_tuple *pi))
-{
-}
-static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-}
-static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-}
-static void nvme_init_integrity(struct nvme_ns *ns)
-{
-}
-#endif
-
-static void req_completion(struct nvme_queue *nvmeq, void *ctx,
- struct nvme_completion
*cqe)
-{
- struct nvme_iod *iod = ctx;
- struct request *req = iod_get_private(iod);
- struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
-
- u16 status = le16_to_cpup(&cqe->status) >> 1;
-
- if (unlikely(status)) {
- if (!(status & NVME_SC_DNR ||
blk_noretry_request(req))
- && (jiffies - req->start_time) < req->timeout) {
- unsigned long flags;
-
- blk_mq_requeue_request(req);
- spin_lock_irqsave(req->q->queue_lock, flags);
- if (!blk_queue_stopped(req->q))
- blk_mq_kick_requeue_list(req->q);
- spin_unlock_irqrestore(req->q->queue_lock,
flags);
- return;
- }
- if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
- if (cmd_rq->ctx == CMD_CTX_CANCELLED)
- req->errors = -EINTR;
- else
- req->errors = status;
- } else {
- req->errors = nvme_error_status(status);
- }
- } else
- req->errors = 0;
- if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
- u32 result = le32_to_cpup(&cqe->result);
- req->special = (void *)(uintptr_t)result;
- }
-
- if (cmd_rq->aborted)
- dev_warn(nvmeq->dev->dev,
- "completing aborted command with
status:%04x\n",
- status);
-
- if (iod->nents) {
- dma_unmap_sg(nvmeq->dev->dev, iod->sg, iod->nents,
- rq_data_dir(req) ? DMA_TO_DEVICE :
DMA_FROM_DEVICE);
- if (blk_integrity_rq(req)) {
- if (!rq_data_dir(req))
- nvme_dif_remap(req,
nvme_dif_complete);
- dma_unmap_sg(nvmeq->dev->dev, iod->meta_sg, 1,
- rq_data_dir(req) ? DMA_TO_DEVICE :
DMA_FROM_DEVICE);
- }
- }
- nvme_free_iod(nvmeq->dev, iod);
-
- blk_mq_complete_request(req);
-}
-
-/* length is in bytes. gfp flags indicates whether we may sleep. */
-static int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod,
- int total_len, gfp_t gfp)
-{
- struct dma_pool *pool;
- int length = total_len;
- struct scatterlist *sg = iod->sg;
- int dma_len = sg_dma_len(sg);
- u64 dma_addr = sg_dma_address(sg);
- u32 page_size = dev->page_size;
- int offset = dma_addr & (page_size - 1);
- __le64 *prp_list;
- __le64 **list = iod_list(iod);
- dma_addr_t prp_dma;
- int nprps, i;
-
- length -= (page_size - offset);
- if (length <= 0)
- return total_len;
-
- dma_len -= (page_size - offset);
- if (dma_len) {
- dma_addr += (page_size - offset);
- } else {
- sg = sg_next(sg);
- dma_addr = sg_dma_address(sg);
- dma_len = sg_dma_len(sg);
- }
-
- if (length <= page_size) {
- iod->first_dma = dma_addr;
- return total_len;
- }
-
- nprps = DIV_ROUND_UP(length, page_size);
- if (nprps <= (256 / 8)) {
- pool = dev->prp_small_pool;
- iod->npages = 0;
- } else {
- pool = dev->prp_page_pool;
- iod->npages = 1;
- }
-
- prp_list = dma_pool_alloc(pool, gfp, &prp_dma);
- if (!prp_list) {
- iod->first_dma = dma_addr;
- iod->npages = -1;
- return (total_len - length) + page_size;
- }
- list[0] = prp_list;
- iod->first_dma = prp_dma;
- i = 0;
- for (;;) {
- if (i == page_size >> 3) {
- __le64 *old_prp_list = prp_list;
- prp_list = dma_pool_alloc(pool, gfp,
&prp_dma);
- if (!prp_list)
- return total_len - length;
- list[iod->npages++] = prp_list;
- prp_list[0] = old_prp_list[i - 1];
- old_prp_list[i - 1] = cpu_to_le64(prp_dma);
- i = 1;
- }
- prp_list[i++] = cpu_to_le64(dma_addr);
- dma_len -= page_size;
- dma_addr += page_size;
- length -= page_size;
- if (length <= 0)
- break;
- if (dma_len > 0)
- continue;
- BUG_ON(dma_len < 0);
- sg = sg_next(sg);
- dma_addr = sg_dma_address(sg);
- dma_len = sg_dma_len(sg);
- }
-
- return total_len;
-}
-
-static void nvme_submit_priv(struct nvme_queue *nvmeq, struct request
*req,
- struct nvme_iod *iod)
-{
- struct nvme_command cmnd;
-
- memcpy(&cmnd, req->cmd, sizeof(cmnd));
- cmnd.rw.command_id = req->tag;
- if (req->nr_phys_segments) {
- cmnd.rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
- cmnd.rw.prp2 = cpu_to_le64(iod->first_dma);
- }
-
- __nvme_submit_cmd(nvmeq, &cmnd);
-}
-
-/*
- * We reuse the small pool to allocate the 16-byte range here as it is
not
- * worth having a special pool for these or additional cases to handle
freeing
- * the iod.
- */
-static void nvme_submit_discard(struct nvme_queue *nvmeq, struct
nvme_ns *ns,
- struct request *req, struct nvme_iod *iod)
-{
- struct nvme_dsm_range *range =
- (struct nvme_dsm_range
*)iod_list(iod)[0];
- struct nvme_command cmnd;
-
- range->cattr = cpu_to_le32(0);
- range->nlb = cpu_to_le32(blk_rq_bytes(req) >> ns->lba_shift);
- range->slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
-
- memset(&cmnd, 0, sizeof(cmnd));
- cmnd.dsm.opcode = nvme_cmd_dsm;
- cmnd.dsm.command_id = req->tag;
- cmnd.dsm.nsid = cpu_to_le32(ns->ns_id);
- cmnd.dsm.prp1 = cpu_to_le64(iod->first_dma);
- cmnd.dsm.nr = 0;
- cmnd.dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
-
- __nvme_submit_cmd(nvmeq, &cmnd);
-}
-
-static void nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns
*ns,
- int
cmdid)
-{
- struct nvme_command cmnd;
-
- memset(&cmnd, 0, sizeof(cmnd));
- cmnd.common.opcode = nvme_cmd_flush;
- cmnd.common.command_id = cmdid;
- cmnd.common.nsid = cpu_to_le32(ns->ns_id);
-
- __nvme_submit_cmd(nvmeq, &cmnd);
-}
-
-static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod
*iod,
- struct nvme_ns
*ns)
-{
- struct request *req = iod_get_private(iod);
- struct nvme_command cmnd;
- u16 control = 0;
- u32 dsmgmt = 0;
-
- if (req->cmd_flags & REQ_FUA)
- control |= NVME_RW_FUA;
- if (req->cmd_flags & (REQ_FAILFAST_DEV | REQ_RAHEAD))
- control |= NVME_RW_LR;
-
- if (req->cmd_flags & REQ_RAHEAD)
- dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
-
- memset(&cmnd, 0, sizeof(cmnd));
- cmnd.rw.opcode = (rq_data_dir(req) ? nvme_cmd_write :
nvme_cmd_read);
- cmnd.rw.command_id = req->tag;
- cmnd.rw.nsid = cpu_to_le32(ns->ns_id);
- cmnd.rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
- cmnd.rw.prp2 = cpu_to_le64(iod->first_dma);
- cmnd.rw.slba = cpu_to_le64(nvme_block_nr(ns,
blk_rq_pos(req)));
- cmnd.rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns
->lba_shift) - 1);
-
- if (ns->ms) {
- switch (ns->pi_type) {
- case NVME_NS_DPS_PI_TYPE3:
- control |= NVME_RW_PRINFO_PRCHK_GUARD;
- break;
- case NVME_NS_DPS_PI_TYPE1:
- case NVME_NS_DPS_PI_TYPE2:
- control |= NVME_RW_PRINFO_PRCHK_GUARD |
- NVME_RW_PRINFO_PRCHK_REF;
- cmnd.rw.reftag = cpu_to_le32(
- nvme_block_nr(ns,
blk_rq_pos(req)));
- break;
- }
- if (blk_integrity_rq(req))
- cmnd.rw.metadata =
- cpu_to_le64(sg_dma_address(iod
->meta_sg));
- else
- control |= NVME_RW_PRINFO_PRACT;
- }
-
- cmnd.rw.control = cpu_to_le16(control);
- cmnd.rw.dsmgmt = cpu_to_le32(dsmgmt);
-
- __nvme_submit_cmd(nvmeq, &cmnd);
-
- return 0;
-}
-
-/*
- * NOTE: ns is NULL when called on the admin queue.
- */
-static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
- const struct blk_mq_queue_data *bd)
-{
- struct nvme_ns *ns = hctx->queue->queuedata;
- struct nvme_queue *nvmeq = hctx->driver_data;
- struct nvme_dev *dev = nvmeq->dev;
- struct request *req = bd->rq;
- struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
- struct nvme_iod *iod;
- enum dma_data_direction dma_dir;
-
- /*
- * If formated with metadata, require the block layer provide
a buffer
- * unless this namespace is formated such that the metadata
can be
- * stripped/generated by the controller with PRACT=1.
- */
- if (ns && ns->ms && !blk_integrity_rq(req)) {
- if (!(ns->pi_type && ns->ms == 8) &&
- req->cmd_type !=
REQ_TYPE_DRV_PRIV) {
- req->errors = -EFAULT;
- blk_mq_complete_request(req);
- return BLK_MQ_RQ_QUEUE_OK;
- }
- }
-
- iod = nvme_alloc_iod(req, dev, GFP_ATOMIC);
- if (!iod)
- return BLK_MQ_RQ_QUEUE_BUSY;
-
- if (req->cmd_flags & REQ_DISCARD) {
- void *range;
- /*
- * We reuse the small pool to allocate the 16-byte
range here
- * as it is not worth having a special pool for these
or
- * additional cases to handle freeing the iod.
- */
- range = dma_pool_alloc(dev->prp_small_pool,
GFP_ATOMIC,
- &iod->first_dma);
- if (!range)
- goto retry_cmd;
- iod_list(iod)[0] = (__le64 *)range;
- iod->npages = 0;
- } else if (req->nr_phys_segments) {
- dma_dir = rq_data_dir(req) ? DMA_TO_DEVICE :
DMA_FROM_DEVICE;
-
- sg_init_table(iod->sg, req->nr_phys_segments);
- iod->nents = blk_rq_map_sg(req->q, req, iod->sg);
- if (!iod->nents)
- goto error_cmd;
-
- if (!dma_map_sg(nvmeq->q_dmadev, iod->sg, iod->nents,
dma_dir))
- goto retry_cmd;
-
- if (blk_rq_bytes(req) !=
- nvme_setup_prps(dev, iod, blk_rq_bytes(req),
GFP_ATOMIC)) {
- dma_unmap_sg(dev->dev, iod->sg, iod->nents,
dma_dir);
- goto retry_cmd;
- }
- if (blk_integrity_rq(req)) {
- if (blk_rq_count_integrity_sg(req->q, req
->bio) != 1)
- goto error_cmd;
-
- sg_init_table(iod->meta_sg, 1);
- if (blk_rq_map_integrity_sg(
- req->q, req->bio, iod
->meta_sg) != 1)
- goto error_cmd;
-
- if (rq_data_dir(req))
- nvme_dif_remap(req, nvme_dif_prep);
-
- if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg,
1, dma_dir))
- goto error_cmd;
- }
- }
-
- nvme_set_info(cmd, iod, req_completion);
- spin_lock_irq(&nvmeq->q_lock);
- if (req->cmd_type == REQ_TYPE_DRV_PRIV)
- nvme_submit_priv(nvmeq, req, iod);
- else if (req->cmd_flags & REQ_DISCARD)
- nvme_submit_discard(nvmeq, ns, req, iod);
- else if (req->cmd_flags & REQ_FLUSH)
- nvme_submit_flush(nvmeq, ns, req->tag);
- else
- nvme_submit_iod(nvmeq, iod, ns);
-
- nvme_process_cq(nvmeq);
- spin_unlock_irq(&nvmeq->q_lock);
- return BLK_MQ_RQ_QUEUE_OK;
-
- error_cmd:
- nvme_free_iod(dev, iod);
- return BLK_MQ_RQ_QUEUE_ERROR;
- retry_cmd:
- nvme_free_iod(dev, iod);
- return BLK_MQ_RQ_QUEUE_BUSY;
-}
-
-static int nvme_process_cq(struct nvme_queue *nvmeq)
-{
- u16 head, phase;
-
- head = nvmeq->cq_head;
- phase = nvmeq->cq_phase;
-
- for (;;) {
- void *ctx;
- nvme_completion_fn fn;
- struct nvme_completion cqe = nvmeq->cqes[head];
- if ((le16_to_cpu(cqe.status) & 1) != phase)
- break;
- nvmeq->sq_head = le16_to_cpu(cqe.sq_head);
- if (++head == nvmeq->q_depth) {
- head = 0;
- phase = !phase;
- }
- ctx = nvme_finish_cmd(nvmeq, cqe.command_id, &fn);
- fn(nvmeq, ctx, &cqe);
- }
-
- /* If the controller ignores the cq head doorbell and
continuously
- * writes to the queue, it is theoretically possible to wrap
around
- * the queue twice and mistakenly return IRQ_NONE. Linux only
- * requires that 0.1% of your interrupts are handled, so this
isn't
- * a big problem.
- */
- if (head == nvmeq->cq_head && phase == nvmeq->cq_phase)
- return 0;
-
- writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
- nvmeq->cq_head = head;
- nvmeq->cq_phase = phase;
-
- nvmeq->cqe_seen = 1;
- return 1;
-}
-
-static irqreturn_t nvme_irq(int irq, void *data)
-{
- irqreturn_t result;
- struct nvme_queue *nvmeq = data;
- spin_lock(&nvmeq->q_lock);
- nvme_process_cq(nvmeq);
- result = nvmeq->cqe_seen ? IRQ_HANDLED : IRQ_NONE;
- nvmeq->cqe_seen = 0;
- spin_unlock(&nvmeq->q_lock);
- return result;
-}
-
-static irqreturn_t nvme_irq_check(int irq, void *data)
-{
- struct nvme_queue *nvmeq = data;
- struct nvme_completion cqe = nvmeq->cqes[nvmeq->cq_head];
- if ((le16_to_cpu(cqe.status) & 1) != nvmeq->cq_phase)
- return IRQ_NONE;
- return IRQ_WAKE_THREAD;
-}
-
-/*
- * 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, void __user *ubuffer, unsigned bufflen,
- u32 *result, unsigned timeout)
-{
- bool write = cmd->common.opcode & 1;
- struct bio *bio = NULL;
- struct request *req;
- int ret;
-
- req = blk_mq_alloc_request(q, write, GFP_KERNEL, false);
- if (IS_ERR(req))
- return PTR_ERR(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->timeout = timeout ? timeout : ADMIN_TIMEOUT;
-
- req->cmd = (unsigned char *)cmd;
- req->cmd_len = sizeof(struct nvme_command);
- req->special = (void *)0;
-
- if (buffer && bufflen) {
- ret = blk_rq_map_kern(q, req, buffer, bufflen,
__GFP_WAIT);
- if (ret)
- goto out;
- } else if (ubuffer && bufflen) {
- ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen,
__GFP_WAIT);
- if (ret)
- goto out;
- bio = req->bio;
- }
-
- blk_execute_rq(req->q, NULL, req, 0);
- if (bio)
- blk_rq_unmap_user(bio);
- 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, NULL, bufflen,
NULL, 0);
-}
-
-static int nvme_submit_async_admin_req(struct nvme_dev *dev)
-{
- struct nvme_queue *nvmeq = dev->queues[0];
- struct nvme_command c;
- struct nvme_cmd_info *cmd_info;
- struct request *req;
-
- req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_ATOMIC,
true);
- if (IS_ERR(req))
- return PTR_ERR(req);
-
- req->cmd_flags |= REQ_NO_TIMEOUT;
- cmd_info = blk_mq_rq_to_pdu(req);
- nvme_set_info(cmd_info, NULL, async_req_completion);
-
- memset(&c, 0, sizeof(c));
- c.common.opcode = nvme_admin_async_event;
- c.common.command_id = req->tag;
-
- blk_mq_free_request(req);
- __nvme_submit_cmd(nvmeq, &c);
- return 0;
-}
-
-static int nvme_submit_admin_async_cmd(struct nvme_dev *dev,
- struct nvme_command *cmd,
- struct async_cmd_info *cmdinfo, unsigned
timeout)
-{
- struct nvme_queue *nvmeq = dev->queues[0];
- struct request *req;
- struct nvme_cmd_info *cmd_rq;
-
- req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_KERNEL,
false);
- if (IS_ERR(req))
- return PTR_ERR(req);
-
- req->timeout = timeout;
- cmd_rq = blk_mq_rq_to_pdu(req);
- cmdinfo->req = req;
- nvme_set_info(cmd_rq, cmdinfo, async_completion);
- cmdinfo->status = -EINTR;
-
- cmd->common.command_id = req->tag;
-
- nvme_submit_cmd(nvmeq, cmd);
- return 0;
-}
-
-static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16
id)
-{
- struct nvme_command c;
-
- memset(&c, 0, sizeof(c));
- c.delete_queue.opcode = opcode;
- c.delete_queue.qid = cpu_to_le16(id);
-
- return nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0);
-}
-
-static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
- struct nvme_queue
*nvmeq)
-{
- struct nvme_command c;
- int flags = NVME_QUEUE_PHYS_CONTIG | NVME_CQ_IRQ_ENABLED;
-
- /*
- * Note: we (ab)use the fact the the prp fields survive if no
data
- * is attached to the request.
- */
- memset(&c, 0, sizeof(c));
- c.create_cq.opcode = nvme_admin_create_cq;
- c.create_cq.prp1 = cpu_to_le64(nvmeq->cq_dma_addr);
- c.create_cq.cqid = cpu_to_le16(qid);
- c.create_cq.qsize = cpu_to_le16(nvmeq->q_depth - 1);
- c.create_cq.cq_flags = cpu_to_le16(flags);
- c.create_cq.irq_vector = cpu_to_le16(nvmeq->cq_vector);
-
- return nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0);
-}
-
-static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
- struct nvme_queue
*nvmeq)
-{
- struct nvme_command c;
- int flags = NVME_QUEUE_PHYS_CONTIG | NVME_SQ_PRIO_MEDIUM;
-
- /*
- * Note: we (ab)use the fact the the prp fields survive if no
data
- * is attached to the request.
- */
- memset(&c, 0, sizeof(c));
- c.create_sq.opcode = nvme_admin_create_sq;
- c.create_sq.prp1 = cpu_to_le64(nvmeq->sq_dma_addr);
- c.create_sq.sqid = cpu_to_le16(qid);
- c.create_sq.qsize = cpu_to_le16(nvmeq->q_depth - 1);
- c.create_sq.sq_flags = cpu_to_le16(flags);
- c.create_sq.cqid = cpu_to_le16(qid);
-
- return nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0);
-}
-
-static int adapter_delete_cq(struct nvme_dev *dev, u16 cqid)
-{
- return adapter_delete_queue(dev, nvme_admin_delete_cq, cqid);
-}
-
-static int adapter_delete_sq(struct nvme_dev *dev, u16 sqid)
-{
- return adapter_delete_queue(dev, nvme_admin_delete_sq, sqid);
-}
-
-int nvme_identify_ctrl(struct nvme_dev *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_dev *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_dev *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, NULL, 0,
- result, 0);
-}
-
-int nvme_set_features(struct nvme_dev *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, NULL, 0,
- result, 0);
-}
-
-int nvme_get_log_page(struct nvme_dev *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;
-}
-
-/**
- * nvme_abort_req - Attempt aborting a request
- *
- * Schedule controller reset if the command was already aborted once
before and
- * still hasn't been returned to the driver, or if this is the admin
queue.
- */
-static void nvme_abort_req(struct request *req)
-{
- struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
- struct nvme_queue *nvmeq = cmd_rq->nvmeq;
- struct nvme_dev *dev = nvmeq->dev;
- struct request *abort_req;
- struct nvme_cmd_info *abort_cmd;
- struct nvme_command cmd;
-
- if (!nvmeq->qid || cmd_rq->aborted) {
- unsigned long flags;
-
- spin_lock_irqsave(&dev_list_lock, flags);
- if (work_busy(&dev->reset_work))
- goto out;
- list_del_init(&dev->node);
- dev_warn(dev->dev, "I/O %d QID %d timeout, reset
controller\n",
- req->tag,
nvmeq->qid);
- dev->reset_workfn = nvme_reset_failed_dev;
- queue_work(nvme_workq, &dev->reset_work);
- out:
- spin_unlock_irqrestore(&dev_list_lock, flags);
- return;
- }
-
- if (!dev->abort_limit)
- return;
-
- abort_req = blk_mq_alloc_request(dev->admin_q, WRITE,
GFP_ATOMIC,
- false);
- if (IS_ERR(abort_req))
- return;
-
- abort_cmd = blk_mq_rq_to_pdu(abort_req);
- nvme_set_info(abort_cmd, abort_req, abort_completion);
-
- memset(&cmd, 0, sizeof(cmd));
- cmd.abort.opcode = nvme_admin_abort_cmd;
- cmd.abort.cid = req->tag;
- cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
- cmd.abort.command_id = abort_req->tag;
-
- --dev->abort_limit;
- cmd_rq->aborted = 1;
-
- dev_warn(nvmeq->q_dmadev, "Aborting I/O %d QID %d\n", req
->tag,
- nvmeq->qid);
- nvme_submit_cmd(dev->queues[0], &cmd);
-}
-
-static void nvme_cancel_queue_ios(struct request *req, void *data,
bool reserved)
-{
- struct nvme_queue *nvmeq = data;
- void *ctx;
- nvme_completion_fn fn;
- struct nvme_cmd_info *cmd;
- struct nvme_completion cqe;
-
- if (!blk_mq_request_started(req))
- return;
-
- cmd = blk_mq_rq_to_pdu(req);
-
- if (cmd->ctx == CMD_CTX_CANCELLED)
- return;
-
- if (blk_queue_dying(req->q))
- cqe.status = cpu_to_le16((NVME_SC_ABORT_REQ |
NVME_SC_DNR) << 1);
- else
- cqe.status = cpu_to_le16(NVME_SC_ABORT_REQ << 1);
-
-
- dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d QID %d\n",
- req->tag, nvmeq->qid);
- ctx = cancel_cmd_info(cmd, &fn);
- fn(nvmeq, ctx, &cqe);
-}
-
-static enum blk_eh_timer_return nvme_timeout(struct request *req, bool
reserved)
-{
- struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
- struct nvme_queue *nvmeq = cmd->nvmeq;
-
- dev_warn(nvmeq->q_dmadev, "Timeout I/O %d QID %d\n", req->tag,
- nvmeq->qid);
- spin_lock_irq(&nvmeq->q_lock);
- nvme_abort_req(req);
- spin_unlock_irq(&nvmeq->q_lock);
-
- /*
- * The aborted req will be completed on receiving the abort
req.
- * We enable the timer again. If hit twice, it'll cause a
device reset,
- * as the device then is in a faulty state.
- */
- return BLK_EH_RESET_TIMER;
-}
-
-static void nvme_free_queue(struct nvme_queue *nvmeq)
-{
- dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
- (void *)nvmeq->cqes, nvmeq
->cq_dma_addr);
- if (nvmeq->sq_cmds)
- dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq
->q_depth),
- nvmeq->sq_cmds, nvmeq
->sq_dma_addr);
- kfree(nvmeq);
-}
-
-static void nvme_free_queues(struct nvme_dev *dev, int lowest)
-{
- int i;
-
- for (i = dev->queue_count - 1; i >= lowest; i--) {
- struct nvme_queue *nvmeq = dev->queues[i];
- dev->queue_count--;
- dev->queues[i] = NULL;
- nvme_free_queue(nvmeq);
- }
-}
-
-/**
- * nvme_suspend_queue - put queue into suspended state
- * @nvmeq - queue to suspend
- */
-static int nvme_suspend_queue(struct nvme_queue *nvmeq)
-{
- int vector;
-
- spin_lock_irq(&nvmeq->q_lock);
- if (nvmeq->cq_vector == -1) {
- spin_unlock_irq(&nvmeq->q_lock);
- return 1;
- }
- vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
- nvmeq->dev->online_queues--;
- nvmeq->cq_vector = -1;
- spin_unlock_irq(&nvmeq->q_lock);
-
- if (!nvmeq->qid && nvmeq->dev->admin_q)
- blk_mq_freeze_queue_start(nvmeq->dev->admin_q);
-
- irq_set_affinity_hint(vector, NULL);
- free_irq(vector, nvmeq);
-
- return 0;
-}
-
-static void nvme_clear_queue(struct nvme_queue *nvmeq)
-{
- spin_lock_irq(&nvmeq->q_lock);
- if (nvmeq->tags && *nvmeq->tags)
- blk_mq_all_tag_busy_iter(*nvmeq->tags,
nvme_cancel_queue_ios, nvmeq);
- spin_unlock_irq(&nvmeq->q_lock);
-}
-
-static void nvme_disable_queue(struct nvme_dev *dev, int qid)
-{
- struct nvme_queue *nvmeq = dev->queues[qid];
-
- if (!nvmeq)
- return;
- if (nvme_suspend_queue(nvmeq))
- return;
-
- /* Don't tell the adapter to delete the admin queue.
- * Don't tell a removed adapter to delete IO queues. */
- if (qid && readl(&dev->bar->csts) != -1) {
- adapter_delete_sq(dev, qid);
- adapter_delete_cq(dev, qid);
- }
-
- spin_lock_irq(&nvmeq->q_lock);
- nvme_process_cq(nvmeq);
- spin_unlock_irq(&nvmeq->q_lock);
-}
-
-static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
- int entry_size)
-{
- int q_depth = dev->q_depth;
- unsigned q_size_aligned = roundup(q_depth * entry_size, dev
->page_size);
-
- if (q_size_aligned * nr_io_queues > dev->cmb_size) {
- u64 mem_per_q = div_u64(dev->cmb_size, nr_io_queues);
- mem_per_q = round_down(mem_per_q, dev->page_size);
- q_depth = div_u64(mem_per_q, entry_size);
-
- /*
- * Ensure the reduced q_depth is above some threshold
where it
- * would be better to map queues in system memory with
the
- * original depth
- */
- if (q_depth < 64)
- return -ENOMEM;
- }
-
- return q_depth;
-}
-
-static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue
*nvmeq,
- int qid, int depth)
-{
- if (qid && dev->cmb && use_cmb_sqes && NVME_CMB_SQS(dev
->cmbsz)) {
- unsigned offset = (qid - 1) *
- roundup(SQ_SIZE(depth), dev
->page_size);
- nvmeq->sq_dma_addr = dev->cmb_dma_addr + offset;
- nvmeq->sq_cmds_io = dev->cmb + offset;
- } else {
- nvmeq->sq_cmds = dma_alloc_coherent(dev->dev,
SQ_SIZE(depth),
- &nvmeq->sq_dma_addr,
GFP_KERNEL);
- if (!nvmeq->sq_cmds)
- return -ENOMEM;
- }
-
- return 0;
-}
-
-static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int
qid,
- int depth)
-{
- struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq),
GFP_KERNEL);
- if (!nvmeq)
- return NULL;
-
- nvmeq->cqes = dma_zalloc_coherent(dev->dev, CQ_SIZE(depth),
- &nvmeq->cq_dma_addr,
GFP_KERNEL);
- if (!nvmeq->cqes)
- goto free_nvmeq;
-
- if (nvme_alloc_sq_cmds(dev, nvmeq, qid, depth))
- goto free_cqdma;
-
- nvmeq->q_dmadev = dev->dev;
- nvmeq->dev = dev;
- snprintf(nvmeq->irqname, sizeof(nvmeq->irqname), "nvme%dq%d",
- dev->instance, qid);
- spin_lock_init(&nvmeq->q_lock);
- nvmeq->cq_head = 0;
- nvmeq->cq_phase = 1;
- nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
- nvmeq->q_depth = depth;
- nvmeq->qid = qid;
- nvmeq->cq_vector = -1;
- dev->queues[qid] = nvmeq;
-
- /* make sure queue descriptor is set before queue count, for
kthread */
- mb();
- dev->queue_count++;
-
- return nvmeq;
-
- free_cqdma:
- dma_free_coherent(dev->dev, CQ_SIZE(depth), (void *)nvmeq
->cqes,
- nvmeq
->cq_dma_addr);
- free_nvmeq:
- kfree(nvmeq);
- return NULL;
-}
-
-static int queue_request_irq(struct nvme_dev *dev, struct nvme_queue
*nvmeq,
- const char
*name)
-{
- if (use_threaded_interrupts)
- return request_threaded_irq(dev->entry[nvmeq
->cq_vector].vector,
- nvme_irq_check, nvme_irq,
IRQF_SHARED,
- name, nvmeq);
- return request_irq(dev->entry[nvmeq->cq_vector].vector,
nvme_irq,
- IRQF_SHARED, name, nvmeq);
-}
-
-static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
-{
- struct nvme_dev *dev = nvmeq->dev;
-
- spin_lock_irq(&nvmeq->q_lock);
- nvmeq->sq_tail = 0;
- nvmeq->cq_head = 0;
- nvmeq->cq_phase = 1;
- nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
- memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
- dev->online_queues++;
- spin_unlock_irq(&nvmeq->q_lock);
-}
-
-static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
-{
- struct nvme_dev *dev = nvmeq->dev;
- int result;
-
- nvmeq->cq_vector = qid - 1;
- result = adapter_alloc_cq(dev, qid, nvmeq);
- if (result < 0)
- return result;
-
- result = adapter_alloc_sq(dev, qid, nvmeq);
- if (result < 0)
- goto release_cq;
-
- result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
- if (result < 0)
- goto release_sq;
-
- nvme_init_queue(nvmeq, qid);
- return result;
-
- release_sq:
- adapter_delete_sq(dev, qid);
- release_cq:
- adapter_delete_cq(dev, qid);
- return result;
-}
-
-static int nvme_wait_ready(struct nvme_dev *dev, u64 cap, bool
enabled)
-{
- unsigned long timeout;
- u32 bit = enabled ? NVME_CSTS_RDY : 0;
-
- timeout = ((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies;
-
- while ((readl(&dev->bar->csts) & NVME_CSTS_RDY) != bit) {
- msleep(100);
- if (fatal_signal_pending(current))
- return -EINTR;
- if (time_after(jiffies, timeout)) {
- dev_err(dev->dev,
- "Device not ready; aborting %s\n",
enabled ?
- "initialisation" :
"reset");
- return -ENODEV;
- }
- }
-
- return 0;
-}
-
-/*
- * If the device has been passed off to us in an enabled state, just
clear
- * the enabled bit. The spec says we should set the 'shutdown
notification
- * bits', but doing so may cause the device to complete commands to
the
- * admin queue ... and we don't know what memory that might be
pointing at!
- */
-static int nvme_disable_ctrl(struct nvme_dev *dev, u64 cap)
-{
- dev->ctrl_config &= ~NVME_CC_SHN_MASK;
- dev->ctrl_config &= ~NVME_CC_ENABLE;
- writel(dev->ctrl_config, &dev->bar->cc);
-
- return nvme_wait_ready(dev, cap, false);
-}
-
-static int nvme_enable_ctrl(struct nvme_dev *dev, u64 cap)
-{
- dev->ctrl_config &= ~NVME_CC_SHN_MASK;
- dev->ctrl_config |= NVME_CC_ENABLE;
- writel(dev->ctrl_config, &dev->bar->cc);
-
- return nvme_wait_ready(dev, cap, true);
-}
-
-static int nvme_shutdown_ctrl(struct nvme_dev *dev)
-{
- unsigned long timeout;
-
- dev->ctrl_config &= ~NVME_CC_SHN_MASK;
- dev->ctrl_config |= NVME_CC_SHN_NORMAL;
-
- writel(dev->ctrl_config, &dev->bar->cc);
-
- timeout = SHUTDOWN_TIMEOUT + jiffies;
- while ((readl(&dev->bar->csts) & NVME_CSTS_SHST_MASK) !=
- NVME_CSTS_SHST
_CMPLT) {
- msleep(100);
- if (fatal_signal_pending(current))
- return -EINTR;
- if (time_after(jiffies, timeout)) {
- dev_err(dev->dev,
- "Device shutdown incomplete; abort
shutdown\n");
- return -ENODEV;
- }
- }
-
- return 0;
-}
-
-static struct blk_mq_ops nvme_mq_admin_ops = {
- .queue_rq = nvme_queue_rq,
- .map_queue = blk_mq_map_queue,
- .init_hctx = nvme_admin_init_hctx,
- .exit_hctx = nvme_admin_exit_hctx,
- .init_request = nvme_admin_init_request,
- .timeout = nvme_timeout,
-};
-
-static struct blk_mq_ops nvme_mq_ops = {
- .queue_rq = nvme_queue_rq,
- .map_queue = blk_mq_map_queue,
- .init_hctx = nvme_init_hctx,
- .init_request = nvme_init_request,
- .timeout = nvme_timeout,
-};
-
-static void nvme_dev_remove_admin(struct nvme_dev *dev)
-{
- if (dev->admin_q && !blk_queue_dying(dev->admin_q)) {
- blk_cleanup_queue(dev->admin_q);
- blk_mq_free_tag_set(&dev->admin_tagset);
- }
-}
-
-static int nvme_alloc_admin_tags(struct nvme_dev *dev)
-{
- if (!dev->admin_q) {
- dev->admin_tagset.ops = &nvme_mq_admin_ops;
- dev->admin_tagset.nr_hw_queues = 1;
- dev->admin_tagset.queue_depth = NVME_AQ_DEPTH - 1;
- dev->admin_tagset.reserved_tags = 1;
- dev->admin_tagset.timeout = ADMIN_TIMEOUT;
- dev->admin_tagset.numa_node = dev_to_node(dev->dev);
- dev->admin_tagset.cmd_size = nvme_cmd_size(dev);
- dev->admin_tagset.driver_data = dev;
-
- if (blk_mq_alloc_tag_set(&dev->admin_tagset))
- return -ENOMEM;
-
- dev->admin_q = blk_mq_init_queue(&dev->admin_tagset);
- if (IS_ERR(dev->admin_q)) {
- blk_mq_free_tag_set(&dev->admin_tagset);
- return -ENOMEM;
- }
- if (!blk_get_queue(dev->admin_q)) {
- nvme_dev_remove_admin(dev);
- dev->admin_q = NULL;
- return -ENODEV;
- }
- } else
- blk_mq_unfreeze_queue(dev->admin_q);
-
- return 0;
-}
-
-static int nvme_configure_admin_queue(struct nvme_dev *dev)
-{
- int result;
- u32 aqa;
- u64 cap = readq(&dev->bar->cap);
- struct nvme_queue *nvmeq;
- unsigned page_shift = PAGE_SHIFT;
- unsigned dev_page_min = NVME_CAP_MPSMIN(cap) + 12;
- unsigned dev_page_max = NVME_CAP_MPSMAX(cap) + 12;
-
- if (page_shift < dev_page_min) {
- dev_err(dev->dev,
- "Minimum device page size (%u) too
large for "
- "host (%u)\n", 1 << dev_page_min,
- 1 << page_shift);
- return -ENODEV;
- }
- if (page_shift > dev_page_max) {
- dev_info(dev->dev,
- "Device maximum page size (%u) smaller
than "
- "host (%u); enabling work-around\n",
- 1 << dev_page_max, 1 << page_shift);
- page_shift = dev_page_max;
- }
-
- dev->subsystem = readl(&dev->bar->vs) >= NVME_VS(1, 1) ?
- NVME_CAP_NSSRC(cap) :
0;
-
- if (dev->subsystem && (readl(&dev->bar->csts) &
NVME_CSTS_NSSRO))
- writel(NVME_CSTS_NSSRO, &dev->bar->csts);
-
- result = nvme_disable_ctrl(dev, cap);
- if (result < 0)
- return result;
-
- nvmeq = dev->queues[0];
- if (!nvmeq) {
- nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH);
- if (!nvmeq)
- return -ENOMEM;
- }
-
- aqa = nvmeq->q_depth - 1;
- aqa |= aqa << 16;
-
- dev->page_size = 1 << page_shift;
-
- dev->ctrl_config = NVME_CC_CSS_NVM;
- dev->ctrl_config |= (page_shift - 12) << NVME_CC_MPS_SHIFT;
- dev->ctrl_config |= NVME_CC_ARB_RR | NVME_CC_SHN_NONE;
- dev->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES;
-
- writel(aqa, &dev->bar->aqa);
- writeq(nvmeq->sq_dma_addr, &dev->bar->asq);
- writeq(nvmeq->cq_dma_addr, &dev->bar->acq);
-
- result = nvme_enable_ctrl(dev, cap);
- if (result)
- goto free_nvmeq;
-
- nvmeq->cq_vector = 0;
- result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
- if (result) {
- nvmeq->cq_vector = -1;
- goto free_nvmeq;
- }
-
- return result;
-
- free_nvmeq:
- nvme_free_queues(dev, 0);
- return result;
-}
-
-static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io
__user *uio)
-{
- struct nvme_dev *dev = ns->dev;
- struct nvme_user_io io;
- struct nvme_command c;
- unsigned length, meta_len;
- int status, write;
- dma_addr_t meta_dma = 0;
- void *meta = NULL;
- 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 *)(unsigned long)io.metadata;
- write = io.opcode & 1;
-
- if (ns->ext) {
- length += meta_len;
- meta_len = 0;
- }
- if (meta_len) {
- if (((io.metadata & 3) || !io.metadata) && !ns->ext)
- return -EINVAL;
-
- meta = dma_alloc_coherent(dev->dev, meta_len,
- &meta_dma,
GFP_KERNEL);
-
- if (!meta) {
- status = -ENOMEM;
- goto unmap;
- }
- if (write) {
- if (copy_from_user(meta, metadata, meta_len))
{
- status = -EFAULT;
- goto unmap;
- }
- }
- }
-
- 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);
- c.rw.metadata = cpu_to_le64(meta_dma);
-
- status = __nvme_submit_sync_cmd(ns->queue, &c, NULL,
- (void __user *)io.addr, length, NULL, 0);
- unmap:
- if (meta) {
- if (status == NVME_SC_SUCCESS && !write) {
- if (copy_to_user(metadata, meta, meta_len))
- status = -EFAULT;
- }
- dma_free_coherent(dev->dev, meta_len, meta, meta_dma);
- }
- return status;
-}
-
-static int nvme_user_cmd(struct nvme_dev *dev, 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_sync_cmd(ns ? ns->queue : dev->admin_q,
&c,
- NULL, (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_subsys_reset(struct nvme_dev *dev)
-{
- if (!dev->subsystem)
- return -ENOTTY;
-
- writel(0x4E564D65, &dev->bar->nssr); /* "NVMe" */
- return 0;
-}
-
-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->dev, NULL, (void __user
*)arg);
- case NVME_IOCTL_IO_CMD:
- return nvme_user_cmd(ns->dev, 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)
-{
- int ret = 0;
- struct nvme_ns *ns;
-
- spin_lock(&dev_list_lock);
- ns = bdev->bd_disk->private_data;
- if (!ns)
- ret = -ENXIO;
- else if (!kref_get_unless_zero(&ns->dev->kref))
- ret = -ENXIO;
- spin_unlock(&dev_list_lock);
-
- return ret;
-}
-
-static void nvme_free_dev(struct kref *kref);
-
-static void nvme_release(struct gendisk *disk, fmode_t mode)
-{
- struct nvme_ns *ns = disk->private_data;
- struct nvme_dev *dev = ns->dev;
-
- kref_put(&dev->kref, nvme_free_dev);
-}
-
-static int nvme_getgeo(struct block_device *bd, struct hd_geometry
*geo)
-{
- /* some standard values */
- geo->heads = 1 << 6;
- geo->sectors = 1 << 5;
- geo->cylinders = get_capacity(bd->bd_disk) >> 11;
- return 0;
-}
-
-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);
-}
-
-static int nvme_revalidate_disk(struct gendisk *disk)
-{
- struct nvme_ns *ns = disk->private_data;
- struct nvme_dev *dev = ns->dev;
- struct nvme_id_ns *id;
- u8 lbaf, pi_type;
- u16 old_ms;
- unsigned short bs;
-
- if (nvme_identify_ns(dev, ns->ns_id, &id)) {
- dev_warn(dev->dev, "%s: Identify failure nvme%dn%d\n",
__func__,
- dev->instance, ns
->ns_id);
- return -ENODEV;
- }
- if (id->ncap == 0) {
- kfree(id);
- return -ENODEV;
- }
-
- 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;
-
- 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 && !blk_get_integrity(disk) && (disk->flags &
GENHD_FL_UP) &&
- !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 (dev->oncs & NVME_CTRL_ONCS_DSM)
- nvme_config_discard(ns);
-
- kfree(id);
- return 0;
-}
-
-static 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,
-};
-
-static int nvme_kthread(void *data)
-{
- struct nvme_dev *dev, *next;
-
- while (!kthread_should_stop()) {
- set_current_state(TASK_INTERRUPTIBLE);
- spin_lock(&dev_list_lock);
- list_for_each_entry_safe(dev, next, &dev_list, node) {
- int i;
- u32 csts = readl(&dev->bar->csts);
-
- if ((dev->subsystem && (csts &
NVME_CSTS_NSSRO)) ||
- csts &
NVME_CSTS_CFS) {
- if (work_busy(&dev->reset_work))
- continue;
- list_del_init(&dev->node);
- dev_warn(dev->dev,
- "Failed status: %x, reset
controller\n",
- readl(&dev->bar->csts));
- dev->reset_workfn =
nvme_reset_failed_dev;
- queue_work(nvme_workq, &dev
->reset_work);
- continue;
- }
- for (i = 0; i < dev->queue_count; i++) {
- struct nvme_queue *nvmeq = dev
->queues[i];
- if (!nvmeq)
- continue;
- spin_lock_irq(&nvmeq->q_lock);
- nvme_process_cq(nvmeq);
-
- while ((i == 0) && (dev->event_limit >
0)) {
- if
(nvme_submit_async_admin_req(dev))
- break;
- dev->event_limit--;
- }
- spin_unlock_irq(&nvmeq->q_lock);
- }
- }
- spin_unlock(&dev_list_lock);
- schedule_timeout(round_jiffies_relative(HZ));
- }
- return 0;
-}
-
-static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
-{
- struct nvme_ns *ns;
- struct gendisk *disk;
- int node = dev_to_node(dev->dev);
-
- ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
- if (!ns)
- return;
-
- ns->queue = blk_mq_init_queue(&dev->tagset);
- if (IS_ERR(ns->queue))
- goto out_free_ns;
- queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, ns->queue);
- queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue);
- ns->dev = dev;
- ns->queue->queuedata = ns;
-
- disk = alloc_disk_node(0, node);
- if (!disk)
- goto out_free_queue;
-
- ns->ns_id = nsid;
- ns->disk = disk;
- ns->lba_shift = 9; /* set to a default value for 512 until
disk is validated */
- list_add_tail(&ns->list, &dev->namespaces);
-
- blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
- if (dev->max_hw_sectors) {
- blk_queue_max_hw_sectors(ns->queue, dev
->max_hw_sectors);
- blk_queue_max_segments(ns->queue,
- ((dev->max_hw_sectors << 9) / dev->page_size)
+ 1);
- }
- if (dev->stripe_size)
- blk_queue_chunk_sectors(ns->queue, dev->stripe_size >>
9);
- if (dev->vwc & NVME_CTRL_VWC_PRESENT)
- blk_queue_flush(ns->queue, REQ_FLUSH | REQ_FUA);
- blk_queue_virt_boundary(ns->queue, dev->page_size - 1);
-
- disk->major = nvme_major;
- disk->first_minor = 0;
- disk->fops = &nvme_fops;
- disk->private_data = ns;
- disk->queue = ns->queue;
- disk->driverfs_dev = dev->device;
- disk->flags = GENHD_FL_EXT_DEVT;
- sprintf(disk->disk_name, "nvme%dn%d", dev->instance, nsid);
-
- /*
- * Initialize capacity to 0 until we establish the namespace
format and
- * setup integrity extentions if necessary. The
revalidate_disk after
- * add_disk allows the driver to register with integrity if
the format
- * requires it.
- */
- set_capacity(disk, 0);
- if (nvme_revalidate_disk(ns->disk))
- goto out_free_disk;
-
- add_disk(ns->disk);
- if (ns->ms) {
- struct block_device *bd = bdget_disk(ns->disk, 0);
- if (!bd)
- return;
- if (blkdev_get(bd, FMODE_READ, NULL)) {
- bdput(bd);
- return;
- }
- blkdev_reread_part(bd);
- blkdev_put(bd, FMODE_READ);
- }
- return;
- out_free_disk:
- kfree(disk);
- list_del(&ns->list);
- out_free_queue:
- blk_cleanup_queue(ns->queue);
- out_free_ns:
- kfree(ns);
-}
-
-static void nvme_create_io_queues(struct nvme_dev *dev)
-{
- unsigned i;
-
- for (i = dev->queue_count; i <= dev->max_qid; i++)
- if (!nvme_alloc_queue(dev, i, dev->q_depth))
- break;
-
- for (i = dev->online_queues; i <= dev->queue_count - 1; i++)
- if (nvme_create_queue(dev->queues[i], i))
- break;
-}
-
-static int set_queue_count(struct nvme_dev *dev, int count)
-{
- int status;
- u32 result;
- u32 q_count = (count - 1) | ((count - 1) << 16);
-
- status = nvme_set_features(dev, NVME_FEAT_NUM_QUEUES, q_count,
0,
- &resul
t);
- if (status < 0)
- return status;
- if (status > 0) {
- dev_err(dev->dev, "Could not set queue count (%d)\n",
status);
- return 0;
- }
- return min(result & 0xffff, result >> 16) + 1;
-}
-
-static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
-{
- u64 szu, size, offset;
- u32 cmbloc;
- resource_size_t bar_size;
- struct pci_dev *pdev = to_pci_dev(dev->dev);
- void __iomem *cmb;
- dma_addr_t dma_addr;
-
- if (!use_cmb_sqes)
- return NULL;
-
- dev->cmbsz = readl(&dev->bar->cmbsz);
- if (!(NVME_CMB_SZ(dev->cmbsz)))
- return NULL;
-
- cmbloc = readl(&dev->bar->cmbloc);
-
- szu = (u64)1 << (12 + 4 * NVME_CMB_SZU(dev->cmbsz));
- size = szu * NVME_CMB_SZ(dev->cmbsz);
- offset = szu * NVME_CMB_OFST(cmbloc);
- bar_size = pci_resource_len(pdev, NVME_CMB_BIR(cmbloc));
-
- if (offset > bar_size)
- return NULL;
-
- /*
- * Controllers may support a CMB size larger than their BAR,
- * for example, due to being behind a bridge. Reduce the CMB
to
- * the reported size of the BAR
- */
- if (size > bar_size - offset)
- size = bar_size - offset;
-
- dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(cmbloc)) +
offset;
- cmb = ioremap_wc(dma_addr, size);
- if (!cmb)
- return NULL;
-
- dev->cmb_dma_addr = dma_addr;
- dev->cmb_size = size;
- return cmb;
-}
-
-static inline void nvme_release_cmb(struct nvme_dev *dev)
-{
- if (dev->cmb) {
- iounmap(dev->cmb);
- dev->cmb = NULL;
- }
-}
-
-static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
-{
- return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride);
-}
-
-static int nvme_setup_io_queues(struct nvme_dev *dev)
-{
- struct nvme_queue *adminq = dev->queues[0];
- struct pci_dev *pdev = to_pci_dev(dev->dev);
- int result, i, vecs, nr_io_queues, size;
-
- nr_io_queues = num_possible_cpus();
- result = set_queue_count(dev, nr_io_queues);
- if (result <= 0)
- return result;
- if (result < nr_io_queues)
- nr_io_queues = result;
-
- if (dev->cmb && NVME_CMB_SQS(dev->cmbsz)) {
- result = nvme_cmb_qdepth(dev, nr_io_queues,
- sizeof(struct nvme_command));
- if (result > 0)
- dev->q_depth = result;
- else
- nvme_release_cmb(dev);
- }
-
- size = db_bar_size(dev, nr_io_queues);
- if (size > 8192) {
- iounmap(dev->bar);
- do {
- dev->bar = ioremap(pci_resource_start(pdev,
0), size);
- if (dev->bar)
- break;
- if (!--nr_io_queues)
- return -ENOMEM;
- size = db_bar_size(dev, nr_io_queues);
- } while (1);
- dev->dbs = ((void __iomem *)dev->bar) + 4096;
- adminq->q_db = dev->dbs;
- }
-
- /* Deregister the admin queue's interrupt */
- free_irq(dev->entry[0].vector, adminq);
-
- /*
- * If we enable msix early due to not intx, disable it again
before
- * setting up the full range we need.
- */
- if (!pdev->irq)
- pci_disable_msix(pdev);
-
- for (i = 0; i < nr_io_queues; i++)
- dev->entry[i].entry = i;
- vecs = pci_enable_msix_range(pdev, dev->entry, 1,
nr_io_queues);
- if (vecs < 0) {
- vecs = pci_enable_msi_range(pdev, 1, min(nr_io_queues,
32));
- if (vecs < 0) {
- vecs = 1;
- } else {
- for (i = 0; i < vecs; i++)
- dev->entry[i].vector = i + pdev->irq;
- }
- }
-
- /*
- * Should investigate if there's a performance win from
allocating
- * more queues than interrupt vectors; it might allow the
submission
- * path to scale better, even if the receive path is limited
by the
- * number of interrupts.
- */
- nr_io_queues = vecs;
- dev->max_qid = nr_io_queues;
-
- result = queue_request_irq(dev, adminq, adminq->irqname);
- if (result) {
- adminq->cq_vector = -1;
- goto free_queues;
- }
-
- /* Free previously allocated queues that are no longer usable
*/
- nvme_free_queues(dev, nr_io_queues + 1);
- nvme_create_io_queues(dev);
-
- return 0;
-
- free_queues:
- nvme_free_queues(dev, 1);
- return result;
-}
-
-static void nvme_free_namespace(struct nvme_ns *ns)
-{
- list_del(&ns->list);
-
- spin_lock(&dev_list_lock);
- ns->disk->private_data = NULL;
- spin_unlock(&dev_list_lock);
-
- put_disk(ns->disk);
- kfree(ns);
-}
-
-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);
- struct nvme_ns *nsb = container_of(b, struct nvme_ns, list);
-
- return nsa->ns_id - nsb->ns_id;
-}
-
-static struct nvme_ns *nvme_find_ns(struct nvme_dev *dev, unsigned
nsid)
-{
- struct nvme_ns *ns;
-
- list_for_each_entry(ns, &dev->namespaces, list) {
- if (ns->ns_id == nsid)
- return ns;
- if (ns->ns_id > nsid)
- break;
- }
- return NULL;
-}
-
-static inline bool nvme_io_incapable(struct nvme_dev *dev)
-{
- return (!dev->bar || readl(&dev->bar->csts) & NVME_CSTS_CFS ||
- dev
->online_queues < 2);
-}
-
-static void nvme_ns_remove(struct nvme_ns *ns)
-{
- bool kill = nvme_io_incapable(ns->dev) && !blk_queue_dying(ns
->queue);
-
- if (kill)
- blk_set_queue_dying(ns->queue);
- if (ns->disk->flags & GENHD_FL_UP) {
- if (blk_get_integrity(ns->disk))
- blk_integrity_unregister(ns->disk);
- del_gendisk(ns->disk);
- }
- if (kill || !blk_queue_dying(ns->queue)) {
- blk_mq_abort_requeue_list(ns->queue);
- blk_cleanup_queue(ns->queue);
- }
-}
-
-static void nvme_scan_namespaces(struct nvme_dev *dev, unsigned nn)
-{
- struct nvme_ns *ns, *next;
- unsigned i;
-
- for (i = 1; i <= nn; i++) {
- ns = nvme_find_ns(dev, i);
- if (ns) {
- if (revalidate_disk(ns->disk)) {
- nvme_ns_remove(ns);
- nvme_free_namespace(ns);
- }
- } else
- nvme_alloc_ns(dev, i);
- }
- list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
- if (ns->ns_id > nn) {
- nvme_ns_remove(ns);
- nvme_free_namespace(ns);
- }
- }
- list_sort(NULL, &dev->namespaces, ns_cmp);
-}
-
-static void nvme_dev_scan(struct work_struct *work)
-{
- struct nvme_dev *dev = container_of(work, struct nvme_dev,
scan_work);
- struct nvme_id_ctrl *ctrl;
-
- if (!dev->tagset.tags)
- return;
- if (nvme_identify_ctrl(dev, &ctrl))
- return;
- nvme_scan_namespaces(dev, le32_to_cpup(&ctrl->nn));
- kfree(ctrl);
-}
-
-/*
- * Return: error value if an error occurred setting up the queues or
calling
- * Identify Device. 0 if these succeeded, even if adding some of the
- * namespaces failed. At the moment, these failures are silent. TBD
which
- * failures should be reported.
- */
-static int nvme_dev_add(struct nvme_dev *dev)
-{
- struct pci_dev *pdev = to_pci_dev(dev->dev);
- int res;
- struct nvme_id_ctrl *ctrl;
- int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12;
-
- res = nvme_identify_ctrl(dev, &ctrl);
- if (res) {
- dev_err(dev->dev, "Identify Controller failed (%d)\n",
res);
- return -EIO;
- }
-
- dev->oncs = le16_to_cpup(&ctrl->oncs);
- dev->abort_limit = ctrl->acl + 1;
- dev->vwc = ctrl->vwc;
- memcpy(dev->serial, ctrl->sn, sizeof(ctrl->sn));
- memcpy(dev->model, ctrl->mn, sizeof(ctrl->mn));
- memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr));
- if (ctrl->mdts)
- dev->max_hw_sectors = 1 << (ctrl->mdts + shift - 9);
- if ((pdev->vendor == PCI_VENDOR_ID_INTEL) &&
- (pdev->device == 0x0953) && ctrl->vs[3]) {
- unsigned int max_hw_sectors;
-
- dev->stripe_size = 1 << (ctrl->vs[3] + shift);
- max_hw_sectors = dev->stripe_size >> (shift - 9);
- if (dev->max_hw_sectors) {
- dev->max_hw_sectors = min(max_hw_sectors,
- dev
->max_hw_sectors);
- } else
- dev->max_hw_sectors = max_hw_sectors;
- }
- kfree(ctrl);
-
- if (!dev->tagset.tags) {
- dev->tagset.ops = &nvme_mq_ops;
- dev->tagset.nr_hw_queues = dev->online_queues - 1;
- dev->tagset.timeout = NVME_IO_TIMEOUT;
- dev->tagset.numa_node = dev_to_node(dev->dev);
- dev->tagset.queue_depth =
- min_t(int, dev->q_depth,
BLK_MQ_MAX_DEPTH) - 1;
- dev->tagset.cmd_size = nvme_cmd_size(dev);
- dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
- dev->tagset.driver_data = dev;
-
- if (blk_mq_alloc_tag_set(&dev->tagset))
- return 0;
- }
- schedule_work(&dev->scan_work);
- return 0;
-}
-
-static int nvme_dev_map(struct nvme_dev *dev)
-{
- u64 cap;
- int bars, result = -ENOMEM;
- struct pci_dev *pdev = to_pci_dev(dev->dev);
-
- if (pci_enable_device_mem(pdev))
- return result;
-
- dev->entry[0].vector = pdev->irq;
- pci_set_master(pdev);
- bars = pci_select_bars(pdev, IORESOURCE_MEM);
- if (!bars)
- goto disable_pci;
-
- if (pci_request_selected_regions(pdev, bars, "nvme"))
- goto disable_pci;
-
- if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)) &&
- dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(32)))
- goto disable;
-
- dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
- if (!dev->bar)
- goto disable;
-
- if (readl(&dev->bar->csts) == -1) {
- result = -ENODEV;
- goto unmap;
- }
-
- /*
- * Some devices don't advertse INTx interrupts, pre-enable a
single
- * MSIX vec for setup. We'll adjust this later.
- */
- if (!pdev->irq) {
- result = pci_enable_msix(pdev, dev->entry, 1);
- if (result < 0)
- goto unmap;
- }
-
- cap = readq(&dev->bar->cap);
- dev->q_depth = min_t(int, NVME_CAP_MQES(cap) + 1,
NVME_Q_DEPTH);
- dev->db_stride = 1 << NVME_CAP_STRIDE(cap);
- dev->dbs = ((void __iomem *)dev->bar) + 4096;
- if (readl(&dev->bar->vs) >= NVME_VS(1, 2))
- dev->cmb = nvme_map_cmb(dev);
-
- return 0;
-
- unmap:
- iounmap(dev->bar);
- dev->bar = NULL;
- disable:
- pci_release_regions(pdev);
- disable_pci:
- pci_disable_device(pdev);
- return result;
-}
-
-static void nvme_dev_unmap(struct nvme_dev *dev)
-{
- struct pci_dev *pdev = to_pci_dev(dev->dev);
-
- if (pdev->msi_enabled)
- pci_disable_msi(pdev);
- else if (pdev->msix_enabled)
- pci_disable_msix(pdev);
-
- if (dev->bar) {
- iounmap(dev->bar);
- dev->bar = NULL;
- pci_release_regions(pdev);
- }
-
- if (pci_is_enabled(pdev))
- pci_disable_device(pdev);
-}
-
-struct nvme_delq_ctx {
- struct task_struct *waiter;
- struct kthread_worker *worker;
- atomic_t refcount;
-};
-
-static void nvme_wait_dq(struct nvme_delq_ctx *dq, struct nvme_dev
*dev)
-{
- dq->waiter = current;
- mb();
-
- for (;;) {
- set_current_state(TASK_KILLABLE);
- if (!atomic_read(&dq->refcount))
- break;
- if (!schedule_timeout(ADMIN_TIMEOUT) ||
- fatal_signal_pending(current))
{
- /*
- * Disable the controller first since we can't
trust it
- * at this point, but leave the admin queue
enabled
- * until all queue deletion requests are
flushed.
- * FIXME: This may take a while if there are
more h/w
- * queues than admin tags.
- */
- set_current_state(TASK_RUNNING);
- nvme_disable_ctrl(dev, readq(&dev->bar->cap));
- nvme_clear_queue(dev->queues[0]);
- flush_kthread_worker(dq->worker);
- nvme_disable_queue(dev, 0);
- return;
- }
- }
- set_current_state(TASK_RUNNING);
-}
-
-static void nvme_put_dq(struct nvme_delq_ctx *dq)
-{
- atomic_dec(&dq->refcount);
- if (dq->waiter)
- wake_up_process(dq->waiter);
-}
-
-static struct nvme_delq_ctx *nvme_get_dq(struct nvme_delq_ctx *dq)
-{
- atomic_inc(&dq->refcount);
- return dq;
-}
-
-static void nvme_del_queue_end(struct nvme_queue *nvmeq)
-{
- struct nvme_delq_ctx *dq = nvmeq->cmdinfo.ctx;
- nvme_put_dq(dq);
-}
-
-static int adapter_async_del_queue(struct nvme_queue *nvmeq, u8
opcode,
- kthread_work_func_t
fn)
-{
- struct nvme_command c;
-
- memset(&c, 0, sizeof(c));
- c.delete_queue.opcode = opcode;
- c.delete_queue.qid = cpu_to_le16(nvmeq->qid);
-
- init_kthread_work(&nvmeq->cmdinfo.work, fn);
- return nvme_submit_admin_async_cmd(nvmeq->dev, &c, &nvmeq
->cmdinfo,
- ADMIN_
TIMEOUT);
-}
-
-static void nvme_del_cq_work_handler(struct kthread_work *work)
-{
- struct nvme_queue *nvmeq = container_of(work, struct
nvme_queue,
- cmdinfo.work);
- nvme_del_queue_end(nvmeq);
-}
-
-static int nvme_delete_cq(struct nvme_queue *nvmeq)
-{
- return adapter_async_del_queue(nvmeq, nvme_admin_delete_cq,
- nvme_del_cq_work_handl
er);
-}
-
-static void nvme_del_sq_work_handler(struct kthread_work *work)
-{
- struct nvme_queue *nvmeq = container_of(work, struct
nvme_queue,
- cmdinfo.work);
- int status = nvmeq->cmdinfo.status;
-
- if (!status)
- status = nvme_delete_cq(nvmeq);
- if (status)
- nvme_del_queue_end(nvmeq);
-}
-
-static int nvme_delete_sq(struct nvme_queue *nvmeq)
-{
- return adapter_async_del_queue(nvmeq, nvme_admin_delete_sq,
- nvme_del_sq_work_handl
er);
-}
-
-static void nvme_del_queue_start(struct kthread_work *work)
-{
- struct nvme_queue *nvmeq = container_of(work, struct
nvme_queue,
- cmdinfo.work);
- if (nvme_delete_sq(nvmeq))
- nvme_del_queue_end(nvmeq);
-}
-
-static void nvme_disable_io_queues(struct nvme_dev *dev)
-{
- int i;
- DEFINE_KTHREAD_WORKER_ONSTACK(worker);
- struct nvme_delq_ctx dq;
- struct task_struct *kworker_task =
kthread_run(kthread_worker_fn,
- &worker, "nvme%d", dev
->instance);
-
- if (IS_ERR(kworker_task)) {
- dev_err(dev->dev,
- "Failed to create queue del task\n");
- for (i = dev->queue_count - 1; i > 0; i--)
- nvme_disable_queue(dev, i);
- return;
- }
-
- dq.waiter = NULL;
- atomic_set(&dq.refcount, 0);
- dq.worker = &worker;
- for (i = dev->queue_count - 1; i > 0; i--) {
- struct nvme_queue *nvmeq = dev->queues[i];
-
- if (nvme_suspend_queue(nvmeq))
- continue;
- nvmeq->cmdinfo.ctx = nvme_get_dq(&dq);
- nvmeq->cmdinfo.worker = dq.worker;
- init_kthread_work(&nvmeq->cmdinfo.work,
nvme_del_queue_start);
- queue_kthread_work(dq.worker, &nvmeq->cmdinfo.work);
- }
- nvme_wait_dq(&dq, dev);
- kthread_stop(kworker_task);
-}
-
-/*
-* Remove the node from the device list and check
-* for whether or not we need to stop the nvme_thread.
-*/
-static void nvme_dev_list_remove(struct nvme_dev *dev)
-{
- struct task_struct *tmp = NULL;
-
- spin_lock(&dev_list_lock);
- list_del_init(&dev->node);
- if (list_empty(&dev_list) && !IS_ERR_OR_NULL(nvme_thread)) {
- tmp = nvme_thread;
- nvme_thread = NULL;
- }
- spin_unlock(&dev_list_lock);
-
- if (tmp)
- kthread_stop(tmp);
-}
-
-static void nvme_freeze_queues(struct nvme_dev *dev)
-{
- struct nvme_ns *ns;
-
- list_for_each_entry(ns, &dev->namespaces, list) {
- blk_mq_freeze_queue_start(ns->queue);
-
- spin_lock_irq(ns->queue->queue_lock);
- queue_flag_set(QUEUE_FLAG_STOPPED, ns->queue);
- spin_unlock_irq(ns->queue->queue_lock);
-
- blk_mq_cancel_requeue_work(ns->queue);
- blk_mq_stop_hw_queues(ns->queue);
- }
-}
-
-static void nvme_unfreeze_queues(struct nvme_dev *dev)
-{
- struct nvme_ns *ns;
-
- list_for_each_entry(ns, &dev->namespaces, list) {
- queue_flag_clear_unlocked(QUEUE_FLAG_STOPPED, ns
->queue);
- blk_mq_unfreeze_queue(ns->queue);
- blk_mq_start_stopped_hw_queues(ns->queue, true);
- blk_mq_kick_requeue_list(ns->queue);
- }
-}
-
-static void nvme_dev_shutdown(struct nvme_dev *dev)
-{
- int i;
- u32 csts = -1;
-
- nvme_dev_list_remove(dev);
-
- if (dev->bar) {
- nvme_freeze_queues(dev);
- csts = readl(&dev->bar->csts);
- }
- if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) {
- for (i = dev->queue_count - 1; i >= 0; i--) {
- struct nvme_queue *nvmeq = dev->queues[i];
- nvme_suspend_queue(nvmeq);
- }
- } else {
- nvme_disable_io_queues(dev);
- nvme_shutdown_ctrl(dev);
- nvme_disable_queue(dev, 0);
- }
- nvme_dev_unmap(dev);
-
- for (i = dev->queue_count - 1; i >= 0; i--)
- nvme_clear_queue(dev->queues[i]);
-}
-
-static void nvme_dev_remove(struct nvme_dev *dev)
-{
- struct nvme_ns *ns;
-
- list_for_each_entry(ns, &dev->namespaces, list)
- nvme_ns_remove(ns);
-}
-
-static int nvme_setup_prp_pools(struct nvme_dev *dev)
-{
- dev->prp_page_pool = dma_pool_create("prp list page", dev
->dev,
- PAGE_SIZE, PAGE_SIZE,
0);
- if (!dev->prp_page_pool)
- return -ENOMEM;
-
- /* Optimisation for I/Os between 4k and 128k */
- dev->prp_small_pool = dma_pool_create("prp list 256", dev
->dev,
- 256, 256, 0);
- if (!dev->prp_small_pool) {
- dma_pool_destroy(dev->prp_page_pool);
- return -ENOMEM;
- }
- return 0;
-}
-
-static void nvme_release_prp_pools(struct nvme_dev *dev)
-{
- dma_pool_destroy(dev->prp_page_pool);
- 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->instance = instance;
- return 0;
-}
-
-static void nvme_release_instance(struct nvme_dev *dev)
-{
- spin_lock(&dev_list_lock);
- ida_remove(&nvme_instance_ida, dev->instance);
- spin_unlock(&dev_list_lock);
-}
-
-static void nvme_free_namespaces(struct nvme_dev *dev)
-{
- struct nvme_ns *ns, *next;
-
- list_for_each_entry_safe(ns, next, &dev->namespaces, list)
- nvme_free_namespace(ns);
-}
-
-static void nvme_free_dev(struct kref *kref)
-{
- struct nvme_dev *dev = container_of(kref, struct nvme_dev,
kref);
-
- put_device(dev->dev);
- put_device(dev->device);
- nvme_free_namespaces(dev);
- nvme_release_instance(dev);
- if (dev->tagset.tags)
- blk_mq_free_tag_set(&dev->tagset);
- if (dev->admin_q)
- blk_put_queue(dev->admin_q);
- kfree(dev->queues);
- kfree(dev->entry);
- 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->instance == instance) {
- if (!dev->admin_q) {
- ret = -EWOULDBLOCK;
- break;
- }
- if (!kref_get_unless_zero(&dev->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;
- kref_put(&dev->kref, nvme_free_dev);
- 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, NULL, (void __user *)arg);
- case NVME_IOCTL_IO_CMD:
- if (list_empty(&dev->namespaces))
- return -ENOTTY;
- ns = list_first_entry(&dev->namespaces, struct
nvme_ns, list);
- return nvme_user_cmd(dev, 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_set_irq_hints(struct nvme_dev *dev)
-{
- struct nvme_queue *nvmeq;
- int i;
-
- for (i = 0; i < dev->online_queues; i++) {
- nvmeq = dev->queues[i];
-
- if (!nvmeq->tags || !(*nvmeq->tags))
- continue;
-
- irq_set_affinity_hint(dev->entry[nvmeq
->cq_vector].vector,
- blk_mq_tags_cpumask(*nvmeq
->tags));
- }
-}
-
-static int nvme_dev_start(struct nvme_dev *dev)
-{
- int result;
- bool start_thread = false;
-
- result = nvme_dev_map(dev);
- if (result)
- return result;
-
- result = nvme_configure_admin_queue(dev);
- if (result)
- goto unmap;
-
- spin_lock(&dev_list_lock);
- if (list_empty(&dev_list) && IS_ERR_OR_NULL(nvme_thread)) {
- start_thread = true;
- nvme_thread = NULL;
- }
- list_add(&dev->node, &dev_list);
- spin_unlock(&dev_list_lock);
-
- if (start_thread) {
- nvme_thread = kthread_run(nvme_kthread, NULL, "nvme");
- wake_up_all(&nvme_kthread_wait);
- } else
- wait_event_killable(nvme_kthread_wait, nvme_thread);
-
- if (IS_ERR_OR_NULL(nvme_thread)) {
- result = nvme_thread ? PTR_ERR(nvme_thread) : -EINTR;
- goto disable;
- }
-
- nvme_init_queue(dev->queues[0], 0);
- result = nvme_alloc_admin_tags(dev);
- if (result)
- goto disable;
-
- result = nvme_setup_io_queues(dev);
- if (result)
- goto free_tags;
-
- nvme_set_irq_hints(dev);
-
- dev->event_limit = 1;
- return result;
-
- free_tags:
- nvme_dev_remove_admin(dev);
- blk_put_queue(dev->admin_q);
- dev->admin_q = NULL;
- dev->queues[0]->tags = NULL;
- disable:
- nvme_disable_queue(dev, 0);
- nvme_dev_list_remove(dev);
- unmap:
- nvme_dev_unmap(dev);
- return result;
-}
-
-static int nvme_remove_dead_ctrl(void *arg)
-{
- struct nvme_dev *dev = (struct nvme_dev *)arg;
- struct pci_dev *pdev = to_pci_dev(dev->dev);
-
- if (pci_get_drvdata(pdev))
- pci_stop_and_remove_bus_device_locked(pdev);
- kref_put(&dev->kref, nvme_free_dev);
- return 0;
-}
-
-static void nvme_remove_disks(struct work_struct *ws)
-{
- struct nvme_dev *dev = container_of(ws, struct nvme_dev,
reset_work);
-
- nvme_free_queues(dev, 1);
- nvme_dev_remove(dev);
-}
-
-static int nvme_dev_resume(struct nvme_dev *dev)
-{
- int ret;
-
- ret = nvme_dev_start(dev);
- if (ret)
- return ret;
- if (dev->online_queues < 2) {
- spin_lock(&dev_list_lock);
- dev->reset_workfn = nvme_remove_disks;
- queue_work(nvme_workq, &dev->reset_work);
- spin_unlock(&dev_list_lock);
- } else {
- nvme_unfreeze_queues(dev);
- nvme_dev_add(dev);
- nvme_set_irq_hints(dev);
- }
- return 0;
-}
-
-static void nvme_dead_ctrl(struct nvme_dev *dev)
-{
- dev_warn(dev->dev, "Device failed to resume\n");
- kref_get(&dev->kref);
- if (IS_ERR(kthread_run(nvme_remove_dead_ctrl, dev, "nvme%d",
- dev->instance))) {
- dev_err(dev->dev,
- "Failed to start controller remove task\n");
- kref_put(&dev->kref, nvme_free_dev);
- }
-}
-
-static void nvme_dev_reset(struct nvme_dev *dev)
-{
- bool in_probe = work_busy(&dev->probe_work);
-
- nvme_dev_shutdown(dev);
-
- /* Synchronize with device probe so that work will see failure
status
- * and exit gracefully without trying to schedule another
reset */
- flush_work(&dev->probe_work);
-
- /* Fail this device if reset occured during probe to avoid
- * infinite initialization loops. */
- if (in_probe) {
- nvme_dead_ctrl(dev);
- return;
- }
- /* Schedule device resume asynchronously so the reset work is
available
- * to cleanup errors that may occur during reinitialization */
- schedule_work(&dev->probe_work);
-}
-
-static void nvme_reset_failed_dev(struct work_struct *ws)
-{
- struct nvme_dev *dev = container_of(ws, struct nvme_dev,
reset_work);
- nvme_dev_reset(dev);
-}
-
-static void nvme_reset_workfn(struct work_struct *work)
-{
- struct nvme_dev *dev = container_of(work, struct nvme_dev,
reset_work);
- dev->reset_workfn(work);
-}
-
-static int nvme_reset(struct nvme_dev *dev)
-{
- int ret = -EBUSY;
-
- if (!dev->admin_q || blk_queue_dying(dev->admin_q))
- return -ENODEV;
-
- spin_lock(&dev_list_lock);
- if (!work_pending(&dev->reset_work)) {
- dev->reset_workfn = nvme_reset_failed_dev;
- queue_work(nvme_workq, &dev->reset_work);
- ret = 0;
- }
- spin_unlock(&dev_list_lock);
-
- if (!ret) {
- flush_work(&dev->reset_work);
- flush_work(&dev->probe_work);
- return 0;
- }
-
- 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 void nvme_async_probe(struct work_struct *work);
-static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id
*id)
-{
- int node, result = -ENOMEM;
- struct nvme_dev *dev;
-
- node = dev_to_node(&pdev->dev);
- if (node == NUMA_NO_NODE)
- set_dev_node(&pdev->dev, 0);
-
- dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
- if (!dev)
- return -ENOMEM;
- dev->entry = kzalloc_node(num_possible_cpus() * sizeof(*dev
->entry),
- GFP_KERNEL,
node);
- if (!dev->entry)
- goto free;
- dev->queues = kzalloc_node((num_possible_cpus() + 1) *
sizeof(void *),
- GFP_KERNEL,
node);
- if (!dev->queues)
- goto free;
-
- INIT_LIST_HEAD(&dev->namespaces);
- dev->reset_workfn = nvme_reset_failed_dev;
- INIT_WORK(&dev->reset_work, nvme_reset_workfn);
- dev->dev = get_device(&pdev->dev);
- pci_set_drvdata(pdev, dev);
- result = nvme_set_instance(dev);
- if (result)
- goto put_pci;
-
- result = nvme_setup_prp_pools(dev);
- if (result)
- goto release;
-
- kref_init(&dev->kref);
- dev->device = device_create(nvme_class, &pdev->dev,
- MKDEV(nvme_char_major, dev->instance),
- dev, "nvme%d", dev->instance);
- if (IS_ERR(dev->device)) {
- result = PTR_ERR(dev->device);
- goto release_pools;
- }
- get_device(dev->device);
- dev_set_drvdata(dev->device, dev);
-
- result = device_create_file(dev->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_async_probe);
- schedule_work(&dev->probe_work);
- return 0;
-
- put_dev:
- device_destroy(nvme_class, MKDEV(nvme_char_major, dev
->instance));
- put_device(dev->device);
- release_pools:
- nvme_release_prp_pools(dev);
- release:
- nvme_release_instance(dev);
- put_pci:
- put_device(dev->dev);
- free:
- kfree(dev->queues);
- kfree(dev->entry);
- kfree(dev);
- return result;
-}
-
-static void nvme_async_probe(struct work_struct *work)
-{
- struct nvme_dev *dev = container_of(work, struct nvme_dev,
probe_work);
-
- if (nvme_dev_resume(dev) && !work_busy(&dev->reset_work))
- nvme_dead_ctrl(dev);
-}
-
-static void nvme_reset_notify(struct pci_dev *pdev, bool prepare)
-{
- struct nvme_dev *dev = pci_get_drvdata(pdev);
-
- if (prepare)
- nvme_dev_shutdown(dev);
- else
- nvme_dev_resume(dev);
-}
-
-static void nvme_shutdown(struct pci_dev *pdev)
-{
- struct nvme_dev *dev = pci_get_drvdata(pdev);
- nvme_dev_shutdown(dev);
-}
-
-static void nvme_remove(struct pci_dev *pdev)
-{
- struct nvme_dev *dev = pci_get_drvdata(pdev);
-
- spin_lock(&dev_list_lock);
- list_del_init(&dev->node);
- spin_unlock(&dev_list_lock);
-
- pci_set_drvdata(pdev, NULL);
- flush_work(&dev->probe_work);
- flush_work(&dev->reset_work);
- flush_work(&dev->scan_work);
- device_remove_file(dev->device, &dev_attr_reset_controller);
- nvme_dev_remove(dev);
- nvme_dev_shutdown(dev);
- nvme_dev_remove_admin(dev);
- device_destroy(nvme_class, MKDEV(nvme_char_major, dev
->instance));
- nvme_free_queues(dev, 0);
- nvme_release_cmb(dev);
- nvme_release_prp_pools(dev);
- kref_put(&dev->kref, nvme_free_dev);
-}
-
-/* These functions are yet to be implemented */
-#define nvme_error_detected NULL
-#define nvme_dump_registers NULL
-#define nvme_link_reset NULL
-#define nvme_slot_reset NULL
-#define nvme_error_resume NULL
-
-#ifdef CONFIG_PM_SLEEP
-static int nvme_suspend(struct device *dev)
-{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct nvme_dev *ndev = pci_get_drvdata(pdev);
-
- nvme_dev_shutdown(ndev);
- return 0;
-}
-
-static int nvme_resume(struct device *dev)
-{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct nvme_dev *ndev = pci_get_drvdata(pdev);
-
- if (nvme_dev_resume(ndev) && !work_busy(&ndev->reset_work)) {
- ndev->reset_workfn = nvme_reset_failed_dev;
- queue_work(nvme_workq, &ndev->reset_work);
- }
- return 0;
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(nvme_dev_pm_ops, nvme_suspend, nvme_resume);
-
-static const struct pci_error_handlers nvme_err_handler = {
- .error_detected = nvme_error_detected,
- .mmio_enabled = nvme_dump_registers,
- .link_reset = nvme_link_reset,
- .slot_reset = nvme_slot_reset,
- .resume = nvme_error_resume,
- .reset_notify = nvme_reset_notify,
-};
-
-/* Move to pci_ids.h later */
-#define PCI_CLASS_STORAGE_EXPRESS 0x010802
-
-static const struct pci_device_id nvme_id_table[] = {
- { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
- { 0, }
-};
-MODULE_DEVICE_TABLE(pci, nvme_id_table);
-
-static struct pci_driver nvme_driver = {
- .name = "nvme",
- .id_table = nvme_id_table,
- .probe = nvme_probe,
- .remove = nvme_remove,
- .shutdown = nvme_shutdown,
- .driver = {
- .pm = &nvme_dev_pm_ops,
- },
- .err_handler = &nvme_err_handler,
-};
-
-static int __init nvme_init(void)
-{
- int result;
-
- init_waitqueue_head(&nvme_kthread_wait);
-
- nvme_workq = create_singlethread_workqueue("nvme");
- if (!nvme_workq)
- return -ENOMEM;
-
- result = register_blkdev(nvme_major, "nvme");
- if (result < 0)
- goto kill_workq;
- 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;
- }
-
- result = pci_register_driver(&nvme_driver);
- if (result)
- goto destroy_class;
- return 0;
-
- destroy_class:
- class_destroy(nvme_class);
- unregister_chrdev:
- __unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
- unregister_blkdev:
- unregister_blkdev(nvme_major, "nvme");
- kill_workq:
- destroy_workqueue(nvme_workq);
- return result;
-}
-
-static void __exit nvme_exit(void)
-{
- pci_unregister_driver(&nvme_driver);
- unregister_blkdev(nvme_major, "nvme");
- 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();
-}
-
-MODULE_AUTHOR("Matthew Wilcox <willy at linux.intel.com>");
-MODULE_LICENSE("GPL");
-MODULE_VERSION("1.0");
-module_init(nvme_init);
-module_exit(nvme_exit);
diff --git a/drivers/block/nvme-scsi.c b/drivers/block/nvme-scsi.c
deleted file mode 100644
index e5a63f0..0000000
--- a/drivers/block/nvme-scsi.c
+++ /dev/null
@@ -1,2556 +0,0 @@
-/*
- * 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.
- */
-
-/*
- * Refer to the SCSI-NVMe Translation spec for details on how
- * each command is translated.
- */
-
-#include <linux/nvme.h>
-#include <linux/bio.h>
-#include <linux/bitops.h>
-#include <linux/blkdev.h>
-#include <linux/compat.h>
-#include <linux/delay.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/genhd.h>
-#include <linux/idr.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/kdev_t.h>
-#include <linux/kthread.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/pci.h>
-#include <linux/poison.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/types.h>
-#include <asm/unaligned.h>
-#include <scsi/sg.h>
-#include <scsi/scsi.h>
-
-
-static int sg_version_num = 30534; /* 2 digits for each component
*/
-
-/* VPD Page Codes */
-#define VPD_SUPPORTED_PAGES 0x00
-#define VPD_SERIAL_NUMBER 0x80
-#define VPD_DEVICE_IDENTIFIERS 0x83
-#define VPD_EXTENDED_INQUIRY 0x86
-#define VPD_BLOCK_LIMITS 0xB0
-#define VPD_BLOCK_DEV_CHARACTERISTICS 0xB1
-
-/* format unit paramter list offsets */
-#define FORMAT_UNIT_SHORT_PARM_LIST_LEN 4
-#define FORMAT_UNIT_LONG_PARM_LIST_LEN 8
-#define FORMAT_UNIT_PROT_INT_OFFSET 3
-#define FORMAT_UNIT_PROT_FIELD_USAGE_OFFSET 0
-#define FORMAT_UNIT_PROT_FIELD_USAGE_MASK 0x07
-
-/* Misc. defines */
-#define FIXED_SENSE_DATA 0x70
-#define DESC_FORMAT_SENSE_DATA 0x72
-#define FIXED_SENSE_DATA_ADD_LENGTH 10
-#define LUN_ENTRY_SIZE 8
-#define LUN_DATA_HEADER_SIZE 8
-#define ALL_LUNS_RETURNED 0x02
-#define ALL_WELL_KNOWN_LUNS_RETURNED 0x01
-#define RESTRICTED_LUNS_RETURNED 0x00
-#define NVME_POWER_STATE_START_VALID 0x00
-#define NVME_POWER_STATE_ACTIVE 0x01
-#define NVME_POWER_STATE_IDLE 0x02
-#define NVME_POWER_STATE_STANDBY 0x03
-#define NVME_POWER_STATE_LU_CONTROL 0x07
-#define POWER_STATE_0 0
-#define POWER_STATE_1 1
-#define POWER_STATE_2 2
-#define POWER_STATE_3 3
-#define DOWNLOAD_SAVE_ACTIVATE 0x05
-#define DOWNLOAD_SAVE_DEFER_ACTIVATE 0x0E
-#define ACTIVATE_DEFERRED_MICROCODE 0x0F
-#define FORMAT_UNIT_IMMED_MASK 0x2
-#define FORMAT_UNIT_IMMED_OFFSET 1
-#define KELVIN_TEMP_FACTOR 273
-#define FIXED_FMT_SENSE_DATA_SIZE 18
-#define DESC_FMT_SENSE_DATA_SIZE 8
-
-/* SCSI/NVMe defines and bit masks */
-#define INQ_STANDARD_INQUIRY_PAGE 0x00
-#define INQ_SUPPORTED_VPD_PAGES_PAGE 0x00
-#define INQ_UNIT_SERIAL_NUMBER_PAGE 0x80
-#define INQ_DEVICE_IDENTIFICATION_PAGE 0x83
-#define INQ_EXTENDED_INQUIRY_DATA_PAGE 0x86
-#define INQ_BDEV_LIMITS_PAGE 0xB0
-#define INQ_BDEV_CHARACTERISTICS_PAGE 0xB1
-#define INQ_SERIAL_NUMBER_LENGTH 0x14
-#define INQ_NUM_SUPPORTED_VPD_PAGES 6
-#define VERSION_SPC_4 0x06
-#define ACA_UNSUPPORTED 0
-#define STANDARD_INQUIRY_LENGTH 36
-#define ADDITIONAL_STD_INQ_LENGTH 31
-#define EXTENDED_INQUIRY_DATA_PAGE_LENGTH 0x3C
-#define RESERVED_FIELD 0
-
-/* Mode Sense/Select defines */
-#define MODE_PAGE_INFO_EXCEP 0x1C
-#define MODE_PAGE_CACHING 0x08
-#define MODE_PAGE_CONTROL 0x0A
-#define MODE_PAGE_POWER_CONDITION 0x1A
-#define MODE_PAGE_RETURN_ALL 0x3F
-#define MODE_PAGE_BLK_DES_LEN 0x08
-#define MODE_PAGE_LLBAA_BLK_DES_LEN 0x10
-#define MODE_PAGE_CACHING_LEN 0x14
-#define MODE_PAGE_CONTROL_LEN 0x0C
-#define MODE_PAGE_POW_CND_LEN 0x28
-#define MODE_PAGE_INF_EXC_LEN 0x0C
-#define MODE_PAGE_ALL_LEN 0x54
-#define MODE_SENSE6_MPH_SIZE 4
-#define MODE_SENSE_PAGE_CONTROL_MASK 0xC0
-#define MODE_SENSE_PAGE_CODE_OFFSET 2
-#define MODE_SENSE_PAGE_CODE_MASK 0x3F
-#define MODE_SENSE_LLBAA_MASK 0x10
-#define MODE_SENSE_LLBAA_SHIFT 4
-#define MODE_SENSE_DBD_MASK 8
-#define MODE_SENSE_DBD_SHIFT 3
-#define MODE_SENSE10_MPH_SIZE 8
-#define MODE_SELECT_CDB_PAGE_FORMAT_MASK 0x10
-#define MODE_SELECT_CDB_SAVE_PAGES_MASK 0x1
-#define MODE_SELECT_6_BD_OFFSET 3
-#define MODE_SELECT_10_BD_OFFSET 6
-#define MODE_SELECT_10_LLBAA_OFFSET 4
-#define MODE_SELECT_10_LLBAA_MASK 1
-#define MODE_SELECT_6_MPH_SIZE 4
-#define MODE_SELECT_10_MPH_SIZE 8
-#define CACHING_MODE_PAGE_WCE_MASK 0x04
-#define MODE_SENSE_BLK_DESC_ENABLED 0
-#define MODE_SENSE_BLK_DESC_COUNT 1
-#define MODE_SELECT_PAGE_CODE_MASK 0x3F
-#define SHORT_DESC_BLOCK 8
-#define LONG_DESC_BLOCK 16
-#define MODE_PAGE_POW_CND_LEN_FIELD 0x26
-#define MODE_PAGE_INF_EXC_LEN_FIELD 0x0A
-#define MODE_PAGE_CACHING_LEN_FIELD 0x12
-#define MODE_PAGE_CONTROL_LEN_FIELD 0x0A
-#define MODE_SENSE_PC_CURRENT_VALUES 0
-
-/* Log Sense defines */
-#define LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE 0x00
-#define LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH 0x07
-#define LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE 0x2F
-#define LOG_PAGE_TEMPERATURE_PAGE 0x0D
-#define LOG_SENSE_CDB_SP_NOT_ENABLED 0
-#define LOG_SENSE_CDB_PC_MASK 0xC0
-#define LOG_SENSE_CDB_PC_SHIFT 6
-#define LOG_SENSE_CDB_PC_CUMULATIVE_VALUES 1
-#define LOG_SENSE_CDB_PAGE_CODE_MASK 0x3F
-#define REMAINING_INFO_EXCP_PAGE_LENGTH 0x8
-#define LOG_INFO_EXCP_PAGE_LENGTH 0xC
-#define REMAINING_TEMP_PAGE_LENGTH 0xC
-#define LOG_TEMP_PAGE_LENGTH 0x10
-#define LOG_TEMP_UNKNOWN 0xFF
-#define SUPPORTED_LOG_PAGES_PAGE_LENGTH 0x3
-
-/* Read Capacity defines */
-#define READ_CAP_10_RESP_SIZE 8
-#define READ_CAP_16_RESP_SIZE 32
-
-/* NVMe Namespace and Command Defines */
-#define BYTES_TO_DWORDS 4
-#define NVME_MAX_FIRMWARE_SLOT 7
-
-/* Report LUNs defines */
-#define REPORT_LUNS_FIRST_LUN_OFFSET 8
-
-/* SCSI ADDITIONAL SENSE Codes */
-
-#define SCSI_ASC_NO_SENSE 0x00
-#define SCSI_ASC_PERIPHERAL_DEV_WRITE_FAULT 0x03
-#define SCSI_ASC_LUN_NOT_READY 0x04
-#define SCSI_ASC_WARNING 0x0B
-#define SCSI_ASC_LOG_BLOCK_GUARD_CHECK_FAILED 0x10
-#define SCSI_ASC_LOG_BLOCK_APPTAG_CHECK_FAILED 0x10
-#define SCSI_ASC_LOG_BLOCK_REFTAG_CHECK_FAILED 0x10
-#define SCSI_ASC_UNRECOVERED_READ_ERROR 0x11
-#define SCSI_ASC_MISCOMPARE_DURING_VERIFY 0x1D
-#define SCSI_ASC_ACCESS_DENIED_INVALID_LUN_ID 0x20
-#define SCSI_ASC_ILLEGAL_COMMAND 0x20
-#define SCSI_ASC_ILLEGAL_BLOCK 0x21
-#define SCSI_ASC_INVALID_CDB 0x24
-#define SCSI_ASC_INVALID_LUN 0x25
-#define SCSI_ASC_INVALID_PARAMETER 0x26
-#define SCSI_ASC_FORMAT_COMMAND_FAILED 0x31
-#define SCSI_ASC_INTERNAL_TARGET_FAILURE 0x44
-
-/* SCSI ADDITIONAL SENSE Code Qualifiers */
-
-#define SCSI_ASCQ_CAUSE_NOT_REPORTABLE 0x00
-#define SCSI_ASCQ_FORMAT_COMMAND_FAILED 0x01
-#define SCSI_ASCQ_LOG_BLOCK_GUARD_CHECK_FAILED 0x01
-#define SCSI_ASCQ_LOG_BLOCK_APPTAG_CHECK_FAILED 0x02
-#define SCSI_ASCQ_LOG_BLOCK_REFTAG_CHECK_FAILED 0x03
-#define SCSI_ASCQ_FORMAT_IN_PROGRESS 0x04
-#define SCSI_ASCQ_POWER_LOSS_EXPECTED 0x08
-#define SCSI_ASCQ_INVALID_LUN_ID 0x09
-
-/* copied from drivers/usb/gadget/function/storage_common.h */
-static inline u32 get_unaligned_be24(u8 *buf)
-{
- return 0xffffff & (u32) get_unaligned_be32(buf - 1);
-}
-
-/* Struct to gather data that needs to be extracted from a SCSI CDB.
- Not conforming to any particular CDB variant, but compatible with
all. */
-
-struct nvme_trans_io_cdb {
- u8 fua;
- u8 prot_info;
- u64 lba;
- u32 xfer_len;
-};
-
-
-/* Internal Helper Functions */
-
-
-/* Copy data to userspace memory */
-
-static int nvme_trans_copy_to_user(struct sg_io_hdr *hdr, void *from,
- unsign
ed long n)
-{
- int i;
- void *index = from;
- size_t remaining = n;
- size_t xfer_len;
-
- if (hdr->iovec_count > 0) {
- struct sg_iovec sgl;
-
- for (i = 0; i < hdr->iovec_count; i++) {
- if (copy_from_user(&sgl, hdr->dxferp +
- i * sizeof(struct
sg_iovec),
- sizeof(struct
sg_iovec)))
- return -EFAULT;
- xfer_len = min(remaining, sgl.iov_len);
- if (copy_to_user(sgl.iov_base, index,
xfer_len))
- return -EFAULT;
-
- index += xfer_len;
- remaining -= xfer_len;
- if (remaining == 0)
- break;
- }
- return 0;
- }
-
- if (copy_to_user(hdr->dxferp, from, n))
- return -EFAULT;
- return 0;
-}
-
-/* Copy data from userspace memory */
-
-static int nvme_trans_copy_from_user(struct sg_io_hdr *hdr, void *to,
- unsign
ed long n)
-{
- int i;
- void *index = to;
- size_t remaining = n;
- size_t xfer_len;
-
- if (hdr->iovec_count > 0) {
- struct sg_iovec sgl;
-
- for (i = 0; i < hdr->iovec_count; i++) {
- if (copy_from_user(&sgl, hdr->dxferp +
- i * sizeof(struct
sg_iovec),
- sizeof(struct
sg_iovec)))
- return -EFAULT;
- xfer_len = min(remaining, sgl.iov_len);
- if (copy_from_user(index, sgl.iov_base,
xfer_len))
- return -EFAULT;
- index += xfer_len;
- remaining -= xfer_len;
- if (remaining == 0)
- break;
- }
- return 0;
- }
-
- if (copy_from_user(to, hdr->dxferp, n))
- return -EFAULT;
- return 0;
-}
-
-/* Status/Sense Buffer Writeback */
-
-static int nvme_trans_completion(struct sg_io_hdr *hdr, u8 status, u8
sense_key,
- u8 asc, u8 ascq)
-{
- u8 xfer_len;
- u8 resp[DESC_FMT_SENSE_DATA_SIZE];
-
- if (scsi_status_is_good(status)) {
- hdr->status = SAM_STAT_GOOD;
- hdr->masked_status = GOOD;
- hdr->host_status = DID_OK;
- hdr->driver_status = DRIVER_OK;
- hdr->sb_len_wr = 0;
- } else {
- hdr->status = status;
- hdr->masked_status = status >> 1;
- hdr->host_status = DID_OK;
- hdr->driver_status = DRIVER_OK;
-
- memset(resp, 0, DESC_FMT_SENSE_DATA_SIZE);
- resp[0] = DESC_FORMAT_SENSE_DATA;
- resp[1] = sense_key;
- resp[2] = asc;
- resp[3] = ascq;
-
- xfer_len = min_t(u8, hdr->mx_sb_len,
DESC_FMT_SENSE_DATA_SIZE);
- hdr->sb_len_wr = xfer_len;
- if (copy_to_user(hdr->sbp, resp, xfer_len) > 0)
- return -EFAULT;
- }
-
- return 0;
-}
-
-/*
- * Take a status code from a lowlevel routine, and if it was a
positive NVMe
- * error code update the sense data based on it. In either case the
passed
- * in value is returned again, unless an -EFAULT from copy_to_user
overrides
- * it.
- */
-static int nvme_trans_status_code(struct sg_io_hdr *hdr, int nvme_sc)
-{
- u8 status, sense_key, asc, ascq;
- int res;
-
- /* For non-nvme (Linux) errors, simply return the error code
*/
- if (nvme_sc < 0)
- return nvme_sc;
-
- /* Mask DNR, More, and reserved fields */
- switch (nvme_sc & 0x7FF) {
- /* Generic Command Status */
- case NVME_SC_SUCCESS:
- status = SAM_STAT_GOOD;
- sense_key = NO_SENSE;
- asc = SCSI_ASC_NO_SENSE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_INVALID_OPCODE:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = ILLEGAL_REQUEST;
- asc = SCSI_ASC_ILLEGAL_COMMAND;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_INVALID_FIELD:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = ILLEGAL_REQUEST;
- asc = SCSI_ASC_INVALID_CDB;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_DATA_XFER_ERROR:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = MEDIUM_ERROR;
- asc = SCSI_ASC_NO_SENSE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_POWER_LOSS:
- status = SAM_STAT_TASK_ABORTED;
- sense_key = ABORTED_COMMAND;
- asc = SCSI_ASC_WARNING;
- ascq = SCSI_ASCQ_POWER_LOSS_EXPECTED;
- break;
- case NVME_SC_INTERNAL:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = HARDWARE_ERROR;
- asc = SCSI_ASC_INTERNAL_TARGET_FAILURE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_ABORT_REQ:
- status = SAM_STAT_TASK_ABORTED;
- sense_key = ABORTED_COMMAND;
- asc = SCSI_ASC_NO_SENSE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_ABORT_QUEUE:
- status = SAM_STAT_TASK_ABORTED;
- sense_key = ABORTED_COMMAND;
- asc = SCSI_ASC_NO_SENSE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_FUSED_FAIL:
- status = SAM_STAT_TASK_ABORTED;
- sense_key = ABORTED_COMMAND;
- asc = SCSI_ASC_NO_SENSE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_FUSED_MISSING:
- status = SAM_STAT_TASK_ABORTED;
- sense_key = ABORTED_COMMAND;
- asc = SCSI_ASC_NO_SENSE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_INVALID_NS:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = ILLEGAL_REQUEST;
- asc = SCSI_ASC_ACCESS_DENIED_INVALID_LUN_ID;
- ascq = SCSI_ASCQ_INVALID_LUN_ID;
- break;
- case NVME_SC_LBA_RANGE:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = ILLEGAL_REQUEST;
- asc = SCSI_ASC_ILLEGAL_BLOCK;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_CAP_EXCEEDED:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = MEDIUM_ERROR;
- asc = SCSI_ASC_NO_SENSE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_NS_NOT_READY:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = NOT_READY;
- asc = SCSI_ASC_LUN_NOT_READY;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
-
- /* Command Specific Status */
- case NVME_SC_INVALID_FORMAT:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = ILLEGAL_REQUEST;
- asc = SCSI_ASC_FORMAT_COMMAND_FAILED;
- ascq = SCSI_ASCQ_FORMAT_COMMAND_FAILED;
- break;
- case NVME_SC_BAD_ATTRIBUTES:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = ILLEGAL_REQUEST;
- asc = SCSI_ASC_INVALID_CDB;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
-
- /* Media Errors */
- case NVME_SC_WRITE_FAULT:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = MEDIUM_ERROR;
- asc = SCSI_ASC_PERIPHERAL_DEV_WRITE_FAULT;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_READ_ERROR:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = MEDIUM_ERROR;
- asc = SCSI_ASC_UNRECOVERED_READ_ERROR;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_GUARD_CHECK:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = MEDIUM_ERROR;
- asc = SCSI_ASC_LOG_BLOCK_GUARD_CHECK_FAILED;
- ascq = SCSI_ASCQ_LOG_BLOCK_GUARD_CHECK_FAILED;
- break;
- case NVME_SC_APPTAG_CHECK:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = MEDIUM_ERROR;
- asc = SCSI_ASC_LOG_BLOCK_APPTAG_CHECK_FAILED;
- ascq = SCSI_ASCQ_LOG_BLOCK_APPTAG_CHECK_FAILED;
- break;
- case NVME_SC_REFTAG_CHECK:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = MEDIUM_ERROR;
- asc = SCSI_ASC_LOG_BLOCK_REFTAG_CHECK_FAILED;
- ascq = SCSI_ASCQ_LOG_BLOCK_REFTAG_CHECK_FAILED;
- break;
- case NVME_SC_COMPARE_FAILED:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = MISCOMPARE;
- asc = SCSI_ASC_MISCOMPARE_DURING_VERIFY;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_ACCESS_DENIED:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = ILLEGAL_REQUEST;
- asc = SCSI_ASC_ACCESS_DENIED_INVALID_LUN_ID;
- ascq = SCSI_ASCQ_INVALID_LUN_ID;
- break;
-
- /* Unspecified/Default */
- case NVME_SC_CMDID_CONFLICT:
- case NVME_SC_CMD_SEQ_ERROR:
- case NVME_SC_CQ_INVALID:
- case NVME_SC_QID_INVALID:
- case NVME_SC_QUEUE_SIZE:
- case NVME_SC_ABORT_LIMIT:
- case NVME_SC_ABORT_MISSING:
- case NVME_SC_ASYNC_LIMIT:
- case NVME_SC_FIRMWARE_SLOT:
- case NVME_SC_FIRMWARE_IMAGE:
- case NVME_SC_INVALID_VECTOR:
- case NVME_SC_INVALID_LOG_PAGE:
- default:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = ILLEGAL_REQUEST;
- asc = SCSI_ASC_NO_SENSE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- }
-
- res = nvme_trans_completion(hdr, status, sense_key, asc,
ascq);
- return res ? res : nvme_sc;
-}
-
-/* INQUIRY Helper Functions */
-
-static int nvme_trans_standard_inquiry_page(struct nvme_ns *ns,
- struct sg_io_hdr *hdr, u8
*inq_response,
- int alloc_len)
-{
- struct nvme_dev *dev = ns->dev;
- struct nvme_id_ns *id_ns;
- int res;
- int nvme_sc;
- int xfer_len;
- u8 resp_data_format = 0x02;
- u8 protect;
- u8 cmdque = 0x01 << 1;
- u8 fw_offset = sizeof(dev->firmware_rev);
-
- /* nvme ns identify - use DPS value for PROTECT field */
- nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- if (id_ns->dps)
- protect = 0x01;
- else
- protect = 0;
- kfree(id_ns);
-
- memset(inq_response, 0, STANDARD_INQUIRY_LENGTH);
- inq_response[2] = VERSION_SPC_4;
- inq_response[3] = resp_data_format; /*normaca=0 | hisup=0
*/
- inq_response[4] = ADDITIONAL_STD_INQ_LENGTH;
- inq_response[5] = protect; /* sccs=0 | acc=0 | tpgs=0 |
pc3=0 */
- inq_response[7] = cmdque; /* wbus16=0 | sync=0 | vs=0 */
- strncpy(&inq_response[8], "NVMe ", 8);
- strncpy(&inq_response[16], dev->model, 16);
-
- while (dev->firmware_rev[fw_offset - 1] == ' ' && fw_offset >
4)
- fw_offset--;
- fw_offset -= 4;
- strncpy(&inq_response[32], dev->firmware_rev + fw_offset, 4);
-
- xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH);
- return nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
-}
-
-static int nvme_trans_supported_vpd_pages(struct nvme_ns *ns,
- struct sg_io_hdr *hdr, u8
*inq_response,
- int alloc_len)
-{
- int xfer_len;
-
- memset(inq_response, 0, STANDARD_INQUIRY_LENGTH);
- inq_response[1] = INQ_SUPPORTED_VPD_PAGES_PAGE; /* Page Code
*/
- inq_response[3] = INQ_NUM_SUPPORTED_VPD_PAGES; /* Page
Length */
- inq_response[4] = INQ_SUPPORTED_VPD_PAGES_PAGE;
- inq_response[5] = INQ_UNIT_SERIAL_NUMBER_PAGE;
- inq_response[6] = INQ_DEVICE_IDENTIFICATION_PAGE;
- inq_response[7] = INQ_EXTENDED_INQUIRY_DATA_PAGE;
- inq_response[8] = INQ_BDEV_CHARACTERISTICS_PAGE;
- inq_response[9] = INQ_BDEV_LIMITS_PAGE;
-
- xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH);
- return nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
-}
-
-static int nvme_trans_unit_serial_page(struct nvme_ns *ns,
- struct sg_io_hdr *hdr, u8
*inq_response,
- int alloc_len)
-{
- struct nvme_dev *dev = ns->dev;
- int xfer_len;
-
- memset(inq_response, 0, STANDARD_INQUIRY_LENGTH);
- inq_response[1] = INQ_UNIT_SERIAL_NUMBER_PAGE; /* Page Code */
- inq_response[3] = INQ_SERIAL_NUMBER_LENGTH; /* Page Length
*/
- strncpy(&inq_response[4], dev->serial,
INQ_SERIAL_NUMBER_LENGTH);
-
- xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH);
- return nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
-}
-
-static int nvme_trans_device_id_page(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
- u8 *inq_response, int
alloc_len)
-{
- struct nvme_dev *dev = ns->dev;
- int res;
- int nvme_sc;
- int xfer_len;
- __be32 tmp_id = cpu_to_be32(ns->ns_id);
-
- memset(inq_response, 0, alloc_len);
- inq_response[1] = INQ_DEVICE_IDENTIFICATION_PAGE; /* Page
Code */
- if (readl(&dev->bar->vs) >= NVME_VS(1, 1)) {
- struct nvme_id_ns *id_ns;
- void *eui;
- int len;
-
- nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- eui = id_ns->eui64;
- len = sizeof(id_ns->eui64);
- if (readl(&dev->bar->vs) >= NVME_VS(1, 2)) {
- if (bitmap_empty(eui, len * 8)) {
- eui = id_ns->nguid;
- len = sizeof(id_ns->nguid);
- }
- }
- if (bitmap_empty(eui, len * 8)) {
- kfree(id_ns);
- goto scsi_string;
- }
-
- inq_response[3] = 4 + len; /* Page Length */
- /* Designation Descriptor start */
- inq_response[4] = 0x01; /* Proto ID=0h | Code
set=1h */
- inq_response[5] = 0x02; /* PIV=0b | Asso=00b |
Designator Type=2h */
- inq_response[6] = 0x00; /* Rsvd */
- inq_response[7] = len; /* Designator Length */
- memcpy(&inq_response[8], eui, len);
- kfree(id_ns);
- } else {
- scsi_string:
- if (alloc_len < 72) {
- return nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- }
- inq_response[3] = 0x48; /* Page Length */
- /* Designation Descriptor start */
- inq_response[4] = 0x03; /* Proto ID=0h | Code
set=3h */
- inq_response[5] = 0x08; /* PIV=0b | Asso=00b |
Designator Type=8h */
- inq_response[6] = 0x00; /* Rsvd */
- inq_response[7] = 0x44; /* Designator Length */
-
- sprintf(&inq_response[8], "%04x", to_pci_dev(dev->dev)
->vendor);
- memcpy(&inq_response[12], dev->model, sizeof(dev
->model));
- sprintf(&inq_response[52], "%04x", tmp_id);
- memcpy(&inq_response[56], dev->serial, sizeof(dev
->serial));
- }
- xfer_len = alloc_len;
- return nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
-}
-
-static int nvme_trans_ext_inq_page(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
- int alloc_len)
-{
- u8 *inq_response;
- int res;
- int nvme_sc;
- struct nvme_dev *dev = ns->dev;
- struct nvme_id_ctrl *id_ctrl;
- struct nvme_id_ns *id_ns;
- int xfer_len;
- u8 microcode = 0x80;
- u8 spt;
- u8 spt_lut[8] = {0, 0, 2, 1, 4, 6, 5, 7};
- u8 grd_chk, app_chk, ref_chk, protect;
- u8 uask_sup = 0x20;
- u8 v_sup;
- u8 luiclr = 0x01;
-
- inq_response = kmalloc(EXTENDED_INQUIRY_DATA_PAGE_LENGTH,
GFP_KERNEL);
- if (inq_response == NULL)
- return -ENOMEM;
-
- nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- goto out_free_inq;
-
- spt = spt_lut[id_ns->dpc & 0x07] << 3;
- if (id_ns->dps)
- protect = 0x01;
- else
- protect = 0;
- kfree(id_ns);
-
- grd_chk = protect << 2;
- app_chk = protect << 1;
- ref_chk = protect;
-
- nvme_sc = nvme_identify_ctrl(dev, &id_ctrl);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- goto out_free_inq;
-
- v_sup = id_ctrl->vwc;
- kfree(id_ctrl);
-
- memset(inq_response, 0, EXTENDED_INQUIRY_DATA_PAGE_LENGTH);
- inq_response[1] = INQ_EXTENDED_INQUIRY_DATA_PAGE; /* Page
Code */
- inq_response[2] = 0x00; /* Page Length MSB */
- inq_response[3] = 0x3C; /* Page Length LSB */
- inq_response[4] = microcode | spt | grd_chk | app_chk |
ref_chk;
- inq_response[5] = uask_sup;
- inq_response[6] = v_sup;
- inq_response[7] = luiclr;
- inq_response[8] = 0;
- inq_response[9] = 0;
-
- xfer_len = min(alloc_len, EXTENDED_INQUIRY_DATA_PAGE_LENGTH);
- res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
-
- out_free_inq:
- kfree(inq_response);
- return res;
-}
-
-static int nvme_trans_bdev_limits_page(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
- u8 *inq_response, int
alloc_len)
-{
- __be32 max_sectors = cpu_to_be32(
- nvme_block_nr(ns, queue_max_hw_sectors(ns->queue)));
- __be32 max_discard = cpu_to_be32(ns->queue
->limits.max_discard_sectors);
- __be32 discard_desc_count = cpu_to_be32(0x100);
-
- memset(inq_response, 0, STANDARD_INQUIRY_LENGTH);
- inq_response[1] = VPD_BLOCK_LIMITS;
- inq_response[3] = 0x3c; /* Page Length */
- memcpy(&inq_response[8], &max_sectors, sizeof(u32));
- memcpy(&inq_response[20], &max_discard, sizeof(u32));
-
- if (max_discard)
- memcpy(&inq_response[24], &discard_desc_count,
sizeof(u32));
-
- return nvme_trans_copy_to_user(hdr, inq_response, 0x3c);
-}
-
-static int nvme_trans_bdev_char_page(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
- int alloc_len)
-{
- u8 *inq_response;
- int res;
- int xfer_len;
-
- inq_response = kzalloc(EXTENDED_INQUIRY_DATA_PAGE_LENGTH,
GFP_KERNEL);
- if (inq_response == NULL) {
- res = -ENOMEM;
- goto out_mem;
- }
-
- inq_response[1] = INQ_BDEV_CHARACTERISTICS_PAGE; /* Page
Code */
- inq_response[2] = 0x00; /* Page Length MSB */
- inq_response[3] = 0x3C; /* Page Length LSB */
- inq_response[4] = 0x00; /* Medium Rotation Rate MSB */
- inq_response[5] = 0x01; /* Medium Rotation Rate LSB */
- inq_response[6] = 0x00; /* Form Factor */
-
- xfer_len = min(alloc_len, EXTENDED_INQUIRY_DATA_PAGE_LENGTH);
- res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
-
- kfree(inq_response);
- out_mem:
- return res;
-}
-
-/* LOG SENSE Helper Functions */
-
-static int nvme_trans_log_supp_pages(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
- int alloc_len)
-{
- int res;
- int xfer_len;
- u8 *log_response;
-
- log_response = kzalloc(LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH,
GFP_KERNEL);
- if (log_response == NULL) {
- res = -ENOMEM;
- goto out_mem;
- }
-
- log_response[0] = LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE;
- /* Subpage=0x00, Page Length MSB=0 */
- log_response[3] = SUPPORTED_LOG_PAGES_PAGE_LENGTH;
- log_response[4] = LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE;
- log_response[5] = LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE;
- log_response[6] = LOG_PAGE_TEMPERATURE_PAGE;
-
- xfer_len = min(alloc_len,
LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH);
- res = nvme_trans_copy_to_user(hdr, log_response, xfer_len);
-
- kfree(log_response);
- out_mem:
- return res;
-}
-
-static int nvme_trans_log_info_exceptions(struct nvme_ns *ns,
- struct sg_io_hdr *hdr, int
alloc_len)
-{
- int res;
- int xfer_len;
- u8 *log_response;
- struct nvme_dev *dev = ns->dev;
- struct nvme_smart_log *smart_log;
- u8 temp_c;
- u16 temp_k;
-
- log_response = kzalloc(LOG_INFO_EXCP_PAGE_LENGTH, GFP_KERNEL);
- if (log_response == NULL)
- return -ENOMEM;
-
- res = nvme_get_log_page(dev, &smart_log);
- if (res < 0)
- goto out_free_response;
-
- if (res != NVME_SC_SUCCESS) {
- temp_c = LOG_TEMP_UNKNOWN;
- } else {
- temp_k = (smart_log->temperature[1] << 8) +
- (smart_log->temperature[0]);
- temp_c = temp_k - KELVIN_TEMP_FACTOR;
- }
- kfree(smart_log);
-
- log_response[0] = LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE;
- /* Subpage=0x00, Page Length MSB=0 */
- log_response[3] = REMAINING_INFO_EXCP_PAGE_LENGTH;
- /* Informational Exceptions Log Parameter 1 Start */
- /* Parameter Code=0x0000 bytes 4,5 */
- log_response[6] = 0x23; /* DU=0, TSD=1, ETC=0, TMC=0,
FMT_AND_LNK=11b */
- log_response[7] = 0x04; /* PARAMETER LENGTH */
- /* Add sense Code and qualifier = 0x00 each */
- /* Use Temperature from NVMe Get Log Page, convert to C from K
*/
- log_response[10] = temp_c;
-
- xfer_len = min(alloc_len, LOG_INFO_EXCP_PAGE_LENGTH);
- res = nvme_trans_copy_to_user(hdr, log_response, xfer_len);
-
- out_free_response:
- kfree(log_response);
- return res;
-}
-
-static int nvme_trans_log_temperature(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
- int alloc_len)
-{
- int res;
- int xfer_len;
- u8 *log_response;
- struct nvme_dev *dev = ns->dev;
- struct nvme_smart_log *smart_log;
- u32 feature_resp;
- u8 temp_c_cur, temp_c_thresh;
- u16 temp_k;
-
- log_response = kzalloc(LOG_TEMP_PAGE_LENGTH, GFP_KERNEL);
- if (log_response == NULL)
- return -ENOMEM;
-
- res = nvme_get_log_page(dev, &smart_log);
- if (res < 0)
- goto out_free_response;
-
- if (res != NVME_SC_SUCCESS) {
- temp_c_cur = LOG_TEMP_UNKNOWN;
- } else {
- temp_k = (smart_log->temperature[1] << 8) +
- (smart_log->temperature[0]);
- temp_c_cur = temp_k - KELVIN_TEMP_FACTOR;
- }
- kfree(smart_log);
-
- /* Get Features for Temp Threshold */
- res = nvme_get_features(dev, NVME_FEAT_TEMP_THRESH, 0, 0,
- &featu
re_resp);
- if (res != NVME_SC_SUCCESS)
- temp_c_thresh = LOG_TEMP_UNKNOWN;
- else
- temp_c_thresh = (feature_resp & 0xFFFF) -
KELVIN_TEMP_FACTOR;
-
- log_response[0] = LOG_PAGE_TEMPERATURE_PAGE;
- /* Subpage=0x00, Page Length MSB=0 */
- log_response[3] = REMAINING_TEMP_PAGE_LENGTH;
- /* Temperature Log Parameter 1 (Temperature) Start */
- /* Parameter Code = 0x0000 */
- log_response[6] = 0x01; /* Format and Linking
= 01b */
- log_response[7] = 0x02; /* Parameter Length */
- /* Use Temperature from NVMe Get Log Page, convert to C from K
*/
- log_response[9] = temp_c_cur;
- /* Temperature Log Parameter 2 (Reference Temperature) Start
*/
- log_response[11] = 0x01; /* Parameter Code = 0x0001 */
- log_response[12] = 0x01; /* Format and Linking = 01b */
- log_response[13] = 0x02; /* Parameter Length */
- /* Use Temperature Thresh from NVMe Get Log Page, convert to C
from K */
- log_response[15] = temp_c_thresh;
-
- xfer_len = min(alloc_len, LOG_TEMP_PAGE_LENGTH);
- res = nvme_trans_copy_to_user(hdr, log_response, xfer_len);
-
- out_free_response:
- kfree(log_response);
- return res;
-}
-
-/* MODE SENSE Helper Functions */
-
-static int nvme_trans_fill_mode_parm_hdr(u8 *resp, int len, u8 cdb10,
u8 llbaa,
- u16 mode_data_length, u16
blk_desc_len)
-{
- /* Quick check to make sure I don't stomp on my own memory...
*/
- if ((cdb10 && len < 8) || (!cdb10 && len < 4))
- return -EINVAL;
-
- if (cdb10) {
- resp[0] = (mode_data_length & 0xFF00) >> 8;
- resp[1] = (mode_data_length & 0x00FF);
- resp[3] = 0x10 /* DPOFUA */;
- resp[4] = llbaa;
- resp[5] = RESERVED_FIELD;
- resp[6] = (blk_desc_len & 0xFF00) >> 8;
- resp[7] = (blk_desc_len & 0x00FF);
- } else {
- resp[0] = (mode_data_length & 0x00FF);
- resp[2] = 0x10 /* DPOFUA */;
- resp[3] = (blk_desc_len & 0x00FF);
- }
-
- return 0;
-}
-
-static int nvme_trans_fill_blk_desc(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
- u8 *resp, int len, u8 llbaa)
-{
- int res;
- int nvme_sc;
- struct nvme_dev *dev = ns->dev;
- struct nvme_id_ns *id_ns;
- u8 flbas;
- u32 lba_length;
-
- if (llbaa == 0 && len < MODE_PAGE_BLK_DES_LEN)
- return -EINVAL;
- else if (llbaa > 0 && len < MODE_PAGE_LLBAA_BLK_DES_LEN)
- return -EINVAL;
-
- nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- flbas = (id_ns->flbas) & 0x0F;
- lba_length = (1 << (id_ns->lbaf[flbas].ds));
-
- if (llbaa == 0) {
- __be32 tmp_cap = cpu_to_be32(le64_to_cpu(id_ns
->ncap));
- /* Byte 4 is reserved */
- __be32 tmp_len = cpu_to_be32(lba_length & 0x00FFFFFF);
-
- memcpy(resp, &tmp_cap, sizeof(u32));
- memcpy(&resp[4], &tmp_len, sizeof(u32));
- } else {
- __be64 tmp_cap = cpu_to_be64(le64_to_cpu(id_ns
->ncap));
- __be32 tmp_len = cpu_to_be32(lba_length);
-
- memcpy(resp, &tmp_cap, sizeof(u64));
- /* Bytes 8, 9, 10, 11 are reserved */
- memcpy(&resp[12], &tmp_len, sizeof(u32));
- }
-
- kfree(id_ns);
- return res;
-}
-
-static int nvme_trans_fill_control_page(struct nvme_ns *ns,
- struct sg_io_hdr *hdr, u8
*resp,
- int len)
-{
- if (len < MODE_PAGE_CONTROL_LEN)
- return -EINVAL;
-
- resp[0] = MODE_PAGE_CONTROL;
- resp[1] = MODE_PAGE_CONTROL_LEN_FIELD;
- resp[2] = 0x0E; /* TST=000b, TMF_ONLY=0,
DPICZ=1,
- * D_SENSE=1, GLTSD=1, RLEC=0 */
- resp[3] = 0x12; /* Q_ALGO_MODIFIER=1h, NUAR=0,
QERR=01b */
- /* Byte 4: VS=0, RAC=0, UA_INT=0, SWP=0 */
- resp[5] = 0x40; /* ATO=0, TAS=1, ATMPE=0,
RWWP=0, AUTOLOAD=0 */
- /* resp[6] and [7] are obsolete, thus zero */
- resp[8] = 0xFF; /* Busy timeout period =
0xffff */
- resp[9] = 0xFF;
- /* Bytes 10,11: Extended selftest completion time = 0x0000 */
-
- return 0;
-}
-
-static int nvme_trans_fill_caching_page(struct nvme_ns *ns,
- struct sg_io_hdr *hdr,
- u8 *resp, int len)
-{
- int res = 0;
- int nvme_sc;
- struct nvme_dev *dev = ns->dev;
- u32 feature_resp;
- u8 vwc;
-
- if (len < MODE_PAGE_CACHING_LEN)
- return -EINVAL;
-
- nvme_sc = nvme_get_features(dev, NVME_FEAT_VOLATILE_WC, 0, 0,
- &featu
re_resp);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- vwc = feature_resp & 0x00000001;
-
- resp[0] = MODE_PAGE_CACHING;
- resp[1] = MODE_PAGE_CACHING_LEN_FIELD;
- resp[2] = vwc << 2;
- return 0;
-}
-
-static int nvme_trans_fill_pow_cnd_page(struct nvme_ns *ns,
- struct sg_io_hdr *hdr, u8
*resp,
- int len)
-{
- if (len < MODE_PAGE_POW_CND_LEN)
- return -EINVAL;
-
- resp[0] = MODE_PAGE_POWER_CONDITION;
- resp[1] = MODE_PAGE_POW_CND_LEN_FIELD;
- /* All other bytes are zero */
-
- return 0;
-}
-
-static int nvme_trans_fill_inf_exc_page(struct nvme_ns *ns,
- struct sg_io_hdr *hdr, u8
*resp,
- int len)
-{
- if (len < MODE_PAGE_INF_EXC_LEN)
- return -EINVAL;
-
- resp[0] = MODE_PAGE_INFO_EXCEP;
- resp[1] = MODE_PAGE_INF_EXC_LEN_FIELD;
- resp[2] = 0x88;
- /* All other bytes are zero */
-
- return 0;
-}
-
-static int nvme_trans_fill_all_pages(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
- u8 *resp, int len)
-{
- int res;
- u16 mode_pages_offset_1 = 0;
- u16 mode_pages_offset_2, mode_pages_offset_3,
mode_pages_offset_4;
-
- mode_pages_offset_2 = mode_pages_offset_1 +
MODE_PAGE_CACHING_LEN;
- mode_pages_offset_3 = mode_pages_offset_2 +
MODE_PAGE_CONTROL_LEN;
- mode_pages_offset_4 = mode_pages_offset_3 +
MODE_PAGE_POW_CND_LEN;
-
- res = nvme_trans_fill_caching_page(ns, hdr,
&resp[mode_pages_offset_1],
- MODE_PAGE_CACHING_LEN);
- if (res)
- return res;
- res = nvme_trans_fill_control_page(ns, hdr,
&resp[mode_pages_offset_2],
- MODE_PAGE_CONTROL_LEN);
- if (res)
- return res;
- res = nvme_trans_fill_pow_cnd_page(ns, hdr,
&resp[mode_pages_offset_3],
- MODE_PAGE_POW_CND_LEN);
- if (res)
- return res;
- return nvme_trans_fill_inf_exc_page(ns, hdr,
&resp[mode_pages_offset_4],
- MODE_PAGE_INF_EXC_LEN);
-}
-
-static inline int nvme_trans_get_blk_desc_len(u8 dbd, u8 llbaa)
-{
- if (dbd == MODE_SENSE_BLK_DESC_ENABLED) {
- /* SPC-4: len = 8 x Num_of_descriptors if llbaa = 0,
16x if 1 */
- return 8 * (llbaa + 1) * MODE_SENSE_BLK_DESC_COUNT;
- } else {
- return 0;
- }
-}
-
-static int nvme_trans_mode_page_create(struct nvme_ns *ns,
- struct sg_io_hdr *hdr, u8
*cmd,
- u16 alloc_len, u8 cdb10,
- int (*mode_page_fill_func)
- (struct nvme_ns *,
- struct sg_io_hdr *hdr, u8 *,
int),
- u16 mode_pages_tot_len)
-{
- int res;
- int xfer_len;
- u8 *response;
- u8 dbd, llbaa;
- u16 resp_size;
- int mph_size;
- u16 mode_pages_offset_1;
- u16 blk_desc_len, blk_desc_offset, mode_data_length;
-
- dbd = (cmd[1] & MODE_SENSE_DBD_MASK) >> MODE_SENSE_DBD_SHIFT;
- llbaa = (cmd[1] & MODE_SENSE_LLBAA_MASK) >>
MODE_SENSE_LLBAA_SHIFT;
- mph_size = cdb10 ? MODE_SENSE10_MPH_SIZE :
MODE_SENSE6_MPH_SIZE;
-
- blk_desc_len = nvme_trans_get_blk_desc_len(dbd, llbaa);
-
- resp_size = mph_size + blk_desc_len + mode_pages_tot_len;
- /* Refer spc4r34 Table 440 for calculation of Mode data Length
field */
- mode_data_length = 3 + (3 * cdb10) + blk_desc_len +
mode_pages_tot_len;
-
- blk_desc_offset = mph_size;
- mode_pages_offset_1 = blk_desc_offset + blk_desc_len;
-
- response = kzalloc(resp_size, GFP_KERNEL);
- if (response == NULL) {
- res = -ENOMEM;
- goto out_mem;
- }
-
- res = nvme_trans_fill_mode_parm_hdr(&response[0], mph_size,
cdb10,
- llbaa, mode_data_length,
blk_desc_len);
- if (res)
- goto out_free;
- if (blk_desc_len > 0) {
- res = nvme_trans_fill_blk_desc(ns, hdr,
-
&response[blk_desc_offset],
- blk_desc_len, llbaa);
- if (res)
- goto out_free;
- }
- res = mode_page_fill_func(ns, hdr,
&response[mode_pages_offset_1],
- mode_pages_tot_len);
- if (res)
- goto out_free;
-
- xfer_len = min(alloc_len, resp_size);
- res = nvme_trans_copy_to_user(hdr, response, xfer_len);
-
- out_free:
- kfree(response);
- out_mem:
- return res;
-}
-
-/* Read Capacity Helper Functions */
-
-static void nvme_trans_fill_read_cap(u8 *response, struct nvme_id_ns
*id_ns,
- u8
cdb16)
-{
- u8 flbas;
- u32 lba_length;
- u64 rlba;
- u8 prot_en;
- u8 p_type_lut[4] = {0, 0, 1, 2};
- __be64 tmp_rlba;
- __be32 tmp_rlba_32;
- __be32 tmp_len;
-
- flbas = (id_ns->flbas) & 0x0F;
- lba_length = (1 << (id_ns->lbaf[flbas].ds));
- rlba = le64_to_cpup(&id_ns->nsze) - 1;
- (id_ns->dps) ? (prot_en = 0x01) : (prot_en = 0);
-
- if (!cdb16) {
- if (rlba > 0xFFFFFFFF)
- rlba = 0xFFFFFFFF;
- tmp_rlba_32 = cpu_to_be32(rlba);
- tmp_len = cpu_to_be32(lba_length);
- memcpy(response, &tmp_rlba_32, sizeof(u32));
- memcpy(&response[4], &tmp_len, sizeof(u32));
- } else {
- tmp_rlba = cpu_to_be64(rlba);
- tmp_len = cpu_to_be32(lba_length);
- memcpy(response, &tmp_rlba, sizeof(u64));
- memcpy(&response[8], &tmp_len, sizeof(u32));
- response[12] = (p_type_lut[id_ns->dps & 0x3] << 1) |
prot_en;
- /* P_I_Exponent = 0x0 | LBPPBE = 0x0 */
- /* LBPME = 0 | LBPRZ = 0 | LALBA = 0x00 */
- /* Bytes 16-31 - Reserved */
- }
-}
-
-/* Start Stop Unit Helper Functions */
-
-static int nvme_trans_power_state(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
- u8 pc, u8 pcmod, u8
start)
-{
- int res;
- int nvme_sc;
- struct nvme_dev *dev = ns->dev;
- struct nvme_id_ctrl *id_ctrl;
- int lowest_pow_st; /* max npss = lowest power consumption
*/
- unsigned ps_desired = 0;
-
- nvme_sc = nvme_identify_ctrl(dev, &id_ctrl);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- lowest_pow_st = max(POWER_STATE_0, (int)(id_ctrl->npss - 1));
- kfree(id_ctrl);
-
- switch (pc) {
- case NVME_POWER_STATE_START_VALID:
- /* Action unspecified if POWER CONDITION MODIFIER != 0
*/
- if (pcmod == 0 && start == 0x1)
- ps_desired = POWER_STATE_0;
- if (pcmod == 0 && start == 0x0)
- ps_desired = lowest_pow_st;
- break;
- case NVME_POWER_STATE_ACTIVE:
- /* Action unspecified if POWER CONDITION MODIFIER != 0
*/
- if (pcmod == 0)
- ps_desired = POWER_STATE_0;
- break;
- case NVME_POWER_STATE_IDLE:
- /* Action unspecified if POWER CONDITION MODIFIER !=
[0,1,2] */
- if (pcmod == 0x0)
- ps_desired = POWER_STATE_1;
- else if (pcmod == 0x1)
- ps_desired = POWER_STATE_2;
- else if (pcmod == 0x2)
- ps_desired = POWER_STATE_3;
- break;
- case NVME_POWER_STATE_STANDBY:
- /* Action unspecified if POWER CONDITION MODIFIER !=
[0,1] */
- if (pcmod == 0x0)
- ps_desired = max(POWER_STATE_0, (lowest_pow_st
- 2));
- else if (pcmod == 0x1)
- ps_desired = max(POWER_STATE_0, (lowest_pow_st
- 1));
- break;
- case NVME_POWER_STATE_LU_CONTROL:
- default:
- res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- break;
- }
- nvme_sc = nvme_set_features(dev, NVME_FEAT_POWER_MGMT,
ps_desired, 0,
- NULL);
- return nvme_trans_status_code(hdr, nvme_sc);
-}
-
-static int nvme_trans_send_activate_fw_cmd(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
- u8 buffer_id)
-{
- struct nvme_command c;
- int nvme_sc;
-
- memset(&c, 0, sizeof(c));
- c.common.opcode = nvme_admin_activate_fw;
- c.common.cdw10[0] = cpu_to_le32(buffer_id |
NVME_FWACT_REPL_ACTV);
-
- nvme_sc = nvme_submit_sync_cmd(ns->queue, &c, NULL, 0);
- return nvme_trans_status_code(hdr, nvme_sc);
-}
-
-static int nvme_trans_send_download_fw_cmd(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
- u8 opcode, u32 tot_len, u32
offset,
- u8 buffer_id)
-{
- int nvme_sc;
- struct nvme_dev *dev = ns->dev;
- struct nvme_command c;
-
- if (hdr->iovec_count > 0) {
- /* Assuming SGL is not allowed for this command */
- return nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
- SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- }
-
- memset(&c, 0, sizeof(c));
- c.common.opcode = nvme_admin_download_fw;
- c.dlfw.numd = cpu_to_le32((tot_len/BYTES_TO_DWORDS) - 1);
- c.dlfw.offset = cpu_to_le32(offset/BYTES_TO_DWORDS);
-
- nvme_sc = __nvme_submit_sync_cmd(dev->admin_q, &c, NULL,
- hdr->dxferp, tot_len, NULL, 0);
- return nvme_trans_status_code(hdr, nvme_sc);
-}
-
-/* Mode Select Helper Functions */
-
-static inline void nvme_trans_modesel_get_bd_len(u8 *parm_list, u8
cdb10,
- u16 *bd_len, u8
*llbaa)
-{
- if (cdb10) {
- /* 10 Byte CDB */
- *bd_len = (parm_list[MODE_SELECT_10_BD_OFFSET] << 8) +
- parm_list[MODE_SELECT_10_BD_OFFSET + 1];
- *llbaa = parm_list[MODE_SELECT_10_LLBAA_OFFSET] &
- MODE_SELECT_10_LLBAA_MASK;
- } else {
- /* 6 Byte CDB */
- *bd_len = parm_list[MODE_SELECT_6_BD_OFFSET];
- }
-}
-
-static void nvme_trans_modesel_save_bd(struct nvme_ns *ns, u8
*parm_list,
- u16 idx, u16 bd_len, u8 llbaa)
-{
- u16 bd_num;
-
- bd_num = bd_len / ((llbaa == 0) ?
- SHORT_DESC_BLOCK : LONG_DESC_BLOCK);
- /* Store block descriptor info if a FORMAT UNIT comes later */
- /* TODO Saving 1st BD info; what to do if multiple BD
received? */
- if (llbaa == 0) {
- /* Standard Block Descriptor - spc4r34 7.5.5.1 */
- ns->mode_select_num_blocks =
- (parm_list[idx + 1] << 16) +
- (parm_list[idx + 2] << 8) +
- (parm_list[idx + 3]);
-
- ns->mode_select_block_len =
- (parm_list[idx + 5] << 16) +
- (parm_list[idx + 6] << 8) +
- (parm_list[idx + 7]);
- } else {
- /* Long LBA Block Descriptor - sbc3r27 6.4.2.3 */
- ns->mode_select_num_blocks =
- (((u64)parm_list[idx + 0]) << 56) +
- (((u64)parm_list[idx + 1]) << 48) +
- (((u64)parm_list[idx + 2]) << 40) +
- (((u64)parm_list[idx + 3]) << 32) +
- (((u64)parm_list[idx + 4]) << 24) +
- (((u64)parm_list[idx + 5]) << 16) +
- (((u64)parm_list[idx + 6]) << 8) +
- ((u64)parm_list[idx + 7]);
-
- ns->mode_select_block_len =
- (parm_list[idx + 12] << 24) +
- (parm_list[idx + 13] << 16) +
- (parm_list[idx + 14] << 8) +
- (parm_list[idx + 15]);
- }
-}
-
-static int nvme_trans_modesel_get_mp(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
- u8 *mode_page, u8 page_code)
-{
- int res = 0;
- int nvme_sc;
- struct nvme_dev *dev = ns->dev;
- unsigned dword11;
-
- switch (page_code) {
- case MODE_PAGE_CACHING:
- dword11 = ((mode_page[2] & CACHING_MODE_PAGE_WCE_MASK)
? 1 : 0);
- nvme_sc = nvme_set_features(dev,
NVME_FEAT_VOLATILE_WC, dword11,
- 0, NULL);
- res = nvme_trans_status_code(hdr, nvme_sc);
- break;
- case MODE_PAGE_CONTROL:
- break;
- case MODE_PAGE_POWER_CONDITION:
- /* Verify the OS is not trying to set timers */
- if ((mode_page[2] & 0x01) != 0 || (mode_page[3] &
0x0F) != 0) {
- res = nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITI
ON,
- ILLEGAL_REQUEST,
- SCSI_ASC_INVALID_PARAM
ETER,
- SCSI_ASCQ_CAUSE_NOT_RE
PORTABLE);
- break;
- }
- break;
- default:
- res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- break;
- }
-
- return res;
-}
-
-static int nvme_trans_modesel_data(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
- u8 *cmd, u16 parm_list_len, u8
pf,
- u8 sp, u8 cdb10)
-{
- int res;
- u8 *parm_list;
- u16 bd_len;
- u8 llbaa = 0;
- u16 index, saved_index;
- u8 page_code;
- u16 mp_size;
-
- /* Get parm list from data-in/out buffer */
- parm_list = kmalloc(parm_list_len, GFP_KERNEL);
- if (parm_list == NULL) {
- res = -ENOMEM;
- goto out;
- }
-
- res = nvme_trans_copy_from_user(hdr, parm_list,
parm_list_len);
- if (res)
- goto out_mem;
-
- nvme_trans_modesel_get_bd_len(parm_list, cdb10, &bd_len,
&llbaa);
- index = (cdb10) ? (MODE_SELECT_10_MPH_SIZE) :
(MODE_SELECT_6_MPH_SIZE);
-
- if (bd_len != 0) {
- /* Block Descriptors present, parse */
- nvme_trans_modesel_save_bd(ns, parm_list, index,
bd_len, llbaa);
- index += bd_len;
- }
- saved_index = index;
-
- /* Multiple mode pages may be present; iterate through all */
- /* In 1st Iteration, don't do NVME Command, only check for CDB
errors */
- do {
- page_code = parm_list[index] &
MODE_SELECT_PAGE_CODE_MASK;
- mp_size = parm_list[index + 1] + 2;
- if ((page_code != MODE_PAGE_CACHING) &&
- (page_code != MODE_PAGE_CONTROL) &&
- (page_code != MODE_PAGE_POWER_CONDITION)) {
- res = nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITI
ON,
- ILLEGAL_REQUEST,
- SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_RE
PORTABLE);
- goto out_mem;
- }
- index += mp_size;
- } while (index < parm_list_len);
-
- /* In 2nd Iteration, do the NVME Commands */
- index = saved_index;
- do {
- page_code = parm_list[index] &
MODE_SELECT_PAGE_CODE_MASK;
- mp_size = parm_list[index + 1] + 2;
- res = nvme_trans_modesel_get_mp(ns, hdr,
&parm_list[index],
- page_c
ode);
- if (res)
- break;
- index += mp_size;
- } while (index < parm_list_len);
-
- out_mem:
- kfree(parm_list);
- out:
- return res;
-}
-
-/* Format Unit Helper Functions */
-
-static int nvme_trans_fmt_set_blk_size_count(struct nvme_ns *ns,
- struct sg_io_hdr *hdr)
-{
- int res = 0;
- int nvme_sc;
- struct nvme_dev *dev = ns->dev;
- u8 flbas;
-
- /*
- * SCSI Expects a MODE SELECT would have been issued prior to
- * a FORMAT UNIT, and the block size and number would be used
- * from the block descriptor in it. If a MODE SELECT had not
- * been issued, FORMAT shall use the current values for both.
- */
-
- if (ns->mode_select_num_blocks == 0 || ns
->mode_select_block_len == 0) {
- struct nvme_id_ns *id_ns;
-
- nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- if (ns->mode_select_num_blocks == 0)
- ns->mode_select_num_blocks = le64_to_cpu(id_ns
->ncap);
- if (ns->mode_select_block_len == 0) {
- flbas = (id_ns->flbas) & 0x0F;
- ns->mode_select_block_len =
- (1 << (id_ns
->lbaf[flbas].ds));
- }
-
- kfree(id_ns);
- }
-
- return 0;
-}
-
-static int nvme_trans_fmt_get_parm_header(struct sg_io_hdr *hdr, u8
len,
- u8 format_prot_info, u8
*nvme_pf_code)
-{
- int res;
- u8 *parm_list;
- u8 pf_usage, pf_code;
-
- parm_list = kmalloc(len, GFP_KERNEL);
- if (parm_list == NULL) {
- res = -ENOMEM;
- goto out;
- }
- res = nvme_trans_copy_from_user(hdr, parm_list, len);
- if (res)
- goto out_mem;
-
- if ((parm_list[FORMAT_UNIT_IMMED_OFFSET] &
- FORMAT_UNIT_IMMED_MASK) != 0) {
- res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- goto out_mem;
- }
-
- if (len == FORMAT_UNIT_LONG_PARM_LIST_LEN &&
- (parm_list[FORMAT_UNIT_PROT_INT_OFFSET] & 0x0F) != 0) {
- res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- goto out_mem;
- }
- pf_usage = parm_list[FORMAT_UNIT_PROT_FIELD_USAGE_OFFSET] &
- FORMAT_UNIT_PROT_FIELD_USAGE_MASK;
- pf_code = (pf_usage << 2) | format_prot_info;
- switch (pf_code) {
- case 0:
- *nvme_pf_code = 0;
- break;
- case 2:
- *nvme_pf_code = 1;
- break;
- case 3:
- *nvme_pf_code = 2;
- break;
- case 7:
- *nvme_pf_code = 3;
- break;
- default:
- res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- break;
- }
-
- out_mem:
- kfree(parm_list);
- out:
- return res;
-}
-
-static int nvme_trans_fmt_send_cmd(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
- u8 prot_info)
-{
- int res;
- int nvme_sc;
- struct nvme_dev *dev = ns->dev;
- struct nvme_id_ns *id_ns;
- u8 i;
- u8 flbas, nlbaf;
- u8 selected_lbaf = 0xFF;
- u32 cdw10 = 0;
- struct nvme_command c;
-
- /* Loop thru LBAF's in id_ns to match reqd lbaf, put in cdw10
*/
- nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- flbas = (id_ns->flbas) & 0x0F;
- nlbaf = id_ns->nlbaf;
-
- for (i = 0; i < nlbaf; i++) {
- if (ns->mode_select_block_len == (1 << (id_ns
->lbaf[i].ds))) {
- selected_lbaf = i;
- break;
- }
- }
- if (selected_lbaf > 0x0F) {
- res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_PARAMETER,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- }
- if (ns->mode_select_num_blocks != le64_to_cpu(id_ns->ncap)) {
- res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_PARAMETER,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- }
-
- cdw10 |= prot_info << 5;
- cdw10 |= selected_lbaf & 0x0F;
- memset(&c, 0, sizeof(c));
- c.format.opcode = nvme_admin_format_nvm;
- c.format.nsid = cpu_to_le32(ns->ns_id);
- c.format.cdw10 = cpu_to_le32(cdw10);
-
- nvme_sc = nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0);
- res = nvme_trans_status_code(hdr, nvme_sc);
-
- kfree(id_ns);
- return res;
-}
-
-static inline u32 nvme_trans_io_get_num_cmds(struct sg_io_hdr *hdr,
- struct nvme_trans_io_cdb
*cdb_info,
- u32 max_blocks)
-{
- /* If using iovecs, send one nvme command per vector */
- if (hdr->iovec_count > 0)
- return hdr->iovec_count;
- else if (cdb_info->xfer_len > max_blocks)
- return ((cdb_info->xfer_len - 1) / max_blocks) + 1;
- else
- return 1;
-}
-
-static u16 nvme_trans_io_get_control(struct nvme_ns *ns,
- struct nvme_trans_io_cdb
*cdb_info)
-{
- u16 control = 0;
-
- /* When Protection information support is added, implement
here */
-
- if (cdb_info->fua > 0)
- control |= NVME_RW_FUA;
-
- return control;
-}
-
-static int nvme_trans_do_nvme_io(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
- struct nvme_trans_io_cdb *cdb_info, u8
is_write)
-{
- int nvme_sc = NVME_SC_SUCCESS;
- u32 num_cmds;
- u64 unit_len;
- u64 unit_num_blocks; /* Number of blocks to xfer in each
nvme cmd */
- u32 retcode;
- u32 i = 0;
- u64 nvme_offset = 0;
- void __user *next_mapping_addr;
- struct nvme_command c;
- u8 opcode = (is_write ? nvme_cmd_write : nvme_cmd_read);
- u16 control;
- u32 max_blocks = queue_max_hw_sectors(ns->queue);
-
- num_cmds = nvme_trans_io_get_num_cmds(hdr, cdb_info,
max_blocks);
-
- /*
- * This loop handles two cases.
- * First, when an SGL is used in the form of an iovec list:
- * - Use iov_base as the next mapping address for the nvme
command_id
- * - Use iov_len as the data transfer length for the
command.
- * Second, when we have a single buffer
- * - If larger than max_blocks, split into chunks, offset
- * each nvme command accordingly.
- */
- for (i = 0; i < num_cmds; i++) {
- memset(&c, 0, sizeof(c));
- if (hdr->iovec_count > 0) {
- struct sg_iovec sgl;
-
- retcode = copy_from_user(&sgl, hdr->dxferp +
- i * sizeof(struct sg_iovec),
- sizeof(struct sg_iovec));
- if (retcode)
- return -EFAULT;
- unit_len = sgl.iov_len;
- unit_num_blocks = unit_len >> ns->lba_shift;
- next_mapping_addr = sgl.iov_base;
- } else {
- unit_num_blocks = min((u64)max_blocks,
- (cdb_info->xfer_len -
nvme_offset));
- unit_len = unit_num_blocks << ns->lba_shift;
- next_mapping_addr = hdr->dxferp +
- ((1 << ns->lba_shift) *
nvme_offset);
- }
-
- c.rw.opcode = opcode;
- c.rw.nsid = cpu_to_le32(ns->ns_id);
- c.rw.slba = cpu_to_le64(cdb_info->lba + nvme_offset);
- c.rw.length = cpu_to_le16(unit_num_blocks - 1);
- control = nvme_trans_io_get_control(ns, cdb_info);
- c.rw.control = cpu_to_le16(control);
-
- if (get_capacity(ns->disk) - unit_num_blocks <
- cdb_info->lba + nvme_offset) {
- nvme_sc = NVME_SC_LBA_RANGE;
- break;
- }
- nvme_sc = __nvme_submit_sync_cmd(ns->queue, &c, NULL,
- next_mapping_addr, unit_len, NULL, 0);
- if (nvme_sc)
- break;
-
- nvme_offset += unit_num_blocks;
- }
-
- return nvme_trans_status_code(hdr, nvme_sc);
-}
-
-
-/* SCSI Command Translation Functions */
-
-static int nvme_trans_io(struct nvme_ns *ns, struct sg_io_hdr *hdr, u8
is_write,
- u8 *cmd)
-{
- int res = 0;
- struct nvme_trans_io_cdb cdb_info = { 0, };
- u8 opcode = cmd[0];
- u64 xfer_bytes;
- u64 sum_iov_len = 0;
- struct sg_iovec sgl;
- int i;
- size_t not_copied;
-
- /*
- * The FUA and WPROTECT fields are not supported in 6-byte
CDBs,
- * but always in the same place for all others.
- */
- switch (opcode) {
- case WRITE_6:
- case READ_6:
- break;
- default:
- cdb_info.fua = cmd[1] & 0x8;
- cdb_info.prot_info = (cmd[1] & 0xe0) >> 5;
- if (cdb_info.prot_info && !ns->pi_type) {
- return nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
- SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- }
- }
-
- switch (opcode) {
- case WRITE_6:
- case READ_6:
- cdb_info.lba = get_unaligned_be24(&cmd[1]);
- cdb_info.xfer_len = cmd[4];
- if (cdb_info.xfer_len == 0)
- cdb_info.xfer_len = 256;
- break;
- case WRITE_10:
- case READ_10:
- cdb_info.lba = get_unaligned_be32(&cmd[2]);
- cdb_info.xfer_len = get_unaligned_be16(&cmd[7]);
- break;
- case WRITE_12:
- case READ_12:
- cdb_info.lba = get_unaligned_be32(&cmd[2]);
- cdb_info.xfer_len = get_unaligned_be32(&cmd[6]);
- break;
- case WRITE_16:
- case READ_16:
- cdb_info.lba = get_unaligned_be64(&cmd[2]);
- cdb_info.xfer_len = get_unaligned_be32(&cmd[10]);
- break;
- default:
- /* Will never really reach here */
- res = -EIO;
- goto out;
- }
-
- /* Calculate total length of transfer (in bytes) */
- if (hdr->iovec_count > 0) {
- for (i = 0; i < hdr->iovec_count; i++) {
- not_copied = copy_from_user(&sgl, hdr->dxferp
+
- i * sizeof(struct
sg_iovec),
- sizeof(struct
sg_iovec));
- if (not_copied)
- return -EFAULT;
- sum_iov_len += sgl.iov_len;
- /* IO vector sizes should be multiples of
block size */
- if (sgl.iov_len % (1 << ns->lba_shift) != 0) {
- res = nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITI
ON,
- ILLEGAL_REQUEST,
- SCSI_ASC_INVALID_PARAM
ETER,
- SCSI_ASCQ_CAUSE_NOT_RE
PORTABLE);
- goto out;
- }
- }
- } else {
- sum_iov_len = hdr->dxfer_len;
- }
-
- /* As Per sg ioctl howto, if the lengths differ, use the lower
one */
- xfer_bytes = min(((u64)hdr->dxfer_len), sum_iov_len);
-
- /* If block count and actual data buffer size dont match,
error out */
- if (xfer_bytes != (cdb_info.xfer_len << ns->lba_shift)) {
- res = -EINVAL;
- goto out;
- }
-
- /* Check for 0 length transfer - it is not illegal */
- if (cdb_info.xfer_len == 0)
- goto out;
-
- /* Send NVMe IO Command(s) */
- res = nvme_trans_do_nvme_io(ns, hdr, &cdb_info, is_write);
- if (res)
- goto out;
-
- out:
- return res;
-}
-
-static int nvme_trans_inquiry(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
- u8 *cmd)
-{
- int res = 0;
- u8 evpd;
- u8 page_code;
- int alloc_len;
- u8 *inq_response;
-
- evpd = cmd[1] & 0x01;
- page_code = cmd[2];
- alloc_len = get_unaligned_be16(&cmd[3]);
-
- inq_response = kmalloc(max(alloc_len,
STANDARD_INQUIRY_LENGTH),
- GFP_KERNEL);
- if (inq_response == NULL) {
- res = -ENOMEM;
- goto out_mem;
- }
-
- if (evpd == 0) {
- if (page_code == INQ_STANDARD_INQUIRY_PAGE) {
- res = nvme_trans_standard_inquiry_page(ns,
hdr,
- inq_response,
alloc_len);
- } else {
- res = nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITI
ON,
- ILLEGAL_REQUEST,
- SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_RE
PORTABLE);
- }
- } else {
- switch (page_code) {
- case VPD_SUPPORTED_PAGES:
- res = nvme_trans_supported_vpd_pages(ns, hdr,
- inq_response,
alloc_len);
- break;
- case VPD_SERIAL_NUMBER:
- res = nvme_trans_unit_serial_page(ns, hdr,
inq_response,
- alloc_
len);
- break;
- case VPD_DEVICE_IDENTIFIERS:
- res = nvme_trans_device_id_page(ns, hdr,
inq_response,
- alloc_
len);
- break;
- case VPD_EXTENDED_INQUIRY:
- res = nvme_trans_ext_inq_page(ns, hdr,
alloc_len);
- break;
- case VPD_BLOCK_LIMITS:
- res = nvme_trans_bdev_limits_page(ns, hdr,
inq_response,
- alloc_
len);
- break;
- case VPD_BLOCK_DEV_CHARACTERISTICS:
- res = nvme_trans_bdev_char_page(ns, hdr,
alloc_len);
- break;
- default:
- res = nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITI
ON,
- ILLEGAL_REQUEST,
- SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_RE
PORTABLE);
- break;
- }
- }
- kfree(inq_response);
- out_mem:
- return res;
-}
-
-static int nvme_trans_log_sense(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
- u8 *cmd)
-{
- int res;
- u16 alloc_len;
- u8 pc;
- u8 page_code;
-
- if (cmd[1] != LOG_SENSE_CDB_SP_NOT_ENABLED) {
- res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- goto out;
- }
-
- page_code = cmd[2] & LOG_SENSE_CDB_PAGE_CODE_MASK;
- pc = (cmd[2] & LOG_SENSE_CDB_PC_MASK) >>
LOG_SENSE_CDB_PC_SHIFT;
- if (pc != LOG_SENSE_CDB_PC_CUMULATIVE_VALUES) {
- res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- goto out;
- }
- alloc_len = get_unaligned_be16(&cmd[7]);
- switch (page_code) {
- case LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE:
- res = nvme_trans_log_supp_pages(ns, hdr, alloc_len);
- break;
- case LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE:
- res = nvme_trans_log_info_exceptions(ns, hdr,
alloc_len);
- break;
- case LOG_PAGE_TEMPERATURE_PAGE:
- res = nvme_trans_log_temperature(ns, hdr, alloc_len);
- break;
- default:
- res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- break;
- }
-
- out:
- return res;
-}
-
-static int nvme_trans_mode_select(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
- u8 *cmd)
-{
- u8 cdb10 = 0;
- u16 parm_list_len;
- u8 page_format;
- u8 save_pages;
-
- page_format = cmd[1] & MODE_SELECT_CDB_PAGE_FORMAT_MASK;
- save_pages = cmd[1] & MODE_SELECT_CDB_SAVE_PAGES_MASK;
-
- if (cmd[0] == MODE_SELECT) {
- parm_list_len = cmd[4];
- } else {
- parm_list_len = cmd[7];
- cdb10 = 1;
- }
-
- if (parm_list_len != 0) {
- /*
- * According to SPC-4 r24, a paramter list length
field of 0
- * shall not be considered an error
- */
- return nvme_trans_modesel_data(ns, hdr, cmd,
parm_list_len,
- page_format,
save_pages, cdb10);
- }
-
- return 0;
-}
-
-static int nvme_trans_mode_sense(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
- u8 *cmd)
-{
- int res = 0;
- u16 alloc_len;
- u8 cdb10 = 0;
-
- if (cmd[0] == MODE_SENSE) {
- alloc_len = cmd[4];
- } else {
- alloc_len = get_unaligned_be16(&cmd[7]);
- cdb10 = 1;
- }
-
- if ((cmd[2] & MODE_SENSE_PAGE_CONTROL_MASK) !=
- MODE_SENSE_PC_CURRENT_VALUES) {
- res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- goto out;
- }
-
- switch (cmd[2] & MODE_SENSE_PAGE_CODE_MASK) {
- case MODE_PAGE_CACHING:
- res = nvme_trans_mode_page_create(ns, hdr, cmd,
alloc_len,
- cdb10,
- &nvme_trans_fill_cachi
ng_page,
- MODE_PAGE_CACHING_LEN)
;
- break;
- case MODE_PAGE_CONTROL:
- res = nvme_trans_mode_page_create(ns, hdr, cmd,
alloc_len,
- cdb10,
- &nvme_trans_fill_contr
ol_page,
- MODE_PAGE_CONTROL_LEN)
;
- break;
- case MODE_PAGE_POWER_CONDITION:
- res = nvme_trans_mode_page_create(ns, hdr, cmd,
alloc_len,
- cdb10,
- &nvme_trans_fill_pow_c
nd_page,
- MODE_PAGE_POW_CND_LEN)
;
- break;
- case MODE_PAGE_INFO_EXCEP:
- res = nvme_trans_mode_page_create(ns, hdr, cmd,
alloc_len,
- cdb10,
- &nvme_trans_fill_inf_e
xc_page,
- MODE_PAGE_INF_EXC_LEN)
;
- break;
- case MODE_PAGE_RETURN_ALL:
- res = nvme_trans_mode_page_create(ns, hdr, cmd,
alloc_len,
- cdb10,
- &nvme_trans_fill_all_p
ages,
- MODE_PAGE_ALL_LEN);
- break;
- default:
- res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- break;
- }
-
- out:
- return res;
-}
-
-static int nvme_trans_read_capacity(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
- u8 *cmd, u8
cdb16)
-{
- int res;
- int nvme_sc;
- u32 alloc_len;
- u32 resp_size;
- u32 xfer_len;
- struct nvme_dev *dev = ns->dev;
- struct nvme_id_ns *id_ns;
- u8 *response;
-
- if (cdb16) {
- alloc_len = get_unaligned_be32(&cmd[10]);
- resp_size = READ_CAP_16_RESP_SIZE;
- } else {
- alloc_len = READ_CAP_10_RESP_SIZE;
- resp_size = READ_CAP_10_RESP_SIZE;
- }
-
- nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- response = kzalloc(resp_size, GFP_KERNEL);
- if (response == NULL) {
- res = -ENOMEM;
- goto out_free_id;
- }
- nvme_trans_fill_read_cap(response, id_ns, cdb16);
-
- xfer_len = min(alloc_len, resp_size);
- res = nvme_trans_copy_to_user(hdr, response, xfer_len);
-
- kfree(response);
- out_free_id:
- kfree(id_ns);
- return res;
-}
-
-static int nvme_trans_report_luns(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
- u8 *cmd)
-{
- int res;
- int nvme_sc;
- u32 alloc_len, xfer_len, resp_size;
- u8 *response;
- struct nvme_dev *dev = ns->dev;
- struct nvme_id_ctrl *id_ctrl;
- u32 ll_length, lun_id;
- u8 lun_id_offset = REPORT_LUNS_FIRST_LUN_OFFSET;
- __be32 tmp_len;
-
- switch (cmd[2]) {
- default:
- return nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- case ALL_LUNS_RETURNED:
- case ALL_WELL_KNOWN_LUNS_RETURNED:
- case RESTRICTED_LUNS_RETURNED:
- nvme_sc = nvme_identify_ctrl(dev, &id_ctrl);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- ll_length = le32_to_cpu(id_ctrl->nn) * LUN_ENTRY_SIZE;
- resp_size = ll_length + LUN_DATA_HEADER_SIZE;
-
- alloc_len = get_unaligned_be32(&cmd[6]);
- if (alloc_len < resp_size) {
- res = nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- goto out_free_id;
- }
-
- response = kzalloc(resp_size, GFP_KERNEL);
- if (response == NULL) {
- res = -ENOMEM;
- goto out_free_id;
- }
-
- /* The first LUN ID will always be 0 per the SAM spec
*/
- for (lun_id = 0; lun_id < le32_to_cpu(id_ctrl->nn);
lun_id++) {
- /*
- * Set the LUN Id and then increment to the
next LUN
- * location in the parameter data.
- */
- __be64 tmp_id = cpu_to_be64(lun_id);
- memcpy(&response[lun_id_offset], &tmp_id,
sizeof(u64));
- lun_id_offset += LUN_ENTRY_SIZE;
- }
- tmp_len = cpu_to_be32(ll_length);
- memcpy(response, &tmp_len, sizeof(u32));
- }
-
- xfer_len = min(alloc_len, resp_size);
- res = nvme_trans_copy_to_user(hdr, response, xfer_len);
-
- kfree(response);
- out_free_id:
- kfree(id_ctrl);
- return res;
-}
-
-static int nvme_trans_request_sense(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
- u8 *cmd)
-{
- int res;
- u8 alloc_len, xfer_len, resp_size;
- u8 desc_format;
- u8 *response;
-
- desc_format = cmd[1] & 0x01;
- alloc_len = cmd[4];
-
- resp_size = ((desc_format) ? (DESC_FMT_SENSE_DATA_SIZE) :
- (FIXED_FMT_SENSE_DATA_SIZE));
- response = kzalloc(resp_size, GFP_KERNEL);
- if (response == NULL) {
- res = -ENOMEM;
- goto out;
- }
-
- if (desc_format) {
- /* Descriptor Format Sense Data */
- response[0] = DESC_FORMAT_SENSE_DATA;
- response[1] = NO_SENSE;
- /* TODO How is LOW POWER CONDITION ON handled? (byte
2) */
- response[2] = SCSI_ASC_NO_SENSE;
- response[3] = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- /* SDAT_OVFL = 0 | Additional Sense Length = 0 */
- } else {
- /* Fixed Format Sense Data */
- response[0] = FIXED_SENSE_DATA;
- /* Byte 1 = Obsolete */
- response[2] = NO_SENSE; /* FM, EOM, ILI, SDAT_OVFL = 0
*/
- /* Bytes 3-6 - Information - set to zero */
- response[7] = FIXED_SENSE_DATA_ADD_LENGTH;
- /* Bytes 8-11 - Cmd Specific Information - set to zero
*/
- response[12] = SCSI_ASC_NO_SENSE;
- response[13] = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- /* Byte 14 = Field Replaceable Unit Code = 0 */
- /* Bytes 15-17 - SKSV=0; Sense Key Specific = 0 */
- }
-
- xfer_len = min(alloc_len, resp_size);
- res = nvme_trans_copy_to_user(hdr, response, xfer_len);
-
- kfree(response);
- out:
- return res;
-}
-
-static int nvme_trans_security_protocol(struct nvme_ns *ns,
- struct sg_io_hdr *hdr,
- u8 *cmd)
-{
- return nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_ILLEGAL_COMMAND,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
-}
-
-static int nvme_trans_synchronize_cache(struct nvme_ns *ns,
- struct sg_io_hdr *hdr)
-{
- int nvme_sc;
- struct nvme_command c;
-
- memset(&c, 0, sizeof(c));
- c.common.opcode = nvme_cmd_flush;
- c.common.nsid = cpu_to_le32(ns->ns_id);
-
- nvme_sc = nvme_submit_sync_cmd(ns->queue, &c, NULL, 0);
- return nvme_trans_status_code(hdr, nvme_sc);
-}
-
-static int nvme_trans_start_stop(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
- u8 *cmd)
-{
- u8 immed, pcmod, pc, no_flush, start;
-
- immed = cmd[1] & 0x01;
- pcmod = cmd[3] & 0x0f;
- pc = (cmd[4] & 0xf0) >> 4;
- no_flush = cmd[4] & 0x04;
- start = cmd[4] & 0x01;
-
- if (immed != 0) {
- return nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- } else {
- if (no_flush == 0) {
- /* Issue NVME FLUSH command prior to START
STOP UNIT */
- int res = nvme_trans_synchronize_cache(ns,
hdr);
- if (res)
- return res;
- }
- /* Setup the expected power state transition */
- return nvme_trans_power_state(ns, hdr, pc, pcmod,
start);
- }
-}
-
-static int nvme_trans_format_unit(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
- u8 *cmd)
-{
- int res;
- u8 parm_hdr_len = 0;
- u8 nvme_pf_code = 0;
- u8 format_prot_info, long_list, format_data;
-
- format_prot_info = (cmd[1] & 0xc0) >> 6;
- long_list = cmd[1] & 0x20;
- format_data = cmd[1] & 0x10;
-
- if (format_data != 0) {
- if (format_prot_info != 0) {
- if (long_list == 0)
- parm_hdr_len =
FORMAT_UNIT_SHORT_PARM_LIST_LEN;
- else
- parm_hdr_len =
FORMAT_UNIT_LONG_PARM_LIST_LEN;
- }
- } else if (format_data == 0 && format_prot_info != 0) {
- res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- goto out;
- }
-
- /* Get parm header from data-in/out buffer */
- /*
- * According to the translation spec, the only fields in the
parameter
- * list we are concerned with are in the header. So allocate
only that.
- */
- if (parm_hdr_len > 0) {
- res = nvme_trans_fmt_get_parm_header(hdr,
parm_hdr_len,
- format_prot_info,
&nvme_pf_code);
- if (res)
- goto out;
- }
-
- /* Attempt to activate any previously downloaded firmware
image */
- res = nvme_trans_send_activate_fw_cmd(ns, hdr, 0);
-
- /* Determine Block size and count and send format command */
- res = nvme_trans_fmt_set_blk_size_count(ns, hdr);
- if (res)
- goto out;
-
- res = nvme_trans_fmt_send_cmd(ns, hdr, nvme_pf_code);
-
- out:
- return res;
-}
-
-static int nvme_trans_test_unit_ready(struct nvme_ns *ns,
- struct sg_io_hdr *hdr,
- u8 *cmd)
-{
- struct nvme_dev *dev = ns->dev;
-
- if (!(readl(&dev->bar->csts) & NVME_CSTS_RDY))
- return nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- NOT_READY,
SCSI_ASC_LUN_NOT_READY,
-
SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- else
- return nvme_trans_completion(hdr, SAM_STAT_GOOD,
NO_SENSE, 0, 0);
-}
-
-static int nvme_trans_write_buffer(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
- u8 *cmd)
-{
- int res = 0;
- u32 buffer_offset, parm_list_length;
- u8 buffer_id, mode;
-
- parm_list_length = get_unaligned_be24(&cmd[6]);
- if (parm_list_length % BYTES_TO_DWORDS != 0) {
- /* NVMe expects Firmware file to be a whole number of
DWORDS */
- res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- goto out;
- }
- buffer_id = cmd[2];
- if (buffer_id > NVME_MAX_FIRMWARE_SLOT) {
- res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- goto out;
- }
- mode = cmd[1] & 0x1f;
- buffer_offset = get_unaligned_be24(&cmd[3]);
-
- switch (mode) {
- case DOWNLOAD_SAVE_ACTIVATE:
- res = nvme_trans_send_download_fw_cmd(ns, hdr,
nvme_admin_download_fw,
- parm_list_length,
buffer_offset,
- buffer_id);
- if (res)
- goto out;
- res = nvme_trans_send_activate_fw_cmd(ns, hdr,
buffer_id);
- break;
- case DOWNLOAD_SAVE_DEFER_ACTIVATE:
- res = nvme_trans_send_download_fw_cmd(ns, hdr,
nvme_admin_download_fw,
- parm_list_length,
buffer_offset,
- buffer_id);
- break;
- case ACTIVATE_DEFERRED_MICROCODE:
- res = nvme_trans_send_activate_fw_cmd(ns, hdr,
buffer_id);
- break;
- default:
- res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
- break;
- }
-
- out:
- return res;
-}
-
-struct scsi_unmap_blk_desc {
- __be64 slba;
- __be32 nlb;
- u32 resv;
-};
-
-struct scsi_unmap_parm_list {
- __be16 unmap_data_len;
- __be16 unmap_blk_desc_data_len;
- u32 resv;
- struct scsi_unmap_blk_desc desc[0];
-};
-
-static int nvme_trans_unmap(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *cmd)
-{
- struct scsi_unmap_parm_list *plist;
- struct nvme_dsm_range *range;
- struct nvme_command c;
- int i, nvme_sc, res;
- u16 ndesc, list_len;
-
- list_len = get_unaligned_be16(&cmd[7]);
- if (!list_len)
- return -EINVAL;
-
- plist = kmalloc(list_len, GFP_KERNEL);
- if (!plist)
- return -ENOMEM;
-
- res = nvme_trans_copy_from_user(hdr, plist, list_len);
- if (res)
- goto out;
-
- ndesc = be16_to_cpu(plist->unmap_blk_desc_data_len) >> 4;
- if (!ndesc || ndesc > 256) {
- res = -EINVAL;
- goto out;
- }
-
- range = kcalloc(ndesc, sizeof(*range), GFP_KERNEL);
- if (!range) {
- res = -ENOMEM;
- goto out;
- }
-
- for (i = 0; i < ndesc; i++) {
- range[i].nlb = cpu_to_le32(be32_to_cpu(plist
->desc[i].nlb));
- range[i].slba = cpu_to_le64(be64_to_cpu(plist
->desc[i].slba));
- range[i].cattr = 0;
- }
-
- memset(&c, 0, sizeof(c));
- c.dsm.opcode = nvme_cmd_dsm;
- c.dsm.nsid = cpu_to_le32(ns->ns_id);
- c.dsm.nr = cpu_to_le32(ndesc - 1);
- c.dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
-
- nvme_sc = nvme_submit_sync_cmd(ns->queue, &c, range,
- ndesc * sizeof(*range));
- res = nvme_trans_status_code(hdr, nvme_sc);
-
- kfree(range);
- out:
- kfree(plist);
- return res;
-}
-
-static int nvme_scsi_translate(struct nvme_ns *ns, struct sg_io_hdr
*hdr)
-{
- u8 cmd[BLK_MAX_CDB];
- int retcode;
- unsigned int opcode;
-
- if (hdr->cmdp == NULL)
- return -EMSGSIZE;
- if (copy_from_user(cmd, hdr->cmdp, hdr->cmd_len))
- return -EFAULT;
-
- /*
- * Prime the hdr with good status for scsi commands that don't
require
- * an nvme command for translation.
- */
- retcode = nvme_trans_status_code(hdr, NVME_SC_SUCCESS);
- if (retcode)
- return retcode;
-
- opcode = cmd[0];
-
- switch (opcode) {
- case READ_6:
- case READ_10:
- case READ_12:
- case READ_16:
- retcode = nvme_trans_io(ns, hdr, 0, cmd);
- break;
- case WRITE_6:
- case WRITE_10:
- case WRITE_12:
- case WRITE_16:
- retcode = nvme_trans_io(ns, hdr, 1, cmd);
- break;
- case INQUIRY:
- retcode = nvme_trans_inquiry(ns, hdr, cmd);
- break;
- case LOG_SENSE:
- retcode = nvme_trans_log_sense(ns, hdr, cmd);
- break;
- case MODE_SELECT:
- case MODE_SELECT_10:
- retcode = nvme_trans_mode_select(ns, hdr, cmd);
- break;
- case MODE_SENSE:
- case MODE_SENSE_10:
- retcode = nvme_trans_mode_sense(ns, hdr, cmd);
- break;
- case READ_CAPACITY:
- retcode = nvme_trans_read_capacity(ns, hdr, cmd, 0);
- break;
- case SERVICE_ACTION_IN_16:
- switch (cmd[1]) {
- case SAI_READ_CAPACITY_16:
- retcode = nvme_trans_read_capacity(ns, hdr,
cmd, 1);
- break;
- default:
- goto out;
- }
- break;
- case REPORT_LUNS:
- retcode = nvme_trans_report_luns(ns, hdr, cmd);
- break;
- case REQUEST_SENSE:
- retcode = nvme_trans_request_sense(ns, hdr, cmd);
- break;
- case SECURITY_PROTOCOL_IN:
- case SECURITY_PROTOCOL_OUT:
- retcode = nvme_trans_security_protocol(ns, hdr, cmd);
- break;
- case START_STOP:
- retcode = nvme_trans_start_stop(ns, hdr, cmd);
- break;
- case SYNCHRONIZE_CACHE:
- retcode = nvme_trans_synchronize_cache(ns, hdr);
- break;
- case FORMAT_UNIT:
- retcode = nvme_trans_format_unit(ns, hdr, cmd);
- break;
- case TEST_UNIT_READY:
- retcode = nvme_trans_test_unit_ready(ns, hdr, cmd);
- break;
- case WRITE_BUFFER:
- retcode = nvme_trans_write_buffer(ns, hdr, cmd);
- break;
- case UNMAP:
- retcode = nvme_trans_unmap(ns, hdr, cmd);
- break;
- default:
- out:
- retcode = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
SCSI_ASC_ILLEGAL_COMMAND,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- break;
- }
- return retcode;
-}
-
-int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr)
-{
- struct sg_io_hdr hdr;
- int retcode;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
- if (copy_from_user(&hdr, u_hdr, sizeof(hdr)))
- return -EFAULT;
- if (hdr.interface_id != 'S')
- return -EINVAL;
- if (hdr.cmd_len > BLK_MAX_CDB)
- return -EINVAL;
-
- /*
- * A positive return code means a NVMe status, which has been
- * translated to sense data.
- */
- retcode = nvme_scsi_translate(ns, &hdr);
- if (retcode < 0)
- return retcode;
- if (copy_to_user(u_hdr, &hdr, sizeof(sg_io_hdr_t)) > 0)
- return -EFAULT;
- return 0;
-}
-
-int nvme_sg_get_version_num(int __user *ip)
-{
- return put_user(sg_version_num, ip);
-}
diff --git a/drivers/block/nvme/Kconfig b/drivers/block/nvme/Kconfig
new file mode 100644
index 0000000..0089f78
--- /dev/null
+++ b/drivers/block/nvme/Kconfig
@@ -0,0 +1,10 @@
+config BLK_DEV_NVME
+ tristate "NVM Express block device"
+ depends on PCI
+ ---help---
+ The NVM Express driver is for solid state drives directly
+ connected to the PCI or PCI Express bus. If you know you
+ don't have one of these, it is safe to answer N.
+
+ To compile this driver as a module, choose M here: the
+ module will be called nvme.
diff --git a/drivers/block/nvme/Makefile b/drivers/block/nvme/Makefile
new file mode 100644
index 0000000..52e1310
--- /dev/null
+++ b/drivers/block/nvme/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_BLK_DEV_NVME) += nvme.o
+
+nvme-y := core.o scsi.o
diff --git a/drivers/block/nvme/core.c b/drivers/block/nvme/core.c
new file mode 100644
index 0000000..b97fc3f
--- /dev/null
+++ b/drivers/block/nvme/core.c
@@ -0,0 +1,3395 @@
+/*
+ * 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/nvme.h>
+#include <linux/bitops.h>
+#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/genhd.h>
+#include <linux/hdreg.h>
+#include <linux/idr.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kdev_t.h>
+#include <linux/kthread.h>
+#include <linux/kernel.h>
+#include <linux/list_sort.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/pci.h>
+#include <linux/poison.h>
+#include <linux/ptrace.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/t10-pi.h>
+#include <linux/types.h>
+#include <scsi/sg.h>
+#include <asm-generic/io-64-nonatomic-lo-hi.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))
+#define CQ_SIZE(depth) (depth * sizeof(struct
nvme_completion))
+#define ADMIN_TIMEOUT (admin_timeout * HZ)
+#define SHUTDOWN_TIMEOUT (shutdown_timeout * HZ)
+
+static unsigned char admin_timeout = 60;
+module_param(admin_timeout, byte, 0644);
+MODULE_PARM_DESC(admin_timeout, "timeout in seconds for admin
commands");
+
+unsigned char nvme_io_timeout = 30;
+module_param_named(io_timeout, nvme_io_timeout, byte, 0644);
+MODULE_PARM_DESC(io_timeout, "timeout in seconds for I/O");
+
+static 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_major;
+module_param(nvme_major, int, 0);
+
+static int nvme_char_major;
+module_param(nvme_char_major, int, 0);
+
+static int use_threaded_interrupts;
+module_param(use_threaded_interrupts, int, 0);
+
+static bool use_cmb_sqes = true;
+module_param(use_cmb_sqes, bool, 0644);
+MODULE_PARM_DESC(use_cmb_sqes, "use controller's memory buffer for I/O
SQes");
+
+static DEFINE_SPINLOCK(dev_list_lock);
+static LIST_HEAD(dev_list);
+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;
+
+static void nvme_reset_failed_dev(struct work_struct *ws);
+static int nvme_reset(struct nvme_dev *dev);
+static int nvme_process_cq(struct nvme_queue *nvmeq);
+
+struct async_cmd_info {
+ struct kthread_work work;
+ struct kthread_worker *worker;
+ struct request *req;
+ u32 result;
+ int status;
+ void *ctx;
+};
+
+/*
+ * An NVM Express queue. Each device has at least two (one for admin
+ * commands and one for I/O commands).
+ */
+struct nvme_queue {
+ struct device *q_dmadev;
+ struct nvme_dev *dev;
+ char irqname[24]; /* nvme4294967295-65535\0 */
+ spinlock_t q_lock;
+ struct nvme_command *sq_cmds;
+ struct nvme_command __iomem *sq_cmds_io;
+ volatile struct nvme_completion *cqes;
+ struct blk_mq_tags **tags;
+ dma_addr_t sq_dma_addr;
+ dma_addr_t cq_dma_addr;
+ u32 __iomem *q_db;
+ u16 q_depth;
+ s16 cq_vector;
+ u16 sq_head;
+ u16 sq_tail;
+ u16 cq_head;
+ u16 qid;
+ u8 cq_phase;
+ u8 cqe_seen;
+ struct async_cmd_info cmdinfo;
+};
+
+/*
+ * Check we didin't inadvertently grow the command struct
+ */
+static inline void _nvme_check_size(void)
+{
+ BUILD_BUG_ON(sizeof(struct nvme_rw_command) != 64);
+ BUILD_BUG_ON(sizeof(struct nvme_create_cq) != 64);
+ BUILD_BUG_ON(sizeof(struct nvme_create_sq) != 64);
+ BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64);
+ BUILD_BUG_ON(sizeof(struct nvme_features) != 64);
+ BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64);
+ BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64);
+ BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
+ BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != 4096);
+ BUILD_BUG_ON(sizeof(struct nvme_id_ns) != 4096);
+ BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
+ BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
+}
+
+typedef void (*nvme_completion_fn)(struct nvme_queue *, void *,
+ struct nvme_completion
*);
+
+struct nvme_cmd_info {
+ nvme_completion_fn fn;
+ void *ctx;
+ int aborted;
+ struct nvme_queue *nvmeq;
+ struct nvme_iod iod[0];
+};
+
+/*
+ * Max size of iod being embedded in the request payload
+ */
+#define NVME_INT_PAGES 2
+#define NVME_INT_BYTES(dev) (NVME_INT_PAGES * (dev)->page_size)
+#define NVME_INT_MASK 0x01
+
+/*
+ * Will slightly overestimate the number of pages needed. This is OK
+ * as it only leads to a small amount of wasted memory for the
lifetime of
+ * the I/O.
+ */
+static int nvme_npages(unsigned size, struct nvme_dev *dev)
+{
+ unsigned nprps = DIV_ROUND_UP(size + dev->page_size, dev
->page_size);
+ return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8);
+}
+
+static unsigned int nvme_cmd_size(struct nvme_dev *dev)
+{
+ unsigned int ret = sizeof(struct nvme_cmd_info);
+
+ ret += sizeof(struct nvme_iod);
+ ret += sizeof(__le64 *) * nvme_npages(NVME_INT_BYTES(dev),
dev);
+ ret += sizeof(struct scatterlist) * NVME_INT_PAGES;
+
+ return ret;
+}
+
+static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void
*data,
+ unsigned int hctx_idx)
+{
+ struct nvme_dev *dev = data;
+ struct nvme_queue *nvmeq = dev->queues[0];
+
+ WARN_ON(hctx_idx != 0);
+ WARN_ON(dev->admin_tagset.tags[0] != hctx->tags);
+ WARN_ON(nvmeq->tags);
+
+ hctx->driver_data = nvmeq;
+ nvmeq->tags = &dev->admin_tagset.tags[0];
+ return 0;
+}
+
+static void nvme_admin_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned
int hctx_idx)
+{
+ struct nvme_queue *nvmeq = hctx->driver_data;
+
+ nvmeq->tags = NULL;
+}
+
+static int nvme_admin_init_request(void *data, struct request *req,
+ unsigned int hctx_idx, unsigned int
rq_idx,
+ unsigned int numa_node)
+{
+ struct nvme_dev *dev = data;
+ struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
+ struct nvme_queue *nvmeq = dev->queues[0];
+
+ BUG_ON(!nvmeq);
+ cmd->nvmeq = nvmeq;
+ return 0;
+}
+
+static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+ unsigned int hctx_idx)
+{
+ struct nvme_dev *dev = data;
+ struct nvme_queue *nvmeq = dev->queues[hctx_idx + 1];
+
+ if (!nvmeq->tags)
+ nvmeq->tags = &dev->tagset.tags[hctx_idx];
+
+ WARN_ON(dev->tagset.tags[hctx_idx] != hctx->tags);
+ hctx->driver_data = nvmeq;
+ return 0;
+}
+
+static int nvme_init_request(void *data, struct request *req,
+ unsigned int hctx_idx, unsigned int
rq_idx,
+ unsigned int numa_node)
+{
+ struct nvme_dev *dev = data;
+ struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
+ struct nvme_queue *nvmeq = dev->queues[hctx_idx + 1];
+
+ BUG_ON(!nvmeq);
+ cmd->nvmeq = nvmeq;
+ return 0;
+}
+
+static void nvme_set_info(struct nvme_cmd_info *cmd, void *ctx,
+ nvme_completion_fn handler)
+{
+ cmd->fn = handler;
+ cmd->ctx = ctx;
+ cmd->aborted = 0;
+ blk_mq_start_request(blk_mq_rq_from_pdu(cmd));
+}
+
+static void *iod_get_private(struct nvme_iod *iod)
+{
+ return (void *) (iod->private & ~0x1UL);
+}
+
+/*
+ * If bit 0 is set, the iod is embedded in the request payload.
+ */
+static bool iod_should_kfree(struct nvme_iod *iod)
+{
+ return (iod->private & NVME_INT_MASK) == 0;
+}
+
+/* Special values must be less than 0x1000 */
+#define CMD_CTX_BASE ((void *)POISON_POINTER_DELTA)
+#define CMD_CTX_CANCELLED (0x30C + CMD_CTX_BASE)
+#define CMD_CTX_COMPLETED (0x310 + CMD_CTX_BASE)
+#define CMD_CTX_INVALID (0x314 + CMD_CTX_BASE)
+
+static void special_completion(struct nvme_queue *nvmeq, void *ctx,
+ struct nvme_completion
*cqe)
+{
+ if (ctx == CMD_CTX_CANCELLED)
+ return;
+ if (ctx == CMD_CTX_COMPLETED) {
+ dev_warn(nvmeq->q_dmadev,
+ "completed id %d twice on queue %d\n",
+ cqe->command_id, le16_to_cpup(&cqe
->sq_id));
+ return;
+ }
+ if (ctx == CMD_CTX_INVALID) {
+ dev_warn(nvmeq->q_dmadev,
+ "invalid id %d completed on queue
%d\n",
+ cqe->command_id, le16_to_cpup(&cqe
->sq_id));
+ return;
+ }
+ dev_warn(nvmeq->q_dmadev, "Unknown special completion %p\n",
ctx);
+}
+
+static void *cancel_cmd_info(struct nvme_cmd_info *cmd,
nvme_completion_fn *fn)
+{
+ void *ctx;
+
+ if (fn)
+ *fn = cmd->fn;
+ ctx = cmd->ctx;
+ cmd->fn = special_completion;
+ cmd->ctx = CMD_CTX_CANCELLED;
+ return ctx;
+}
+
+static void async_req_completion(struct nvme_queue *nvmeq, void *ctx,
+ struct nvme_completion
*cqe)
+{
+ u32 result = le32_to_cpup(&cqe->result);
+ u16 status = le16_to_cpup(&cqe->status) >> 1;
+
+ if (status == NVME_SC_SUCCESS || status == NVME_SC_ABORT_REQ)
+ ++nvmeq->dev->event_limit;
+ if (status != NVME_SC_SUCCESS)
+ return;
+
+ switch (result & 0xff07) {
+ case NVME_AER_NOTICE_NS_CHANGED:
+ dev_info(nvmeq->q_dmadev, "rescanning\n");
+ schedule_work(&nvmeq->dev->scan_work);
+ default:
+ dev_warn(nvmeq->q_dmadev, "async event result %08x\n",
result);
+ }
+}
+
+static void abort_completion(struct nvme_queue *nvmeq, void *ctx,
+ struct nvme_completion
*cqe)
+{
+ struct request *req = ctx;
+
+ u16 status = le16_to_cpup(&cqe->status) >> 1;
+ u32 result = le32_to_cpup(&cqe->result);
+
+ blk_mq_free_request(req);
+
+ dev_warn(nvmeq->q_dmadev, "Abort status:%x result:%x", status,
result);
+ ++nvmeq->dev->abort_limit;
+}
+
+static void async_completion(struct nvme_queue *nvmeq, void *ctx,
+ struct nvme_completion
*cqe)
+{
+ struct async_cmd_info *cmdinfo = ctx;
+ cmdinfo->result = le32_to_cpup(&cqe->result);
+ cmdinfo->status = le16_to_cpup(&cqe->status) >> 1;
+ queue_kthread_work(cmdinfo->worker, &cmdinfo->work);
+ blk_mq_free_request(cmdinfo->req);
+}
+
+static inline struct nvme_cmd_info *get_cmd_from_tag(struct nvme_queue
*nvmeq,
+ unsigned int tag)
+{
+ struct request *req = blk_mq_tag_to_rq(*nvmeq->tags, tag);
+
+ return blk_mq_rq_to_pdu(req);
+}
+
+/*
+ * Called with local interrupts disabled and the q_lock held. May not
sleep.
+ */
+static void *nvme_finish_cmd(struct nvme_queue *nvmeq, int tag,
+ nvme_completion_fn
*fn)
+{
+ struct nvme_cmd_info *cmd = get_cmd_from_tag(nvmeq, tag);
+ void *ctx;
+ if (tag >= nvmeq->q_depth) {
+ *fn = special_completion;
+ return CMD_CTX_INVALID;
+ }
+ if (fn)
+ *fn = cmd->fn;
+ ctx = cmd->ctx;
+ cmd->fn = special_completion;
+ cmd->ctx = CMD_CTX_COMPLETED;
+ return ctx;
+}
+
+/**
+ * nvme_submit_cmd() - Copy a command into a queue and ring the
doorbell
+ * @nvmeq: The queue to use
+ * @cmd: The command to send
+ *
+ * Safe to use from interrupt context
+ */
+static void __nvme_submit_cmd(struct nvme_queue *nvmeq,
+ struct nvme_command
*cmd)
+{
+ u16 tail = nvmeq->sq_tail;
+
+ if (nvmeq->sq_cmds_io)
+ memcpy_toio(&nvmeq->sq_cmds_io[tail], cmd,
sizeof(*cmd));
+ else
+ memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
+
+ if (++tail == nvmeq->q_depth)
+ tail = 0;
+ writel(tail, nvmeq->q_db);
+ nvmeq->sq_tail = tail;
+}
+
+static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct
nvme_command *cmd)
+{
+ unsigned long flags;
+ spin_lock_irqsave(&nvmeq->q_lock, flags);
+ __nvme_submit_cmd(nvmeq, cmd);
+ spin_unlock_irqrestore(&nvmeq->q_lock, flags);
+}
+
+static __le64 **iod_list(struct nvme_iod *iod)
+{
+ return ((void *)iod) + iod->offset;
+}
+
+static inline void iod_init(struct nvme_iod *iod, unsigned nbytes,
+ unsigned nseg, unsigned long private)
+{
+ iod->private = private;
+ iod->offset = offsetof(struct nvme_iod, sg[nseg]);
+ iod->npages = -1;
+ iod->length = nbytes;
+ iod->nents = 0;
+}
+
+static struct nvme_iod *
+__nvme_alloc_iod(unsigned nseg, unsigned bytes, struct nvme_dev *dev,
+ unsigned long priv, gfp_t gfp)
+{
+ struct nvme_iod *iod = kmalloc(sizeof(struct nvme_iod) +
+ sizeof(__le64 *) * nvme_npages(bytes,
dev) +
+ sizeof(struct scatterlist) * nseg,
gfp);
+
+ if (iod)
+ iod_init(iod, bytes, nseg, priv);
+
+ return iod;
+}
+
+static struct nvme_iod *nvme_alloc_iod(struct request *rq, struct
nvme_dev *dev,
+ gfp_t gfp)
+{
+ unsigned size = !(rq->cmd_flags & REQ_DISCARD) ?
blk_rq_bytes(rq) :
+ sizeof(struct
nvme_dsm_range);
+ struct nvme_iod *iod;
+
+ if (rq->nr_phys_segments <= NVME_INT_PAGES &&
+ size <= NVME_INT_BYTES(dev)) {
+ struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(rq);
+
+ iod = cmd->iod;
+ iod_init(iod, size, rq->nr_phys_segments,
+ (unsigned long) rq | NVME_INT_MASK);
+ return iod;
+ }
+
+ return __nvme_alloc_iod(rq->nr_phys_segments, size, dev,
+ (unsigned long) rq, gfp);
+}
+
+static void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
+{
+ const int last_prp = dev->page_size / 8 - 1;
+ int i;
+ __le64 **list = iod_list(iod);
+ dma_addr_t prp_dma = iod->first_dma;
+
+ if (iod->npages == 0)
+ dma_pool_free(dev->prp_small_pool, list[0], prp_dma);
+ for (i = 0; i < iod->npages; i++) {
+ __le64 *prp_list = list[i];
+ dma_addr_t next_prp_dma =
le64_to_cpu(prp_list[last_prp]);
+ dma_pool_free(dev->prp_page_pool, prp_list, prp_dma);
+ prp_dma = next_prp_dma;
+ }
+
+ if (iod_should_kfree(iod))
+ kfree(iod);
+}
+
+static int nvme_error_status(u16 status)
+{
+ switch (status & 0x7ff) {
+ case NVME_SC_SUCCESS:
+ return 0;
+ case NVME_SC_CAP_EXCEEDED:
+ return -ENOSPC;
+ default:
+ return -EIO;
+ }
+}
+
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
+{
+ if (be32_to_cpu(pi->ref_tag) == v)
+ pi->ref_tag = cpu_to_be32(p);
+}
+
+static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
+{
+ if (be32_to_cpu(pi->ref_tag) == p)
+ pi->ref_tag = cpu_to_be32(v);
+}
+
+/**
+ * nvme_dif_remap - remaps ref tags to bip seed and physical lba
+ *
+ * The virtual start sector is the one that was originally submitted
by the
+ * block layer. Due to partitioning, MD/DM cloning, etc. the
actual physical
+ * start sector may be different. Remap protection information to
match the
+ * physical LBA on writes, and back to the original seed on reads.
+ *
+ * Type 0 and 3 do not have a ref tag, so no remapping required.
+ */
+static void nvme_dif_remap(struct request *req,
+ void (*dif_swap)(u32 p, u32 v, struct
t10_pi_tuple *pi))
+{
+ struct nvme_ns *ns = req->rq_disk->private_data;
+ struct bio_integrity_payload *bip;
+ struct t10_pi_tuple *pi;
+ void *p, *pmap;
+ u32 i, nlb, ts, phys, virt;
+
+ if (!ns->pi_type || ns->pi_type == NVME_NS_DPS_PI_TYPE3)
+ return;
+
+ bip = bio_integrity(req->bio);
+ if (!bip)
+ return;
+
+ pmap = kmap_atomic(bip->bip_vec->bv_page) + bip->bip_vec
->bv_offset;
+
+ p = pmap;
+ virt = bip_get_seed(bip);
+ phys = nvme_block_nr(ns, blk_rq_pos(req));
+ nlb = (blk_rq_bytes(req) >> ns->lba_shift);
+ ts = ns->disk->integrity->tuple_size;
+
+ for (i = 0; i < nlb; i++, virt++, phys++) {
+ pi = (struct t10_pi_tuple *)p;
+ dif_swap(phys, virt, pi);
+ p += ts;
+ }
+ kunmap_atomic(pmap);
+}
+
+static int nvme_noop_verify(struct blk_integrity_iter *iter)
+{
+ return 0;
+}
+
+static int nvme_noop_generate(struct blk_integrity_iter *iter)
+{
+ return 0;
+}
+
+struct blk_integrity nvme_meta_noop = {
+ .name = "NVME_META_NOOP",
+ .generate_fn = nvme_noop_generate,
+ .verify_fn = nvme_noop_verify,
+};
+
+static void nvme_init_integrity(struct nvme_ns *ns)
+{
+ struct blk_integrity integrity;
+
+ switch (ns->pi_type) {
+ case NVME_NS_DPS_PI_TYPE3:
+ integrity = t10_pi_type3_crc;
+ break;
+ case NVME_NS_DPS_PI_TYPE1:
+ case NVME_NS_DPS_PI_TYPE2:
+ integrity = t10_pi_type1_crc;
+ break;
+ default:
+ integrity = nvme_meta_noop;
+ break;
+ }
+ integrity.tuple_size = ns->ms;
+ blk_integrity_register(ns->disk, &integrity);
+ blk_queue_max_integrity_segments(ns->queue, 1);
+}
+#else /* CONFIG_BLK_DEV_INTEGRITY */
+static void nvme_dif_remap(struct request *req,
+ void (*dif_swap)(u32 p, u32 v, struct
t10_pi_tuple *pi))
+{
+}
+static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
+{
+}
+static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
+{
+}
+static void nvme_init_integrity(struct nvme_ns *ns)
+{
+}
+#endif
+
+static void req_completion(struct nvme_queue *nvmeq, void *ctx,
+ struct nvme_completion
*cqe)
+{
+ struct nvme_iod *iod = ctx;
+ struct request *req = iod_get_private(iod);
+ struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
+
+ u16 status = le16_to_cpup(&cqe->status) >> 1;
+
+ if (unlikely(status)) {
+ if (!(status & NVME_SC_DNR ||
blk_noretry_request(req))
+ && (jiffies - req->start_time) < req->timeout) {
+ unsigned long flags;
+
+ blk_mq_requeue_request(req);
+ spin_lock_irqsave(req->q->queue_lock, flags);
+ if (!blk_queue_stopped(req->q))
+ blk_mq_kick_requeue_list(req->q);
+ spin_unlock_irqrestore(req->q->queue_lock,
flags);
+ return;
+ }
+ if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
+ if (cmd_rq->ctx == CMD_CTX_CANCELLED)
+ req->errors = -EINTR;
+ else
+ req->errors = status;
+ } else {
+ req->errors = nvme_error_status(status);
+ }
+ } else
+ req->errors = 0;
+ if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
+ u32 result = le32_to_cpup(&cqe->result);
+ req->special = (void *)(uintptr_t)result;
+ }
+
+ if (cmd_rq->aborted)
+ dev_warn(nvmeq->dev->dev,
+ "completing aborted command with
status:%04x\n",
+ status);
+
+ if (iod->nents) {
+ dma_unmap_sg(nvmeq->dev->dev, iod->sg, iod->nents,
+ rq_data_dir(req) ? DMA_TO_DEVICE :
DMA_FROM_DEVICE);
+ if (blk_integrity_rq(req)) {
+ if (!rq_data_dir(req))
+ nvme_dif_remap(req,
nvme_dif_complete);
+ dma_unmap_sg(nvmeq->dev->dev, iod->meta_sg, 1,
+ rq_data_dir(req) ? DMA_TO_DEVICE :
DMA_FROM_DEVICE);
+ }
+ }
+ nvme_free_iod(nvmeq->dev, iod);
+
+ blk_mq_complete_request(req);
+}
+
+/* length is in bytes. gfp flags indicates whether we may sleep. */
+static int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod,
+ int total_len, gfp_t gfp)
+{
+ struct dma_pool *pool;
+ int length = total_len;
+ struct scatterlist *sg = iod->sg;
+ int dma_len = sg_dma_len(sg);
+ u64 dma_addr = sg_dma_address(sg);
+ u32 page_size = dev->page_size;
+ int offset = dma_addr & (page_size - 1);
+ __le64 *prp_list;
+ __le64 **list = iod_list(iod);
+ dma_addr_t prp_dma;
+ int nprps, i;
+
+ length -= (page_size - offset);
+ if (length <= 0)
+ return total_len;
+
+ dma_len -= (page_size - offset);
+ if (dma_len) {
+ dma_addr += (page_size - offset);
+ } else {
+ sg = sg_next(sg);
+ dma_addr = sg_dma_address(sg);
+ dma_len = sg_dma_len(sg);
+ }
+
+ if (length <= page_size) {
+ iod->first_dma = dma_addr;
+ return total_len;
+ }
+
+ nprps = DIV_ROUND_UP(length, page_size);
+ if (nprps <= (256 / 8)) {
+ pool = dev->prp_small_pool;
+ iod->npages = 0;
+ } else {
+ pool = dev->prp_page_pool;
+ iod->npages = 1;
+ }
+
+ prp_list = dma_pool_alloc(pool, gfp, &prp_dma);
+ if (!prp_list) {
+ iod->first_dma = dma_addr;
+ iod->npages = -1;
+ return (total_len - length) + page_size;
+ }
+ list[0] = prp_list;
+ iod->first_dma = prp_dma;
+ i = 0;
+ for (;;) {
+ if (i == page_size >> 3) {
+ __le64 *old_prp_list = prp_list;
+ prp_list = dma_pool_alloc(pool, gfp,
&prp_dma);
+ if (!prp_list)
+ return total_len - length;
+ list[iod->npages++] = prp_list;
+ prp_list[0] = old_prp_list[i - 1];
+ old_prp_list[i - 1] = cpu_to_le64(prp_dma);
+ i = 1;
+ }
+ prp_list[i++] = cpu_to_le64(dma_addr);
+ dma_len -= page_size;
+ dma_addr += page_size;
+ length -= page_size;
+ if (length <= 0)
+ break;
+ if (dma_len > 0)
+ continue;
+ BUG_ON(dma_len < 0);
+ sg = sg_next(sg);
+ dma_addr = sg_dma_address(sg);
+ dma_len = sg_dma_len(sg);
+ }
+
+ return total_len;
+}
+
+static void nvme_submit_priv(struct nvme_queue *nvmeq, struct request
*req,
+ struct nvme_iod *iod)
+{
+ struct nvme_command cmnd;
+
+ memcpy(&cmnd, req->cmd, sizeof(cmnd));
+ cmnd.rw.command_id = req->tag;
+ if (req->nr_phys_segments) {
+ cmnd.rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+ cmnd.rw.prp2 = cpu_to_le64(iod->first_dma);
+ }
+
+ __nvme_submit_cmd(nvmeq, &cmnd);
+}
+
+/*
+ * We reuse the small pool to allocate the 16-byte range here as it is
not
+ * worth having a special pool for these or additional cases to handle
freeing
+ * the iod.
+ */
+static void nvme_submit_discard(struct nvme_queue *nvmeq, struct
nvme_ns *ns,
+ struct request *req, struct nvme_iod *iod)
+{
+ struct nvme_dsm_range *range =
+ (struct nvme_dsm_range
*)iod_list(iod)[0];
+ struct nvme_command cmnd;
+
+ range->cattr = cpu_to_le32(0);
+ range->nlb = cpu_to_le32(blk_rq_bytes(req) >> ns->lba_shift);
+ range->slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
+
+ memset(&cmnd, 0, sizeof(cmnd));
+ cmnd.dsm.opcode = nvme_cmd_dsm;
+ cmnd.dsm.command_id = req->tag;
+ cmnd.dsm.nsid = cpu_to_le32(ns->ns_id);
+ cmnd.dsm.prp1 = cpu_to_le64(iod->first_dma);
+ cmnd.dsm.nr = 0;
+ cmnd.dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
+
+ __nvme_submit_cmd(nvmeq, &cmnd);
+}
+
+static void nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns
*ns,
+ int
cmdid)
+{
+ struct nvme_command cmnd;
+
+ memset(&cmnd, 0, sizeof(cmnd));
+ cmnd.common.opcode = nvme_cmd_flush;
+ cmnd.common.command_id = cmdid;
+ cmnd.common.nsid = cpu_to_le32(ns->ns_id);
+
+ __nvme_submit_cmd(nvmeq, &cmnd);
+}
+
+static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod
*iod,
+ struct nvme_ns
*ns)
+{
+ struct request *req = iod_get_private(iod);
+ struct nvme_command cmnd;
+ u16 control = 0;
+ u32 dsmgmt = 0;
+
+ if (req->cmd_flags & REQ_FUA)
+ control |= NVME_RW_FUA;
+ if (req->cmd_flags & (REQ_FAILFAST_DEV | REQ_RAHEAD))
+ control |= NVME_RW_LR;
+
+ if (req->cmd_flags & REQ_RAHEAD)
+ dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
+
+ memset(&cmnd, 0, sizeof(cmnd));
+ cmnd.rw.opcode = (rq_data_dir(req) ? nvme_cmd_write :
nvme_cmd_read);
+ cmnd.rw.command_id = req->tag;
+ cmnd.rw.nsid = cpu_to_le32(ns->ns_id);
+ cmnd.rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+ cmnd.rw.prp2 = cpu_to_le64(iod->first_dma);
+ cmnd.rw.slba = cpu_to_le64(nvme_block_nr(ns,
blk_rq_pos(req)));
+ cmnd.rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns
->lba_shift) - 1);
+
+ if (ns->ms) {
+ switch (ns->pi_type) {
+ case NVME_NS_DPS_PI_TYPE3:
+ control |= NVME_RW_PRINFO_PRCHK_GUARD;
+ break;
+ case NVME_NS_DPS_PI_TYPE1:
+ case NVME_NS_DPS_PI_TYPE2:
+ control |= NVME_RW_PRINFO_PRCHK_GUARD |
+ NVME_RW_PRINFO_PRCHK_REF;
+ cmnd.rw.reftag = cpu_to_le32(
+ nvme_block_nr(ns,
blk_rq_pos(req)));
+ break;
+ }
+ if (blk_integrity_rq(req))
+ cmnd.rw.metadata =
+ cpu_to_le64(sg_dma_address(iod
->meta_sg));
+ else
+ control |= NVME_RW_PRINFO_PRACT;
+ }
+
+ cmnd.rw.control = cpu_to_le16(control);
+ cmnd.rw.dsmgmt = cpu_to_le32(dsmgmt);
+
+ __nvme_submit_cmd(nvmeq, &cmnd);
+
+ return 0;
+}
+
+/*
+ * NOTE: ns is NULL when called on the admin queue.
+ */
+static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
+ const struct blk_mq_queue_data *bd)
+{
+ struct nvme_ns *ns = hctx->queue->queuedata;
+ struct nvme_queue *nvmeq = hctx->driver_data;
+ struct nvme_dev *dev = nvmeq->dev;
+ struct request *req = bd->rq;
+ struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
+ struct nvme_iod *iod;
+ enum dma_data_direction dma_dir;
+
+ /*
+ * If formated with metadata, require the block layer provide
a buffer
+ * unless this namespace is formated such that the metadata
can be
+ * stripped/generated by the controller with PRACT=1.
+ */
+ if (ns && ns->ms && !blk_integrity_rq(req)) {
+ if (!(ns->pi_type && ns->ms == 8) &&
+ req->cmd_type !=
REQ_TYPE_DRV_PRIV) {
+ req->errors = -EFAULT;
+ blk_mq_complete_request(req);
+ return BLK_MQ_RQ_QUEUE_OK;
+ }
+ }
+
+ iod = nvme_alloc_iod(req, dev, GFP_ATOMIC);
+ if (!iod)
+ return BLK_MQ_RQ_QUEUE_BUSY;
+
+ if (req->cmd_flags & REQ_DISCARD) {
+ void *range;
+ /*
+ * We reuse the small pool to allocate the 16-byte
range here
+ * as it is not worth having a special pool for these
or
+ * additional cases to handle freeing the iod.
+ */
+ range = dma_pool_alloc(dev->prp_small_pool,
GFP_ATOMIC,
+ &iod->first_dma);
+ if (!range)
+ goto retry_cmd;
+ iod_list(iod)[0] = (__le64 *)range;
+ iod->npages = 0;
+ } else if (req->nr_phys_segments) {
+ dma_dir = rq_data_dir(req) ? DMA_TO_DEVICE :
DMA_FROM_DEVICE;
+
+ sg_init_table(iod->sg, req->nr_phys_segments);
+ iod->nents = blk_rq_map_sg(req->q, req, iod->sg);
+ if (!iod->nents)
+ goto error_cmd;
+
+ if (!dma_map_sg(nvmeq->q_dmadev, iod->sg, iod->nents,
dma_dir))
+ goto retry_cmd;
+
+ if (blk_rq_bytes(req) !=
+ nvme_setup_prps(dev, iod, blk_rq_bytes(req),
GFP_ATOMIC)) {
+ dma_unmap_sg(dev->dev, iod->sg, iod->nents,
dma_dir);
+ goto retry_cmd;
+ }
+ if (blk_integrity_rq(req)) {
+ if (blk_rq_count_integrity_sg(req->q, req
->bio) != 1)
+ goto error_cmd;
+
+ sg_init_table(iod->meta_sg, 1);
+ if (blk_rq_map_integrity_sg(
+ req->q, req->bio, iod
->meta_sg) != 1)
+ goto error_cmd;
+
+ if (rq_data_dir(req))
+ nvme_dif_remap(req, nvme_dif_prep);
+
+ if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg,
1, dma_dir))
+ goto error_cmd;
+ }
+ }
+
+ nvme_set_info(cmd, iod, req_completion);
+ spin_lock_irq(&nvmeq->q_lock);
+ if (req->cmd_type == REQ_TYPE_DRV_PRIV)
+ nvme_submit_priv(nvmeq, req, iod);
+ else if (req->cmd_flags & REQ_DISCARD)
+ nvme_submit_discard(nvmeq, ns, req, iod);
+ else if (req->cmd_flags & REQ_FLUSH)
+ nvme_submit_flush(nvmeq, ns, req->tag);
+ else
+ nvme_submit_iod(nvmeq, iod, ns);
+
+ nvme_process_cq(nvmeq);
+ spin_unlock_irq(&nvmeq->q_lock);
+ return BLK_MQ_RQ_QUEUE_OK;
+
+ error_cmd:
+ nvme_free_iod(dev, iod);
+ return BLK_MQ_RQ_QUEUE_ERROR;
+ retry_cmd:
+ nvme_free_iod(dev, iod);
+ return BLK_MQ_RQ_QUEUE_BUSY;
+}
+
+static int nvme_process_cq(struct nvme_queue *nvmeq)
+{
+ u16 head, phase;
+
+ head = nvmeq->cq_head;
+ phase = nvmeq->cq_phase;
+
+ for (;;) {
+ void *ctx;
+ nvme_completion_fn fn;
+ struct nvme_completion cqe = nvmeq->cqes[head];
+ if ((le16_to_cpu(cqe.status) & 1) != phase)
+ break;
+ nvmeq->sq_head = le16_to_cpu(cqe.sq_head);
+ if (++head == nvmeq->q_depth) {
+ head = 0;
+ phase = !phase;
+ }
+ ctx = nvme_finish_cmd(nvmeq, cqe.command_id, &fn);
+ fn(nvmeq, ctx, &cqe);
+ }
+
+ /* If the controller ignores the cq head doorbell and
continuously
+ * writes to the queue, it is theoretically possible to wrap
around
+ * the queue twice and mistakenly return IRQ_NONE. Linux only
+ * requires that 0.1% of your interrupts are handled, so this
isn't
+ * a big problem.
+ */
+ if (head == nvmeq->cq_head && phase == nvmeq->cq_phase)
+ return 0;
+
+ writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
+ nvmeq->cq_head = head;
+ nvmeq->cq_phase = phase;
+
+ nvmeq->cqe_seen = 1;
+ return 1;
+}
+
+static irqreturn_t nvme_irq(int irq, void *data)
+{
+ irqreturn_t result;
+ struct nvme_queue *nvmeq = data;
+ spin_lock(&nvmeq->q_lock);
+ nvme_process_cq(nvmeq);
+ result = nvmeq->cqe_seen ? IRQ_HANDLED : IRQ_NONE;
+ nvmeq->cqe_seen = 0;
+ spin_unlock(&nvmeq->q_lock);
+ return result;
+}
+
+static irqreturn_t nvme_irq_check(int irq, void *data)
+{
+ struct nvme_queue *nvmeq = data;
+ struct nvme_completion cqe = nvmeq->cqes[nvmeq->cq_head];
+ if ((le16_to_cpu(cqe.status) & 1) != nvmeq->cq_phase)
+ return IRQ_NONE;
+ return IRQ_WAKE_THREAD;
+}
+
+/*
+ * 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, void __user *ubuffer, unsigned bufflen,
+ u32 *result, unsigned timeout)
+{
+ bool write = cmd->common.opcode & 1;
+ struct bio *bio = NULL;
+ struct request *req;
+ int ret;
+
+ req = blk_mq_alloc_request(q, write, GFP_KERNEL, false);
+ if (IS_ERR(req))
+ return PTR_ERR(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->timeout = timeout ? timeout : ADMIN_TIMEOUT;
+
+ req->cmd = (unsigned char *)cmd;
+ req->cmd_len = sizeof(struct nvme_command);
+ req->special = (void *)0;
+
+ if (buffer && bufflen) {
+ ret = blk_rq_map_kern(q, req, buffer, bufflen,
__GFP_WAIT);
+ if (ret)
+ goto out;
+ } else if (ubuffer && bufflen) {
+ ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen,
__GFP_WAIT);
+ if (ret)
+ goto out;
+ bio = req->bio;
+ }
+
+ blk_execute_rq(req->q, NULL, req, 0);
+ if (bio)
+ blk_rq_unmap_user(bio);
+ 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, NULL, bufflen,
NULL, 0);
+}
+
+static int nvme_submit_async_admin_req(struct nvme_dev *dev)
+{
+ struct nvme_queue *nvmeq = dev->queues[0];
+ struct nvme_command c;
+ struct nvme_cmd_info *cmd_info;
+ struct request *req;
+
+ req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_ATOMIC,
true);
+ if (IS_ERR(req))
+ return PTR_ERR(req);
+
+ req->cmd_flags |= REQ_NO_TIMEOUT;
+ cmd_info = blk_mq_rq_to_pdu(req);
+ nvme_set_info(cmd_info, NULL, async_req_completion);
+
+ memset(&c, 0, sizeof(c));
+ c.common.opcode = nvme_admin_async_event;
+ c.common.command_id = req->tag;
+
+ blk_mq_free_request(req);
+ __nvme_submit_cmd(nvmeq, &c);
+ return 0;
+}
+
+static int nvme_submit_admin_async_cmd(struct nvme_dev *dev,
+ struct nvme_command *cmd,
+ struct async_cmd_info *cmdinfo, unsigned
timeout)
+{
+ struct nvme_queue *nvmeq = dev->queues[0];
+ struct request *req;
+ struct nvme_cmd_info *cmd_rq;
+
+ req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_KERNEL,
false);
+ if (IS_ERR(req))
+ return PTR_ERR(req);
+
+ req->timeout = timeout;
+ cmd_rq = blk_mq_rq_to_pdu(req);
+ cmdinfo->req = req;
+ nvme_set_info(cmd_rq, cmdinfo, async_completion);
+ cmdinfo->status = -EINTR;
+
+ cmd->common.command_id = req->tag;
+
+ nvme_submit_cmd(nvmeq, cmd);
+ return 0;
+}
+
+static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16
id)
+{
+ struct nvme_command c;
+
+ memset(&c, 0, sizeof(c));
+ c.delete_queue.opcode = opcode;
+ c.delete_queue.qid = cpu_to_le16(id);
+
+ return nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0);
+}
+
+static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
+ struct nvme_queue
*nvmeq)
+{
+ struct nvme_command c;
+ int flags = NVME_QUEUE_PHYS_CONTIG | NVME_CQ_IRQ_ENABLED;
+
+ /*
+ * Note: we (ab)use the fact the the prp fields survive if no
data
+ * is attached to the request.
+ */
+ memset(&c, 0, sizeof(c));
+ c.create_cq.opcode = nvme_admin_create_cq;
+ c.create_cq.prp1 = cpu_to_le64(nvmeq->cq_dma_addr);
+ c.create_cq.cqid = cpu_to_le16(qid);
+ c.create_cq.qsize = cpu_to_le16(nvmeq->q_depth - 1);
+ c.create_cq.cq_flags = cpu_to_le16(flags);
+ c.create_cq.irq_vector = cpu_to_le16(nvmeq->cq_vector);
+
+ return nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0);
+}
+
+static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
+ struct nvme_queue
*nvmeq)
+{
+ struct nvme_command c;
+ int flags = NVME_QUEUE_PHYS_CONTIG | NVME_SQ_PRIO_MEDIUM;
+
+ /*
+ * Note: we (ab)use the fact the the prp fields survive if no
data
+ * is attached to the request.
+ */
+ memset(&c, 0, sizeof(c));
+ c.create_sq.opcode = nvme_admin_create_sq;
+ c.create_sq.prp1 = cpu_to_le64(nvmeq->sq_dma_addr);
+ c.create_sq.sqid = cpu_to_le16(qid);
+ c.create_sq.qsize = cpu_to_le16(nvmeq->q_depth - 1);
+ c.create_sq.sq_flags = cpu_to_le16(flags);
+ c.create_sq.cqid = cpu_to_le16(qid);
+
+ return nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0);
+}
+
+static int adapter_delete_cq(struct nvme_dev *dev, u16 cqid)
+{
+ return adapter_delete_queue(dev, nvme_admin_delete_cq, cqid);
+}
+
+static int adapter_delete_sq(struct nvme_dev *dev, u16 sqid)
+{
+ return adapter_delete_queue(dev, nvme_admin_delete_sq, sqid);
+}
+
+int nvme_identify_ctrl(struct nvme_dev *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_dev *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_dev *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, NULL, 0,
+ result, 0);
+}
+
+int nvme_set_features(struct nvme_dev *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, NULL, 0,
+ result, 0);
+}
+
+int nvme_get_log_page(struct nvme_dev *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;
+}
+
+/**
+ * nvme_abort_req - Attempt aborting a request
+ *
+ * Schedule controller reset if the command was already aborted once
before and
+ * still hasn't been returned to the driver, or if this is the admin
queue.
+ */
+static void nvme_abort_req(struct request *req)
+{
+ struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
+ struct nvme_queue *nvmeq = cmd_rq->nvmeq;
+ struct nvme_dev *dev = nvmeq->dev;
+ struct request *abort_req;
+ struct nvme_cmd_info *abort_cmd;
+ struct nvme_command cmd;
+
+ if (!nvmeq->qid || cmd_rq->aborted) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&dev_list_lock, flags);
+ if (work_busy(&dev->reset_work))
+ goto out;
+ list_del_init(&dev->node);
+ dev_warn(dev->dev, "I/O %d QID %d timeout, reset
controller\n",
+ req->tag,
nvmeq->qid);
+ dev->reset_workfn = nvme_reset_failed_dev;
+ queue_work(nvme_workq, &dev->reset_work);
+ out:
+ spin_unlock_irqrestore(&dev_list_lock, flags);
+ return;
+ }
+
+ if (!dev->abort_limit)
+ return;
+
+ abort_req = blk_mq_alloc_request(dev->admin_q, WRITE,
GFP_ATOMIC,
+ false);
+ if (IS_ERR(abort_req))
+ return;
+
+ abort_cmd = blk_mq_rq_to_pdu(abort_req);
+ nvme_set_info(abort_cmd, abort_req, abort_completion);
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.abort.opcode = nvme_admin_abort_cmd;
+ cmd.abort.cid = req->tag;
+ cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
+ cmd.abort.command_id = abort_req->tag;
+
+ --dev->abort_limit;
+ cmd_rq->aborted = 1;
+
+ dev_warn(nvmeq->q_dmadev, "Aborting I/O %d QID %d\n", req
->tag,
+ nvmeq->qid);
+ nvme_submit_cmd(dev->queues[0], &cmd);
+}
+
+static void nvme_cancel_queue_ios(struct request *req, void *data,
bool reserved)
+{
+ struct nvme_queue *nvmeq = data;
+ void *ctx;
+ nvme_completion_fn fn;
+ struct nvme_cmd_info *cmd;
+ struct nvme_completion cqe;
+
+ if (!blk_mq_request_started(req))
+ return;
+
+ cmd = blk_mq_rq_to_pdu(req);
+
+ if (cmd->ctx == CMD_CTX_CANCELLED)
+ return;
+
+ if (blk_queue_dying(req->q))
+ cqe.status = cpu_to_le16((NVME_SC_ABORT_REQ |
NVME_SC_DNR) << 1);
+ else
+ cqe.status = cpu_to_le16(NVME_SC_ABORT_REQ << 1);
+
+
+ dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d QID %d\n",
+ req->tag, nvmeq->qid);
+ ctx = cancel_cmd_info(cmd, &fn);
+ fn(nvmeq, ctx, &cqe);
+}
+
+static enum blk_eh_timer_return nvme_timeout(struct request *req, bool
reserved)
+{
+ struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
+ struct nvme_queue *nvmeq = cmd->nvmeq;
+
+ dev_warn(nvmeq->q_dmadev, "Timeout I/O %d QID %d\n", req->tag,
+ nvmeq->qid);
+ spin_lock_irq(&nvmeq->q_lock);
+ nvme_abort_req(req);
+ spin_unlock_irq(&nvmeq->q_lock);
+
+ /*
+ * The aborted req will be completed on receiving the abort
req.
+ * We enable the timer again. If hit twice, it'll cause a
device reset,
+ * as the device then is in a faulty state.
+ */
+ return BLK_EH_RESET_TIMER;
+}
+
+static void nvme_free_queue(struct nvme_queue *nvmeq)
+{
+ dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
+ (void *)nvmeq->cqes, nvmeq
->cq_dma_addr);
+ if (nvmeq->sq_cmds)
+ dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq
->q_depth),
+ nvmeq->sq_cmds, nvmeq
->sq_dma_addr);
+ kfree(nvmeq);
+}
+
+static void nvme_free_queues(struct nvme_dev *dev, int lowest)
+{
+ int i;
+
+ for (i = dev->queue_count - 1; i >= lowest; i--) {
+ struct nvme_queue *nvmeq = dev->queues[i];
+ dev->queue_count--;
+ dev->queues[i] = NULL;
+ nvme_free_queue(nvmeq);
+ }
+}
+
+/**
+ * nvme_suspend_queue - put queue into suspended state
+ * @nvmeq - queue to suspend
+ */
+static int nvme_suspend_queue(struct nvme_queue *nvmeq)
+{
+ int vector;
+
+ spin_lock_irq(&nvmeq->q_lock);
+ if (nvmeq->cq_vector == -1) {
+ spin_unlock_irq(&nvmeq->q_lock);
+ return 1;
+ }
+ vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
+ nvmeq->dev->online_queues--;
+ nvmeq->cq_vector = -1;
+ spin_unlock_irq(&nvmeq->q_lock);
+
+ if (!nvmeq->qid && nvmeq->dev->admin_q)
+ blk_mq_freeze_queue_start(nvmeq->dev->admin_q);
+
+ irq_set_affinity_hint(vector, NULL);
+ free_irq(vector, nvmeq);
+
+ return 0;
+}
+
+static void nvme_clear_queue(struct nvme_queue *nvmeq)
+{
+ spin_lock_irq(&nvmeq->q_lock);
+ if (nvmeq->tags && *nvmeq->tags)
+ blk_mq_all_tag_busy_iter(*nvmeq->tags,
nvme_cancel_queue_ios, nvmeq);
+ spin_unlock_irq(&nvmeq->q_lock);
+}
+
+static void nvme_disable_queue(struct nvme_dev *dev, int qid)
+{
+ struct nvme_queue *nvmeq = dev->queues[qid];
+
+ if (!nvmeq)
+ return;
+ if (nvme_suspend_queue(nvmeq))
+ return;
+
+ /* Don't tell the adapter to delete the admin queue.
+ * Don't tell a removed adapter to delete IO queues. */
+ if (qid && readl(&dev->bar->csts) != -1) {
+ adapter_delete_sq(dev, qid);
+ adapter_delete_cq(dev, qid);
+ }
+
+ spin_lock_irq(&nvmeq->q_lock);
+ nvme_process_cq(nvmeq);
+ spin_unlock_irq(&nvmeq->q_lock);
+}
+
+static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
+ int entry_size)
+{
+ int q_depth = dev->q_depth;
+ unsigned q_size_aligned = roundup(q_depth * entry_size, dev
->page_size);
+
+ if (q_size_aligned * nr_io_queues > dev->cmb_size) {
+ u64 mem_per_q = div_u64(dev->cmb_size, nr_io_queues);
+ mem_per_q = round_down(mem_per_q, dev->page_size);
+ q_depth = div_u64(mem_per_q, entry_size);
+
+ /*
+ * Ensure the reduced q_depth is above some threshold
where it
+ * would be better to map queues in system memory with
the
+ * original depth
+ */
+ if (q_depth < 64)
+ return -ENOMEM;
+ }
+
+ return q_depth;
+}
+
+static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue
*nvmeq,
+ int qid, int depth)
+{
+ if (qid && dev->cmb && use_cmb_sqes && NVME_CMB_SQS(dev
->cmbsz)) {
+ unsigned offset = (qid - 1) *
+ roundup(SQ_SIZE(depth), dev
->page_size);
+ nvmeq->sq_dma_addr = dev->cmb_dma_addr + offset;
+ nvmeq->sq_cmds_io = dev->cmb + offset;
+ } else {
+ nvmeq->sq_cmds = dma_alloc_coherent(dev->dev,
SQ_SIZE(depth),
+ &nvmeq->sq_dma_addr,
GFP_KERNEL);
+ if (!nvmeq->sq_cmds)
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int
qid,
+ int depth)
+{
+ struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq),
GFP_KERNEL);
+ if (!nvmeq)
+ return NULL;
+
+ nvmeq->cqes = dma_zalloc_coherent(dev->dev, CQ_SIZE(depth),
+ &nvmeq->cq_dma_addr,
GFP_KERNEL);
+ if (!nvmeq->cqes)
+ goto free_nvmeq;
+
+ if (nvme_alloc_sq_cmds(dev, nvmeq, qid, depth))
+ goto free_cqdma;
+
+ nvmeq->q_dmadev = dev->dev;
+ nvmeq->dev = dev;
+ snprintf(nvmeq->irqname, sizeof(nvmeq->irqname), "nvme%dq%d",
+ dev->instance, qid);
+ spin_lock_init(&nvmeq->q_lock);
+ nvmeq->cq_head = 0;
+ nvmeq->cq_phase = 1;
+ nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
+ nvmeq->q_depth = depth;
+ nvmeq->qid = qid;
+ nvmeq->cq_vector = -1;
+ dev->queues[qid] = nvmeq;
+
+ /* make sure queue descriptor is set before queue count, for
kthread */
+ mb();
+ dev->queue_count++;
+
+ return nvmeq;
+
+ free_cqdma:
+ dma_free_coherent(dev->dev, CQ_SIZE(depth), (void *)nvmeq
->cqes,
+ nvmeq
->cq_dma_addr);
+ free_nvmeq:
+ kfree(nvmeq);
+ return NULL;
+}
+
+static int queue_request_irq(struct nvme_dev *dev, struct nvme_queue
*nvmeq,
+ const char
*name)
+{
+ if (use_threaded_interrupts)
+ return request_threaded_irq(dev->entry[nvmeq
->cq_vector].vector,
+ nvme_irq_check, nvme_irq,
IRQF_SHARED,
+ name, nvmeq);
+ return request_irq(dev->entry[nvmeq->cq_vector].vector,
nvme_irq,
+ IRQF_SHARED, name, nvmeq);
+}
+
+static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
+{
+ struct nvme_dev *dev = nvmeq->dev;
+
+ spin_lock_irq(&nvmeq->q_lock);
+ nvmeq->sq_tail = 0;
+ nvmeq->cq_head = 0;
+ nvmeq->cq_phase = 1;
+ nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
+ memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
+ dev->online_queues++;
+ spin_unlock_irq(&nvmeq->q_lock);
+}
+
+static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
+{
+ struct nvme_dev *dev = nvmeq->dev;
+ int result;
+
+ nvmeq->cq_vector = qid - 1;
+ result = adapter_alloc_cq(dev, qid, nvmeq);
+ if (result < 0)
+ return result;
+
+ result = adapter_alloc_sq(dev, qid, nvmeq);
+ if (result < 0)
+ goto release_cq;
+
+ result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
+ if (result < 0)
+ goto release_sq;
+
+ nvme_init_queue(nvmeq, qid);
+ return result;
+
+ release_sq:
+ adapter_delete_sq(dev, qid);
+ release_cq:
+ adapter_delete_cq(dev, qid);
+ return result;
+}
+
+static int nvme_wait_ready(struct nvme_dev *dev, u64 cap, bool
enabled)
+{
+ unsigned long timeout;
+ u32 bit = enabled ? NVME_CSTS_RDY : 0;
+
+ timeout = ((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies;
+
+ while ((readl(&dev->bar->csts) & NVME_CSTS_RDY) != bit) {
+ msleep(100);
+ if (fatal_signal_pending(current))
+ return -EINTR;
+ if (time_after(jiffies, timeout)) {
+ dev_err(dev->dev,
+ "Device not ready; aborting %s\n",
enabled ?
+ "initialisation" :
"reset");
+ return -ENODEV;
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * If the device has been passed off to us in an enabled state, just
clear
+ * the enabled bit. The spec says we should set the 'shutdown
notification
+ * bits', but doing so may cause the device to complete commands to
the
+ * admin queue ... and we don't know what memory that might be
pointing at!
+ */
+static int nvme_disable_ctrl(struct nvme_dev *dev, u64 cap)
+{
+ dev->ctrl_config &= ~NVME_CC_SHN_MASK;
+ dev->ctrl_config &= ~NVME_CC_ENABLE;
+ writel(dev->ctrl_config, &dev->bar->cc);
+
+ return nvme_wait_ready(dev, cap, false);
+}
+
+static int nvme_enable_ctrl(struct nvme_dev *dev, u64 cap)
+{
+ dev->ctrl_config &= ~NVME_CC_SHN_MASK;
+ dev->ctrl_config |= NVME_CC_ENABLE;
+ writel(dev->ctrl_config, &dev->bar->cc);
+
+ return nvme_wait_ready(dev, cap, true);
+}
+
+static int nvme_shutdown_ctrl(struct nvme_dev *dev)
+{
+ unsigned long timeout;
+
+ dev->ctrl_config &= ~NVME_CC_SHN_MASK;
+ dev->ctrl_config |= NVME_CC_SHN_NORMAL;
+
+ writel(dev->ctrl_config, &dev->bar->cc);
+
+ timeout = SHUTDOWN_TIMEOUT + jiffies;
+ while ((readl(&dev->bar->csts) & NVME_CSTS_SHST_MASK) !=
+ NVME_CSTS_SHST
_CMPLT) {
+ msleep(100);
+ if (fatal_signal_pending(current))
+ return -EINTR;
+ if (time_after(jiffies, timeout)) {
+ dev_err(dev->dev,
+ "Device shutdown incomplete; abort
shutdown\n");
+ return -ENODEV;
+ }
+ }
+
+ return 0;
+}
+
+static struct blk_mq_ops nvme_mq_admin_ops = {
+ .queue_rq = nvme_queue_rq,
+ .map_queue = blk_mq_map_queue,
+ .init_hctx = nvme_admin_init_hctx,
+ .exit_hctx = nvme_admin_exit_hctx,
+ .init_request = nvme_admin_init_request,
+ .timeout = nvme_timeout,
+};
+
+static struct blk_mq_ops nvme_mq_ops = {
+ .queue_rq = nvme_queue_rq,
+ .map_queue = blk_mq_map_queue,
+ .init_hctx = nvme_init_hctx,
+ .init_request = nvme_init_request,
+ .timeout = nvme_timeout,
+};
+
+static void nvme_dev_remove_admin(struct nvme_dev *dev)
+{
+ if (dev->admin_q && !blk_queue_dying(dev->admin_q)) {
+ blk_cleanup_queue(dev->admin_q);
+ blk_mq_free_tag_set(&dev->admin_tagset);
+ }
+}
+
+static int nvme_alloc_admin_tags(struct nvme_dev *dev)
+{
+ if (!dev->admin_q) {
+ dev->admin_tagset.ops = &nvme_mq_admin_ops;
+ dev->admin_tagset.nr_hw_queues = 1;
+ dev->admin_tagset.queue_depth = NVME_AQ_DEPTH - 1;
+ dev->admin_tagset.reserved_tags = 1;
+ dev->admin_tagset.timeout = ADMIN_TIMEOUT;
+ dev->admin_tagset.numa_node = dev_to_node(dev->dev);
+ dev->admin_tagset.cmd_size = nvme_cmd_size(dev);
+ dev->admin_tagset.driver_data = dev;
+
+ if (blk_mq_alloc_tag_set(&dev->admin_tagset))
+ return -ENOMEM;
+
+ dev->admin_q = blk_mq_init_queue(&dev->admin_tagset);
+ if (IS_ERR(dev->admin_q)) {
+ blk_mq_free_tag_set(&dev->admin_tagset);
+ return -ENOMEM;
+ }
+ if (!blk_get_queue(dev->admin_q)) {
+ nvme_dev_remove_admin(dev);
+ dev->admin_q = NULL;
+ return -ENODEV;
+ }
+ } else
+ blk_mq_unfreeze_queue(dev->admin_q);
+
+ return 0;
+}
+
+static int nvme_configure_admin_queue(struct nvme_dev *dev)
+{
+ int result;
+ u32 aqa;
+ u64 cap = readq(&dev->bar->cap);
+ struct nvme_queue *nvmeq;
+ unsigned page_shift = PAGE_SHIFT;
+ unsigned dev_page_min = NVME_CAP_MPSMIN(cap) + 12;
+ unsigned dev_page_max = NVME_CAP_MPSMAX(cap) + 12;
+
+ if (page_shift < dev_page_min) {
+ dev_err(dev->dev,
+ "Minimum device page size (%u) too
large for "
+ "host (%u)\n", 1 << dev_page_min,
+ 1 << page_shift);
+ return -ENODEV;
+ }
+ if (page_shift > dev_page_max) {
+ dev_info(dev->dev,
+ "Device maximum page size (%u) smaller
than "
+ "host (%u); enabling work-around\n",
+ 1 << dev_page_max, 1 << page_shift);
+ page_shift = dev_page_max;
+ }
+
+ dev->subsystem = readl(&dev->bar->vs) >= NVME_VS(1, 1) ?
+ NVME_CAP_NSSRC(cap) :
0;
+
+ if (dev->subsystem && (readl(&dev->bar->csts) &
NVME_CSTS_NSSRO))
+ writel(NVME_CSTS_NSSRO, &dev->bar->csts);
+
+ result = nvme_disable_ctrl(dev, cap);
+ if (result < 0)
+ return result;
+
+ nvmeq = dev->queues[0];
+ if (!nvmeq) {
+ nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH);
+ if (!nvmeq)
+ return -ENOMEM;
+ }
+
+ aqa = nvmeq->q_depth - 1;
+ aqa |= aqa << 16;
+
+ dev->page_size = 1 << page_shift;
+
+ dev->ctrl_config = NVME_CC_CSS_NVM;
+ dev->ctrl_config |= (page_shift - 12) << NVME_CC_MPS_SHIFT;
+ dev->ctrl_config |= NVME_CC_ARB_RR | NVME_CC_SHN_NONE;
+ dev->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES;
+
+ writel(aqa, &dev->bar->aqa);
+ writeq(nvmeq->sq_dma_addr, &dev->bar->asq);
+ writeq(nvmeq->cq_dma_addr, &dev->bar->acq);
+
+ result = nvme_enable_ctrl(dev, cap);
+ if (result)
+ goto free_nvmeq;
+
+ nvmeq->cq_vector = 0;
+ result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
+ if (result) {
+ nvmeq->cq_vector = -1;
+ goto free_nvmeq;
+ }
+
+ return result;
+
+ free_nvmeq:
+ nvme_free_queues(dev, 0);
+ return result;
+}
+
+static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io
__user *uio)
+{
+ struct nvme_dev *dev = ns->dev;
+ struct nvme_user_io io;
+ struct nvme_command c;
+ unsigned length, meta_len;
+ int status, write;
+ dma_addr_t meta_dma = 0;
+ void *meta = NULL;
+ 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 *)(unsigned long)io.metadata;
+ write = io.opcode & 1;
+
+ if (ns->ext) {
+ length += meta_len;
+ meta_len = 0;
+ }
+ if (meta_len) {
+ if (((io.metadata & 3) || !io.metadata) && !ns->ext)
+ return -EINVAL;
+
+ meta = dma_alloc_coherent(dev->dev, meta_len,
+ &meta_dma,
GFP_KERNEL);
+
+ if (!meta) {
+ status = -ENOMEM;
+ goto unmap;
+ }
+ if (write) {
+ if (copy_from_user(meta, metadata, meta_len))
{
+ status = -EFAULT;
+ goto unmap;
+ }
+ }
+ }
+
+ 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);
+ c.rw.metadata = cpu_to_le64(meta_dma);
+
+ status = __nvme_submit_sync_cmd(ns->queue, &c, NULL,
+ (void __user *)io.addr, length, NULL, 0);
+ unmap:
+ if (meta) {
+ if (status == NVME_SC_SUCCESS && !write) {
+ if (copy_to_user(metadata, meta, meta_len))
+ status = -EFAULT;
+ }
+ dma_free_coherent(dev->dev, meta_len, meta, meta_dma);
+ }
+ return status;
+}
+
+static int nvme_user_cmd(struct nvme_dev *dev, 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_sync_cmd(ns ? ns->queue : dev->admin_q,
&c,
+ NULL, (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_subsys_reset(struct nvme_dev *dev)
+{
+ if (!dev->subsystem)
+ return -ENOTTY;
+
+ writel(0x4E564D65, &dev->bar->nssr); /* "NVMe" */
+ return 0;
+}
+
+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->dev, NULL, (void __user
*)arg);
+ case NVME_IOCTL_IO_CMD:
+ return nvme_user_cmd(ns->dev, 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)
+{
+ int ret = 0;
+ struct nvme_ns *ns;
+
+ spin_lock(&dev_list_lock);
+ ns = bdev->bd_disk->private_data;
+ if (!ns)
+ ret = -ENXIO;
+ else if (!kref_get_unless_zero(&ns->dev->kref))
+ ret = -ENXIO;
+ spin_unlock(&dev_list_lock);
+
+ return ret;
+}
+
+static void nvme_free_dev(struct kref *kref);
+
+static void nvme_release(struct gendisk *disk, fmode_t mode)
+{
+ struct nvme_ns *ns = disk->private_data;
+ struct nvme_dev *dev = ns->dev;
+
+ kref_put(&dev->kref, nvme_free_dev);
+}
+
+static int nvme_getgeo(struct block_device *bd, struct hd_geometry
*geo)
+{
+ /* some standard values */
+ geo->heads = 1 << 6;
+ geo->sectors = 1 << 5;
+ geo->cylinders = get_capacity(bd->bd_disk) >> 11;
+ return 0;
+}
+
+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);
+}
+
+static int nvme_revalidate_disk(struct gendisk *disk)
+{
+ struct nvme_ns *ns = disk->private_data;
+ struct nvme_dev *dev = ns->dev;
+ struct nvme_id_ns *id;
+ u8 lbaf, pi_type;
+ u16 old_ms;
+ unsigned short bs;
+
+ if (nvme_identify_ns(dev, ns->ns_id, &id)) {
+ dev_warn(dev->dev, "%s: Identify failure nvme%dn%d\n",
__func__,
+ dev->instance, ns
->ns_id);
+ return -ENODEV;
+ }
+ if (id->ncap == 0) {
+ kfree(id);
+ return -ENODEV;
+ }
+
+ 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;
+
+ 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 && !blk_get_integrity(disk) && (disk->flags &
GENHD_FL_UP) &&
+ !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 (dev->oncs & NVME_CTRL_ONCS_DSM)
+ nvme_config_discard(ns);
+
+ kfree(id);
+ return 0;
+}
+
+static 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,
+};
+
+static int nvme_kthread(void *data)
+{
+ struct nvme_dev *dev, *next;
+
+ while (!kthread_should_stop()) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ spin_lock(&dev_list_lock);
+ list_for_each_entry_safe(dev, next, &dev_list, node) {
+ int i;
+ u32 csts = readl(&dev->bar->csts);
+
+ if ((dev->subsystem && (csts &
NVME_CSTS_NSSRO)) ||
+ csts &
NVME_CSTS_CFS) {
+ if (work_busy(&dev->reset_work))
+ continue;
+ list_del_init(&dev->node);
+ dev_warn(dev->dev,
+ "Failed status: %x, reset
controller\n",
+ readl(&dev->bar->csts));
+ dev->reset_workfn =
nvme_reset_failed_dev;
+ queue_work(nvme_workq, &dev
->reset_work);
+ continue;
+ }
+ for (i = 0; i < dev->queue_count; i++) {
+ struct nvme_queue *nvmeq = dev
->queues[i];
+ if (!nvmeq)
+ continue;
+ spin_lock_irq(&nvmeq->q_lock);
+ nvme_process_cq(nvmeq);
+
+ while ((i == 0) && (dev->event_limit >
0)) {
+ if
(nvme_submit_async_admin_req(dev))
+ break;
+ dev->event_limit--;
+ }
+ spin_unlock_irq(&nvmeq->q_lock);
+ }
+ }
+ spin_unlock(&dev_list_lock);
+ schedule_timeout(round_jiffies_relative(HZ));
+ }
+ return 0;
+}
+
+static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
+{
+ struct nvme_ns *ns;
+ struct gendisk *disk;
+ int node = dev_to_node(dev->dev);
+
+ ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
+ if (!ns)
+ return;
+
+ ns->queue = blk_mq_init_queue(&dev->tagset);
+ if (IS_ERR(ns->queue))
+ goto out_free_ns;
+ queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, ns->queue);
+ queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue);
+ ns->dev = dev;
+ ns->queue->queuedata = ns;
+
+ disk = alloc_disk_node(0, node);
+ if (!disk)
+ goto out_free_queue;
+
+ ns->ns_id = nsid;
+ ns->disk = disk;
+ ns->lba_shift = 9; /* set to a default value for 512 until
disk is validated */
+ list_add_tail(&ns->list, &dev->namespaces);
+
+ blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
+ if (dev->max_hw_sectors) {
+ blk_queue_max_hw_sectors(ns->queue, dev
->max_hw_sectors);
+ blk_queue_max_segments(ns->queue,
+ ((dev->max_hw_sectors << 9) / dev->page_size)
+ 1);
+ }
+ if (dev->stripe_size)
+ blk_queue_chunk_sectors(ns->queue, dev->stripe_size >>
9);
+ if (dev->vwc & NVME_CTRL_VWC_PRESENT)
+ blk_queue_flush(ns->queue, REQ_FLUSH | REQ_FUA);
+ blk_queue_virt_boundary(ns->queue, dev->page_size - 1);
+
+ disk->major = nvme_major;
+ disk->first_minor = 0;
+ disk->fops = &nvme_fops;
+ disk->private_data = ns;
+ disk->queue = ns->queue;
+ disk->driverfs_dev = dev->device;
+ disk->flags = GENHD_FL_EXT_DEVT;
+ sprintf(disk->disk_name, "nvme%dn%d", dev->instance, nsid);
+
+ /*
+ * Initialize capacity to 0 until we establish the namespace
format and
+ * setup integrity extentions if necessary. The
revalidate_disk after
+ * add_disk allows the driver to register with integrity if
the format
+ * requires it.
+ */
+ set_capacity(disk, 0);
+ if (nvme_revalidate_disk(ns->disk))
+ goto out_free_disk;
+
+ add_disk(ns->disk);
+ if (ns->ms) {
+ struct block_device *bd = bdget_disk(ns->disk, 0);
+ if (!bd)
+ return;
+ if (blkdev_get(bd, FMODE_READ, NULL)) {
+ bdput(bd);
+ return;
+ }
+ blkdev_reread_part(bd);
+ blkdev_put(bd, FMODE_READ);
+ }
+ return;
+ out_free_disk:
+ kfree(disk);
+ list_del(&ns->list);
+ out_free_queue:
+ blk_cleanup_queue(ns->queue);
+ out_free_ns:
+ kfree(ns);
+}
+
+static void nvme_create_io_queues(struct nvme_dev *dev)
+{
+ unsigned i;
+
+ for (i = dev->queue_count; i <= dev->max_qid; i++)
+ if (!nvme_alloc_queue(dev, i, dev->q_depth))
+ break;
+
+ for (i = dev->online_queues; i <= dev->queue_count - 1; i++)
+ if (nvme_create_queue(dev->queues[i], i))
+ break;
+}
+
+static int set_queue_count(struct nvme_dev *dev, int count)
+{
+ int status;
+ u32 result;
+ u32 q_count = (count - 1) | ((count - 1) << 16);
+
+ status = nvme_set_features(dev, NVME_FEAT_NUM_QUEUES, q_count,
0,
+ &resul
t);
+ if (status < 0)
+ return status;
+ if (status > 0) {
+ dev_err(dev->dev, "Could not set queue count (%d)\n",
status);
+ return 0;
+ }
+ return min(result & 0xffff, result >> 16) + 1;
+}
+
+static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
+{
+ u64 szu, size, offset;
+ u32 cmbloc;
+ resource_size_t bar_size;
+ struct pci_dev *pdev = to_pci_dev(dev->dev);
+ void __iomem *cmb;
+ dma_addr_t dma_addr;
+
+ if (!use_cmb_sqes)
+ return NULL;
+
+ dev->cmbsz = readl(&dev->bar->cmbsz);
+ if (!(NVME_CMB_SZ(dev->cmbsz)))
+ return NULL;
+
+ cmbloc = readl(&dev->bar->cmbloc);
+
+ szu = (u64)1 << (12 + 4 * NVME_CMB_SZU(dev->cmbsz));
+ size = szu * NVME_CMB_SZ(dev->cmbsz);
+ offset = szu * NVME_CMB_OFST(cmbloc);
+ bar_size = pci_resource_len(pdev, NVME_CMB_BIR(cmbloc));
+
+ if (offset > bar_size)
+ return NULL;
+
+ /*
+ * Controllers may support a CMB size larger than their BAR,
+ * for example, due to being behind a bridge. Reduce the CMB
to
+ * the reported size of the BAR
+ */
+ if (size > bar_size - offset)
+ size = bar_size - offset;
+
+ dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(cmbloc)) +
offset;
+ cmb = ioremap_wc(dma_addr, size);
+ if (!cmb)
+ return NULL;
+
+ dev->cmb_dma_addr = dma_addr;
+ dev->cmb_size = size;
+ return cmb;
+}
+
+static inline void nvme_release_cmb(struct nvme_dev *dev)
+{
+ if (dev->cmb) {
+ iounmap(dev->cmb);
+ dev->cmb = NULL;
+ }
+}
+
+static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
+{
+ return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride);
+}
+
+static int nvme_setup_io_queues(struct nvme_dev *dev)
+{
+ struct nvme_queue *adminq = dev->queues[0];
+ struct pci_dev *pdev = to_pci_dev(dev->dev);
+ int result, i, vecs, nr_io_queues, size;
+
+ nr_io_queues = num_possible_cpus();
+ result = set_queue_count(dev, nr_io_queues);
+ if (result <= 0)
+ return result;
+ if (result < nr_io_queues)
+ nr_io_queues = result;
+
+ if (dev->cmb && NVME_CMB_SQS(dev->cmbsz)) {
+ result = nvme_cmb_qdepth(dev, nr_io_queues,
+ sizeof(struct nvme_command));
+ if (result > 0)
+ dev->q_depth = result;
+ else
+ nvme_release_cmb(dev);
+ }
+
+ size = db_bar_size(dev, nr_io_queues);
+ if (size > 8192) {
+ iounmap(dev->bar);
+ do {
+ dev->bar = ioremap(pci_resource_start(pdev,
0), size);
+ if (dev->bar)
+ break;
+ if (!--nr_io_queues)
+ return -ENOMEM;
+ size = db_bar_size(dev, nr_io_queues);
+ } while (1);
+ dev->dbs = ((void __iomem *)dev->bar) + 4096;
+ adminq->q_db = dev->dbs;
+ }
+
+ /* Deregister the admin queue's interrupt */
+ free_irq(dev->entry[0].vector, adminq);
+
+ /*
+ * If we enable msix early due to not intx, disable it again
before
+ * setting up the full range we need.
+ */
+ if (!pdev->irq)
+ pci_disable_msix(pdev);
+
+ for (i = 0; i < nr_io_queues; i++)
+ dev->entry[i].entry = i;
+ vecs = pci_enable_msix_range(pdev, dev->entry, 1,
nr_io_queues);
+ if (vecs < 0) {
+ vecs = pci_enable_msi_range(pdev, 1, min(nr_io_queues,
32));
+ if (vecs < 0) {
+ vecs = 1;
+ } else {
+ for (i = 0; i < vecs; i++)
+ dev->entry[i].vector = i + pdev->irq;
+ }
+ }
+
+ /*
+ * Should investigate if there's a performance win from
allocating
+ * more queues than interrupt vectors; it might allow the
submission
+ * path to scale better, even if the receive path is limited
by the
+ * number of interrupts.
+ */
+ nr_io_queues = vecs;
+ dev->max_qid = nr_io_queues;
+
+ result = queue_request_irq(dev, adminq, adminq->irqname);
+ if (result) {
+ adminq->cq_vector = -1;
+ goto free_queues;
+ }
+
+ /* Free previously allocated queues that are no longer usable
*/
+ nvme_free_queues(dev, nr_io_queues + 1);
+ nvme_create_io_queues(dev);
+
+ return 0;
+
+ free_queues:
+ nvme_free_queues(dev, 1);
+ return result;
+}
+
+static void nvme_free_namespace(struct nvme_ns *ns)
+{
+ list_del(&ns->list);
+
+ spin_lock(&dev_list_lock);
+ ns->disk->private_data = NULL;
+ spin_unlock(&dev_list_lock);
+
+ put_disk(ns->disk);
+ kfree(ns);
+}
+
+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);
+ struct nvme_ns *nsb = container_of(b, struct nvme_ns, list);
+
+ return nsa->ns_id - nsb->ns_id;
+}
+
+static struct nvme_ns *nvme_find_ns(struct nvme_dev *dev, unsigned
nsid)
+{
+ struct nvme_ns *ns;
+
+ list_for_each_entry(ns, &dev->namespaces, list) {
+ if (ns->ns_id == nsid)
+ return ns;
+ if (ns->ns_id > nsid)
+ break;
+ }
+ return NULL;
+}
+
+static inline bool nvme_io_incapable(struct nvme_dev *dev)
+{
+ return (!dev->bar || readl(&dev->bar->csts) & NVME_CSTS_CFS ||
+ dev
->online_queues < 2);
+}
+
+static void nvme_ns_remove(struct nvme_ns *ns)
+{
+ bool kill = nvme_io_incapable(ns->dev) && !blk_queue_dying(ns
->queue);
+
+ if (kill)
+ blk_set_queue_dying(ns->queue);
+ if (ns->disk->flags & GENHD_FL_UP) {
+ if (blk_get_integrity(ns->disk))
+ blk_integrity_unregister(ns->disk);
+ del_gendisk(ns->disk);
+ }
+ if (kill || !blk_queue_dying(ns->queue)) {
+ blk_mq_abort_requeue_list(ns->queue);
+ blk_cleanup_queue(ns->queue);
+ }
+}
+
+static void nvme_scan_namespaces(struct nvme_dev *dev, unsigned nn)
+{
+ struct nvme_ns *ns, *next;
+ unsigned i;
+
+ for (i = 1; i <= nn; i++) {
+ ns = nvme_find_ns(dev, i);
+ if (ns) {
+ if (revalidate_disk(ns->disk)) {
+ nvme_ns_remove(ns);
+ nvme_free_namespace(ns);
+ }
+ } else
+ nvme_alloc_ns(dev, i);
+ }
+ list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
+ if (ns->ns_id > nn) {
+ nvme_ns_remove(ns);
+ nvme_free_namespace(ns);
+ }
+ }
+ list_sort(NULL, &dev->namespaces, ns_cmp);
+}
+
+static void nvme_dev_scan(struct work_struct *work)
+{
+ struct nvme_dev *dev = container_of(work, struct nvme_dev,
scan_work);
+ struct nvme_id_ctrl *ctrl;
+
+ if (!dev->tagset.tags)
+ return;
+ if (nvme_identify_ctrl(dev, &ctrl))
+ return;
+ nvme_scan_namespaces(dev, le32_to_cpup(&ctrl->nn));
+ kfree(ctrl);
+}
+
+/*
+ * Return: error value if an error occurred setting up the queues or
calling
+ * Identify Device. 0 if these succeeded, even if adding some of the
+ * namespaces failed. At the moment, these failures are silent. TBD
which
+ * failures should be reported.
+ */
+static int nvme_dev_add(struct nvme_dev *dev)
+{
+ struct pci_dev *pdev = to_pci_dev(dev->dev);
+ int res;
+ struct nvme_id_ctrl *ctrl;
+ int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12;
+
+ res = nvme_identify_ctrl(dev, &ctrl);
+ if (res) {
+ dev_err(dev->dev, "Identify Controller failed (%d)\n",
res);
+ return -EIO;
+ }
+
+ dev->oncs = le16_to_cpup(&ctrl->oncs);
+ dev->abort_limit = ctrl->acl + 1;
+ dev->vwc = ctrl->vwc;
+ memcpy(dev->serial, ctrl->sn, sizeof(ctrl->sn));
+ memcpy(dev->model, ctrl->mn, sizeof(ctrl->mn));
+ memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr));
+ if (ctrl->mdts)
+ dev->max_hw_sectors = 1 << (ctrl->mdts + shift - 9);
+ if ((pdev->vendor == PCI_VENDOR_ID_INTEL) &&
+ (pdev->device == 0x0953) && ctrl->vs[3]) {
+ unsigned int max_hw_sectors;
+
+ dev->stripe_size = 1 << (ctrl->vs[3] + shift);
+ max_hw_sectors = dev->stripe_size >> (shift - 9);
+ if (dev->max_hw_sectors) {
+ dev->max_hw_sectors = min(max_hw_sectors,
+ dev
->max_hw_sectors);
+ } else
+ dev->max_hw_sectors = max_hw_sectors;
+ }
+ kfree(ctrl);
+
+ if (!dev->tagset.tags) {
+ dev->tagset.ops = &nvme_mq_ops;
+ dev->tagset.nr_hw_queues = dev->online_queues - 1;
+ dev->tagset.timeout = NVME_IO_TIMEOUT;
+ dev->tagset.numa_node = dev_to_node(dev->dev);
+ dev->tagset.queue_depth =
+ min_t(int, dev->q_depth,
BLK_MQ_MAX_DEPTH) - 1;
+ dev->tagset.cmd_size = nvme_cmd_size(dev);
+ dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
+ dev->tagset.driver_data = dev;
+
+ if (blk_mq_alloc_tag_set(&dev->tagset))
+ return 0;
+ }
+ schedule_work(&dev->scan_work);
+ return 0;
+}
+
+static int nvme_dev_map(struct nvme_dev *dev)
+{
+ u64 cap;
+ int bars, result = -ENOMEM;
+ struct pci_dev *pdev = to_pci_dev(dev->dev);
+
+ if (pci_enable_device_mem(pdev))
+ return result;
+
+ dev->entry[0].vector = pdev->irq;
+ pci_set_master(pdev);
+ bars = pci_select_bars(pdev, IORESOURCE_MEM);
+ if (!bars)
+ goto disable_pci;
+
+ if (pci_request_selected_regions(pdev, bars, "nvme"))
+ goto disable_pci;
+
+ if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)) &&
+ dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(32)))
+ goto disable;
+
+ dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
+ if (!dev->bar)
+ goto disable;
+
+ if (readl(&dev->bar->csts) == -1) {
+ result = -ENODEV;
+ goto unmap;
+ }
+
+ /*
+ * Some devices don't advertse INTx interrupts, pre-enable a
single
+ * MSIX vec for setup. We'll adjust this later.
+ */
+ if (!pdev->irq) {
+ result = pci_enable_msix(pdev, dev->entry, 1);
+ if (result < 0)
+ goto unmap;
+ }
+
+ cap = readq(&dev->bar->cap);
+ dev->q_depth = min_t(int, NVME_CAP_MQES(cap) + 1,
NVME_Q_DEPTH);
+ dev->db_stride = 1 << NVME_CAP_STRIDE(cap);
+ dev->dbs = ((void __iomem *)dev->bar) + 4096;
+ if (readl(&dev->bar->vs) >= NVME_VS(1, 2))
+ dev->cmb = nvme_map_cmb(dev);
+
+ return 0;
+
+ unmap:
+ iounmap(dev->bar);
+ dev->bar = NULL;
+ disable:
+ pci_release_regions(pdev);
+ disable_pci:
+ pci_disable_device(pdev);
+ return result;
+}
+
+static void nvme_dev_unmap(struct nvme_dev *dev)
+{
+ struct pci_dev *pdev = to_pci_dev(dev->dev);
+
+ if (pdev->msi_enabled)
+ pci_disable_msi(pdev);
+ else if (pdev->msix_enabled)
+ pci_disable_msix(pdev);
+
+ if (dev->bar) {
+ iounmap(dev->bar);
+ dev->bar = NULL;
+ pci_release_regions(pdev);
+ }
+
+ if (pci_is_enabled(pdev))
+ pci_disable_device(pdev);
+}
+
+struct nvme_delq_ctx {
+ struct task_struct *waiter;
+ struct kthread_worker *worker;
+ atomic_t refcount;
+};
+
+static void nvme_wait_dq(struct nvme_delq_ctx *dq, struct nvme_dev
*dev)
+{
+ dq->waiter = current;
+ mb();
+
+ for (;;) {
+ set_current_state(TASK_KILLABLE);
+ if (!atomic_read(&dq->refcount))
+ break;
+ if (!schedule_timeout(ADMIN_TIMEOUT) ||
+ fatal_signal_pending(current))
{
+ /*
+ * Disable the controller first since we can't
trust it
+ * at this point, but leave the admin queue
enabled
+ * until all queue deletion requests are
flushed.
+ * FIXME: This may take a while if there are
more h/w
+ * queues than admin tags.
+ */
+ set_current_state(TASK_RUNNING);
+ nvme_disable_ctrl(dev, readq(&dev->bar->cap));
+ nvme_clear_queue(dev->queues[0]);
+ flush_kthread_worker(dq->worker);
+ nvme_disable_queue(dev, 0);
+ return;
+ }
+ }
+ set_current_state(TASK_RUNNING);
+}
+
+static void nvme_put_dq(struct nvme_delq_ctx *dq)
+{
+ atomic_dec(&dq->refcount);
+ if (dq->waiter)
+ wake_up_process(dq->waiter);
+}
+
+static struct nvme_delq_ctx *nvme_get_dq(struct nvme_delq_ctx *dq)
+{
+ atomic_inc(&dq->refcount);
+ return dq;
+}
+
+static void nvme_del_queue_end(struct nvme_queue *nvmeq)
+{
+ struct nvme_delq_ctx *dq = nvmeq->cmdinfo.ctx;
+ nvme_put_dq(dq);
+}
+
+static int adapter_async_del_queue(struct nvme_queue *nvmeq, u8
opcode,
+ kthread_work_func_t
fn)
+{
+ struct nvme_command c;
+
+ memset(&c, 0, sizeof(c));
+ c.delete_queue.opcode = opcode;
+ c.delete_queue.qid = cpu_to_le16(nvmeq->qid);
+
+ init_kthread_work(&nvmeq->cmdinfo.work, fn);
+ return nvme_submit_admin_async_cmd(nvmeq->dev, &c, &nvmeq
->cmdinfo,
+ ADMIN_
TIMEOUT);
+}
+
+static void nvme_del_cq_work_handler(struct kthread_work *work)
+{
+ struct nvme_queue *nvmeq = container_of(work, struct
nvme_queue,
+ cmdinfo.work);
+ nvme_del_queue_end(nvmeq);
+}
+
+static int nvme_delete_cq(struct nvme_queue *nvmeq)
+{
+ return adapter_async_del_queue(nvmeq, nvme_admin_delete_cq,
+ nvme_del_cq_work_handl
er);
+}
+
+static void nvme_del_sq_work_handler(struct kthread_work *work)
+{
+ struct nvme_queue *nvmeq = container_of(work, struct
nvme_queue,
+ cmdinfo.work);
+ int status = nvmeq->cmdinfo.status;
+
+ if (!status)
+ status = nvme_delete_cq(nvmeq);
+ if (status)
+ nvme_del_queue_end(nvmeq);
+}
+
+static int nvme_delete_sq(struct nvme_queue *nvmeq)
+{
+ return adapter_async_del_queue(nvmeq, nvme_admin_delete_sq,
+ nvme_del_sq_work_handl
er);
+}
+
+static void nvme_del_queue_start(struct kthread_work *work)
+{
+ struct nvme_queue *nvmeq = container_of(work, struct
nvme_queue,
+ cmdinfo.work);
+ if (nvme_delete_sq(nvmeq))
+ nvme_del_queue_end(nvmeq);
+}
+
+static void nvme_disable_io_queues(struct nvme_dev *dev)
+{
+ int i;
+ DEFINE_KTHREAD_WORKER_ONSTACK(worker);
+ struct nvme_delq_ctx dq;
+ struct task_struct *kworker_task =
kthread_run(kthread_worker_fn,
+ &worker, "nvme%d", dev
->instance);
+
+ if (IS_ERR(kworker_task)) {
+ dev_err(dev->dev,
+ "Failed to create queue del task\n");
+ for (i = dev->queue_count - 1; i > 0; i--)
+ nvme_disable_queue(dev, i);
+ return;
+ }
+
+ dq.waiter = NULL;
+ atomic_set(&dq.refcount, 0);
+ dq.worker = &worker;
+ for (i = dev->queue_count - 1; i > 0; i--) {
+ struct nvme_queue *nvmeq = dev->queues[i];
+
+ if (nvme_suspend_queue(nvmeq))
+ continue;
+ nvmeq->cmdinfo.ctx = nvme_get_dq(&dq);
+ nvmeq->cmdinfo.worker = dq.worker;
+ init_kthread_work(&nvmeq->cmdinfo.work,
nvme_del_queue_start);
+ queue_kthread_work(dq.worker, &nvmeq->cmdinfo.work);
+ }
+ nvme_wait_dq(&dq, dev);
+ kthread_stop(kworker_task);
+}
+
+/*
+* Remove the node from the device list and check
+* for whether or not we need to stop the nvme_thread.
+*/
+static void nvme_dev_list_remove(struct nvme_dev *dev)
+{
+ struct task_struct *tmp = NULL;
+
+ spin_lock(&dev_list_lock);
+ list_del_init(&dev->node);
+ if (list_empty(&dev_list) && !IS_ERR_OR_NULL(nvme_thread)) {
+ tmp = nvme_thread;
+ nvme_thread = NULL;
+ }
+ spin_unlock(&dev_list_lock);
+
+ if (tmp)
+ kthread_stop(tmp);
+}
+
+static void nvme_freeze_queues(struct nvme_dev *dev)
+{
+ struct nvme_ns *ns;
+
+ list_for_each_entry(ns, &dev->namespaces, list) {
+ blk_mq_freeze_queue_start(ns->queue);
+
+ spin_lock_irq(ns->queue->queue_lock);
+ queue_flag_set(QUEUE_FLAG_STOPPED, ns->queue);
+ spin_unlock_irq(ns->queue->queue_lock);
+
+ blk_mq_cancel_requeue_work(ns->queue);
+ blk_mq_stop_hw_queues(ns->queue);
+ }
+}
+
+static void nvme_unfreeze_queues(struct nvme_dev *dev)
+{
+ struct nvme_ns *ns;
+
+ list_for_each_entry(ns, &dev->namespaces, list) {
+ queue_flag_clear_unlocked(QUEUE_FLAG_STOPPED, ns
->queue);
+ blk_mq_unfreeze_queue(ns->queue);
+ blk_mq_start_stopped_hw_queues(ns->queue, true);
+ blk_mq_kick_requeue_list(ns->queue);
+ }
+}
+
+static void nvme_dev_shutdown(struct nvme_dev *dev)
+{
+ int i;
+ u32 csts = -1;
+
+ nvme_dev_list_remove(dev);
+
+ if (dev->bar) {
+ nvme_freeze_queues(dev);
+ csts = readl(&dev->bar->csts);
+ }
+ if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) {
+ for (i = dev->queue_count - 1; i >= 0; i--) {
+ struct nvme_queue *nvmeq = dev->queues[i];
+ nvme_suspend_queue(nvmeq);
+ }
+ } else {
+ nvme_disable_io_queues(dev);
+ nvme_shutdown_ctrl(dev);
+ nvme_disable_queue(dev, 0);
+ }
+ nvme_dev_unmap(dev);
+
+ for (i = dev->queue_count - 1; i >= 0; i--)
+ nvme_clear_queue(dev->queues[i]);
+}
+
+static void nvme_dev_remove(struct nvme_dev *dev)
+{
+ struct nvme_ns *ns;
+
+ list_for_each_entry(ns, &dev->namespaces, list)
+ nvme_ns_remove(ns);
+}
+
+static int nvme_setup_prp_pools(struct nvme_dev *dev)
+{
+ dev->prp_page_pool = dma_pool_create("prp list page", dev
->dev,
+ PAGE_SIZE, PAGE_SIZE,
0);
+ if (!dev->prp_page_pool)
+ return -ENOMEM;
+
+ /* Optimisation for I/Os between 4k and 128k */
+ dev->prp_small_pool = dma_pool_create("prp list 256", dev
->dev,
+ 256, 256, 0);
+ if (!dev->prp_small_pool) {
+ dma_pool_destroy(dev->prp_page_pool);
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+static void nvme_release_prp_pools(struct nvme_dev *dev)
+{
+ dma_pool_destroy(dev->prp_page_pool);
+ 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->instance = instance;
+ return 0;
+}
+
+static void nvme_release_instance(struct nvme_dev *dev)
+{
+ spin_lock(&dev_list_lock);
+ ida_remove(&nvme_instance_ida, dev->instance);
+ spin_unlock(&dev_list_lock);
+}
+
+static void nvme_free_namespaces(struct nvme_dev *dev)
+{
+ struct nvme_ns *ns, *next;
+
+ list_for_each_entry_safe(ns, next, &dev->namespaces, list)
+ nvme_free_namespace(ns);
+}
+
+static void nvme_free_dev(struct kref *kref)
+{
+ struct nvme_dev *dev = container_of(kref, struct nvme_dev,
kref);
+
+ put_device(dev->dev);
+ put_device(dev->device);
+ nvme_free_namespaces(dev);
+ nvme_release_instance(dev);
+ if (dev->tagset.tags)
+ blk_mq_free_tag_set(&dev->tagset);
+ if (dev->admin_q)
+ blk_put_queue(dev->admin_q);
+ kfree(dev->queues);
+ kfree(dev->entry);
+ 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->instance == instance) {
+ if (!dev->admin_q) {
+ ret = -EWOULDBLOCK;
+ break;
+ }
+ if (!kref_get_unless_zero(&dev->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;
+ kref_put(&dev->kref, nvme_free_dev);
+ 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, NULL, (void __user *)arg);
+ case NVME_IOCTL_IO_CMD:
+ if (list_empty(&dev->namespaces))
+ return -ENOTTY;
+ ns = list_first_entry(&dev->namespaces, struct
nvme_ns, list);
+ return nvme_user_cmd(dev, 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_set_irq_hints(struct nvme_dev *dev)
+{
+ struct nvme_queue *nvmeq;
+ int i;
+
+ for (i = 0; i < dev->online_queues; i++) {
+ nvmeq = dev->queues[i];
+
+ if (!nvmeq->tags || !(*nvmeq->tags))
+ continue;
+
+ irq_set_affinity_hint(dev->entry[nvmeq
->cq_vector].vector,
+ blk_mq_tags_cpumask(*nvmeq
->tags));
+ }
+}
+
+static int nvme_dev_start(struct nvme_dev *dev)
+{
+ int result;
+ bool start_thread = false;
+
+ result = nvme_dev_map(dev);
+ if (result)
+ return result;
+
+ result = nvme_configure_admin_queue(dev);
+ if (result)
+ goto unmap;
+
+ spin_lock(&dev_list_lock);
+ if (list_empty(&dev_list) && IS_ERR_OR_NULL(nvme_thread)) {
+ start_thread = true;
+ nvme_thread = NULL;
+ }
+ list_add(&dev->node, &dev_list);
+ spin_unlock(&dev_list_lock);
+
+ if (start_thread) {
+ nvme_thread = kthread_run(nvme_kthread, NULL, "nvme");
+ wake_up_all(&nvme_kthread_wait);
+ } else
+ wait_event_killable(nvme_kthread_wait, nvme_thread);
+
+ if (IS_ERR_OR_NULL(nvme_thread)) {
+ result = nvme_thread ? PTR_ERR(nvme_thread) : -EINTR;
+ goto disable;
+ }
+
+ nvme_init_queue(dev->queues[0], 0);
+ result = nvme_alloc_admin_tags(dev);
+ if (result)
+ goto disable;
+
+ result = nvme_setup_io_queues(dev);
+ if (result)
+ goto free_tags;
+
+ nvme_set_irq_hints(dev);
+
+ dev->event_limit = 1;
+ return result;
+
+ free_tags:
+ nvme_dev_remove_admin(dev);
+ blk_put_queue(dev->admin_q);
+ dev->admin_q = NULL;
+ dev->queues[0]->tags = NULL;
+ disable:
+ nvme_disable_queue(dev, 0);
+ nvme_dev_list_remove(dev);
+ unmap:
+ nvme_dev_unmap(dev);
+ return result;
+}
+
+static int nvme_remove_dead_ctrl(void *arg)
+{
+ struct nvme_dev *dev = (struct nvme_dev *)arg;
+ struct pci_dev *pdev = to_pci_dev(dev->dev);
+
+ if (pci_get_drvdata(pdev))
+ pci_stop_and_remove_bus_device_locked(pdev);
+ kref_put(&dev->kref, nvme_free_dev);
+ return 0;
+}
+
+static void nvme_remove_disks(struct work_struct *ws)
+{
+ struct nvme_dev *dev = container_of(ws, struct nvme_dev,
reset_work);
+
+ nvme_free_queues(dev, 1);
+ nvme_dev_remove(dev);
+}
+
+static int nvme_dev_resume(struct nvme_dev *dev)
+{
+ int ret;
+
+ ret = nvme_dev_start(dev);
+ if (ret)
+ return ret;
+ if (dev->online_queues < 2) {
+ spin_lock(&dev_list_lock);
+ dev->reset_workfn = nvme_remove_disks;
+ queue_work(nvme_workq, &dev->reset_work);
+ spin_unlock(&dev_list_lock);
+ } else {
+ nvme_unfreeze_queues(dev);
+ nvme_dev_add(dev);
+ nvme_set_irq_hints(dev);
+ }
+ return 0;
+}
+
+static void nvme_dead_ctrl(struct nvme_dev *dev)
+{
+ dev_warn(dev->dev, "Device failed to resume\n");
+ kref_get(&dev->kref);
+ if (IS_ERR(kthread_run(nvme_remove_dead_ctrl, dev, "nvme%d",
+ dev->instance))) {
+ dev_err(dev->dev,
+ "Failed to start controller remove task\n");
+ kref_put(&dev->kref, nvme_free_dev);
+ }
+}
+
+static void nvme_dev_reset(struct nvme_dev *dev)
+{
+ bool in_probe = work_busy(&dev->probe_work);
+
+ nvme_dev_shutdown(dev);
+
+ /* Synchronize with device probe so that work will see failure
status
+ * and exit gracefully without trying to schedule another
reset */
+ flush_work(&dev->probe_work);
+
+ /* Fail this device if reset occured during probe to avoid
+ * infinite initialization loops. */
+ if (in_probe) {
+ nvme_dead_ctrl(dev);
+ return;
+ }
+ /* Schedule device resume asynchronously so the reset work is
available
+ * to cleanup errors that may occur during reinitialization */
+ schedule_work(&dev->probe_work);
+}
+
+static void nvme_reset_failed_dev(struct work_struct *ws)
+{
+ struct nvme_dev *dev = container_of(ws, struct nvme_dev,
reset_work);
+ nvme_dev_reset(dev);
+}
+
+static void nvme_reset_workfn(struct work_struct *work)
+{
+ struct nvme_dev *dev = container_of(work, struct nvme_dev,
reset_work);
+ dev->reset_workfn(work);
+}
+
+static int nvme_reset(struct nvme_dev *dev)
+{
+ int ret = -EBUSY;
+
+ if (!dev->admin_q || blk_queue_dying(dev->admin_q))
+ return -ENODEV;
+
+ spin_lock(&dev_list_lock);
+ if (!work_pending(&dev->reset_work)) {
+ dev->reset_workfn = nvme_reset_failed_dev;
+ queue_work(nvme_workq, &dev->reset_work);
+ ret = 0;
+ }
+ spin_unlock(&dev_list_lock);
+
+ if (!ret) {
+ flush_work(&dev->reset_work);
+ flush_work(&dev->probe_work);
+ return 0;
+ }
+
+ 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 void nvme_async_probe(struct work_struct *work);
+static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id
*id)
+{
+ int node, result = -ENOMEM;
+ struct nvme_dev *dev;
+
+ node = dev_to_node(&pdev->dev);
+ if (node == NUMA_NO_NODE)
+ set_dev_node(&pdev->dev, 0);
+
+ dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
+ if (!dev)
+ return -ENOMEM;
+ dev->entry = kzalloc_node(num_possible_cpus() * sizeof(*dev
->entry),
+ GFP_KERNEL,
node);
+ if (!dev->entry)
+ goto free;
+ dev->queues = kzalloc_node((num_possible_cpus() + 1) *
sizeof(void *),
+ GFP_KERNEL,
node);
+ if (!dev->queues)
+ goto free;
+
+ INIT_LIST_HEAD(&dev->namespaces);
+ dev->reset_workfn = nvme_reset_failed_dev;
+ INIT_WORK(&dev->reset_work, nvme_reset_workfn);
+ dev->dev = get_device(&pdev->dev);
+ pci_set_drvdata(pdev, dev);
+ result = nvme_set_instance(dev);
+ if (result)
+ goto put_pci;
+
+ result = nvme_setup_prp_pools(dev);
+ if (result)
+ goto release;
+
+ kref_init(&dev->kref);
+ dev->device = device_create(nvme_class, &pdev->dev,
+ MKDEV(nvme_char_major, dev->instance),
+ dev, "nvme%d", dev->instance);
+ if (IS_ERR(dev->device)) {
+ result = PTR_ERR(dev->device);
+ goto release_pools;
+ }
+ get_device(dev->device);
+ dev_set_drvdata(dev->device, dev);
+
+ result = device_create_file(dev->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_async_probe);
+ schedule_work(&dev->probe_work);
+ return 0;
+
+ put_dev:
+ device_destroy(nvme_class, MKDEV(nvme_char_major, dev
->instance));
+ put_device(dev->device);
+ release_pools:
+ nvme_release_prp_pools(dev);
+ release:
+ nvme_release_instance(dev);
+ put_pci:
+ put_device(dev->dev);
+ free:
+ kfree(dev->queues);
+ kfree(dev->entry);
+ kfree(dev);
+ return result;
+}
+
+static void nvme_async_probe(struct work_struct *work)
+{
+ struct nvme_dev *dev = container_of(work, struct nvme_dev,
probe_work);
+
+ if (nvme_dev_resume(dev) && !work_busy(&dev->reset_work))
+ nvme_dead_ctrl(dev);
+}
+
+static void nvme_reset_notify(struct pci_dev *pdev, bool prepare)
+{
+ struct nvme_dev *dev = pci_get_drvdata(pdev);
+
+ if (prepare)
+ nvme_dev_shutdown(dev);
+ else
+ nvme_dev_resume(dev);
+}
+
+static void nvme_shutdown(struct pci_dev *pdev)
+{
+ struct nvme_dev *dev = pci_get_drvdata(pdev);
+ nvme_dev_shutdown(dev);
+}
+
+static void nvme_remove(struct pci_dev *pdev)
+{
+ struct nvme_dev *dev = pci_get_drvdata(pdev);
+
+ spin_lock(&dev_list_lock);
+ list_del_init(&dev->node);
+ spin_unlock(&dev_list_lock);
+
+ pci_set_drvdata(pdev, NULL);
+ flush_work(&dev->probe_work);
+ flush_work(&dev->reset_work);
+ flush_work(&dev->scan_work);
+ device_remove_file(dev->device, &dev_attr_reset_controller);
+ nvme_dev_remove(dev);
+ nvme_dev_shutdown(dev);
+ nvme_dev_remove_admin(dev);
+ device_destroy(nvme_class, MKDEV(nvme_char_major, dev
->instance));
+ nvme_free_queues(dev, 0);
+ nvme_release_cmb(dev);
+ nvme_release_prp_pools(dev);
+ kref_put(&dev->kref, nvme_free_dev);
+}
+
+/* These functions are yet to be implemented */
+#define nvme_error_detected NULL
+#define nvme_dump_registers NULL
+#define nvme_link_reset NULL
+#define nvme_slot_reset NULL
+#define nvme_error_resume NULL
+
+#ifdef CONFIG_PM_SLEEP
+static int nvme_suspend(struct device *dev)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct nvme_dev *ndev = pci_get_drvdata(pdev);
+
+ nvme_dev_shutdown(ndev);
+ return 0;
+}
+
+static int nvme_resume(struct device *dev)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct nvme_dev *ndev = pci_get_drvdata(pdev);
+
+ if (nvme_dev_resume(ndev) && !work_busy(&ndev->reset_work)) {
+ ndev->reset_workfn = nvme_reset_failed_dev;
+ queue_work(nvme_workq, &ndev->reset_work);
+ }
+ return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(nvme_dev_pm_ops, nvme_suspend, nvme_resume);
+
+static const struct pci_error_handlers nvme_err_handler = {
+ .error_detected = nvme_error_detected,
+ .mmio_enabled = nvme_dump_registers,
+ .link_reset = nvme_link_reset,
+ .slot_reset = nvme_slot_reset,
+ .resume = nvme_error_resume,
+ .reset_notify = nvme_reset_notify,
+};
+
+/* Move to pci_ids.h later */
+#define PCI_CLASS_STORAGE_EXPRESS 0x010802
+
+static const struct pci_device_id nvme_id_table[] = {
+ { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
+ { 0, }
+};
+MODULE_DEVICE_TABLE(pci, nvme_id_table);
+
+static struct pci_driver nvme_driver = {
+ .name = "nvme",
+ .id_table = nvme_id_table,
+ .probe = nvme_probe,
+ .remove = nvme_remove,
+ .shutdown = nvme_shutdown,
+ .driver = {
+ .pm = &nvme_dev_pm_ops,
+ },
+ .err_handler = &nvme_err_handler,
+};
+
+static int __init nvme_init(void)
+{
+ int result;
+
+ init_waitqueue_head(&nvme_kthread_wait);
+
+ nvme_workq = create_singlethread_workqueue("nvme");
+ if (!nvme_workq)
+ return -ENOMEM;
+
+ result = register_blkdev(nvme_major, "nvme");
+ if (result < 0)
+ goto kill_workq;
+ 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;
+ }
+
+ result = pci_register_driver(&nvme_driver);
+ if (result)
+ goto destroy_class;
+ return 0;
+
+ destroy_class:
+ class_destroy(nvme_class);
+ unregister_chrdev:
+ __unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
+ unregister_blkdev:
+ unregister_blkdev(nvme_major, "nvme");
+ kill_workq:
+ destroy_workqueue(nvme_workq);
+ return result;
+}
+
+static void __exit nvme_exit(void)
+{
+ pci_unregister_driver(&nvme_driver);
+ unregister_blkdev(nvme_major, "nvme");
+ 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();
+}
+
+MODULE_AUTHOR("Matthew Wilcox <willy at linux.intel.com>");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1.0");
+module_init(nvme_init);
+module_exit(nvme_exit);
diff --git a/drivers/block/nvme/scsi.c b/drivers/block/nvme/scsi.c
new file mode 100644
index 0000000..e5a63f0
--- /dev/null
+++ b/drivers/block/nvme/scsi.c
@@ -0,0 +1,2556 @@
+/*
+ * 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.
+ */
+
+/*
+ * Refer to the SCSI-NVMe Translation spec for details on how
+ * each command is translated.
+ */
+
+#include <linux/nvme.h>
+#include <linux/bio.h>
+#include <linux/bitops.h>
+#include <linux/blkdev.h>
+#include <linux/compat.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/genhd.h>
+#include <linux/idr.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kdev_t.h>
+#include <linux/kthread.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/pci.h>
+#include <linux/poison.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <asm/unaligned.h>
+#include <scsi/sg.h>
+#include <scsi/scsi.h>
+
+
+static int sg_version_num = 30534; /* 2 digits for each component
*/
+
+/* VPD Page Codes */
+#define VPD_SUPPORTED_PAGES 0x00
+#define VPD_SERIAL_NUMBER 0x80
+#define VPD_DEVICE_IDENTIFIERS 0x83
+#define VPD_EXTENDED_INQUIRY 0x86
+#define VPD_BLOCK_LIMITS 0xB0
+#define VPD_BLOCK_DEV_CHARACTERISTICS 0xB1
+
+/* format unit paramter list offsets */
+#define FORMAT_UNIT_SHORT_PARM_LIST_LEN 4
+#define FORMAT_UNIT_LONG_PARM_LIST_LEN 8
+#define FORMAT_UNIT_PROT_INT_OFFSET 3
+#define FORMAT_UNIT_PROT_FIELD_USAGE_OFFSET 0
+#define FORMAT_UNIT_PROT_FIELD_USAGE_MASK 0x07
+
+/* Misc. defines */
+#define FIXED_SENSE_DATA 0x70
+#define DESC_FORMAT_SENSE_DATA 0x72
+#define FIXED_SENSE_DATA_ADD_LENGTH 10
+#define LUN_ENTRY_SIZE 8
+#define LUN_DATA_HEADER_SIZE 8
+#define ALL_LUNS_RETURNED 0x02
+#define ALL_WELL_KNOWN_LUNS_RETURNED 0x01
+#define RESTRICTED_LUNS_RETURNED 0x00
+#define NVME_POWER_STATE_START_VALID 0x00
+#define NVME_POWER_STATE_ACTIVE 0x01
+#define NVME_POWER_STATE_IDLE 0x02
+#define NVME_POWER_STATE_STANDBY 0x03
+#define NVME_POWER_STATE_LU_CONTROL 0x07
+#define POWER_STATE_0 0
+#define POWER_STATE_1 1
+#define POWER_STATE_2 2
+#define POWER_STATE_3 3
+#define DOWNLOAD_SAVE_ACTIVATE 0x05
+#define DOWNLOAD_SAVE_DEFER_ACTIVATE 0x0E
+#define ACTIVATE_DEFERRED_MICROCODE 0x0F
+#define FORMAT_UNIT_IMMED_MASK 0x2
+#define FORMAT_UNIT_IMMED_OFFSET 1
+#define KELVIN_TEMP_FACTOR 273
+#define FIXED_FMT_SENSE_DATA_SIZE 18
+#define DESC_FMT_SENSE_DATA_SIZE 8
+
+/* SCSI/NVMe defines and bit masks */
+#define INQ_STANDARD_INQUIRY_PAGE 0x00
+#define INQ_SUPPORTED_VPD_PAGES_PAGE 0x00
+#define INQ_UNIT_SERIAL_NUMBER_PAGE 0x80
+#define INQ_DEVICE_IDENTIFICATION_PAGE 0x83
+#define INQ_EXTENDED_INQUIRY_DATA_PAGE 0x86
+#define INQ_BDEV_LIMITS_PAGE 0xB0
+#define INQ_BDEV_CHARACTERISTICS_PAGE 0xB1
+#define INQ_SERIAL_NUMBER_LENGTH 0x14
+#define INQ_NUM_SUPPORTED_VPD_PAGES 6
+#define VERSION_SPC_4 0x06
+#define ACA_UNSUPPORTED 0
+#define STANDARD_INQUIRY_LENGTH 36
+#define ADDITIONAL_STD_INQ_LENGTH 31
+#define EXTENDED_INQUIRY_DATA_PAGE_LENGTH 0x3C
+#define RESERVED_FIELD 0
+
+/* Mode Sense/Select defines */
+#define MODE_PAGE_INFO_EXCEP 0x1C
+#define MODE_PAGE_CACHING 0x08
+#define MODE_PAGE_CONTROL 0x0A
+#define MODE_PAGE_POWER_CONDITION 0x1A
+#define MODE_PAGE_RETURN_ALL 0x3F
+#define MODE_PAGE_BLK_DES_LEN 0x08
+#define MODE_PAGE_LLBAA_BLK_DES_LEN 0x10
+#define MODE_PAGE_CACHING_LEN 0x14
+#define MODE_PAGE_CONTROL_LEN 0x0C
+#define MODE_PAGE_POW_CND_LEN 0x28
+#define MODE_PAGE_INF_EXC_LEN 0x0C
+#define MODE_PAGE_ALL_LEN 0x54
+#define MODE_SENSE6_MPH_SIZE 4
+#define MODE_SENSE_PAGE_CONTROL_MASK 0xC0
+#define MODE_SENSE_PAGE_CODE_OFFSET 2
+#define MODE_SENSE_PAGE_CODE_MASK 0x3F
+#define MODE_SENSE_LLBAA_MASK 0x10
+#define MODE_SENSE_LLBAA_SHIFT 4
+#define MODE_SENSE_DBD_MASK 8
+#define MODE_SENSE_DBD_SHIFT 3
+#define MODE_SENSE10_MPH_SIZE 8
+#define MODE_SELECT_CDB_PAGE_FORMAT_MASK 0x10
+#define MODE_SELECT_CDB_SAVE_PAGES_MASK 0x1
+#define MODE_SELECT_6_BD_OFFSET 3
+#define MODE_SELECT_10_BD_OFFSET 6
+#define MODE_SELECT_10_LLBAA_OFFSET 4
+#define MODE_SELECT_10_LLBAA_MASK 1
+#define MODE_SELECT_6_MPH_SIZE 4
+#define MODE_SELECT_10_MPH_SIZE 8
+#define CACHING_MODE_PAGE_WCE_MASK 0x04
+#define MODE_SENSE_BLK_DESC_ENABLED 0
+#define MODE_SENSE_BLK_DESC_COUNT 1
+#define MODE_SELECT_PAGE_CODE_MASK 0x3F
+#define SHORT_DESC_BLOCK 8
+#define LONG_DESC_BLOCK 16
+#define MODE_PAGE_POW_CND_LEN_FIELD 0x26
+#define MODE_PAGE_INF_EXC_LEN_FIELD 0x0A
+#define MODE_PAGE_CACHING_LEN_FIELD 0x12
+#define MODE_PAGE_CONTROL_LEN_FIELD 0x0A
+#define MODE_SENSE_PC_CURRENT_VALUES 0
+
+/* Log Sense defines */
+#define LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE 0x00
+#define LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH 0x07
+#define LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE 0x2F
+#define LOG_PAGE_TEMPERATURE_PAGE 0x0D
+#define LOG_SENSE_CDB_SP_NOT_ENABLED 0
+#define LOG_SENSE_CDB_PC_MASK 0xC0
+#define LOG_SENSE_CDB_PC_SHIFT 6
+#define LOG_SENSE_CDB_PC_CUMULATIVE_VALUES 1
+#define LOG_SENSE_CDB_PAGE_CODE_MASK 0x3F
+#define REMAINING_INFO_EXCP_PAGE_LENGTH 0x8
+#define LOG_INFO_EXCP_PAGE_LENGTH 0xC
+#define REMAINING_TEMP_PAGE_LENGTH 0xC
+#define LOG_TEMP_PAGE_LENGTH 0x10
+#define LOG_TEMP_UNKNOWN 0xFF
+#define SUPPORTED_LOG_PAGES_PAGE_LENGTH 0x3
+
+/* Read Capacity defines */
+#define READ_CAP_10_RESP_SIZE 8
+#define READ_CAP_16_RESP_SIZE 32
+
+/* NVMe Namespace and Command Defines */
+#define BYTES_TO_DWORDS 4
+#define NVME_MAX_FIRMWARE_SLOT 7
+
+/* Report LUNs defines */
+#define REPORT_LUNS_FIRST_LUN_OFFSET 8
+
+/* SCSI ADDITIONAL SENSE Codes */
+
+#define SCSI_ASC_NO_SENSE 0x00
+#define SCSI_ASC_PERIPHERAL_DEV_WRITE_FAULT 0x03
+#define SCSI_ASC_LUN_NOT_READY 0x04
+#define SCSI_ASC_WARNING 0x0B
+#define SCSI_ASC_LOG_BLOCK_GUARD_CHECK_FAILED 0x10
+#define SCSI_ASC_LOG_BLOCK_APPTAG_CHECK_FAILED 0x10
+#define SCSI_ASC_LOG_BLOCK_REFTAG_CHECK_FAILED 0x10
+#define SCSI_ASC_UNRECOVERED_READ_ERROR 0x11
+#define SCSI_ASC_MISCOMPARE_DURING_VERIFY 0x1D
+#define SCSI_ASC_ACCESS_DENIED_INVALID_LUN_ID 0x20
+#define SCSI_ASC_ILLEGAL_COMMAND 0x20
+#define SCSI_ASC_ILLEGAL_BLOCK 0x21
+#define SCSI_ASC_INVALID_CDB 0x24
+#define SCSI_ASC_INVALID_LUN 0x25
+#define SCSI_ASC_INVALID_PARAMETER 0x26
+#define SCSI_ASC_FORMAT_COMMAND_FAILED 0x31
+#define SCSI_ASC_INTERNAL_TARGET_FAILURE 0x44
+
+/* SCSI ADDITIONAL SENSE Code Qualifiers */
+
+#define SCSI_ASCQ_CAUSE_NOT_REPORTABLE 0x00
+#define SCSI_ASCQ_FORMAT_COMMAND_FAILED 0x01
+#define SCSI_ASCQ_LOG_BLOCK_GUARD_CHECK_FAILED 0x01
+#define SCSI_ASCQ_LOG_BLOCK_APPTAG_CHECK_FAILED 0x02
+#define SCSI_ASCQ_LOG_BLOCK_REFTAG_CHECK_FAILED 0x03
+#define SCSI_ASCQ_FORMAT_IN_PROGRESS 0x04
+#define SCSI_ASCQ_POWER_LOSS_EXPECTED 0x08
+#define SCSI_ASCQ_INVALID_LUN_ID 0x09
+
+/* copied from drivers/usb/gadget/function/storage_common.h */
+static inline u32 get_unaligned_be24(u8 *buf)
+{
+ return 0xffffff & (u32) get_unaligned_be32(buf - 1);
+}
+
+/* Struct to gather data that needs to be extracted from a SCSI CDB.
+ Not conforming to any particular CDB variant, but compatible with
all. */
+
+struct nvme_trans_io_cdb {
+ u8 fua;
+ u8 prot_info;
+ u64 lba;
+ u32 xfer_len;
+};
+
+
+/* Internal Helper Functions */
+
+
+/* Copy data to userspace memory */
+
+static int nvme_trans_copy_to_user(struct sg_io_hdr *hdr, void *from,
+ unsign
ed long n)
+{
+ int i;
+ void *index = from;
+ size_t remaining = n;
+ size_t xfer_len;
+
+ if (hdr->iovec_count > 0) {
+ struct sg_iovec sgl;
+
+ for (i = 0; i < hdr->iovec_count; i++) {
+ if (copy_from_user(&sgl, hdr->dxferp +
+ i * sizeof(struct
sg_iovec),
+ sizeof(struct
sg_iovec)))
+ return -EFAULT;
+ xfer_len = min(remaining, sgl.iov_len);
+ if (copy_to_user(sgl.iov_base, index,
xfer_len))
+ return -EFAULT;
+
+ index += xfer_len;
+ remaining -= xfer_len;
+ if (remaining == 0)
+ break;
+ }
+ return 0;
+ }
+
+ if (copy_to_user(hdr->dxferp, from, n))
+ return -EFAULT;
+ return 0;
+}
+
+/* Copy data from userspace memory */
+
+static int nvme_trans_copy_from_user(struct sg_io_hdr *hdr, void *to,
+ unsign
ed long n)
+{
+ int i;
+ void *index = to;
+ size_t remaining = n;
+ size_t xfer_len;
+
+ if (hdr->iovec_count > 0) {
+ struct sg_iovec sgl;
+
+ for (i = 0; i < hdr->iovec_count; i++) {
+ if (copy_from_user(&sgl, hdr->dxferp +
+ i * sizeof(struct
sg_iovec),
+ sizeof(struct
sg_iovec)))
+ return -EFAULT;
+ xfer_len = min(remaining, sgl.iov_len);
+ if (copy_from_user(index, sgl.iov_base,
xfer_len))
+ return -EFAULT;
+ index += xfer_len;
+ remaining -= xfer_len;
+ if (remaining == 0)
+ break;
+ }
+ return 0;
+ }
+
+ if (copy_from_user(to, hdr->dxferp, n))
+ return -EFAULT;
+ return 0;
+}
+
+/* Status/Sense Buffer Writeback */
+
+static int nvme_trans_completion(struct sg_io_hdr *hdr, u8 status, u8
sense_key,
+ u8 asc, u8 ascq)
+{
+ u8 xfer_len;
+ u8 resp[DESC_FMT_SENSE_DATA_SIZE];
+
+ if (scsi_status_is_good(status)) {
+ hdr->status = SAM_STAT_GOOD;
+ hdr->masked_status = GOOD;
+ hdr->host_status = DID_OK;
+ hdr->driver_status = DRIVER_OK;
+ hdr->sb_len_wr = 0;
+ } else {
+ hdr->status = status;
+ hdr->masked_status = status >> 1;
+ hdr->host_status = DID_OK;
+ hdr->driver_status = DRIVER_OK;
+
+ memset(resp, 0, DESC_FMT_SENSE_DATA_SIZE);
+ resp[0] = DESC_FORMAT_SENSE_DATA;
+ resp[1] = sense_key;
+ resp[2] = asc;
+ resp[3] = ascq;
+
+ xfer_len = min_t(u8, hdr->mx_sb_len,
DESC_FMT_SENSE_DATA_SIZE);
+ hdr->sb_len_wr = xfer_len;
+ if (copy_to_user(hdr->sbp, resp, xfer_len) > 0)
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
+/*
+ * Take a status code from a lowlevel routine, and if it was a
positive NVMe
+ * error code update the sense data based on it. In either case the
passed
+ * in value is returned again, unless an -EFAULT from copy_to_user
overrides
+ * it.
+ */
+static int nvme_trans_status_code(struct sg_io_hdr *hdr, int nvme_sc)
+{
+ u8 status, sense_key, asc, ascq;
+ int res;
+
+ /* For non-nvme (Linux) errors, simply return the error code
*/
+ if (nvme_sc < 0)
+ return nvme_sc;
+
+ /* Mask DNR, More, and reserved fields */
+ switch (nvme_sc & 0x7FF) {
+ /* Generic Command Status */
+ case NVME_SC_SUCCESS:
+ status = SAM_STAT_GOOD;
+ sense_key = NO_SENSE;
+ asc = SCSI_ASC_NO_SENSE;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+ case NVME_SC_INVALID_OPCODE:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = ILLEGAL_REQUEST;
+ asc = SCSI_ASC_ILLEGAL_COMMAND;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+ case NVME_SC_INVALID_FIELD:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = ILLEGAL_REQUEST;
+ asc = SCSI_ASC_INVALID_CDB;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+ case NVME_SC_DATA_XFER_ERROR:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = MEDIUM_ERROR;
+ asc = SCSI_ASC_NO_SENSE;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+ case NVME_SC_POWER_LOSS:
+ status = SAM_STAT_TASK_ABORTED;
+ sense_key = ABORTED_COMMAND;
+ asc = SCSI_ASC_WARNING;
+ ascq = SCSI_ASCQ_POWER_LOSS_EXPECTED;
+ break;
+ case NVME_SC_INTERNAL:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = HARDWARE_ERROR;
+ asc = SCSI_ASC_INTERNAL_TARGET_FAILURE;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+ case NVME_SC_ABORT_REQ:
+ status = SAM_STAT_TASK_ABORTED;
+ sense_key = ABORTED_COMMAND;
+ asc = SCSI_ASC_NO_SENSE;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+ case NVME_SC_ABORT_QUEUE:
+ status = SAM_STAT_TASK_ABORTED;
+ sense_key = ABORTED_COMMAND;
+ asc = SCSI_ASC_NO_SENSE;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+ case NVME_SC_FUSED_FAIL:
+ status = SAM_STAT_TASK_ABORTED;
+ sense_key = ABORTED_COMMAND;
+ asc = SCSI_ASC_NO_SENSE;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+ case NVME_SC_FUSED_MISSING:
+ status = SAM_STAT_TASK_ABORTED;
+ sense_key = ABORTED_COMMAND;
+ asc = SCSI_ASC_NO_SENSE;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+ case NVME_SC_INVALID_NS:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = ILLEGAL_REQUEST;
+ asc = SCSI_ASC_ACCESS_DENIED_INVALID_LUN_ID;
+ ascq = SCSI_ASCQ_INVALID_LUN_ID;
+ break;
+ case NVME_SC_LBA_RANGE:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = ILLEGAL_REQUEST;
+ asc = SCSI_ASC_ILLEGAL_BLOCK;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+ case NVME_SC_CAP_EXCEEDED:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = MEDIUM_ERROR;
+ asc = SCSI_ASC_NO_SENSE;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+ case NVME_SC_NS_NOT_READY:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = NOT_READY;
+ asc = SCSI_ASC_LUN_NOT_READY;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+
+ /* Command Specific Status */
+ case NVME_SC_INVALID_FORMAT:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = ILLEGAL_REQUEST;
+ asc = SCSI_ASC_FORMAT_COMMAND_FAILED;
+ ascq = SCSI_ASCQ_FORMAT_COMMAND_FAILED;
+ break;
+ case NVME_SC_BAD_ATTRIBUTES:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = ILLEGAL_REQUEST;
+ asc = SCSI_ASC_INVALID_CDB;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+
+ /* Media Errors */
+ case NVME_SC_WRITE_FAULT:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = MEDIUM_ERROR;
+ asc = SCSI_ASC_PERIPHERAL_DEV_WRITE_FAULT;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+ case NVME_SC_READ_ERROR:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = MEDIUM_ERROR;
+ asc = SCSI_ASC_UNRECOVERED_READ_ERROR;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+ case NVME_SC_GUARD_CHECK:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = MEDIUM_ERROR;
+ asc = SCSI_ASC_LOG_BLOCK_GUARD_CHECK_FAILED;
+ ascq = SCSI_ASCQ_LOG_BLOCK_GUARD_CHECK_FAILED;
+ break;
+ case NVME_SC_APPTAG_CHECK:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = MEDIUM_ERROR;
+ asc = SCSI_ASC_LOG_BLOCK_APPTAG_CHECK_FAILED;
+ ascq = SCSI_ASCQ_LOG_BLOCK_APPTAG_CHECK_FAILED;
+ break;
+ case NVME_SC_REFTAG_CHECK:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = MEDIUM_ERROR;
+ asc = SCSI_ASC_LOG_BLOCK_REFTAG_CHECK_FAILED;
+ ascq = SCSI_ASCQ_LOG_BLOCK_REFTAG_CHECK_FAILED;
+ break;
+ case NVME_SC_COMPARE_FAILED:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = MISCOMPARE;
+ asc = SCSI_ASC_MISCOMPARE_DURING_VERIFY;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+ case NVME_SC_ACCESS_DENIED:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = ILLEGAL_REQUEST;
+ asc = SCSI_ASC_ACCESS_DENIED_INVALID_LUN_ID;
+ ascq = SCSI_ASCQ_INVALID_LUN_ID;
+ break;
+
+ /* Unspecified/Default */
+ case NVME_SC_CMDID_CONFLICT:
+ case NVME_SC_CMD_SEQ_ERROR:
+ case NVME_SC_CQ_INVALID:
+ case NVME_SC_QID_INVALID:
+ case NVME_SC_QUEUE_SIZE:
+ case NVME_SC_ABORT_LIMIT:
+ case NVME_SC_ABORT_MISSING:
+ case NVME_SC_ASYNC_LIMIT:
+ case NVME_SC_FIRMWARE_SLOT:
+ case NVME_SC_FIRMWARE_IMAGE:
+ case NVME_SC_INVALID_VECTOR:
+ case NVME_SC_INVALID_LOG_PAGE:
+ default:
+ status = SAM_STAT_CHECK_CONDITION;
+ sense_key = ILLEGAL_REQUEST;
+ asc = SCSI_ASC_NO_SENSE;
+ ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ break;
+ }
+
+ res = nvme_trans_completion(hdr, status, sense_key, asc,
ascq);
+ return res ? res : nvme_sc;
+}
+
+/* INQUIRY Helper Functions */
+
+static int nvme_trans_standard_inquiry_page(struct nvme_ns *ns,
+ struct sg_io_hdr *hdr, u8
*inq_response,
+ int alloc_len)
+{
+ struct nvme_dev *dev = ns->dev;
+ struct nvme_id_ns *id_ns;
+ int res;
+ int nvme_sc;
+ int xfer_len;
+ u8 resp_data_format = 0x02;
+ u8 protect;
+ u8 cmdque = 0x01 << 1;
+ u8 fw_offset = sizeof(dev->firmware_rev);
+
+ /* nvme ns identify - use DPS value for PROTECT field */
+ nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
+ res = nvme_trans_status_code(hdr, nvme_sc);
+ if (res)
+ return res;
+
+ if (id_ns->dps)
+ protect = 0x01;
+ else
+ protect = 0;
+ kfree(id_ns);
+
+ memset(inq_response, 0, STANDARD_INQUIRY_LENGTH);
+ inq_response[2] = VERSION_SPC_4;
+ inq_response[3] = resp_data_format; /*normaca=0 | hisup=0
*/
+ inq_response[4] = ADDITIONAL_STD_INQ_LENGTH;
+ inq_response[5] = protect; /* sccs=0 | acc=0 | tpgs=0 |
pc3=0 */
+ inq_response[7] = cmdque; /* wbus16=0 | sync=0 | vs=0 */
+ strncpy(&inq_response[8], "NVMe ", 8);
+ strncpy(&inq_response[16], dev->model, 16);
+
+ while (dev->firmware_rev[fw_offset - 1] == ' ' && fw_offset >
4)
+ fw_offset--;
+ fw_offset -= 4;
+ strncpy(&inq_response[32], dev->firmware_rev + fw_offset, 4);
+
+ xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH);
+ return nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
+}
+
+static int nvme_trans_supported_vpd_pages(struct nvme_ns *ns,
+ struct sg_io_hdr *hdr, u8
*inq_response,
+ int alloc_len)
+{
+ int xfer_len;
+
+ memset(inq_response, 0, STANDARD_INQUIRY_LENGTH);
+ inq_response[1] = INQ_SUPPORTED_VPD_PAGES_PAGE; /* Page Code
*/
+ inq_response[3] = INQ_NUM_SUPPORTED_VPD_PAGES; /* Page
Length */
+ inq_response[4] = INQ_SUPPORTED_VPD_PAGES_PAGE;
+ inq_response[5] = INQ_UNIT_SERIAL_NUMBER_PAGE;
+ inq_response[6] = INQ_DEVICE_IDENTIFICATION_PAGE;
+ inq_response[7] = INQ_EXTENDED_INQUIRY_DATA_PAGE;
+ inq_response[8] = INQ_BDEV_CHARACTERISTICS_PAGE;
+ inq_response[9] = INQ_BDEV_LIMITS_PAGE;
+
+ xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH);
+ return nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
+}
+
+static int nvme_trans_unit_serial_page(struct nvme_ns *ns,
+ struct sg_io_hdr *hdr, u8
*inq_response,
+ int alloc_len)
+{
+ struct nvme_dev *dev = ns->dev;
+ int xfer_len;
+
+ memset(inq_response, 0, STANDARD_INQUIRY_LENGTH);
+ inq_response[1] = INQ_UNIT_SERIAL_NUMBER_PAGE; /* Page Code */
+ inq_response[3] = INQ_SERIAL_NUMBER_LENGTH; /* Page Length
*/
+ strncpy(&inq_response[4], dev->serial,
INQ_SERIAL_NUMBER_LENGTH);
+
+ xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH);
+ return nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
+}
+
+static int nvme_trans_device_id_page(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
+ u8 *inq_response, int
alloc_len)
+{
+ struct nvme_dev *dev = ns->dev;
+ int res;
+ int nvme_sc;
+ int xfer_len;
+ __be32 tmp_id = cpu_to_be32(ns->ns_id);
+
+ memset(inq_response, 0, alloc_len);
+ inq_response[1] = INQ_DEVICE_IDENTIFICATION_PAGE; /* Page
Code */
+ if (readl(&dev->bar->vs) >= NVME_VS(1, 1)) {
+ struct nvme_id_ns *id_ns;
+ void *eui;
+ int len;
+
+ nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
+ res = nvme_trans_status_code(hdr, nvme_sc);
+ if (res)
+ return res;
+
+ eui = id_ns->eui64;
+ len = sizeof(id_ns->eui64);
+ if (readl(&dev->bar->vs) >= NVME_VS(1, 2)) {
+ if (bitmap_empty(eui, len * 8)) {
+ eui = id_ns->nguid;
+ len = sizeof(id_ns->nguid);
+ }
+ }
+ if (bitmap_empty(eui, len * 8)) {
+ kfree(id_ns);
+ goto scsi_string;
+ }
+
+ inq_response[3] = 4 + len; /* Page Length */
+ /* Designation Descriptor start */
+ inq_response[4] = 0x01; /* Proto ID=0h | Code
set=1h */
+ inq_response[5] = 0x02; /* PIV=0b | Asso=00b |
Designator Type=2h */
+ inq_response[6] = 0x00; /* Rsvd */
+ inq_response[7] = len; /* Designator Length */
+ memcpy(&inq_response[8], eui, len);
+ kfree(id_ns);
+ } else {
+ scsi_string:
+ if (alloc_len < 72) {
+ return nvme_trans_completion(hdr,
+ SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ }
+ inq_response[3] = 0x48; /* Page Length */
+ /* Designation Descriptor start */
+ inq_response[4] = 0x03; /* Proto ID=0h | Code
set=3h */
+ inq_response[5] = 0x08; /* PIV=0b | Asso=00b |
Designator Type=8h */
+ inq_response[6] = 0x00; /* Rsvd */
+ inq_response[7] = 0x44; /* Designator Length */
+
+ sprintf(&inq_response[8], "%04x", to_pci_dev(dev->dev)
->vendor);
+ memcpy(&inq_response[12], dev->model, sizeof(dev
->model));
+ sprintf(&inq_response[52], "%04x", tmp_id);
+ memcpy(&inq_response[56], dev->serial, sizeof(dev
->serial));
+ }
+ xfer_len = alloc_len;
+ return nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
+}
+
+static int nvme_trans_ext_inq_page(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
+ int alloc_len)
+{
+ u8 *inq_response;
+ int res;
+ int nvme_sc;
+ struct nvme_dev *dev = ns->dev;
+ struct nvme_id_ctrl *id_ctrl;
+ struct nvme_id_ns *id_ns;
+ int xfer_len;
+ u8 microcode = 0x80;
+ u8 spt;
+ u8 spt_lut[8] = {0, 0, 2, 1, 4, 6, 5, 7};
+ u8 grd_chk, app_chk, ref_chk, protect;
+ u8 uask_sup = 0x20;
+ u8 v_sup;
+ u8 luiclr = 0x01;
+
+ inq_response = kmalloc(EXTENDED_INQUIRY_DATA_PAGE_LENGTH,
GFP_KERNEL);
+ if (inq_response == NULL)
+ return -ENOMEM;
+
+ nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
+ res = nvme_trans_status_code(hdr, nvme_sc);
+ if (res)
+ goto out_free_inq;
+
+ spt = spt_lut[id_ns->dpc & 0x07] << 3;
+ if (id_ns->dps)
+ protect = 0x01;
+ else
+ protect = 0;
+ kfree(id_ns);
+
+ grd_chk = protect << 2;
+ app_chk = protect << 1;
+ ref_chk = protect;
+
+ nvme_sc = nvme_identify_ctrl(dev, &id_ctrl);
+ res = nvme_trans_status_code(hdr, nvme_sc);
+ if (res)
+ goto out_free_inq;
+
+ v_sup = id_ctrl->vwc;
+ kfree(id_ctrl);
+
+ memset(inq_response, 0, EXTENDED_INQUIRY_DATA_PAGE_LENGTH);
+ inq_response[1] = INQ_EXTENDED_INQUIRY_DATA_PAGE; /* Page
Code */
+ inq_response[2] = 0x00; /* Page Length MSB */
+ inq_response[3] = 0x3C; /* Page Length LSB */
+ inq_response[4] = microcode | spt | grd_chk | app_chk |
ref_chk;
+ inq_response[5] = uask_sup;
+ inq_response[6] = v_sup;
+ inq_response[7] = luiclr;
+ inq_response[8] = 0;
+ inq_response[9] = 0;
+
+ xfer_len = min(alloc_len, EXTENDED_INQUIRY_DATA_PAGE_LENGTH);
+ res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
+
+ out_free_inq:
+ kfree(inq_response);
+ return res;
+}
+
+static int nvme_trans_bdev_limits_page(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
+ u8 *inq_response, int
alloc_len)
+{
+ __be32 max_sectors = cpu_to_be32(
+ nvme_block_nr(ns, queue_max_hw_sectors(ns->queue)));
+ __be32 max_discard = cpu_to_be32(ns->queue
->limits.max_discard_sectors);
+ __be32 discard_desc_count = cpu_to_be32(0x100);
+
+ memset(inq_response, 0, STANDARD_INQUIRY_LENGTH);
+ inq_response[1] = VPD_BLOCK_LIMITS;
+ inq_response[3] = 0x3c; /* Page Length */
+ memcpy(&inq_response[8], &max_sectors, sizeof(u32));
+ memcpy(&inq_response[20], &max_discard, sizeof(u32));
+
+ if (max_discard)
+ memcpy(&inq_response[24], &discard_desc_count,
sizeof(u32));
+
+ return nvme_trans_copy_to_user(hdr, inq_response, 0x3c);
+}
+
+static int nvme_trans_bdev_char_page(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
+ int alloc_len)
+{
+ u8 *inq_response;
+ int res;
+ int xfer_len;
+
+ inq_response = kzalloc(EXTENDED_INQUIRY_DATA_PAGE_LENGTH,
GFP_KERNEL);
+ if (inq_response == NULL) {
+ res = -ENOMEM;
+ goto out_mem;
+ }
+
+ inq_response[1] = INQ_BDEV_CHARACTERISTICS_PAGE; /* Page
Code */
+ inq_response[2] = 0x00; /* Page Length MSB */
+ inq_response[3] = 0x3C; /* Page Length LSB */
+ inq_response[4] = 0x00; /* Medium Rotation Rate MSB */
+ inq_response[5] = 0x01; /* Medium Rotation Rate LSB */
+ inq_response[6] = 0x00; /* Form Factor */
+
+ xfer_len = min(alloc_len, EXTENDED_INQUIRY_DATA_PAGE_LENGTH);
+ res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
+
+ kfree(inq_response);
+ out_mem:
+ return res;
+}
+
+/* LOG SENSE Helper Functions */
+
+static int nvme_trans_log_supp_pages(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
+ int alloc_len)
+{
+ int res;
+ int xfer_len;
+ u8 *log_response;
+
+ log_response = kzalloc(LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH,
GFP_KERNEL);
+ if (log_response == NULL) {
+ res = -ENOMEM;
+ goto out_mem;
+ }
+
+ log_response[0] = LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE;
+ /* Subpage=0x00, Page Length MSB=0 */
+ log_response[3] = SUPPORTED_LOG_PAGES_PAGE_LENGTH;
+ log_response[4] = LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE;
+ log_response[5] = LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE;
+ log_response[6] = LOG_PAGE_TEMPERATURE_PAGE;
+
+ xfer_len = min(alloc_len,
LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH);
+ res = nvme_trans_copy_to_user(hdr, log_response, xfer_len);
+
+ kfree(log_response);
+ out_mem:
+ return res;
+}
+
+static int nvme_trans_log_info_exceptions(struct nvme_ns *ns,
+ struct sg_io_hdr *hdr, int
alloc_len)
+{
+ int res;
+ int xfer_len;
+ u8 *log_response;
+ struct nvme_dev *dev = ns->dev;
+ struct nvme_smart_log *smart_log;
+ u8 temp_c;
+ u16 temp_k;
+
+ log_response = kzalloc(LOG_INFO_EXCP_PAGE_LENGTH, GFP_KERNEL);
+ if (log_response == NULL)
+ return -ENOMEM;
+
+ res = nvme_get_log_page(dev, &smart_log);
+ if (res < 0)
+ goto out_free_response;
+
+ if (res != NVME_SC_SUCCESS) {
+ temp_c = LOG_TEMP_UNKNOWN;
+ } else {
+ temp_k = (smart_log->temperature[1] << 8) +
+ (smart_log->temperature[0]);
+ temp_c = temp_k - KELVIN_TEMP_FACTOR;
+ }
+ kfree(smart_log);
+
+ log_response[0] = LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE;
+ /* Subpage=0x00, Page Length MSB=0 */
+ log_response[3] = REMAINING_INFO_EXCP_PAGE_LENGTH;
+ /* Informational Exceptions Log Parameter 1 Start */
+ /* Parameter Code=0x0000 bytes 4,5 */
+ log_response[6] = 0x23; /* DU=0, TSD=1, ETC=0, TMC=0,
FMT_AND_LNK=11b */
+ log_response[7] = 0x04; /* PARAMETER LENGTH */
+ /* Add sense Code and qualifier = 0x00 each */
+ /* Use Temperature from NVMe Get Log Page, convert to C from K
*/
+ log_response[10] = temp_c;
+
+ xfer_len = min(alloc_len, LOG_INFO_EXCP_PAGE_LENGTH);
+ res = nvme_trans_copy_to_user(hdr, log_response, xfer_len);
+
+ out_free_response:
+ kfree(log_response);
+ return res;
+}
+
+static int nvme_trans_log_temperature(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
+ int alloc_len)
+{
+ int res;
+ int xfer_len;
+ u8 *log_response;
+ struct nvme_dev *dev = ns->dev;
+ struct nvme_smart_log *smart_log;
+ u32 feature_resp;
+ u8 temp_c_cur, temp_c_thresh;
+ u16 temp_k;
+
+ log_response = kzalloc(LOG_TEMP_PAGE_LENGTH, GFP_KERNEL);
+ if (log_response == NULL)
+ return -ENOMEM;
+
+ res = nvme_get_log_page(dev, &smart_log);
+ if (res < 0)
+ goto out_free_response;
+
+ if (res != NVME_SC_SUCCESS) {
+ temp_c_cur = LOG_TEMP_UNKNOWN;
+ } else {
+ temp_k = (smart_log->temperature[1] << 8) +
+ (smart_log->temperature[0]);
+ temp_c_cur = temp_k - KELVIN_TEMP_FACTOR;
+ }
+ kfree(smart_log);
+
+ /* Get Features for Temp Threshold */
+ res = nvme_get_features(dev, NVME_FEAT_TEMP_THRESH, 0, 0,
+ &featu
re_resp);
+ if (res != NVME_SC_SUCCESS)
+ temp_c_thresh = LOG_TEMP_UNKNOWN;
+ else
+ temp_c_thresh = (feature_resp & 0xFFFF) -
KELVIN_TEMP_FACTOR;
+
+ log_response[0] = LOG_PAGE_TEMPERATURE_PAGE;
+ /* Subpage=0x00, Page Length MSB=0 */
+ log_response[3] = REMAINING_TEMP_PAGE_LENGTH;
+ /* Temperature Log Parameter 1 (Temperature) Start */
+ /* Parameter Code = 0x0000 */
+ log_response[6] = 0x01; /* Format and Linking
= 01b */
+ log_response[7] = 0x02; /* Parameter Length */
+ /* Use Temperature from NVMe Get Log Page, convert to C from K
*/
+ log_response[9] = temp_c_cur;
+ /* Temperature Log Parameter 2 (Reference Temperature) Start
*/
+ log_response[11] = 0x01; /* Parameter Code = 0x0001 */
+ log_response[12] = 0x01; /* Format and Linking = 01b */
+ log_response[13] = 0x02; /* Parameter Length */
+ /* Use Temperature Thresh from NVMe Get Log Page, convert to C
from K */
+ log_response[15] = temp_c_thresh;
+
+ xfer_len = min(alloc_len, LOG_TEMP_PAGE_LENGTH);
+ res = nvme_trans_copy_to_user(hdr, log_response, xfer_len);
+
+ out_free_response:
+ kfree(log_response);
+ return res;
+}
+
+/* MODE SENSE Helper Functions */
+
+static int nvme_trans_fill_mode_parm_hdr(u8 *resp, int len, u8 cdb10,
u8 llbaa,
+ u16 mode_data_length, u16
blk_desc_len)
+{
+ /* Quick check to make sure I don't stomp on my own memory...
*/
+ if ((cdb10 && len < 8) || (!cdb10 && len < 4))
+ return -EINVAL;
+
+ if (cdb10) {
+ resp[0] = (mode_data_length & 0xFF00) >> 8;
+ resp[1] = (mode_data_length & 0x00FF);
+ resp[3] = 0x10 /* DPOFUA */;
+ resp[4] = llbaa;
+ resp[5] = RESERVED_FIELD;
+ resp[6] = (blk_desc_len & 0xFF00) >> 8;
+ resp[7] = (blk_desc_len & 0x00FF);
+ } else {
+ resp[0] = (mode_data_length & 0x00FF);
+ resp[2] = 0x10 /* DPOFUA */;
+ resp[3] = (blk_desc_len & 0x00FF);
+ }
+
+ return 0;
+}
+
+static int nvme_trans_fill_blk_desc(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
+ u8 *resp, int len, u8 llbaa)
+{
+ int res;
+ int nvme_sc;
+ struct nvme_dev *dev = ns->dev;
+ struct nvme_id_ns *id_ns;
+ u8 flbas;
+ u32 lba_length;
+
+ if (llbaa == 0 && len < MODE_PAGE_BLK_DES_LEN)
+ return -EINVAL;
+ else if (llbaa > 0 && len < MODE_PAGE_LLBAA_BLK_DES_LEN)
+ return -EINVAL;
+
+ nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
+ res = nvme_trans_status_code(hdr, nvme_sc);
+ if (res)
+ return res;
+
+ flbas = (id_ns->flbas) & 0x0F;
+ lba_length = (1 << (id_ns->lbaf[flbas].ds));
+
+ if (llbaa == 0) {
+ __be32 tmp_cap = cpu_to_be32(le64_to_cpu(id_ns
->ncap));
+ /* Byte 4 is reserved */
+ __be32 tmp_len = cpu_to_be32(lba_length & 0x00FFFFFF);
+
+ memcpy(resp, &tmp_cap, sizeof(u32));
+ memcpy(&resp[4], &tmp_len, sizeof(u32));
+ } else {
+ __be64 tmp_cap = cpu_to_be64(le64_to_cpu(id_ns
->ncap));
+ __be32 tmp_len = cpu_to_be32(lba_length);
+
+ memcpy(resp, &tmp_cap, sizeof(u64));
+ /* Bytes 8, 9, 10, 11 are reserved */
+ memcpy(&resp[12], &tmp_len, sizeof(u32));
+ }
+
+ kfree(id_ns);
+ return res;
+}
+
+static int nvme_trans_fill_control_page(struct nvme_ns *ns,
+ struct sg_io_hdr *hdr, u8
*resp,
+ int len)
+{
+ if (len < MODE_PAGE_CONTROL_LEN)
+ return -EINVAL;
+
+ resp[0] = MODE_PAGE_CONTROL;
+ resp[1] = MODE_PAGE_CONTROL_LEN_FIELD;
+ resp[2] = 0x0E; /* TST=000b, TMF_ONLY=0,
DPICZ=1,
+ * D_SENSE=1, GLTSD=1, RLEC=0 */
+ resp[3] = 0x12; /* Q_ALGO_MODIFIER=1h, NUAR=0,
QERR=01b */
+ /* Byte 4: VS=0, RAC=0, UA_INT=0, SWP=0 */
+ resp[5] = 0x40; /* ATO=0, TAS=1, ATMPE=0,
RWWP=0, AUTOLOAD=0 */
+ /* resp[6] and [7] are obsolete, thus zero */
+ resp[8] = 0xFF; /* Busy timeout period =
0xffff */
+ resp[9] = 0xFF;
+ /* Bytes 10,11: Extended selftest completion time = 0x0000 */
+
+ return 0;
+}
+
+static int nvme_trans_fill_caching_page(struct nvme_ns *ns,
+ struct sg_io_hdr *hdr,
+ u8 *resp, int len)
+{
+ int res = 0;
+ int nvme_sc;
+ struct nvme_dev *dev = ns->dev;
+ u32 feature_resp;
+ u8 vwc;
+
+ if (len < MODE_PAGE_CACHING_LEN)
+ return -EINVAL;
+
+ nvme_sc = nvme_get_features(dev, NVME_FEAT_VOLATILE_WC, 0, 0,
+ &featu
re_resp);
+ res = nvme_trans_status_code(hdr, nvme_sc);
+ if (res)
+ return res;
+
+ vwc = feature_resp & 0x00000001;
+
+ resp[0] = MODE_PAGE_CACHING;
+ resp[1] = MODE_PAGE_CACHING_LEN_FIELD;
+ resp[2] = vwc << 2;
+ return 0;
+}
+
+static int nvme_trans_fill_pow_cnd_page(struct nvme_ns *ns,
+ struct sg_io_hdr *hdr, u8
*resp,
+ int len)
+{
+ if (len < MODE_PAGE_POW_CND_LEN)
+ return -EINVAL;
+
+ resp[0] = MODE_PAGE_POWER_CONDITION;
+ resp[1] = MODE_PAGE_POW_CND_LEN_FIELD;
+ /* All other bytes are zero */
+
+ return 0;
+}
+
+static int nvme_trans_fill_inf_exc_page(struct nvme_ns *ns,
+ struct sg_io_hdr *hdr, u8
*resp,
+ int len)
+{
+ if (len < MODE_PAGE_INF_EXC_LEN)
+ return -EINVAL;
+
+ resp[0] = MODE_PAGE_INFO_EXCEP;
+ resp[1] = MODE_PAGE_INF_EXC_LEN_FIELD;
+ resp[2] = 0x88;
+ /* All other bytes are zero */
+
+ return 0;
+}
+
+static int nvme_trans_fill_all_pages(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
+ u8 *resp, int len)
+{
+ int res;
+ u16 mode_pages_offset_1 = 0;
+ u16 mode_pages_offset_2, mode_pages_offset_3,
mode_pages_offset_4;
+
+ mode_pages_offset_2 = mode_pages_offset_1 +
MODE_PAGE_CACHING_LEN;
+ mode_pages_offset_3 = mode_pages_offset_2 +
MODE_PAGE_CONTROL_LEN;
+ mode_pages_offset_4 = mode_pages_offset_3 +
MODE_PAGE_POW_CND_LEN;
+
+ res = nvme_trans_fill_caching_page(ns, hdr,
&resp[mode_pages_offset_1],
+ MODE_PAGE_CACHING_LEN);
+ if (res)
+ return res;
+ res = nvme_trans_fill_control_page(ns, hdr,
&resp[mode_pages_offset_2],
+ MODE_PAGE_CONTROL_LEN);
+ if (res)
+ return res;
+ res = nvme_trans_fill_pow_cnd_page(ns, hdr,
&resp[mode_pages_offset_3],
+ MODE_PAGE_POW_CND_LEN);
+ if (res)
+ return res;
+ return nvme_trans_fill_inf_exc_page(ns, hdr,
&resp[mode_pages_offset_4],
+ MODE_PAGE_INF_EXC_LEN);
+}
+
+static inline int nvme_trans_get_blk_desc_len(u8 dbd, u8 llbaa)
+{
+ if (dbd == MODE_SENSE_BLK_DESC_ENABLED) {
+ /* SPC-4: len = 8 x Num_of_descriptors if llbaa = 0,
16x if 1 */
+ return 8 * (llbaa + 1) * MODE_SENSE_BLK_DESC_COUNT;
+ } else {
+ return 0;
+ }
+}
+
+static int nvme_trans_mode_page_create(struct nvme_ns *ns,
+ struct sg_io_hdr *hdr, u8
*cmd,
+ u16 alloc_len, u8 cdb10,
+ int (*mode_page_fill_func)
+ (struct nvme_ns *,
+ struct sg_io_hdr *hdr, u8 *,
int),
+ u16 mode_pages_tot_len)
+{
+ int res;
+ int xfer_len;
+ u8 *response;
+ u8 dbd, llbaa;
+ u16 resp_size;
+ int mph_size;
+ u16 mode_pages_offset_1;
+ u16 blk_desc_len, blk_desc_offset, mode_data_length;
+
+ dbd = (cmd[1] & MODE_SENSE_DBD_MASK) >> MODE_SENSE_DBD_SHIFT;
+ llbaa = (cmd[1] & MODE_SENSE_LLBAA_MASK) >>
MODE_SENSE_LLBAA_SHIFT;
+ mph_size = cdb10 ? MODE_SENSE10_MPH_SIZE :
MODE_SENSE6_MPH_SIZE;
+
+ blk_desc_len = nvme_trans_get_blk_desc_len(dbd, llbaa);
+
+ resp_size = mph_size + blk_desc_len + mode_pages_tot_len;
+ /* Refer spc4r34 Table 440 for calculation of Mode data Length
field */
+ mode_data_length = 3 + (3 * cdb10) + blk_desc_len +
mode_pages_tot_len;
+
+ blk_desc_offset = mph_size;
+ mode_pages_offset_1 = blk_desc_offset + blk_desc_len;
+
+ response = kzalloc(resp_size, GFP_KERNEL);
+ if (response == NULL) {
+ res = -ENOMEM;
+ goto out_mem;
+ }
+
+ res = nvme_trans_fill_mode_parm_hdr(&response[0], mph_size,
cdb10,
+ llbaa, mode_data_length,
blk_desc_len);
+ if (res)
+ goto out_free;
+ if (blk_desc_len > 0) {
+ res = nvme_trans_fill_blk_desc(ns, hdr,
+
&response[blk_desc_offset],
+ blk_desc_len, llbaa);
+ if (res)
+ goto out_free;
+ }
+ res = mode_page_fill_func(ns, hdr,
&response[mode_pages_offset_1],
+ mode_pages_tot_len);
+ if (res)
+ goto out_free;
+
+ xfer_len = min(alloc_len, resp_size);
+ res = nvme_trans_copy_to_user(hdr, response, xfer_len);
+
+ out_free:
+ kfree(response);
+ out_mem:
+ return res;
+}
+
+/* Read Capacity Helper Functions */
+
+static void nvme_trans_fill_read_cap(u8 *response, struct nvme_id_ns
*id_ns,
+ u8
cdb16)
+{
+ u8 flbas;
+ u32 lba_length;
+ u64 rlba;
+ u8 prot_en;
+ u8 p_type_lut[4] = {0, 0, 1, 2};
+ __be64 tmp_rlba;
+ __be32 tmp_rlba_32;
+ __be32 tmp_len;
+
+ flbas = (id_ns->flbas) & 0x0F;
+ lba_length = (1 << (id_ns->lbaf[flbas].ds));
+ rlba = le64_to_cpup(&id_ns->nsze) - 1;
+ (id_ns->dps) ? (prot_en = 0x01) : (prot_en = 0);
+
+ if (!cdb16) {
+ if (rlba > 0xFFFFFFFF)
+ rlba = 0xFFFFFFFF;
+ tmp_rlba_32 = cpu_to_be32(rlba);
+ tmp_len = cpu_to_be32(lba_length);
+ memcpy(response, &tmp_rlba_32, sizeof(u32));
+ memcpy(&response[4], &tmp_len, sizeof(u32));
+ } else {
+ tmp_rlba = cpu_to_be64(rlba);
+ tmp_len = cpu_to_be32(lba_length);
+ memcpy(response, &tmp_rlba, sizeof(u64));
+ memcpy(&response[8], &tmp_len, sizeof(u32));
+ response[12] = (p_type_lut[id_ns->dps & 0x3] << 1) |
prot_en;
+ /* P_I_Exponent = 0x0 | LBPPBE = 0x0 */
+ /* LBPME = 0 | LBPRZ = 0 | LALBA = 0x00 */
+ /* Bytes 16-31 - Reserved */
+ }
+}
+
+/* Start Stop Unit Helper Functions */
+
+static int nvme_trans_power_state(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
+ u8 pc, u8 pcmod, u8
start)
+{
+ int res;
+ int nvme_sc;
+ struct nvme_dev *dev = ns->dev;
+ struct nvme_id_ctrl *id_ctrl;
+ int lowest_pow_st; /* max npss = lowest power consumption
*/
+ unsigned ps_desired = 0;
+
+ nvme_sc = nvme_identify_ctrl(dev, &id_ctrl);
+ res = nvme_trans_status_code(hdr, nvme_sc);
+ if (res)
+ return res;
+
+ lowest_pow_st = max(POWER_STATE_0, (int)(id_ctrl->npss - 1));
+ kfree(id_ctrl);
+
+ switch (pc) {
+ case NVME_POWER_STATE_START_VALID:
+ /* Action unspecified if POWER CONDITION MODIFIER != 0
*/
+ if (pcmod == 0 && start == 0x1)
+ ps_desired = POWER_STATE_0;
+ if (pcmod == 0 && start == 0x0)
+ ps_desired = lowest_pow_st;
+ break;
+ case NVME_POWER_STATE_ACTIVE:
+ /* Action unspecified if POWER CONDITION MODIFIER != 0
*/
+ if (pcmod == 0)
+ ps_desired = POWER_STATE_0;
+ break;
+ case NVME_POWER_STATE_IDLE:
+ /* Action unspecified if POWER CONDITION MODIFIER !=
[0,1,2] */
+ if (pcmod == 0x0)
+ ps_desired = POWER_STATE_1;
+ else if (pcmod == 0x1)
+ ps_desired = POWER_STATE_2;
+ else if (pcmod == 0x2)
+ ps_desired = POWER_STATE_3;
+ break;
+ case NVME_POWER_STATE_STANDBY:
+ /* Action unspecified if POWER CONDITION MODIFIER !=
[0,1] */
+ if (pcmod == 0x0)
+ ps_desired = max(POWER_STATE_0, (lowest_pow_st
- 2));
+ else if (pcmod == 0x1)
+ ps_desired = max(POWER_STATE_0, (lowest_pow_st
- 1));
+ break;
+ case NVME_POWER_STATE_LU_CONTROL:
+ default:
+ res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
+ break;
+ }
+ nvme_sc = nvme_set_features(dev, NVME_FEAT_POWER_MGMT,
ps_desired, 0,
+ NULL);
+ return nvme_trans_status_code(hdr, nvme_sc);
+}
+
+static int nvme_trans_send_activate_fw_cmd(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
+ u8 buffer_id)
+{
+ struct nvme_command c;
+ int nvme_sc;
+
+ memset(&c, 0, sizeof(c));
+ c.common.opcode = nvme_admin_activate_fw;
+ c.common.cdw10[0] = cpu_to_le32(buffer_id |
NVME_FWACT_REPL_ACTV);
+
+ nvme_sc = nvme_submit_sync_cmd(ns->queue, &c, NULL, 0);
+ return nvme_trans_status_code(hdr, nvme_sc);
+}
+
+static int nvme_trans_send_download_fw_cmd(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
+ u8 opcode, u32 tot_len, u32
offset,
+ u8 buffer_id)
+{
+ int nvme_sc;
+ struct nvme_dev *dev = ns->dev;
+ struct nvme_command c;
+
+ if (hdr->iovec_count > 0) {
+ /* Assuming SGL is not allowed for this command */
+ return nvme_trans_completion(hdr,
+ SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
+ SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ }
+
+ memset(&c, 0, sizeof(c));
+ c.common.opcode = nvme_admin_download_fw;
+ c.dlfw.numd = cpu_to_le32((tot_len/BYTES_TO_DWORDS) - 1);
+ c.dlfw.offset = cpu_to_le32(offset/BYTES_TO_DWORDS);
+
+ nvme_sc = __nvme_submit_sync_cmd(dev->admin_q, &c, NULL,
+ hdr->dxferp, tot_len, NULL, 0);
+ return nvme_trans_status_code(hdr, nvme_sc);
+}
+
+/* Mode Select Helper Functions */
+
+static inline void nvme_trans_modesel_get_bd_len(u8 *parm_list, u8
cdb10,
+ u16 *bd_len, u8
*llbaa)
+{
+ if (cdb10) {
+ /* 10 Byte CDB */
+ *bd_len = (parm_list[MODE_SELECT_10_BD_OFFSET] << 8) +
+ parm_list[MODE_SELECT_10_BD_OFFSET + 1];
+ *llbaa = parm_list[MODE_SELECT_10_LLBAA_OFFSET] &
+ MODE_SELECT_10_LLBAA_MASK;
+ } else {
+ /* 6 Byte CDB */
+ *bd_len = parm_list[MODE_SELECT_6_BD_OFFSET];
+ }
+}
+
+static void nvme_trans_modesel_save_bd(struct nvme_ns *ns, u8
*parm_list,
+ u16 idx, u16 bd_len, u8 llbaa)
+{
+ u16 bd_num;
+
+ bd_num = bd_len / ((llbaa == 0) ?
+ SHORT_DESC_BLOCK : LONG_DESC_BLOCK);
+ /* Store block descriptor info if a FORMAT UNIT comes later */
+ /* TODO Saving 1st BD info; what to do if multiple BD
received? */
+ if (llbaa == 0) {
+ /* Standard Block Descriptor - spc4r34 7.5.5.1 */
+ ns->mode_select_num_blocks =
+ (parm_list[idx + 1] << 16) +
+ (parm_list[idx + 2] << 8) +
+ (parm_list[idx + 3]);
+
+ ns->mode_select_block_len =
+ (parm_list[idx + 5] << 16) +
+ (parm_list[idx + 6] << 8) +
+ (parm_list[idx + 7]);
+ } else {
+ /* Long LBA Block Descriptor - sbc3r27 6.4.2.3 */
+ ns->mode_select_num_blocks =
+ (((u64)parm_list[idx + 0]) << 56) +
+ (((u64)parm_list[idx + 1]) << 48) +
+ (((u64)parm_list[idx + 2]) << 40) +
+ (((u64)parm_list[idx + 3]) << 32) +
+ (((u64)parm_list[idx + 4]) << 24) +
+ (((u64)parm_list[idx + 5]) << 16) +
+ (((u64)parm_list[idx + 6]) << 8) +
+ ((u64)parm_list[idx + 7]);
+
+ ns->mode_select_block_len =
+ (parm_list[idx + 12] << 24) +
+ (parm_list[idx + 13] << 16) +
+ (parm_list[idx + 14] << 8) +
+ (parm_list[idx + 15]);
+ }
+}
+
+static int nvme_trans_modesel_get_mp(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
+ u8 *mode_page, u8 page_code)
+{
+ int res = 0;
+ int nvme_sc;
+ struct nvme_dev *dev = ns->dev;
+ unsigned dword11;
+
+ switch (page_code) {
+ case MODE_PAGE_CACHING:
+ dword11 = ((mode_page[2] & CACHING_MODE_PAGE_WCE_MASK)
? 1 : 0);
+ nvme_sc = nvme_set_features(dev,
NVME_FEAT_VOLATILE_WC, dword11,
+ 0, NULL);
+ res = nvme_trans_status_code(hdr, nvme_sc);
+ break;
+ case MODE_PAGE_CONTROL:
+ break;
+ case MODE_PAGE_POWER_CONDITION:
+ /* Verify the OS is not trying to set timers */
+ if ((mode_page[2] & 0x01) != 0 || (mode_page[3] &
0x0F) != 0) {
+ res = nvme_trans_completion(hdr,
+ SAM_STAT_CHECK_CONDITI
ON,
+ ILLEGAL_REQUEST,
+ SCSI_ASC_INVALID_PARAM
ETER,
+ SCSI_ASCQ_CAUSE_NOT_RE
PORTABLE);
+ break;
+ }
+ break;
+ default:
+ res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ break;
+ }
+
+ return res;
+}
+
+static int nvme_trans_modesel_data(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
+ u8 *cmd, u16 parm_list_len, u8
pf,
+ u8 sp, u8 cdb10)
+{
+ int res;
+ u8 *parm_list;
+ u16 bd_len;
+ u8 llbaa = 0;
+ u16 index, saved_index;
+ u8 page_code;
+ u16 mp_size;
+
+ /* Get parm list from data-in/out buffer */
+ parm_list = kmalloc(parm_list_len, GFP_KERNEL);
+ if (parm_list == NULL) {
+ res = -ENOMEM;
+ goto out;
+ }
+
+ res = nvme_trans_copy_from_user(hdr, parm_list,
parm_list_len);
+ if (res)
+ goto out_mem;
+
+ nvme_trans_modesel_get_bd_len(parm_list, cdb10, &bd_len,
&llbaa);
+ index = (cdb10) ? (MODE_SELECT_10_MPH_SIZE) :
(MODE_SELECT_6_MPH_SIZE);
+
+ if (bd_len != 0) {
+ /* Block Descriptors present, parse */
+ nvme_trans_modesel_save_bd(ns, parm_list, index,
bd_len, llbaa);
+ index += bd_len;
+ }
+ saved_index = index;
+
+ /* Multiple mode pages may be present; iterate through all */
+ /* In 1st Iteration, don't do NVME Command, only check for CDB
errors */
+ do {
+ page_code = parm_list[index] &
MODE_SELECT_PAGE_CODE_MASK;
+ mp_size = parm_list[index + 1] + 2;
+ if ((page_code != MODE_PAGE_CACHING) &&
+ (page_code != MODE_PAGE_CONTROL) &&
+ (page_code != MODE_PAGE_POWER_CONDITION)) {
+ res = nvme_trans_completion(hdr,
+ SAM_STAT_CHECK_CONDITI
ON,
+ ILLEGAL_REQUEST,
+ SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_RE
PORTABLE);
+ goto out_mem;
+ }
+ index += mp_size;
+ } while (index < parm_list_len);
+
+ /* In 2nd Iteration, do the NVME Commands */
+ index = saved_index;
+ do {
+ page_code = parm_list[index] &
MODE_SELECT_PAGE_CODE_MASK;
+ mp_size = parm_list[index + 1] + 2;
+ res = nvme_trans_modesel_get_mp(ns, hdr,
&parm_list[index],
+ page_c
ode);
+ if (res)
+ break;
+ index += mp_size;
+ } while (index < parm_list_len);
+
+ out_mem:
+ kfree(parm_list);
+ out:
+ return res;
+}
+
+/* Format Unit Helper Functions */
+
+static int nvme_trans_fmt_set_blk_size_count(struct nvme_ns *ns,
+ struct sg_io_hdr *hdr)
+{
+ int res = 0;
+ int nvme_sc;
+ struct nvme_dev *dev = ns->dev;
+ u8 flbas;
+
+ /*
+ * SCSI Expects a MODE SELECT would have been issued prior to
+ * a FORMAT UNIT, and the block size and number would be used
+ * from the block descriptor in it. If a MODE SELECT had not
+ * been issued, FORMAT shall use the current values for both.
+ */
+
+ if (ns->mode_select_num_blocks == 0 || ns
->mode_select_block_len == 0) {
+ struct nvme_id_ns *id_ns;
+
+ nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
+ res = nvme_trans_status_code(hdr, nvme_sc);
+ if (res)
+ return res;
+
+ if (ns->mode_select_num_blocks == 0)
+ ns->mode_select_num_blocks = le64_to_cpu(id_ns
->ncap);
+ if (ns->mode_select_block_len == 0) {
+ flbas = (id_ns->flbas) & 0x0F;
+ ns->mode_select_block_len =
+ (1 << (id_ns
->lbaf[flbas].ds));
+ }
+
+ kfree(id_ns);
+ }
+
+ return 0;
+}
+
+static int nvme_trans_fmt_get_parm_header(struct sg_io_hdr *hdr, u8
len,
+ u8 format_prot_info, u8
*nvme_pf_code)
+{
+ int res;
+ u8 *parm_list;
+ u8 pf_usage, pf_code;
+
+ parm_list = kmalloc(len, GFP_KERNEL);
+ if (parm_list == NULL) {
+ res = -ENOMEM;
+ goto out;
+ }
+ res = nvme_trans_copy_from_user(hdr, parm_list, len);
+ if (res)
+ goto out_mem;
+
+ if ((parm_list[FORMAT_UNIT_IMMED_OFFSET] &
+ FORMAT_UNIT_IMMED_MASK) != 0) {
+ res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ goto out_mem;
+ }
+
+ if (len == FORMAT_UNIT_LONG_PARM_LIST_LEN &&
+ (parm_list[FORMAT_UNIT_PROT_INT_OFFSET] & 0x0F) != 0) {
+ res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ goto out_mem;
+ }
+ pf_usage = parm_list[FORMAT_UNIT_PROT_FIELD_USAGE_OFFSET] &
+ FORMAT_UNIT_PROT_FIELD_USAGE_MASK;
+ pf_code = (pf_usage << 2) | format_prot_info;
+ switch (pf_code) {
+ case 0:
+ *nvme_pf_code = 0;
+ break;
+ case 2:
+ *nvme_pf_code = 1;
+ break;
+ case 3:
+ *nvme_pf_code = 2;
+ break;
+ case 7:
+ *nvme_pf_code = 3;
+ break;
+ default:
+ res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ break;
+ }
+
+ out_mem:
+ kfree(parm_list);
+ out:
+ return res;
+}
+
+static int nvme_trans_fmt_send_cmd(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
+ u8 prot_info)
+{
+ int res;
+ int nvme_sc;
+ struct nvme_dev *dev = ns->dev;
+ struct nvme_id_ns *id_ns;
+ u8 i;
+ u8 flbas, nlbaf;
+ u8 selected_lbaf = 0xFF;
+ u32 cdw10 = 0;
+ struct nvme_command c;
+
+ /* Loop thru LBAF's in id_ns to match reqd lbaf, put in cdw10
*/
+ nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
+ res = nvme_trans_status_code(hdr, nvme_sc);
+ if (res)
+ return res;
+
+ flbas = (id_ns->flbas) & 0x0F;
+ nlbaf = id_ns->nlbaf;
+
+ for (i = 0; i < nlbaf; i++) {
+ if (ns->mode_select_block_len == (1 << (id_ns
->lbaf[i].ds))) {
+ selected_lbaf = i;
+ break;
+ }
+ }
+ if (selected_lbaf > 0x0F) {
+ res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_PARAMETER,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
+ }
+ if (ns->mode_select_num_blocks != le64_to_cpu(id_ns->ncap)) {
+ res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_PARAMETER,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
+ }
+
+ cdw10 |= prot_info << 5;
+ cdw10 |= selected_lbaf & 0x0F;
+ memset(&c, 0, sizeof(c));
+ c.format.opcode = nvme_admin_format_nvm;
+ c.format.nsid = cpu_to_le32(ns->ns_id);
+ c.format.cdw10 = cpu_to_le32(cdw10);
+
+ nvme_sc = nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0);
+ res = nvme_trans_status_code(hdr, nvme_sc);
+
+ kfree(id_ns);
+ return res;
+}
+
+static inline u32 nvme_trans_io_get_num_cmds(struct sg_io_hdr *hdr,
+ struct nvme_trans_io_cdb
*cdb_info,
+ u32 max_blocks)
+{
+ /* If using iovecs, send one nvme command per vector */
+ if (hdr->iovec_count > 0)
+ return hdr->iovec_count;
+ else if (cdb_info->xfer_len > max_blocks)
+ return ((cdb_info->xfer_len - 1) / max_blocks) + 1;
+ else
+ return 1;
+}
+
+static u16 nvme_trans_io_get_control(struct nvme_ns *ns,
+ struct nvme_trans_io_cdb
*cdb_info)
+{
+ u16 control = 0;
+
+ /* When Protection information support is added, implement
here */
+
+ if (cdb_info->fua > 0)
+ control |= NVME_RW_FUA;
+
+ return control;
+}
+
+static int nvme_trans_do_nvme_io(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
+ struct nvme_trans_io_cdb *cdb_info, u8
is_write)
+{
+ int nvme_sc = NVME_SC_SUCCESS;
+ u32 num_cmds;
+ u64 unit_len;
+ u64 unit_num_blocks; /* Number of blocks to xfer in each
nvme cmd */
+ u32 retcode;
+ u32 i = 0;
+ u64 nvme_offset = 0;
+ void __user *next_mapping_addr;
+ struct nvme_command c;
+ u8 opcode = (is_write ? nvme_cmd_write : nvme_cmd_read);
+ u16 control;
+ u32 max_blocks = queue_max_hw_sectors(ns->queue);
+
+ num_cmds = nvme_trans_io_get_num_cmds(hdr, cdb_info,
max_blocks);
+
+ /*
+ * This loop handles two cases.
+ * First, when an SGL is used in the form of an iovec list:
+ * - Use iov_base as the next mapping address for the nvme
command_id
+ * - Use iov_len as the data transfer length for the
command.
+ * Second, when we have a single buffer
+ * - If larger than max_blocks, split into chunks, offset
+ * each nvme command accordingly.
+ */
+ for (i = 0; i < num_cmds; i++) {
+ memset(&c, 0, sizeof(c));
+ if (hdr->iovec_count > 0) {
+ struct sg_iovec sgl;
+
+ retcode = copy_from_user(&sgl, hdr->dxferp +
+ i * sizeof(struct sg_iovec),
+ sizeof(struct sg_iovec));
+ if (retcode)
+ return -EFAULT;
+ unit_len = sgl.iov_len;
+ unit_num_blocks = unit_len >> ns->lba_shift;
+ next_mapping_addr = sgl.iov_base;
+ } else {
+ unit_num_blocks = min((u64)max_blocks,
+ (cdb_info->xfer_len -
nvme_offset));
+ unit_len = unit_num_blocks << ns->lba_shift;
+ next_mapping_addr = hdr->dxferp +
+ ((1 << ns->lba_shift) *
nvme_offset);
+ }
+
+ c.rw.opcode = opcode;
+ c.rw.nsid = cpu_to_le32(ns->ns_id);
+ c.rw.slba = cpu_to_le64(cdb_info->lba + nvme_offset);
+ c.rw.length = cpu_to_le16(unit_num_blocks - 1);
+ control = nvme_trans_io_get_control(ns, cdb_info);
+ c.rw.control = cpu_to_le16(control);
+
+ if (get_capacity(ns->disk) - unit_num_blocks <
+ cdb_info->lba + nvme_offset) {
+ nvme_sc = NVME_SC_LBA_RANGE;
+ break;
+ }
+ nvme_sc = __nvme_submit_sync_cmd(ns->queue, &c, NULL,
+ next_mapping_addr, unit_len, NULL, 0);
+ if (nvme_sc)
+ break;
+
+ nvme_offset += unit_num_blocks;
+ }
+
+ return nvme_trans_status_code(hdr, nvme_sc);
+}
+
+
+/* SCSI Command Translation Functions */
+
+static int nvme_trans_io(struct nvme_ns *ns, struct sg_io_hdr *hdr, u8
is_write,
+ u8 *cmd)
+{
+ int res = 0;
+ struct nvme_trans_io_cdb cdb_info = { 0, };
+ u8 opcode = cmd[0];
+ u64 xfer_bytes;
+ u64 sum_iov_len = 0;
+ struct sg_iovec sgl;
+ int i;
+ size_t not_copied;
+
+ /*
+ * The FUA and WPROTECT fields are not supported in 6-byte
CDBs,
+ * but always in the same place for all others.
+ */
+ switch (opcode) {
+ case WRITE_6:
+ case READ_6:
+ break;
+ default:
+ cdb_info.fua = cmd[1] & 0x8;
+ cdb_info.prot_info = (cmd[1] & 0xe0) >> 5;
+ if (cdb_info.prot_info && !ns->pi_type) {
+ return nvme_trans_completion(hdr,
+ SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
+ SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ }
+ }
+
+ switch (opcode) {
+ case WRITE_6:
+ case READ_6:
+ cdb_info.lba = get_unaligned_be24(&cmd[1]);
+ cdb_info.xfer_len = cmd[4];
+ if (cdb_info.xfer_len == 0)
+ cdb_info.xfer_len = 256;
+ break;
+ case WRITE_10:
+ case READ_10:
+ cdb_info.lba = get_unaligned_be32(&cmd[2]);
+ cdb_info.xfer_len = get_unaligned_be16(&cmd[7]);
+ break;
+ case WRITE_12:
+ case READ_12:
+ cdb_info.lba = get_unaligned_be32(&cmd[2]);
+ cdb_info.xfer_len = get_unaligned_be32(&cmd[6]);
+ break;
+ case WRITE_16:
+ case READ_16:
+ cdb_info.lba = get_unaligned_be64(&cmd[2]);
+ cdb_info.xfer_len = get_unaligned_be32(&cmd[10]);
+ break;
+ default:
+ /* Will never really reach here */
+ res = -EIO;
+ goto out;
+ }
+
+ /* Calculate total length of transfer (in bytes) */
+ if (hdr->iovec_count > 0) {
+ for (i = 0; i < hdr->iovec_count; i++) {
+ not_copied = copy_from_user(&sgl, hdr->dxferp
+
+ i * sizeof(struct
sg_iovec),
+ sizeof(struct
sg_iovec));
+ if (not_copied)
+ return -EFAULT;
+ sum_iov_len += sgl.iov_len;
+ /* IO vector sizes should be multiples of
block size */
+ if (sgl.iov_len % (1 << ns->lba_shift) != 0) {
+ res = nvme_trans_completion(hdr,
+ SAM_STAT_CHECK_CONDITI
ON,
+ ILLEGAL_REQUEST,
+ SCSI_ASC_INVALID_PARAM
ETER,
+ SCSI_ASCQ_CAUSE_NOT_RE
PORTABLE);
+ goto out;
+ }
+ }
+ } else {
+ sum_iov_len = hdr->dxfer_len;
+ }
+
+ /* As Per sg ioctl howto, if the lengths differ, use the lower
one */
+ xfer_bytes = min(((u64)hdr->dxfer_len), sum_iov_len);
+
+ /* If block count and actual data buffer size dont match,
error out */
+ if (xfer_bytes != (cdb_info.xfer_len << ns->lba_shift)) {
+ res = -EINVAL;
+ goto out;
+ }
+
+ /* Check for 0 length transfer - it is not illegal */
+ if (cdb_info.xfer_len == 0)
+ goto out;
+
+ /* Send NVMe IO Command(s) */
+ res = nvme_trans_do_nvme_io(ns, hdr, &cdb_info, is_write);
+ if (res)
+ goto out;
+
+ out:
+ return res;
+}
+
+static int nvme_trans_inquiry(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
+ u8 *cmd)
+{
+ int res = 0;
+ u8 evpd;
+ u8 page_code;
+ int alloc_len;
+ u8 *inq_response;
+
+ evpd = cmd[1] & 0x01;
+ page_code = cmd[2];
+ alloc_len = get_unaligned_be16(&cmd[3]);
+
+ inq_response = kmalloc(max(alloc_len,
STANDARD_INQUIRY_LENGTH),
+ GFP_KERNEL);
+ if (inq_response == NULL) {
+ res = -ENOMEM;
+ goto out_mem;
+ }
+
+ if (evpd == 0) {
+ if (page_code == INQ_STANDARD_INQUIRY_PAGE) {
+ res = nvme_trans_standard_inquiry_page(ns,
hdr,
+ inq_response,
alloc_len);
+ } else {
+ res = nvme_trans_completion(hdr,
+ SAM_STAT_CHECK_CONDITI
ON,
+ ILLEGAL_REQUEST,
+ SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_RE
PORTABLE);
+ }
+ } else {
+ switch (page_code) {
+ case VPD_SUPPORTED_PAGES:
+ res = nvme_trans_supported_vpd_pages(ns, hdr,
+ inq_response,
alloc_len);
+ break;
+ case VPD_SERIAL_NUMBER:
+ res = nvme_trans_unit_serial_page(ns, hdr,
inq_response,
+ alloc_
len);
+ break;
+ case VPD_DEVICE_IDENTIFIERS:
+ res = nvme_trans_device_id_page(ns, hdr,
inq_response,
+ alloc_
len);
+ break;
+ case VPD_EXTENDED_INQUIRY:
+ res = nvme_trans_ext_inq_page(ns, hdr,
alloc_len);
+ break;
+ case VPD_BLOCK_LIMITS:
+ res = nvme_trans_bdev_limits_page(ns, hdr,
inq_response,
+ alloc_
len);
+ break;
+ case VPD_BLOCK_DEV_CHARACTERISTICS:
+ res = nvme_trans_bdev_char_page(ns, hdr,
alloc_len);
+ break;
+ default:
+ res = nvme_trans_completion(hdr,
+ SAM_STAT_CHECK_CONDITI
ON,
+ ILLEGAL_REQUEST,
+ SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_RE
PORTABLE);
+ break;
+ }
+ }
+ kfree(inq_response);
+ out_mem:
+ return res;
+}
+
+static int nvme_trans_log_sense(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
+ u8 *cmd)
+{
+ int res;
+ u16 alloc_len;
+ u8 pc;
+ u8 page_code;
+
+ if (cmd[1] != LOG_SENSE_CDB_SP_NOT_ENABLED) {
+ res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ goto out;
+ }
+
+ page_code = cmd[2] & LOG_SENSE_CDB_PAGE_CODE_MASK;
+ pc = (cmd[2] & LOG_SENSE_CDB_PC_MASK) >>
LOG_SENSE_CDB_PC_SHIFT;
+ if (pc != LOG_SENSE_CDB_PC_CUMULATIVE_VALUES) {
+ res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ goto out;
+ }
+ alloc_len = get_unaligned_be16(&cmd[7]);
+ switch (page_code) {
+ case LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE:
+ res = nvme_trans_log_supp_pages(ns, hdr, alloc_len);
+ break;
+ case LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE:
+ res = nvme_trans_log_info_exceptions(ns, hdr,
alloc_len);
+ break;
+ case LOG_PAGE_TEMPERATURE_PAGE:
+ res = nvme_trans_log_temperature(ns, hdr, alloc_len);
+ break;
+ default:
+ res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ break;
+ }
+
+ out:
+ return res;
+}
+
+static int nvme_trans_mode_select(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
+ u8 *cmd)
+{
+ u8 cdb10 = 0;
+ u16 parm_list_len;
+ u8 page_format;
+ u8 save_pages;
+
+ page_format = cmd[1] & MODE_SELECT_CDB_PAGE_FORMAT_MASK;
+ save_pages = cmd[1] & MODE_SELECT_CDB_SAVE_PAGES_MASK;
+
+ if (cmd[0] == MODE_SELECT) {
+ parm_list_len = cmd[4];
+ } else {
+ parm_list_len = cmd[7];
+ cdb10 = 1;
+ }
+
+ if (parm_list_len != 0) {
+ /*
+ * According to SPC-4 r24, a paramter list length
field of 0
+ * shall not be considered an error
+ */
+ return nvme_trans_modesel_data(ns, hdr, cmd,
parm_list_len,
+ page_format,
save_pages, cdb10);
+ }
+
+ return 0;
+}
+
+static int nvme_trans_mode_sense(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
+ u8 *cmd)
+{
+ int res = 0;
+ u16 alloc_len;
+ u8 cdb10 = 0;
+
+ if (cmd[0] == MODE_SENSE) {
+ alloc_len = cmd[4];
+ } else {
+ alloc_len = get_unaligned_be16(&cmd[7]);
+ cdb10 = 1;
+ }
+
+ if ((cmd[2] & MODE_SENSE_PAGE_CONTROL_MASK) !=
+ MODE_SENSE_PC_CURRENT_VALUES) {
+ res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ goto out;
+ }
+
+ switch (cmd[2] & MODE_SENSE_PAGE_CODE_MASK) {
+ case MODE_PAGE_CACHING:
+ res = nvme_trans_mode_page_create(ns, hdr, cmd,
alloc_len,
+ cdb10,
+ &nvme_trans_fill_cachi
ng_page,
+ MODE_PAGE_CACHING_LEN)
;
+ break;
+ case MODE_PAGE_CONTROL:
+ res = nvme_trans_mode_page_create(ns, hdr, cmd,
alloc_len,
+ cdb10,
+ &nvme_trans_fill_contr
ol_page,
+ MODE_PAGE_CONTROL_LEN)
;
+ break;
+ case MODE_PAGE_POWER_CONDITION:
+ res = nvme_trans_mode_page_create(ns, hdr, cmd,
alloc_len,
+ cdb10,
+ &nvme_trans_fill_pow_c
nd_page,
+ MODE_PAGE_POW_CND_LEN)
;
+ break;
+ case MODE_PAGE_INFO_EXCEP:
+ res = nvme_trans_mode_page_create(ns, hdr, cmd,
alloc_len,
+ cdb10,
+ &nvme_trans_fill_inf_e
xc_page,
+ MODE_PAGE_INF_EXC_LEN)
;
+ break;
+ case MODE_PAGE_RETURN_ALL:
+ res = nvme_trans_mode_page_create(ns, hdr, cmd,
alloc_len,
+ cdb10,
+ &nvme_trans_fill_all_p
ages,
+ MODE_PAGE_ALL_LEN);
+ break;
+ default:
+ res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ break;
+ }
+
+ out:
+ return res;
+}
+
+static int nvme_trans_read_capacity(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
+ u8 *cmd, u8
cdb16)
+{
+ int res;
+ int nvme_sc;
+ u32 alloc_len;
+ u32 resp_size;
+ u32 xfer_len;
+ struct nvme_dev *dev = ns->dev;
+ struct nvme_id_ns *id_ns;
+ u8 *response;
+
+ if (cdb16) {
+ alloc_len = get_unaligned_be32(&cmd[10]);
+ resp_size = READ_CAP_16_RESP_SIZE;
+ } else {
+ alloc_len = READ_CAP_10_RESP_SIZE;
+ resp_size = READ_CAP_10_RESP_SIZE;
+ }
+
+ nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
+ res = nvme_trans_status_code(hdr, nvme_sc);
+ if (res)
+ return res;
+
+ response = kzalloc(resp_size, GFP_KERNEL);
+ if (response == NULL) {
+ res = -ENOMEM;
+ goto out_free_id;
+ }
+ nvme_trans_fill_read_cap(response, id_ns, cdb16);
+
+ xfer_len = min(alloc_len, resp_size);
+ res = nvme_trans_copy_to_user(hdr, response, xfer_len);
+
+ kfree(response);
+ out_free_id:
+ kfree(id_ns);
+ return res;
+}
+
+static int nvme_trans_report_luns(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
+ u8 *cmd)
+{
+ int res;
+ int nvme_sc;
+ u32 alloc_len, xfer_len, resp_size;
+ u8 *response;
+ struct nvme_dev *dev = ns->dev;
+ struct nvme_id_ctrl *id_ctrl;
+ u32 ll_length, lun_id;
+ u8 lun_id_offset = REPORT_LUNS_FIRST_LUN_OFFSET;
+ __be32 tmp_len;
+
+ switch (cmd[2]) {
+ default:
+ return nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ case ALL_LUNS_RETURNED:
+ case ALL_WELL_KNOWN_LUNS_RETURNED:
+ case RESTRICTED_LUNS_RETURNED:
+ nvme_sc = nvme_identify_ctrl(dev, &id_ctrl);
+ res = nvme_trans_status_code(hdr, nvme_sc);
+ if (res)
+ return res;
+
+ ll_length = le32_to_cpu(id_ctrl->nn) * LUN_ENTRY_SIZE;
+ resp_size = ll_length + LUN_DATA_HEADER_SIZE;
+
+ alloc_len = get_unaligned_be32(&cmd[6]);
+ if (alloc_len < resp_size) {
+ res = nvme_trans_completion(hdr,
+ SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ goto out_free_id;
+ }
+
+ response = kzalloc(resp_size, GFP_KERNEL);
+ if (response == NULL) {
+ res = -ENOMEM;
+ goto out_free_id;
+ }
+
+ /* The first LUN ID will always be 0 per the SAM spec
*/
+ for (lun_id = 0; lun_id < le32_to_cpu(id_ctrl->nn);
lun_id++) {
+ /*
+ * Set the LUN Id and then increment to the
next LUN
+ * location in the parameter data.
+ */
+ __be64 tmp_id = cpu_to_be64(lun_id);
+ memcpy(&response[lun_id_offset], &tmp_id,
sizeof(u64));
+ lun_id_offset += LUN_ENTRY_SIZE;
+ }
+ tmp_len = cpu_to_be32(ll_length);
+ memcpy(response, &tmp_len, sizeof(u32));
+ }
+
+ xfer_len = min(alloc_len, resp_size);
+ res = nvme_trans_copy_to_user(hdr, response, xfer_len);
+
+ kfree(response);
+ out_free_id:
+ kfree(id_ctrl);
+ return res;
+}
+
+static int nvme_trans_request_sense(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
+ u8 *cmd)
+{
+ int res;
+ u8 alloc_len, xfer_len, resp_size;
+ u8 desc_format;
+ u8 *response;
+
+ desc_format = cmd[1] & 0x01;
+ alloc_len = cmd[4];
+
+ resp_size = ((desc_format) ? (DESC_FMT_SENSE_DATA_SIZE) :
+ (FIXED_FMT_SENSE_DATA_SIZE));
+ response = kzalloc(resp_size, GFP_KERNEL);
+ if (response == NULL) {
+ res = -ENOMEM;
+ goto out;
+ }
+
+ if (desc_format) {
+ /* Descriptor Format Sense Data */
+ response[0] = DESC_FORMAT_SENSE_DATA;
+ response[1] = NO_SENSE;
+ /* TODO How is LOW POWER CONDITION ON handled? (byte
2) */
+ response[2] = SCSI_ASC_NO_SENSE;
+ response[3] = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ /* SDAT_OVFL = 0 | Additional Sense Length = 0 */
+ } else {
+ /* Fixed Format Sense Data */
+ response[0] = FIXED_SENSE_DATA;
+ /* Byte 1 = Obsolete */
+ response[2] = NO_SENSE; /* FM, EOM, ILI, SDAT_OVFL = 0
*/
+ /* Bytes 3-6 - Information - set to zero */
+ response[7] = FIXED_SENSE_DATA_ADD_LENGTH;
+ /* Bytes 8-11 - Cmd Specific Information - set to zero
*/
+ response[12] = SCSI_ASC_NO_SENSE;
+ response[13] = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
+ /* Byte 14 = Field Replaceable Unit Code = 0 */
+ /* Bytes 15-17 - SKSV=0; Sense Key Specific = 0 */
+ }
+
+ xfer_len = min(alloc_len, resp_size);
+ res = nvme_trans_copy_to_user(hdr, response, xfer_len);
+
+ kfree(response);
+ out:
+ return res;
+}
+
+static int nvme_trans_security_protocol(struct nvme_ns *ns,
+ struct sg_io_hdr *hdr,
+ u8 *cmd)
+{
+ return nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_ILLEGAL_COMMAND,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
+}
+
+static int nvme_trans_synchronize_cache(struct nvme_ns *ns,
+ struct sg_io_hdr *hdr)
+{
+ int nvme_sc;
+ struct nvme_command c;
+
+ memset(&c, 0, sizeof(c));
+ c.common.opcode = nvme_cmd_flush;
+ c.common.nsid = cpu_to_le32(ns->ns_id);
+
+ nvme_sc = nvme_submit_sync_cmd(ns->queue, &c, NULL, 0);
+ return nvme_trans_status_code(hdr, nvme_sc);
+}
+
+static int nvme_trans_start_stop(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
+ u8 *cmd)
+{
+ u8 immed, pcmod, pc, no_flush, start;
+
+ immed = cmd[1] & 0x01;
+ pcmod = cmd[3] & 0x0f;
+ pc = (cmd[4] & 0xf0) >> 4;
+ no_flush = cmd[4] & 0x04;
+ start = cmd[4] & 0x01;
+
+ if (immed != 0) {
+ return nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ } else {
+ if (no_flush == 0) {
+ /* Issue NVME FLUSH command prior to START
STOP UNIT */
+ int res = nvme_trans_synchronize_cache(ns,
hdr);
+ if (res)
+ return res;
+ }
+ /* Setup the expected power state transition */
+ return nvme_trans_power_state(ns, hdr, pc, pcmod,
start);
+ }
+}
+
+static int nvme_trans_format_unit(struct nvme_ns *ns, struct sg_io_hdr
*hdr,
+ u8 *cmd)
+{
+ int res;
+ u8 parm_hdr_len = 0;
+ u8 nvme_pf_code = 0;
+ u8 format_prot_info, long_list, format_data;
+
+ format_prot_info = (cmd[1] & 0xc0) >> 6;
+ long_list = cmd[1] & 0x20;
+ format_data = cmd[1] & 0x10;
+
+ if (format_data != 0) {
+ if (format_prot_info != 0) {
+ if (long_list == 0)
+ parm_hdr_len =
FORMAT_UNIT_SHORT_PARM_LIST_LEN;
+ else
+ parm_hdr_len =
FORMAT_UNIT_LONG_PARM_LIST_LEN;
+ }
+ } else if (format_data == 0 && format_prot_info != 0) {
+ res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ goto out;
+ }
+
+ /* Get parm header from data-in/out buffer */
+ /*
+ * According to the translation spec, the only fields in the
parameter
+ * list we are concerned with are in the header. So allocate
only that.
+ */
+ if (parm_hdr_len > 0) {
+ res = nvme_trans_fmt_get_parm_header(hdr,
parm_hdr_len,
+ format_prot_info,
&nvme_pf_code);
+ if (res)
+ goto out;
+ }
+
+ /* Attempt to activate any previously downloaded firmware
image */
+ res = nvme_trans_send_activate_fw_cmd(ns, hdr, 0);
+
+ /* Determine Block size and count and send format command */
+ res = nvme_trans_fmt_set_blk_size_count(ns, hdr);
+ if (res)
+ goto out;
+
+ res = nvme_trans_fmt_send_cmd(ns, hdr, nvme_pf_code);
+
+ out:
+ return res;
+}
+
+static int nvme_trans_test_unit_ready(struct nvme_ns *ns,
+ struct sg_io_hdr *hdr,
+ u8 *cmd)
+{
+ struct nvme_dev *dev = ns->dev;
+
+ if (!(readl(&dev->bar->csts) & NVME_CSTS_RDY))
+ return nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ NOT_READY,
SCSI_ASC_LUN_NOT_READY,
+
SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
+ else
+ return nvme_trans_completion(hdr, SAM_STAT_GOOD,
NO_SENSE, 0, 0);
+}
+
+static int nvme_trans_write_buffer(struct nvme_ns *ns, struct
sg_io_hdr *hdr,
+ u8 *cmd)
+{
+ int res = 0;
+ u32 buffer_offset, parm_list_length;
+ u8 buffer_id, mode;
+
+ parm_list_length = get_unaligned_be24(&cmd[6]);
+ if (parm_list_length % BYTES_TO_DWORDS != 0) {
+ /* NVMe expects Firmware file to be a whole number of
DWORDS */
+ res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ goto out;
+ }
+ buffer_id = cmd[2];
+ if (buffer_id > NVME_MAX_FIRMWARE_SLOT) {
+ res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ goto out;
+ }
+ mode = cmd[1] & 0x1f;
+ buffer_offset = get_unaligned_be24(&cmd[3]);
+
+ switch (mode) {
+ case DOWNLOAD_SAVE_ACTIVATE:
+ res = nvme_trans_send_download_fw_cmd(ns, hdr,
nvme_admin_download_fw,
+ parm_list_length,
buffer_offset,
+ buffer_id);
+ if (res)
+ goto out;
+ res = nvme_trans_send_activate_fw_cmd(ns, hdr,
buffer_id);
+ break;
+ case DOWNLOAD_SAVE_DEFER_ACTIVATE:
+ res = nvme_trans_send_download_fw_cmd(ns, hdr,
nvme_admin_download_fw,
+ parm_list_length,
buffer_offset,
+ buffer_id);
+ break;
+ case ACTIVATE_DEFERRED_MICROCODE:
+ res = nvme_trans_send_activate_fw_cmd(ns, hdr,
buffer_id);
+ break;
+ default:
+ res = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_INVALID_CDB,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE
);
+ break;
+ }
+
+ out:
+ return res;
+}
+
+struct scsi_unmap_blk_desc {
+ __be64 slba;
+ __be32 nlb;
+ u32 resv;
+};
+
+struct scsi_unmap_parm_list {
+ __be16 unmap_data_len;
+ __be16 unmap_blk_desc_data_len;
+ u32 resv;
+ struct scsi_unmap_blk_desc desc[0];
+};
+
+static int nvme_trans_unmap(struct nvme_ns *ns, struct sg_io_hdr *hdr,
+ u8 *cmd)
+{
+ struct scsi_unmap_parm_list *plist;
+ struct nvme_dsm_range *range;
+ struct nvme_command c;
+ int i, nvme_sc, res;
+ u16 ndesc, list_len;
+
+ list_len = get_unaligned_be16(&cmd[7]);
+ if (!list_len)
+ return -EINVAL;
+
+ plist = kmalloc(list_len, GFP_KERNEL);
+ if (!plist)
+ return -ENOMEM;
+
+ res = nvme_trans_copy_from_user(hdr, plist, list_len);
+ if (res)
+ goto out;
+
+ ndesc = be16_to_cpu(plist->unmap_blk_desc_data_len) >> 4;
+ if (!ndesc || ndesc > 256) {
+ res = -EINVAL;
+ goto out;
+ }
+
+ range = kcalloc(ndesc, sizeof(*range), GFP_KERNEL);
+ if (!range) {
+ res = -ENOMEM;
+ goto out;
+ }
+
+ for (i = 0; i < ndesc; i++) {
+ range[i].nlb = cpu_to_le32(be32_to_cpu(plist
->desc[i].nlb));
+ range[i].slba = cpu_to_le64(be64_to_cpu(plist
->desc[i].slba));
+ range[i].cattr = 0;
+ }
+
+ memset(&c, 0, sizeof(c));
+ c.dsm.opcode = nvme_cmd_dsm;
+ c.dsm.nsid = cpu_to_le32(ns->ns_id);
+ c.dsm.nr = cpu_to_le32(ndesc - 1);
+ c.dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
+
+ nvme_sc = nvme_submit_sync_cmd(ns->queue, &c, range,
+ ndesc * sizeof(*range));
+ res = nvme_trans_status_code(hdr, nvme_sc);
+
+ kfree(range);
+ out:
+ kfree(plist);
+ return res;
+}
+
+static int nvme_scsi_translate(struct nvme_ns *ns, struct sg_io_hdr
*hdr)
+{
+ u8 cmd[BLK_MAX_CDB];
+ int retcode;
+ unsigned int opcode;
+
+ if (hdr->cmdp == NULL)
+ return -EMSGSIZE;
+ if (copy_from_user(cmd, hdr->cmdp, hdr->cmd_len))
+ return -EFAULT;
+
+ /*
+ * Prime the hdr with good status for scsi commands that don't
require
+ * an nvme command for translation.
+ */
+ retcode = nvme_trans_status_code(hdr, NVME_SC_SUCCESS);
+ if (retcode)
+ return retcode;
+
+ opcode = cmd[0];
+
+ switch (opcode) {
+ case READ_6:
+ case READ_10:
+ case READ_12:
+ case READ_16:
+ retcode = nvme_trans_io(ns, hdr, 0, cmd);
+ break;
+ case WRITE_6:
+ case WRITE_10:
+ case WRITE_12:
+ case WRITE_16:
+ retcode = nvme_trans_io(ns, hdr, 1, cmd);
+ break;
+ case INQUIRY:
+ retcode = nvme_trans_inquiry(ns, hdr, cmd);
+ break;
+ case LOG_SENSE:
+ retcode = nvme_trans_log_sense(ns, hdr, cmd);
+ break;
+ case MODE_SELECT:
+ case MODE_SELECT_10:
+ retcode = nvme_trans_mode_select(ns, hdr, cmd);
+ break;
+ case MODE_SENSE:
+ case MODE_SENSE_10:
+ retcode = nvme_trans_mode_sense(ns, hdr, cmd);
+ break;
+ case READ_CAPACITY:
+ retcode = nvme_trans_read_capacity(ns, hdr, cmd, 0);
+ break;
+ case SERVICE_ACTION_IN_16:
+ switch (cmd[1]) {
+ case SAI_READ_CAPACITY_16:
+ retcode = nvme_trans_read_capacity(ns, hdr,
cmd, 1);
+ break;
+ default:
+ goto out;
+ }
+ break;
+ case REPORT_LUNS:
+ retcode = nvme_trans_report_luns(ns, hdr, cmd);
+ break;
+ case REQUEST_SENSE:
+ retcode = nvme_trans_request_sense(ns, hdr, cmd);
+ break;
+ case SECURITY_PROTOCOL_IN:
+ case SECURITY_PROTOCOL_OUT:
+ retcode = nvme_trans_security_protocol(ns, hdr, cmd);
+ break;
+ case START_STOP:
+ retcode = nvme_trans_start_stop(ns, hdr, cmd);
+ break;
+ case SYNCHRONIZE_CACHE:
+ retcode = nvme_trans_synchronize_cache(ns, hdr);
+ break;
+ case FORMAT_UNIT:
+ retcode = nvme_trans_format_unit(ns, hdr, cmd);
+ break;
+ case TEST_UNIT_READY:
+ retcode = nvme_trans_test_unit_ready(ns, hdr, cmd);
+ break;
+ case WRITE_BUFFER:
+ retcode = nvme_trans_write_buffer(ns, hdr, cmd);
+ break;
+ case UNMAP:
+ retcode = nvme_trans_unmap(ns, hdr, cmd);
+ break;
+ default:
+ out:
+ retcode = nvme_trans_completion(hdr,
SAM_STAT_CHECK_CONDITION,
+ ILLEGAL_REQUEST,
SCSI_ASC_ILLEGAL_COMMAND,
+ SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
+ break;
+ }
+ return retcode;
+}
+
+int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr)
+{
+ struct sg_io_hdr hdr;
+ int retcode;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (copy_from_user(&hdr, u_hdr, sizeof(hdr)))
+ return -EFAULT;
+ if (hdr.interface_id != 'S')
+ return -EINVAL;
+ if (hdr.cmd_len > BLK_MAX_CDB)
+ return -EINVAL;
+
+ /*
+ * A positive return code means a NVMe status, which has been
+ * translated to sense data.
+ */
+ retcode = nvme_scsi_translate(ns, &hdr);
+ if (retcode < 0)
+ return retcode;
+ if (copy_to_user(u_hdr, &hdr, sizeof(sg_io_hdr_t)) > 0)
+ return -EFAULT;
+ return 0;
+}
+
+int nvme_sg_get_version_num(int __user *ip)
+{
+ return put_user(sg_version_num, ip);
+}
--
1.7.1
More information about the Linux-nvme
mailing list