#include <linux/acpi.h>
#include <linux/async.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/blk-mq-pci.h>
#include <linux/blk-integrity.h>
#include <linux/dmi.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/kstrtox.h>
#include <linux/memremap.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/once.h>
#include <linux/pci.h>
#include <linux/suspend.h>
#include <linux/t10-pi.h>
#include <linux/types.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/io-64-nonatomic-hi-lo.h>
#include <linux/sed-opal.h>
#include <linux/pci-p2pdma.h>
#include "trace.h"
#include "nvme.h"
#define SQ_SIZE(q) ((q)->q_depth << (q)->sqes)
#define CQ_SIZE(q) ((q)->q_depth * sizeof(struct nvme_completion))
#define SGES_PER_PAGE (NVME_CTRL_PAGE_SIZE / sizeof(struct nvme_sgl_desc))
#define NVME_MAX_KB_SZ 8192
#define NVME_MAX_SEGS 128
#define NVME_MAX_NR_ALLOCATIONS 5
static int use_threaded_interrupts;
module_param(use_threaded_interrupts, int, 0444);
static bool use_cmb_sqes = true;
module_param(use_cmb_sqes, bool, 0444);
MODULE_PARM_DESC(use_cmb_sqes, "use controller's memory buffer for I/O SQes");
static unsigned int max_host_mem_size_mb = 128;
module_param(max_host_mem_size_mb, uint, 0444);
MODULE_PARM_DESC(max_host_mem_size_mb,
"Maximum Host Memory Buffer (HMB) size per controller (in MiB)");
static unsigned int sgl_threshold = SZ_32K;
module_param(sgl_threshold, uint, 0644);
MODULE_PARM_DESC(sgl_threshold,
"Use SGLs when average request segment size is larger or equal to "
"this size. Use 0 to disable SGLs.");
#define NVME_PCI_MIN_QUEUE_SIZE 2
#define NVME_PCI_MAX_QUEUE_SIZE 4095
static int io_queue_depth_set(const char *val, const struct kernel_param *kp);
static const struct kernel_param_ops io_queue_depth_ops = {
.set = io_queue_depth_set,
.get = param_get_uint,
};
static unsigned int io_queue_depth = 1024;
module_param_cb(io_queue_depth, &io_queue_depth_ops, &io_queue_depth, 0644);
MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2 and < 4096");
static int io_queue_count_set(const char *val, const struct kernel_param *kp)
{
unsigned int n;
int ret;
ret = kstrtouint(val, 10, &n);
if (ret != 0 || n > num_possible_cpus())
return -EINVAL;
return param_set_uint(val, kp);
}
static const struct kernel_param_ops io_queue_count_ops = {
.set = io_queue_count_set,
.get = param_get_uint,
};
static unsigned int write_queues;
module_param_cb(write_queues, &io_queue_count_ops, &write_queues, 0644);
MODULE_PARM_DESC(write_queues,
"Number of queues to use for writes. If not set, reads and writes "
"will share a queue set.");
static unsigned int poll_queues;
module_param_cb(poll_queues, &io_queue_count_ops, &poll_queues, 0644);
MODULE_PARM_DESC(poll_queues, "Number of queues to use for polled IO.");
static bool noacpi;
module_param(noacpi, bool, 0444);
MODULE_PARM_DESC(noacpi, "disable acpi bios quirks");
struct nvme_dev;
struct nvme_queue;
static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown);
static void nvme_delete_io_queues(struct nvme_dev *dev);
static void nvme_update_attrs(struct nvme_dev *dev);
struct nvme_dev {
struct nvme_queue *queues;
struct blk_mq_tag_set tagset;
struct blk_mq_tag_set admin_tagset;
u32 __iomem *dbs;
struct device *dev;
struct dma_pool *prp_page_pool;
struct dma_pool *prp_small_pool;
unsigned online_queues;
unsigned max_qid;
unsigned io_queues[HCTX_MAX_TYPES];
unsigned int num_vecs;
u32 q_depth;
int io_sqes;
u32 db_stride;
void __iomem *bar;
unsigned long bar_mapped_size;
struct mutex shutdown_lock;
bool subsystem;
u64 cmb_size;
bool cmb_use_sqes;
u32 cmbsz;
u32 cmbloc;
struct nvme_ctrl ctrl;
u32 last_ps;
bool hmb;
mempool_t *iod_mempool;
__le32 *dbbuf_dbs;
dma_addr_t dbbuf_dbs_dma_addr;
__le32 *dbbuf_eis;
dma_addr_t dbbuf_eis_dma_addr;
u64 host_mem_size;
u32 nr_host_mem_descs;
dma_addr_t host_mem_descs_dma;
struct nvme_host_mem_buf_desc *host_mem_descs;
void **host_mem_desc_bufs;
unsigned int nr_allocated_queues;
unsigned int nr_write_queues;
unsigned int nr_poll_queues;
};
static int io_queue_depth_set(const char *val, const struct kernel_param *kp)
{
return param_set_uint_minmax(val, kp, NVME_PCI_MIN_QUEUE_SIZE,
NVME_PCI_MAX_QUEUE_SIZE);
}
static inline unsigned int sq_idx(unsigned int qid, u32 stride)
{
return qid * 2 * stride;
}
static inline unsigned int cq_idx(unsigned int qid, u32 stride)
{
return (qid * 2 + 1) * stride;
}
static inline struct nvme_dev *to_nvme_dev(struct nvme_ctrl *ctrl)
{
return container_of(ctrl, struct nvme_dev, ctrl);
}
struct nvme_queue {
struct nvme_dev *dev;
spinlock_t sq_lock;
void *sq_cmds;
spinlock_t cq_poll_lock ____cacheline_aligned_in_smp;
struct nvme_completion *cqes;
dma_addr_t sq_dma_addr;
dma_addr_t cq_dma_addr;
u32 __iomem *q_db;
u32 q_depth;
u16 cq_vector;
u16 sq_tail;
u16 last_sq_tail;
u16 cq_head;
u16 qid;
u8 cq_phase;
u8 sqes;
unsigned long flags;
#define NVMEQ_ENABLED 0
#define NVMEQ_SQ_CMB 1
#define NVMEQ_DELETE_ERROR 2
#define NVMEQ_POLLED 3
__le32 *dbbuf_sq_db;
__le32 *dbbuf_cq_db;
__le32 *dbbuf_sq_ei;
__le32 *dbbuf_cq_ei;
struct completion delete_done;
};
union nvme_descriptor {
struct nvme_sgl_desc *sg_list;
__le64 *prp_list;
};
struct nvme_iod {
struct nvme_request req;
struct nvme_command cmd;
bool aborted;
s8 nr_allocations;
unsigned int dma_len;
dma_addr_t first_dma;
dma_addr_t meta_dma;
struct sg_table sgt;
union nvme_descriptor list[NVME_MAX_NR_ALLOCATIONS];
};
static inline unsigned int nvme_dbbuf_size(struct nvme_dev *dev)
{
return dev->nr_allocated_queues * 8 * dev->db_stride;
}
static void nvme_dbbuf_dma_alloc(struct nvme_dev *dev)
{
unsigned int mem_size = nvme_dbbuf_size(dev);
if (!(dev->ctrl.oacs & NVME_CTRL_OACS_DBBUF_SUPP))
return;
if (dev->dbbuf_dbs) {
memset(dev->dbbuf_dbs, 0, mem_size);
memset(dev->dbbuf_eis, 0, mem_size);
return;
}
dev->dbbuf_dbs = dma_alloc_coherent(dev->dev, mem_size,
&dev->dbbuf_dbs_dma_addr,
GFP_KERNEL);
if (!dev->dbbuf_dbs)
goto fail;
dev->dbbuf_eis = dma_alloc_coherent(dev->dev, mem_size,
&dev->dbbuf_eis_dma_addr,
GFP_KERNEL);
if (!dev->dbbuf_eis)
goto fail_free_dbbuf_dbs;
return;
fail_free_dbbuf_dbs:
dma_free_coherent(dev->dev, mem_size, dev->dbbuf_dbs,
dev->dbbuf_dbs_dma_addr);
dev->dbbuf_dbs = NULL;
fail:
dev_warn(dev->dev, "unable to allocate dma for dbbuf\n");
}
static void nvme_dbbuf_dma_free(struct nvme_dev *dev)
{
unsigned int mem_size = nvme_dbbuf_size(dev);
if (dev->dbbuf_dbs) {
dma_free_coherent(dev->dev, mem_size,
dev->dbbuf_dbs, dev->dbbuf_dbs_dma_addr);
dev->dbbuf_dbs = NULL;
}
if (dev->dbbuf_eis) {
dma_free_coherent(dev->dev, mem_size,
dev->dbbuf_eis, dev->dbbuf_eis_dma_addr);
dev->dbbuf_eis = NULL;
}
}
static void nvme_dbbuf_init(struct nvme_dev *dev,
struct nvme_queue *nvmeq, int qid)
{
if (!dev->dbbuf_dbs || !qid)
return;
nvmeq->dbbuf_sq_db = &dev->dbbuf_dbs[sq_idx(qid, dev->db_stride)];
nvmeq->dbbuf_cq_db = &dev->dbbuf_dbs[cq_idx(qid, dev->db_stride)];
nvmeq->dbbuf_sq_ei = &dev->dbbuf_eis[sq_idx(qid, dev->db_stride)];
nvmeq->dbbuf_cq_ei = &dev->dbbuf_eis[cq_idx(qid, dev->db_stride)];
}
static void nvme_dbbuf_free(struct nvme_queue *nvmeq)
{
if (!nvmeq->qid)
return;
nvmeq->dbbuf_sq_db = NULL;
nvmeq->dbbuf_cq_db = NULL;
nvmeq->dbbuf_sq_ei = NULL;
nvmeq->dbbuf_cq_ei = NULL;
}
static void nvme_dbbuf_set(struct nvme_dev *dev)
{
struct nvme_command c = { };
unsigned int i;
if (!dev->dbbuf_dbs)
return;
c.dbbuf.opcode = nvme_admin_dbbuf;
c.dbbuf.prp1 = cpu_to_le64(dev->dbbuf_dbs_dma_addr);
c.dbbuf.prp2 = cpu_to_le64(dev->dbbuf_eis_dma_addr);
if (nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0)) {
dev_warn(dev->ctrl.device, "unable to set dbbuf\n");
nvme_dbbuf_dma_free(dev);
for (i = 1; i <= dev->online_queues; i++)
nvme_dbbuf_free(&dev->queues[i]);
}
}
static inline int nvme_dbbuf_need_event(u16 event_idx, u16 new_idx, u16 old)
{
return (u16)(new_idx - event_idx - 1) < (u16)(new_idx - old);
}
static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db,
volatile __le32 *dbbuf_ei)
{
if (dbbuf_db) {
u16 old_value, event_idx;
wmb();
old_value = le32_to_cpu(*dbbuf_db);
*dbbuf_db = cpu_to_le32(value);
mb();
event_idx = le32_to_cpu(*dbbuf_ei);
if (!nvme_dbbuf_need_event(event_idx, value, old_value))
return false;
}
return true;
}
static int nvme_pci_npages_prp(void)
{
unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE;
unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE);
return DIV_ROUND_UP(8 * nprps, NVME_CTRL_PAGE_SIZE - 8);
}
static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
unsigned int hctx_idx)
{
struct nvme_dev *dev = to_nvme_dev(data);
struct nvme_queue *nvmeq = &dev->queues[0];
WARN_ON(hctx_idx != 0);
WARN_ON(dev->admin_tagset.tags[0] != hctx->tags);
hctx->driver_data = nvmeq;
return 0;
}
static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
unsigned int hctx_idx)
{
struct nvme_dev *dev = to_nvme_dev(data);
struct nvme_queue *nvmeq = &dev->queues[hctx_idx + 1];
WARN_ON(dev->tagset.tags[hctx_idx] != hctx->tags);
hctx->driver_data = nvmeq;
return 0;
}
static int nvme_pci_init_request(struct blk_mq_tag_set *set,
struct request *req, unsigned int hctx_idx,
unsigned int numa_node)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
nvme_req(req)->ctrl = set->driver_data;
nvme_req(req)->cmd = &iod->cmd;
return 0;
}
static int queue_irq_offset(struct nvme_dev *dev)
{
if (dev->num_vecs > 1)
return 1;
return 0;
}
static void nvme_pci_map_queues(struct blk_mq_tag_set *set)
{
struct nvme_dev *dev = to_nvme_dev(set->driver_data);
int i, qoff, offset;
offset = queue_irq_offset(dev);
for (i = 0, qoff = 0; i < set->nr_maps; i++) {
struct blk_mq_queue_map *map = &set->map[i];
map->nr_queues = dev->io_queues[i];
if (!map->nr_queues) {
BUG_ON(i == HCTX_TYPE_DEFAULT);
continue;
}
map->queue_offset = qoff;
if (i != HCTX_TYPE_POLL && offset)
blk_mq_pci_map_queues(map, to_pci_dev(dev->dev), offset);
else
blk_mq_map_queues(map);
qoff += map->nr_queues;
offset += map->nr_queues;
}
}
static inline void nvme_write_sq_db(struct nvme_queue *nvmeq, bool write_sq)
{
if (!write_sq) {
u16 next_tail = nvmeq->sq_tail + 1;
if (next_tail == nvmeq->q_depth)
next_tail = 0;
if (next_tail != nvmeq->last_sq_tail)
return;
}
if (nvme_dbbuf_update_and_check_event(nvmeq->sq_tail,
nvmeq->dbbuf_sq_db, nvmeq->dbbuf_sq_ei))
writel(nvmeq->sq_tail, nvmeq->q_db);
nvmeq->last_sq_tail = nvmeq->sq_tail;
}
static inline void nvme_sq_copy_cmd(struct nvme_queue *nvmeq,
struct nvme_command *cmd)
{
memcpy(nvmeq->sq_cmds + (nvmeq->sq_tail << nvmeq->sqes),
absolute_pointer(cmd), sizeof(*cmd));
if (++nvmeq->sq_tail == nvmeq->q_depth)
nvmeq->sq_tail = 0;
}
static void nvme_commit_rqs(struct blk_mq_hw_ctx *hctx)
{
struct nvme_queue *nvmeq = hctx->driver_data;
spin_lock(&nvmeq->sq_lock);
if (nvmeq->sq_tail != nvmeq->last_sq_tail)
nvme_write_sq_db(nvmeq, true);
spin_unlock(&nvmeq->sq_lock);
}
static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req,
int nseg)
{
struct nvme_queue *nvmeq = req->mq_hctx->driver_data;
unsigned int avg_seg_size;
avg_seg_size = DIV_ROUND_UP(blk_rq_payload_bytes(req), nseg);
if (!nvme_ctrl_sgl_supported(&dev->ctrl))
return false;
if (!nvmeq->qid)
return false;
if (!sgl_threshold || avg_seg_size < sgl_threshold)
return false;
return true;
}
static void nvme_free_prps(struct nvme_dev *dev, struct request *req)
{
const int last_prp = NVME_CTRL_PAGE_SIZE / sizeof(__le64) - 1;
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
dma_addr_t dma_addr = iod->first_dma;
int i;
for (i = 0; i < iod->nr_allocations; i++) {
__le64 *prp_list = iod->list[i].prp_list;
dma_addr_t next_dma_addr = le64_to_cpu(prp_list[last_prp]);
dma_pool_free(dev->prp_page_pool, prp_list, dma_addr);
dma_addr = next_dma_addr;
}
}
static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
if (iod->dma_len) {
dma_unmap_page(dev->dev, iod->first_dma, iod->dma_len,
rq_dma_dir(req));
return;
}
WARN_ON_ONCE(!iod->sgt.nents);
dma_unmap_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req), 0);
if (iod->nr_allocations == 0)
dma_pool_free(dev->prp_small_pool, iod->list[0].sg_list,
iod->first_dma);
else if (iod->nr_allocations == 1)
dma_pool_free(dev->prp_page_pool, iod->list[0].sg_list,
iod->first_dma);
else
nvme_free_prps(dev, req);
mempool_free(iod->sgt.sgl, dev->iod_mempool);
}
static void nvme_print_sgl(struct scatterlist *sgl, int nents)
{
int i;
struct scatterlist *sg;
for_each_sg(sgl, sg, nents, i) {
dma_addr_t phys = sg_phys(sg);
pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d "
"dma_address:%pad dma_length:%d\n",
i, &phys, sg->offset, sg->length, &sg_dma_address(sg),
sg_dma_len(sg));
}
}
static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev,
struct request *req, struct nvme_rw_command *cmnd)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
struct dma_pool *pool;
int length = blk_rq_payload_bytes(req);
struct scatterlist *sg = iod->sgt.sgl;
int dma_len = sg_dma_len(sg);
u64 dma_addr = sg_dma_address(sg);
int offset = dma_addr & (NVME_CTRL_PAGE_SIZE - 1);
__le64 *prp_list;
dma_addr_t prp_dma;
int nprps, i;
length -= (NVME_CTRL_PAGE_SIZE - offset);
if (length <= 0) {
iod->first_dma = 0;
goto done;
}
dma_len -= (NVME_CTRL_PAGE_SIZE - offset);
if (dma_len) {
dma_addr += (NVME_CTRL_PAGE_SIZE - offset);
} else {
sg = sg_next(sg);
dma_addr = sg_dma_address(sg);
dma_len = sg_dma_len(sg);
}
if (length <= NVME_CTRL_PAGE_SIZE) {
iod->first_dma = dma_addr;
goto done;
}
nprps = DIV_ROUND_UP(length, NVME_CTRL_PAGE_SIZE);
if (nprps <= (256 / 8)) {
pool = dev->prp_small_pool;
iod->nr_allocations = 0;
} else {
pool = dev->prp_page_pool;
iod->nr_allocations = 1;
}
prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma);
if (!prp_list) {
iod->nr_allocations = -1;
return BLK_STS_RESOURCE;
}
iod->list[0].prp_list = prp_list;
iod->first_dma = prp_dma;
i = 0;
for (;;) {
if (i == NVME_CTRL_PAGE_SIZE >> 3) {
__le64 *old_prp_list = prp_list;
prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma);
if (!prp_list)
goto free_prps;
iod->list[iod->nr_allocations++].prp_list = 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 -= NVME_CTRL_PAGE_SIZE;
dma_addr += NVME_CTRL_PAGE_SIZE;
length -= NVME_CTRL_PAGE_SIZE;
if (length <= 0)
break;
if (dma_len > 0)
continue;
if (unlikely(dma_len < 0))
goto bad_sgl;
sg = sg_next(sg);
dma_addr = sg_dma_address(sg);
dma_len = sg_dma_len(sg);
}
done:
cmnd->dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sgt.sgl));
cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma);
return BLK_STS_OK;
free_prps:
nvme_free_prps(dev, req);
return BLK_STS_RESOURCE;
bad_sgl:
WARN(DO_ONCE(nvme_print_sgl, iod->sgt.sgl, iod->sgt.nents),
"Invalid SGL for payload:%d nents:%d\n",
blk_rq_payload_bytes(req), iod->sgt.nents);
return BLK_STS_IOERR;
}
static void nvme_pci_sgl_set_data(struct nvme_sgl_desc *sge,
struct scatterlist *sg)
{
sge->addr = cpu_to_le64(sg_dma_address(sg));
sge->length = cpu_to_le32(sg_dma_len(sg));
sge->type = NVME_SGL_FMT_DATA_DESC << 4;
}
static void nvme_pci_sgl_set_seg(struct nvme_sgl_desc *sge,
dma_addr_t dma_addr, int entries)
{
sge->addr = cpu_to_le64(dma_addr);
sge->length = cpu_to_le32(entries * sizeof(*sge));
sge->type = NVME_SGL_FMT_LAST_SEG_DESC << 4;
}
static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev,
struct request *req, struct nvme_rw_command *cmd)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
struct dma_pool *pool;
struct nvme_sgl_desc *sg_list;
struct scatterlist *sg = iod->sgt.sgl;
unsigned int entries = iod->sgt.nents;
dma_addr_t sgl_dma;
int i = 0;
cmd->flags = NVME_CMD_SGL_METABUF;
if (entries == 1) {
nvme_pci_sgl_set_data(&cmd->dptr.sgl, sg);
return BLK_STS_OK;
}
if (entries <= (256 / sizeof(struct nvme_sgl_desc))) {
pool = dev->prp_small_pool;
iod->nr_allocations = 0;
} else {
pool = dev->prp_page_pool;
iod->nr_allocations = 1;
}
sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma);
if (!sg_list) {
iod->nr_allocations = -1;
return BLK_STS_RESOURCE;
}
iod->list[0].sg_list = sg_list;
iod->first_dma = sgl_dma;
nvme_pci_sgl_set_seg(&cmd->dptr.sgl, sgl_dma, entries);
do {
nvme_pci_sgl_set_data(&sg_list[i++], sg);
sg = sg_next(sg);
} while (--entries > 0);
return BLK_STS_OK;
}
static blk_status_t nvme_setup_prp_simple(struct nvme_dev *dev,
struct request *req, struct nvme_rw_command *cmnd,
struct bio_vec *bv)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
unsigned int offset = bv->bv_offset & (NVME_CTRL_PAGE_SIZE - 1);
unsigned int first_prp_len = NVME_CTRL_PAGE_SIZE - offset;
iod->first_dma = dma_map_bvec(dev->dev, bv, rq_dma_dir(req), 0);
if (dma_mapping_error(dev->dev, iod->first_dma))
return BLK_STS_RESOURCE;
iod->dma_len = bv->bv_len;
cmnd->dptr.prp1 = cpu_to_le64(iod->first_dma);
if (bv->bv_len > first_prp_len)
cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma + first_prp_len);
else
cmnd->dptr.prp2 = 0;
return BLK_STS_OK;
}
static blk_status_t nvme_setup_sgl_simple(struct nvme_dev *dev,
struct request *req, struct nvme_rw_command *cmnd,
struct bio_vec *bv)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
iod->first_dma = dma_map_bvec(dev->dev, bv, rq_dma_dir(req), 0);
if (dma_mapping_error(dev->dev, iod->first_dma))
return BLK_STS_RESOURCE;
iod->dma_len = bv->bv_len;
cmnd->flags = NVME_CMD_SGL_METABUF;
cmnd->dptr.sgl.addr = cpu_to_le64(iod->first_dma);
cmnd->dptr.sgl.length = cpu_to_le32(iod->dma_len);
cmnd->dptr.sgl.type = NVME_SGL_FMT_DATA_DESC << 4;
return BLK_STS_OK;
}
static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
struct nvme_command *cmnd)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
blk_status_t ret = BLK_STS_RESOURCE;
int rc;
if (blk_rq_nr_phys_segments(req) == 1) {
struct nvme_queue *nvmeq = req->mq_hctx->driver_data;
struct bio_vec bv = req_bvec(req);
if (!is_pci_p2pdma_page(bv.bv_page)) {
if (bv.bv_offset + bv.bv_len <= NVME_CTRL_PAGE_SIZE * 2)
return nvme_setup_prp_simple(dev, req,
&cmnd->rw, &bv);
if (nvmeq->qid && sgl_threshold &&
nvme_ctrl_sgl_supported(&dev->ctrl))
return nvme_setup_sgl_simple(dev, req,
&cmnd->rw, &bv);
}
}
iod->dma_len = 0;
iod->sgt.sgl = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
if (!iod->sgt.sgl)
return BLK_STS_RESOURCE;
sg_init_table(iod->sgt.sgl, blk_rq_nr_phys_segments(req));
iod->sgt.orig_nents = blk_rq_map_sg(req->q, req, iod->sgt.sgl);
if (!iod->sgt.orig_nents)
goto out_free_sg;
rc = dma_map_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req),
DMA_ATTR_NO_WARN);
if (rc) {
if (rc == -EREMOTEIO)
ret = BLK_STS_TARGET;
goto out_free_sg;
}
if (nvme_pci_use_sgls(dev, req, iod->sgt.nents))
ret = nvme_pci_setup_sgls(dev, req, &cmnd->rw);
else
ret = nvme_pci_setup_prps(dev, req, &cmnd->rw);
if (ret != BLK_STS_OK)
goto out_unmap_sg;
return BLK_STS_OK;
out_unmap_sg:
dma_unmap_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req), 0);
out_free_sg:
mempool_free(iod->sgt.sgl, dev->iod_mempool);
return ret;
}
static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req,
struct nvme_command *cmnd)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
iod->meta_dma = dma_map_bvec(dev->dev, rq_integrity_vec(req),
rq_dma_dir(req), 0);
if (dma_mapping_error(dev->dev, iod->meta_dma))
return BLK_STS_IOERR;
cmnd->rw.metadata = cpu_to_le64(iod->meta_dma);
return BLK_STS_OK;
}
static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
blk_status_t ret;
iod->aborted = false;
iod->nr_allocations = -1;
iod->sgt.nents = 0;
ret = nvme_setup_cmd(req->q->queuedata, req);
if (ret)
return ret;
if (blk_rq_nr_phys_segments(req)) {
ret = nvme_map_data(dev, req, &iod->cmd);
if (ret)
goto out_free_cmd;
}
if (blk_integrity_rq(req)) {
ret = nvme_map_metadata(dev, req, &iod->cmd);
if (ret)
goto out_unmap_data;
}
nvme_start_request(req);
return BLK_STS_OK;
out_unmap_data:
nvme_unmap_data(dev, req);
out_free_cmd:
nvme_cleanup_cmd(req);
return ret;
}
static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
struct nvme_queue *nvmeq = hctx->driver_data;
struct nvme_dev *dev = nvmeq->dev;
struct request *req = bd->rq;
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
blk_status_t ret;
if (unlikely(!test_bit(NVMEQ_ENABLED, &nvmeq->flags)))
return BLK_STS_IOERR;
if (unlikely(!nvme_check_ready(&dev->ctrl, req, true)))
return nvme_fail_nonready_command(&dev->ctrl, req);
ret = nvme_prep_rq(dev, req);
if (unlikely(ret))
return ret;
spin_lock(&nvmeq->sq_lock);
nvme_sq_copy_cmd(nvmeq, &iod->cmd);
nvme_write_sq_db(nvmeq, bd->last);
spin_unlock(&nvmeq->sq_lock);
return BLK_STS_OK;
}
static void nvme_submit_cmds(struct nvme_queue *nvmeq, struct request **rqlist)
{
spin_lock(&nvmeq->sq_lock);
while (!rq_list_empty(*rqlist)) {
struct request *req = rq_list_pop(rqlist);
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
nvme_sq_copy_cmd(nvmeq, &iod->cmd);
}
nvme_write_sq_db(nvmeq, true);
spin_unlock(&nvmeq->sq_lock);
}
static bool nvme_prep_rq_batch(struct nvme_queue *nvmeq, struct request *req)
{
if (unlikely(!test_bit(NVMEQ_ENABLED, &nvmeq->flags)))
return false;
if (unlikely(!nvme_check_ready(&nvmeq->dev->ctrl, req, true)))
return false;
req->mq_hctx->tags->rqs[req->tag] = req;
return nvme_prep_rq(nvmeq->dev, req) == BLK_STS_OK;
}
static void nvme_queue_rqs(struct request **rqlist)
{
struct request *req, *next, *prev = NULL;
struct request *requeue_list = NULL;
rq_list_for_each_safe(rqlist, req, next) {
struct nvme_queue *nvmeq = req->mq_hctx->driver_data;
if (!nvme_prep_rq_batch(nvmeq, req)) {
rq_list_move(rqlist, &requeue_list, req, prev);
req = prev;
if (!req)
continue;
}
if (!next || req->mq_hctx != next->mq_hctx) {
req->rq_next = NULL;
nvme_submit_cmds(nvmeq, rqlist);
*rqlist = next;
prev = NULL;
} else
prev = req;
}
*rqlist = requeue_list;
}
static __always_inline void nvme_pci_unmap_rq(struct request *req)
{
struct nvme_queue *nvmeq = req->mq_hctx->driver_data;
struct nvme_dev *dev = nvmeq->dev;
if (blk_integrity_rq(req)) {
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
dma_unmap_page(dev->dev, iod->meta_dma,
rq_integrity_vec(req)->bv_len, rq_dma_dir(req));
}
if (blk_rq_nr_phys_segments(req))
nvme_unmap_data(dev, req);
}
static void nvme_pci_complete_rq(struct request *req)
{
nvme_pci_unmap_rq(req);
nvme_complete_rq(req);
}
static void nvme_pci_complete_batch(struct io_comp_batch *iob)
{
nvme_complete_batch(iob, nvme_pci_unmap_rq);
}
static inline bool nvme_cqe_pending(struct nvme_queue *nvmeq)
{
struct nvme_completion *hcqe = &nvmeq->cqes[nvmeq->cq_head];
return (le16_to_cpu(READ_ONCE(hcqe->status)) & 1) == nvmeq->cq_phase;
}
static inline void nvme_ring_cq_doorbell(struct nvme_queue *nvmeq)
{
u16 head = nvmeq->cq_head;
if (nvme_dbbuf_update_and_check_event(head, nvmeq->dbbuf_cq_db,
nvmeq->dbbuf_cq_ei))
writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
}
static inline struct blk_mq_tags *nvme_queue_tagset(struct nvme_queue *nvmeq)
{
if (!nvmeq->qid)
return nvmeq->dev->admin_tagset.tags[0];
return nvmeq->dev->tagset.tags[nvmeq->qid - 1];
}
static inline void nvme_handle_cqe(struct nvme_queue *nvmeq,
struct io_comp_batch *iob, u16 idx)
{
struct nvme_completion *cqe = &nvmeq->cqes[idx];
__u16 command_id = READ_ONCE(cqe->command_id);
struct request *req;
if (unlikely(nvme_is_aen_req(nvmeq->qid, command_id))) {
nvme_complete_async_event(&nvmeq->dev->ctrl,
cqe->status, &cqe->result);
return;
}
req = nvme_find_rq(nvme_queue_tagset(nvmeq), command_id);
if (unlikely(!req)) {
dev_warn(nvmeq->dev->ctrl.device,
"invalid id %d completed on queue %d\n",
command_id, le16_to_cpu(cqe->sq_id));
return;
}
trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail);
if (!nvme_try_complete_req(req, cqe->status, cqe->result) &&
!blk_mq_add_to_batch(req, iob, nvme_req(req)->status,
nvme_pci_complete_batch))
nvme_pci_complete_rq(req);
}
static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
{
u32 tmp = nvmeq->cq_head + 1;
if (tmp == nvmeq->q_depth) {
nvmeq->cq_head = 0;
nvmeq->cq_phase ^= 1;
} else {
nvmeq->cq_head = tmp;
}
}
static inline int nvme_poll_cq(struct nvme_queue *nvmeq,
struct io_comp_batch *iob)
{
int found = 0;
while (nvme_cqe_pending(nvmeq)) {
found++;
dma_rmb();
nvme_handle_cqe(nvmeq, iob, nvmeq->cq_head);
nvme_update_cq_head(nvmeq);
}
if (found)
nvme_ring_cq_doorbell(nvmeq);
return found;
}
static irqreturn_t nvme_irq(int irq, void *data)
{
struct nvme_queue *nvmeq = data;
DEFINE_IO_COMP_BATCH(iob);
if (nvme_poll_cq(nvmeq, &iob)) {
if (!rq_list_empty(iob.req_list))
nvme_pci_complete_batch(&iob);
return IRQ_HANDLED;
}
return IRQ_NONE;
}
static irqreturn_t nvme_irq_check(int irq, void *data)
{
struct nvme_queue *nvmeq = data;
if (nvme_cqe_pending(nvmeq))
return IRQ_WAKE_THREAD;
return IRQ_NONE;
}
static void nvme_poll_irqdisable(struct nvme_queue *nvmeq)
{
struct pci_dev *pdev = to_pci_dev(nvmeq->dev->dev);
WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags));
disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
nvme_poll_cq(nvmeq, NULL);
enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
}
static int nvme_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
{
struct nvme_queue *nvmeq = hctx->driver_data;
bool found;
if (!nvme_cqe_pending(nvmeq))
return 0;
spin_lock(&nvmeq->cq_poll_lock);
found = nvme_poll_cq(nvmeq, iob);
spin_unlock(&nvmeq->cq_poll_lock);
return found;
}
static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl)
{
struct nvme_dev *dev = to_nvme_dev(ctrl);
struct nvme_queue *nvmeq = &dev->queues[0];
struct nvme_command c = { };
c.common.opcode = nvme_admin_async_event;
c.common.command_id = NVME_AQ_BLK_MQ_DEPTH;
spin_lock(&nvmeq->sq_lock);
nvme_sq_copy_cmd(nvmeq, &c);
nvme_write_sq_db(nvmeq, true);
spin_unlock(&nvmeq->sq_lock);
}
static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
{
struct nvme_command c = { };
c.delete_queue.opcode = opcode;
c.delete_queue.qid = cpu_to_le16(id);
return nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0);
}
static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
struct nvme_queue *nvmeq, s16 vector)
{
struct nvme_command c = { };
int flags = NVME_QUEUE_PHYS_CONTIG;
if (!test_bit(NVMEQ_POLLED, &nvmeq->flags))
flags |= NVME_CQ_IRQ_ENABLED;
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(vector);
return nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0);
}
static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
struct nvme_queue *nvmeq)
{
struct nvme_ctrl *ctrl = &dev->ctrl;
struct nvme_command c = { };
int flags = NVME_QUEUE_PHYS_CONTIG;
if (ctrl->quirks & NVME_QUIRK_MEDIUM_PRIO_SQ)
flags |= NVME_SQ_PRIO_MEDIUM;
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->ctrl.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);
}
static enum rq_end_io_ret abort_endio(struct request *req, blk_status_t error)
{
struct nvme_queue *nvmeq = req->mq_hctx->driver_data;
dev_warn(nvmeq->dev->ctrl.device,
"Abort status: 0x%x", nvme_req(req)->status);
atomic_inc(&nvmeq->dev->ctrl.abort_limit);
blk_mq_free_request(req);
return RQ_END_IO_NONE;
}
static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
{
bool nssro = dev->subsystem && (csts & NVME_CSTS_NSSRO);
switch (dev->ctrl.state) {
case NVME_CTRL_RESETTING:
case NVME_CTRL_CONNECTING:
return false;
default:
break;
}
if (!(csts & NVME_CSTS_CFS) && !nssro)
return false;
return true;
}
static void nvme_warn_reset(struct nvme_dev *dev, u32 csts)
{
u16 pci_status;
int result;
result = pci_read_config_word(to_pci_dev(dev->dev), PCI_STATUS,
&pci_status);
if (result == PCIBIOS_SUCCESSFUL)
dev_warn(dev->ctrl.device,
"controller is down; will reset: CSTS=0x%x, PCI_STATUS=0x%hx\n",
csts, pci_status);
else
dev_warn(dev->ctrl.device,
"controller is down; will reset: CSTS=0x%x, PCI_STATUS read failed (%d)\n",
csts, result);
if (csts != ~0)
return;
dev_warn(dev->ctrl.device,
"Does your device have a faulty power saving mode enabled?\n");
dev_warn(dev->ctrl.device,
"Try \"nvme_core.default_ps_max_latency_us=0 pcie_aspm=off\" and report a bug\n");
}
static enum blk_eh_timer_return nvme_timeout(struct request *req)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
struct nvme_queue *nvmeq = req->mq_hctx->driver_data;
struct nvme_dev *dev = nvmeq->dev;
struct request *abort_req;
struct nvme_command cmd = { };
u32 csts = readl(dev->bar + NVME_REG_CSTS);
mb();
if (pci_channel_offline(to_pci_dev(dev->dev)))
return BLK_EH_RESET_TIMER;
if (nvme_should_reset(dev, csts)) {
nvme_warn_reset(dev, csts);
goto disable;
}
if (test_bit(NVMEQ_POLLED, &nvmeq->flags))
nvme_poll(req->mq_hctx, NULL);
else
nvme_poll_irqdisable(nvmeq);
if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) {
dev_warn(dev->ctrl.device,
"I/O %d QID %d timeout, completion polled\n",
req->tag, nvmeq->qid);
return BLK_EH_DONE;
}
switch (dev->ctrl.state) {
case NVME_CTRL_CONNECTING:
nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
fallthrough;
case NVME_CTRL_DELETING:
dev_warn_ratelimited(dev->ctrl.device,
"I/O %d QID %d timeout, disable controller\n",
req->tag, nvmeq->qid);
nvme_req(req)->flags |= NVME_REQ_CANCELLED;
nvme_dev_disable(dev, true);
return BLK_EH_DONE;
case NVME_CTRL_RESETTING:
return BLK_EH_RESET_TIMER;
default:
break;
}
if (!nvmeq->qid || iod->aborted) {
dev_warn(dev->ctrl.device,
"I/O %d QID %d timeout, reset controller\n",
req->tag, nvmeq->qid);
nvme_req(req)->flags |= NVME_REQ_CANCELLED;
goto disable;
}
if (atomic_dec_return(&dev->ctrl.abort_limit) < 0) {
atomic_inc(&dev->ctrl.abort_limit);
return BLK_EH_RESET_TIMER;
}
iod->aborted = true;
cmd.abort.opcode = nvme_admin_abort_cmd;
cmd.abort.cid = nvme_cid(req);
cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
dev_warn(nvmeq->dev->ctrl.device,
"I/O %d (%s) QID %d timeout, aborting\n",
req->tag,
nvme_get_opcode_str(nvme_req(req)->cmd->common.opcode),
nvmeq->qid);
abort_req = blk_mq_alloc_request(dev->ctrl.admin_q, nvme_req_op(&cmd),
BLK_MQ_REQ_NOWAIT);
if (IS_ERR(abort_req)) {
atomic_inc(&dev->ctrl.abort_limit);
return BLK_EH_RESET_TIMER;
}
nvme_init_request(abort_req, &cmd);
abort_req->end_io = abort_endio;
abort_req->end_io_data = NULL;
blk_execute_rq_nowait(abort_req, false);
return BLK_EH_RESET_TIMER;
disable:
if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING))
return BLK_EH_DONE;
nvme_dev_disable(dev, false);
if (nvme_try_sched_reset(&dev->ctrl))
nvme_unquiesce_io_queues(&dev->ctrl);
return BLK_EH_DONE;
}
static void nvme_free_queue(struct nvme_queue *nvmeq)
{
dma_free_coherent(nvmeq->dev->dev, CQ_SIZE(nvmeq),
(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
if (!nvmeq->sq_cmds)
return;
if (test_and_clear_bit(NVMEQ_SQ_CMB, &nvmeq->flags)) {
pci_free_p2pmem(to_pci_dev(nvmeq->dev->dev),
nvmeq->sq_cmds, SQ_SIZE(nvmeq));
} else {
dma_free_coherent(nvmeq->dev->dev, SQ_SIZE(nvmeq),
nvmeq->sq_cmds, nvmeq->sq_dma_addr);
}
}
static void nvme_free_queues(struct nvme_dev *dev, int lowest)
{
int i;
for (i = dev->ctrl.queue_count - 1; i >= lowest; i--) {
dev->ctrl.queue_count--;
nvme_free_queue(&dev->queues[i]);
}
}
static void nvme_suspend_queue(struct nvme_dev *dev, unsigned int qid)
{
struct nvme_queue *nvmeq = &dev->queues[qid];
if (!test_and_clear_bit(NVMEQ_ENABLED, &nvmeq->flags))
return;
mb();
nvmeq->dev->online_queues--;
if (!nvmeq->qid && nvmeq->dev->ctrl.admin_q)
nvme_quiesce_admin_queue(&nvmeq->dev->ctrl);
if (!test_and_clear_bit(NVMEQ_POLLED, &nvmeq->flags))
pci_free_irq(to_pci_dev(dev->dev), nvmeq->cq_vector, nvmeq);
}
static void nvme_suspend_io_queues(struct nvme_dev *dev)
{
int i;
for (i = dev->ctrl.queue_count - 1; i > 0; i--)
nvme_suspend_queue(dev, i);
}
static void nvme_reap_pending_cqes(struct nvme_dev *dev)
{
int i;
for (i = dev->ctrl.queue_count - 1; i > 0; i--) {
spin_lock(&dev->queues[i].cq_poll_lock);
nvme_poll_cq(&dev->queues[i], NULL);
spin_unlock(&dev->queues[i].cq_poll_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,
NVME_CTRL_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, NVME_CTRL_PAGE_SIZE);
q_depth = div_u64(mem_per_q, entry_size);
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)
{
struct pci_dev *pdev = to_pci_dev(dev->dev);
if (qid && dev->cmb_use_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) {
nvmeq->sq_cmds = pci_alloc_p2pmem(pdev, SQ_SIZE(nvmeq));
if (nvmeq->sq_cmds) {
nvmeq->sq_dma_addr = pci_p2pmem_virt_to_bus(pdev,
nvmeq->sq_cmds);
if (nvmeq->sq_dma_addr) {
set_bit(NVMEQ_SQ_CMB, &nvmeq->flags);
return 0;
}
pci_free_p2pmem(pdev, nvmeq->sq_cmds, SQ_SIZE(nvmeq));
}
}
nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(nvmeq),
&nvmeq->sq_dma_addr, GFP_KERNEL);
if (!nvmeq->sq_cmds)
return -ENOMEM;
return 0;
}
static int nvme_alloc_queue(struct nvme_dev *dev, int qid, int depth)
{
struct nvme_queue *nvmeq = &dev->queues[qid];
if (dev->ctrl.queue_count > qid)
return 0;
nvmeq->sqes = qid ? dev->io_sqes : NVME_ADM_SQES;
nvmeq->q_depth = depth;
nvmeq->cqes = dma_alloc_coherent(dev->dev, CQ_SIZE(nvmeq),
&nvmeq->cq_dma_addr, GFP_KERNEL);
if (!nvmeq->cqes)
goto free_nvmeq;
if (nvme_alloc_sq_cmds(dev, nvmeq, qid))
goto free_cqdma;
nvmeq->dev = dev;
spin_lock_init(&nvmeq->sq_lock);
spin_lock_init(&nvmeq->cq_poll_lock);
nvmeq->cq_head = 0;
nvmeq->cq_phase = 1;
nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
nvmeq->qid = qid;
dev->ctrl.queue_count++;
return 0;
free_cqdma:
dma_free_coherent(dev->dev, CQ_SIZE(nvmeq), (void *)nvmeq->cqes,
nvmeq->cq_dma_addr);
free_nvmeq:
return -ENOMEM;
}
static int queue_request_irq(struct nvme_queue *nvmeq)
{
struct pci_dev *pdev = to_pci_dev(nvmeq->dev->dev);
int nr = nvmeq->dev->ctrl.instance;
if (use_threaded_interrupts) {
return pci_request_irq(pdev, nvmeq->cq_vector, nvme_irq_check,
nvme_irq, nvmeq, "nvme%dq%d", nr, nvmeq->qid);
} else {
return pci_request_irq(pdev, nvmeq->cq_vector, nvme_irq,
NULL, nvmeq, "nvme%dq%d", nr, nvmeq->qid);
}
}
static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
{
struct nvme_dev *dev = nvmeq->dev;
nvmeq->sq_tail = 0;
nvmeq->last_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));
nvme_dbbuf_init(dev, nvmeq, qid);
dev->online_queues++;
wmb();
}
static int nvme_setup_io_queues_trylock(struct nvme_dev *dev)
{
if (!mutex_trylock(&dev->shutdown_lock))
return -ENODEV;
if (dev->ctrl.state != NVME_CTRL_CONNECTING) {
mutex_unlock(&dev->shutdown_lock);
return -ENODEV;
}
return 0;
}
static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled)
{
struct nvme_dev *dev = nvmeq->dev;
int result;
u16 vector = 0;
clear_bit(NVMEQ_DELETE_ERROR, &nvmeq->flags);
if (!polled)
vector = dev->num_vecs == 1 ? 0 : qid;
else
set_bit(NVMEQ_POLLED, &nvmeq->flags);
result = adapter_alloc_cq(dev, qid, nvmeq, vector);
if (result)
return result;
result = adapter_alloc_sq(dev, qid, nvmeq);
if (result < 0)
return result;
if (result)
goto release_cq;
nvmeq->cq_vector = vector;
result = nvme_setup_io_queues_trylock(dev);
if (result)
return result;
nvme_init_queue(nvmeq, qid);
if (!polled) {
result = queue_request_irq(nvmeq);
if (result < 0)
goto release_sq;
}
set_bit(NVMEQ_ENABLED, &nvmeq->flags);
mutex_unlock(&dev->shutdown_lock);
return result;
release_sq:
dev->online_queues--;
mutex_unlock(&dev->shutdown_lock);
adapter_delete_sq(dev, qid);
release_cq:
adapter_delete_cq(dev, qid);
return result;
}
static const struct blk_mq_ops nvme_mq_admin_ops = {
.queue_rq = nvme_queue_rq,
.complete = nvme_pci_complete_rq,
.init_hctx = nvme_admin_init_hctx,
.init_request = nvme_pci_init_request,
.timeout = nvme_timeout,
};
static const struct blk_mq_ops nvme_mq_ops = {
.queue_rq = nvme_queue_rq,
.queue_rqs = nvme_queue_rqs,
.complete = nvme_pci_complete_rq,
.commit_rqs = nvme_commit_rqs,
.init_hctx = nvme_init_hctx,
.init_request = nvme_pci_init_request,
.map_queues = nvme_pci_map_queues,
.timeout = nvme_timeout,
.poll = nvme_poll,
};
static void nvme_dev_remove_admin(struct nvme_dev *dev)
{
if (dev->ctrl.admin_q && !blk_queue_dying(dev->ctrl.admin_q)) {
nvme_unquiesce_admin_queue(&dev->ctrl);
nvme_remove_admin_tag_set(&dev->ctrl);
}
}
static unsigned long db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
{
return NVME_REG_DBS + ((nr_io_queues + 1) * 8 * dev->db_stride);
}
static int nvme_remap_bar(struct nvme_dev *dev, unsigned long size)
{
struct pci_dev *pdev = to_pci_dev(dev->dev);
if (size <= dev->bar_mapped_size)
return 0;
if (size > pci_resource_len(pdev, 0))
return -ENOMEM;
if (dev->bar)
iounmap(dev->bar);
dev->bar = ioremap(pci_resource_start(pdev, 0), size);
if (!dev->bar) {
dev->bar_mapped_size = 0;
return -ENOMEM;
}
dev->bar_mapped_size = size;
dev->dbs = dev->bar + NVME_REG_DBS;
return 0;
}
static int nvme_pci_configure_admin_queue(struct nvme_dev *dev)
{
int result;
u32 aqa;
struct nvme_queue *nvmeq;
result = nvme_remap_bar(dev, db_bar_size(dev, 0));
if (result < 0)
return result;
dev->subsystem = readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 1, 0) ?
NVME_CAP_NSSRC(dev->ctrl.cap) : 0;
if (dev->subsystem &&
(readl(dev->bar + NVME_REG_CSTS) & NVME_CSTS_NSSRO))
writel(NVME_CSTS_NSSRO, dev->bar + NVME_REG_CSTS);
result = nvme_disable_ctrl(&dev->ctrl, false);
if (result < 0)
return result;
result = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH);
if (result)
return result;
dev->ctrl.numa_node = dev_to_node(dev->dev);
nvmeq = &dev->queues[0];
aqa = nvmeq->q_depth - 1;
aqa |= aqa << 16;
writel(aqa, dev->bar + NVME_REG_AQA);
lo_hi_writeq(nvmeq->sq_dma_addr, dev->bar + NVME_REG_ASQ);
lo_hi_writeq(nvmeq->cq_dma_addr, dev->bar + NVME_REG_ACQ);
result = nvme_enable_ctrl(&dev->ctrl);
if (result)
return result;
nvmeq->cq_vector = 0;
nvme_init_queue(nvmeq, 0);
result = queue_request_irq(nvmeq);
if (result) {
dev->online_queues--;
return result;
}
set_bit(NVMEQ_ENABLED, &nvmeq->flags);
return result;
}
static int nvme_create_io_queues(struct nvme_dev *dev)
{
unsigned i, max, rw_queues;
int ret = 0;
for (i = dev->ctrl.queue_count; i <= dev->max_qid; i++) {
if (nvme_alloc_queue(dev, i, dev->q_depth)) {
ret = -ENOMEM;
break;
}
}
max = min(dev->max_qid, dev->ctrl.queue_count - 1);
if (max != 1 && dev->io_queues[HCTX_TYPE_POLL]) {
rw_queues = dev->io_queues[HCTX_TYPE_DEFAULT] +
dev->io_queues[HCTX_TYPE_READ];
} else {
rw_queues = max;
}
for (i = dev->online_queues; i <= max; i++) {
bool polled = i > rw_queues;
ret = nvme_create_queue(&dev->queues[i], i, polled);
if (ret)
break;
}
return ret >= 0 ? 0 : ret;
}
static u64 nvme_cmb_size_unit(struct nvme_dev *dev)
{
u8 szu = (dev->cmbsz >> NVME_CMBSZ_SZU_SHIFT) & NVME_CMBSZ_SZU_MASK;
return 1ULL << (12 + 4 * szu);
}
static u32 nvme_cmb_size(struct nvme_dev *dev)
{
return (dev->cmbsz >> NVME_CMBSZ_SZ_SHIFT) & NVME_CMBSZ_SZ_MASK;
}
static void nvme_map_cmb(struct nvme_dev *dev)
{
u64 size, offset;
resource_size_t bar_size;
struct pci_dev *pdev = to_pci_dev(dev->dev);
int bar;
if (dev->cmb_size)
return;
if (NVME_CAP_CMBS(dev->ctrl.cap))
writel(NVME_CMBMSC_CRE, dev->bar + NVME_REG_CMBMSC);
dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ);
if (!dev->cmbsz)
return;
dev->cmbloc = readl(dev->bar + NVME_REG_CMBLOC);
size = nvme_cmb_size_unit(dev) * nvme_cmb_size(dev);
offset = nvme_cmb_size_unit(dev) * NVME_CMB_OFST(dev->cmbloc);
bar = NVME_CMB_BIR(dev->cmbloc);
bar_size = pci_resource_len(pdev, bar);
if (offset > bar_size)
return;
if (NVME_CAP_CMBS(dev->ctrl.cap)) {
hi_lo_writeq(NVME_CMBMSC_CRE | NVME_CMBMSC_CMSE |
(pci_bus_address(pdev, bar) + offset),
dev->bar + NVME_REG_CMBMSC);
}
if (size > bar_size - offset)
size = bar_size - offset;
if (pci_p2pdma_add_resource(pdev, bar, size, offset)) {
dev_warn(dev->ctrl.device,
"failed to register the CMB\n");
return;
}
dev->cmb_size = size;
dev->cmb_use_sqes = use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS);
if ((dev->cmbsz & (NVME_CMBSZ_WDS | NVME_CMBSZ_RDS)) ==
(NVME_CMBSZ_WDS | NVME_CMBSZ_RDS))
pci_p2pmem_publish(pdev, true);
nvme_update_attrs(dev);
}
static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits)
{
u32 host_mem_size = dev->host_mem_size >> NVME_CTRL_PAGE_SHIFT;
u64 dma_addr = dev->host_mem_descs_dma;
struct nvme_command c = { };
int ret;
c.features.opcode = nvme_admin_set_features;
c.features.fid = cpu_to_le32(NVME_FEAT_HOST_MEM_BUF);
c.features.dword11 = cpu_to_le32(bits);
c.features.dword12 = cpu_to_le32(host_mem_size);
c.features.dword13 = cpu_to_le32(lower_32_bits(dma_addr));
c.features.dword14 = cpu_to_le32(upper_32_bits(dma_addr));
c.features.dword15 = cpu_to_le32(dev->nr_host_mem_descs);
ret = nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0);
if (ret) {
dev_warn(dev->ctrl.device,
"failed to set host mem (err %d, flags %#x).\n",
ret, bits);
} else
dev->hmb = bits & NVME_HOST_MEM_ENABLE;
return ret;
}
static void nvme_free_host_mem(struct nvme_dev *dev)
{
int i;
for (i = 0; i < dev->nr_host_mem_descs; i++) {
struct nvme_host_mem_buf_desc *desc = &dev->host_mem_descs[i];
size_t size = le32_to_cpu(desc->size) * NVME_CTRL_PAGE_SIZE;
dma_free_attrs(dev->dev, size, dev->host_mem_desc_bufs[i],
le64_to_cpu(desc->addr),
DMA_ATTR_NO_KERNEL_MAPPING | DMA_ATTR_NO_WARN);
}
kfree(dev->host_mem_desc_bufs);
dev->host_mem_desc_bufs = NULL;
dma_free_coherent(dev->dev,
dev->nr_host_mem_descs * sizeof(*dev->host_mem_descs),
dev->host_mem_descs, dev->host_mem_descs_dma);
dev->host_mem_descs = NULL;
dev->nr_host_mem_descs = 0;
}
static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
u32 chunk_size)
{
struct nvme_host_mem_buf_desc *descs;
u32 max_entries, len;
dma_addr_t descs_dma;
int i = 0;
void **bufs;
u64 size, tmp;
tmp = (preferred + chunk_size - 1);
do_div(tmp, chunk_size);
max_entries = tmp;
if (dev->ctrl.hmmaxd && dev->ctrl.hmmaxd < max_entries)
max_entries = dev->ctrl.hmmaxd;
descs = dma_alloc_coherent(dev->dev, max_entries * sizeof(*descs),
&descs_dma, GFP_KERNEL);
if (!descs)
goto out;
bufs = kcalloc(max_entries, sizeof(*bufs), GFP_KERNEL);
if (!bufs)
goto out_free_descs;
for (size = 0; size < preferred && i < max_entries; size += len) {
dma_addr_t dma_addr;
len = min_t(u64, chunk_size, preferred - size);
bufs[i] = dma_alloc_attrs(dev->dev, len, &dma_addr, GFP_KERNEL,
DMA_ATTR_NO_KERNEL_MAPPING | DMA_ATTR_NO_WARN);
if (!bufs[i])
break;
descs[i].addr = cpu_to_le64(dma_addr);
descs[i].size = cpu_to_le32(len / NVME_CTRL_PAGE_SIZE);
i++;
}
if (!size)
goto out_free_bufs;
dev->nr_host_mem_descs = i;
dev->host_mem_size = size;
dev->host_mem_descs = descs;
dev->host_mem_descs_dma = descs_dma;
dev->host_mem_desc_bufs = bufs;
return 0;
out_free_bufs:
while (--i >= 0) {
size_t size = le32_to_cpu(descs[i].size) * NVME_CTRL_PAGE_SIZE;
dma_free_attrs(dev->dev, size, bufs[i],
le64_to_cpu(descs[i].addr),
DMA_ATTR_NO_KERNEL_MAPPING | DMA_ATTR_NO_WARN);
}
kfree(bufs);
out_free_descs:
dma_free_coherent(dev->dev, max_entries * sizeof(*descs), descs,
descs_dma);
out:
dev->host_mem_descs = NULL;
return -ENOMEM;
}
static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred)
{
u64 min_chunk = min_t(u64, preferred, PAGE_SIZE * MAX_ORDER_NR_PAGES);
u64 hmminds = max_t(u32, dev->ctrl.hmminds * 4096, PAGE_SIZE * 2);
u64 chunk_size;
for (chunk_size = min_chunk; chunk_size >= hmminds; chunk_size /= 2) {
if (!__nvme_alloc_host_mem(dev, preferred, chunk_size)) {
if (!min || dev->host_mem_size >= min)
return 0;
nvme_free_host_mem(dev);
}
}
return -ENOMEM;
}
static int nvme_setup_host_mem(struct nvme_dev *dev)
{
u64 max = (u64)max_host_mem_size_mb * SZ_1M;
u64 preferred = (u64)dev->ctrl.hmpre * 4096;
u64 min = (u64)dev->ctrl.hmmin * 4096;
u32 enable_bits = NVME_HOST_MEM_ENABLE;
int ret;
if (!dev->ctrl.hmpre)
return 0;
preferred = min(preferred, max);
if (min > max) {
dev_warn(dev->ctrl.device,
"min host memory (%lld MiB) above limit (%d MiB).\n",
min >> ilog2(SZ_1M), max_host_mem_size_mb);
nvme_free_host_mem(dev);
return 0;
}
if (dev->host_mem_descs) {
if (dev->host_mem_size >= min)
enable_bits |= NVME_HOST_MEM_RETURN;
else
nvme_free_host_mem(dev);
}
if (!dev->host_mem_descs) {
if (nvme_alloc_host_mem(dev, min, preferred)) {
dev_warn(dev->ctrl.device,
"failed to allocate host memory buffer.\n");
return 0;
}
dev_info(dev->ctrl.device,
"allocated %lld MiB host memory buffer.\n",
dev->host_mem_size >> ilog2(SZ_1M));
}
ret = nvme_set_host_mem(dev, enable_bits);
if (ret)
nvme_free_host_mem(dev);
return ret;
}
static ssize_t cmb_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
return sysfs_emit(buf, "cmbloc : x%08x\ncmbsz : x%08x\n",
ndev->cmbloc, ndev->cmbsz);
}
static DEVICE_ATTR_RO(cmb);
static ssize_t cmbloc_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
return sysfs_emit(buf, "%u\n", ndev->cmbloc);
}
static DEVICE_ATTR_RO(cmbloc);
static ssize_t cmbsz_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
return sysfs_emit(buf, "%u\n", ndev->cmbsz);
}
static DEVICE_ATTR_RO(cmbsz);
static ssize_t hmb_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
return sysfs_emit(buf, "%d\n", ndev->hmb);
}
static ssize_t hmb_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
bool new;
int ret;
if (kstrtobool(buf, &new) < 0)
return -EINVAL;
if (new == ndev->hmb)
return count;
if (new) {
ret = nvme_setup_host_mem(ndev);
} else {
ret = nvme_set_host_mem(ndev, 0);
if (!ret)
nvme_free_host_mem(ndev);
}
if (ret < 0)
return ret;
return count;
}
static DEVICE_ATTR_RW(hmb);
static umode_t nvme_pci_attrs_are_visible(struct kobject *kobj,
struct attribute *a, int n)
{
struct nvme_ctrl *ctrl =
dev_get_drvdata(container_of(kobj, struct device, kobj));
struct nvme_dev *dev = to_nvme_dev(ctrl);
if (a == &dev_attr_cmb.attr ||
a == &dev_attr_cmbloc.attr ||
a == &dev_attr_cmbsz.attr) {
if (!dev->cmbsz)
return 0;
}
if (a == &dev_attr_hmb.attr && !ctrl->hmpre)
return 0;
return a->mode;
}
static struct attribute *nvme_pci_attrs[] = {
&dev_attr_cmb.attr,
&dev_attr_cmbloc.attr,
&dev_attr_cmbsz.attr,
&dev_attr_hmb.attr,
NULL,
};
static const struct attribute_group nvme_pci_dev_attrs_group = {
.attrs = nvme_pci_attrs,
.is_visible = nvme_pci_attrs_are_visible,
};
static const struct attribute_group *nvme_pci_dev_attr_groups[] = {
&nvme_dev_attrs_group,
&nvme_pci_dev_attrs_group,
NULL,
};
static void nvme_update_attrs(struct nvme_dev *dev)
{
sysfs_update_group(&dev->ctrl.device->kobj, &nvme_pci_dev_attrs_group);
}
static void nvme_calc_irq_sets(struct irq_affinity *affd, unsigned int nrirqs)
{
struct nvme_dev *dev = affd->priv;
unsigned int nr_read_queues, nr_write_queues = dev->nr_write_queues;
if (!nrirqs) {
nrirqs = 1;
nr_read_queues = 0;
} else if (nrirqs == 1 || !nr_write_queues) {
nr_read_queues = 0;
} else if (nr_write_queues >= nrirqs) {
nr_read_queues = 1;
} else {
nr_read_queues = nrirqs - nr_write_queues;
}
dev->io_queues[HCTX_TYPE_DEFAULT] = nrirqs - nr_read_queues;
affd->set_size[HCTX_TYPE_DEFAULT] = nrirqs - nr_read_queues;
dev->io_queues[HCTX_TYPE_READ] = nr_read_queues;
affd->set_size[HCTX_TYPE_READ] = nr_read_queues;
affd->nr_sets = nr_read_queues ? 2 : 1;
}
static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
{
struct pci_dev *pdev = to_pci_dev(dev->dev);
struct irq_affinity affd = {
.pre_vectors = 1,
.calc_sets = nvme_calc_irq_sets,
.priv = dev,
};
unsigned int irq_queues, poll_queues;
poll_queues = min(dev->nr_poll_queues, nr_io_queues - 1);
dev->io_queues[HCTX_TYPE_POLL] = poll_queues;
dev->io_queues[HCTX_TYPE_DEFAULT] = 1;
dev->io_queues[HCTX_TYPE_READ] = 0;
irq_queues = 1;
if (!(dev->ctrl.quirks & NVME_QUIRK_SINGLE_VECTOR))
irq_queues += (nr_io_queues - poll_queues);
return pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues,
PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
}
static unsigned int nvme_max_io_queues(struct nvme_dev *dev)
{
if (dev->ctrl.quirks & NVME_QUIRK_SHARED_TAGS)
return 1;
return num_possible_cpus() + dev->nr_write_queues + dev->nr_poll_queues;
}
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);
unsigned int nr_io_queues;
unsigned long size;
int result;
dev->nr_write_queues = write_queues;
dev->nr_poll_queues = poll_queues;
nr_io_queues = dev->nr_allocated_queues - 1;
result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
if (result < 0)
return result;
if (nr_io_queues == 0)
return 0;
result = nvme_setup_io_queues_trylock(dev);
if (result)
return result;
if (test_and_clear_bit(NVMEQ_ENABLED, &adminq->flags))
pci_free_irq(pdev, 0, adminq);
if (dev->cmb_use_sqes) {
result = nvme_cmb_qdepth(dev, nr_io_queues,
sizeof(struct nvme_command));
if (result > 0) {
dev->q_depth = result;
dev->ctrl.sqsize = result - 1;
} else {
dev->cmb_use_sqes = false;
}
}
do {
size = db_bar_size(dev, nr_io_queues);
result = nvme_remap_bar(dev, size);
if (!result)
break;
if (!--nr_io_queues) {
result = -ENOMEM;
goto out_unlock;
}
} while (1);
adminq->q_db = dev->dbs;
retry:
if (test_and_clear_bit(NVMEQ_ENABLED, &adminq->flags))
pci_free_irq(pdev, 0, adminq);
pci_free_irq_vectors(pdev);
result = nvme_setup_irqs(dev, nr_io_queues);
if (result <= 0) {
result = -EIO;
goto out_unlock;
}
dev->num_vecs = result;
result = max(result - 1, 1);
dev->max_qid = result + dev->io_queues[HCTX_TYPE_POLL];
result = queue_request_irq(adminq);
if (result)
goto out_unlock;
set_bit(NVMEQ_ENABLED, &adminq->flags);
mutex_unlock(&dev->shutdown_lock);
result = nvme_create_io_queues(dev);
if (result || dev->online_queues < 2)
return result;
if (dev->online_queues - 1 < dev->max_qid) {
nr_io_queues = dev->online_queues - 1;
nvme_delete_io_queues(dev);
result = nvme_setup_io_queues_trylock(dev);
if (result)
return result;
nvme_suspend_io_queues(dev);
goto retry;
}
dev_info(dev->ctrl.device, "%d/%d/%d default/read/poll queues\n",
dev->io_queues[HCTX_TYPE_DEFAULT],
dev->io_queues[HCTX_TYPE_READ],
dev->io_queues[HCTX_TYPE_POLL]);
return 0;
out_unlock:
mutex_unlock(&dev->shutdown_lock);
return result;
}
static enum rq_end_io_ret nvme_del_queue_end(struct request *req,
blk_status_t error)
{
struct nvme_queue *nvmeq = req->end_io_data;
blk_mq_free_request(req);
complete(&nvmeq->delete_done);
return RQ_END_IO_NONE;
}
static enum rq_end_io_ret nvme_del_cq_end(struct request *req,
blk_status_t error)
{
struct nvme_queue *nvmeq = req->end_io_data;
if (error)
set_bit(NVMEQ_DELETE_ERROR, &nvmeq->flags);
return nvme_del_queue_end(req, error);
}
static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
{
struct request_queue *q = nvmeq->dev->ctrl.admin_q;
struct request *req;
struct nvme_command cmd = { };
cmd.delete_queue.opcode = opcode;
cmd.delete_queue.qid = cpu_to_le16(nvmeq->qid);
req = blk_mq_alloc_request(q, nvme_req_op(&cmd), BLK_MQ_REQ_NOWAIT);
if (IS_ERR(req))
return PTR_ERR(req);
nvme_init_request(req, &cmd);
if (opcode == nvme_admin_delete_cq)
req->end_io = nvme_del_cq_end;
else
req->end_io = nvme_del_queue_end;
req->end_io_data = nvmeq;
init_completion(&nvmeq->delete_done);
blk_execute_rq_nowait(req, false);
return 0;
}
static bool __nvme_delete_io_queues(struct nvme_dev *dev, u8 opcode)
{
int nr_queues = dev->online_queues - 1, sent = 0;
unsigned long timeout;
retry:
timeout = NVME_ADMIN_TIMEOUT;
while (nr_queues > 0) {
if (nvme_delete_queue(&dev->queues[nr_queues], opcode))
break;
nr_queues--;
sent++;
}
while (sent) {
struct nvme_queue *nvmeq = &dev->queues[nr_queues + sent];
timeout = wait_for_completion_io_timeout(&nvmeq->delete_done,
timeout);
if (timeout == 0)
return false;
sent--;
if (nr_queues)
goto retry;
}
return true;
}
static void nvme_delete_io_queues(struct nvme_dev *dev)
{
if (__nvme_delete_io_queues(dev, nvme_admin_delete_sq))
__nvme_delete_io_queues(dev, nvme_admin_delete_cq);
}
static unsigned int nvme_pci_nr_maps(struct nvme_dev *dev)
{
if (dev->io_queues[HCTX_TYPE_POLL])
return 3;
if (dev->io_queues[HCTX_TYPE_READ])
return 2;
return 1;
}
static void nvme_pci_update_nr_queues(struct nvme_dev *dev)
{
blk_mq_update_nr_hw_queues(&dev->tagset, dev->online_queues - 1);
nvme_free_queues(dev, dev->online_queues);
}
static int nvme_pci_enable(struct nvme_dev *dev)
{
int result = -ENOMEM;
struct pci_dev *pdev = to_pci_dev(dev->dev);
if (pci_enable_device_mem(pdev))
return result;
pci_set_master(pdev);
if (readl(dev->bar + NVME_REG_CSTS) == -1) {
result = -ENODEV;
goto disable;
}
result = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
if (result < 0)
goto disable;
dev->ctrl.cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
dev->q_depth = min_t(u32, NVME_CAP_MQES(dev->ctrl.cap) + 1,
io_queue_depth);
dev->db_stride = 1 << NVME_CAP_STRIDE(dev->ctrl.cap);
dev->dbs = dev->bar + 4096;
if (dev->ctrl.quirks & NVME_QUIRK_128_BYTES_SQES)
dev->io_sqes = 7;
else
dev->io_sqes = NVME_NVM_IOSQES;
if (pdev->vendor == PCI_VENDOR_ID_APPLE && pdev->device == 0x2001) {
dev->q_depth = 2;
dev_warn(dev->ctrl.device, "detected Apple NVMe controller, "
"set queue depth=%u to work around controller resets\n",
dev->q_depth);
} else if (pdev->vendor == PCI_VENDOR_ID_SAMSUNG &&
(pdev->device == 0xa821 || pdev->device == 0xa822) &&
NVME_CAP_MQES(dev->ctrl.cap) == 0) {
dev->q_depth = 64;
dev_err(dev->ctrl.device, "detected PM1725 NVMe controller, "
"set queue depth=%u\n", dev->q_depth);
}
if ((dev->ctrl.quirks & NVME_QUIRK_SHARED_TAGS) &&
(dev->q_depth < (NVME_AQ_DEPTH + 2))) {
dev->q_depth = NVME_AQ_DEPTH + 2;
dev_warn(dev->ctrl.device, "IO queue depth clamped to %d\n",
dev->q_depth);
}
dev->ctrl.sqsize = dev->q_depth - 1;
nvme_map_cmb(dev);
pci_save_state(pdev);
result = nvme_pci_configure_admin_queue(dev);
if (result)
goto free_irq;
return result;
free_irq:
pci_free_irq_vectors(pdev);
disable:
pci_disable_device(pdev);
return result;
}
static void nvme_dev_unmap(struct nvme_dev *dev)
{
if (dev->bar)
iounmap(dev->bar);
pci_release_mem_regions(to_pci_dev(dev->dev));
}
static bool nvme_pci_ctrl_is_dead(struct nvme_dev *dev)
{
struct pci_dev *pdev = to_pci_dev(dev->dev);
u32 csts;
if (!pci_is_enabled(pdev) || !pci_device_is_present(pdev))
return true;
if (pdev->error_state != pci_channel_io_normal)
return true;
csts = readl(dev->bar + NVME_REG_CSTS);
return (csts & NVME_CSTS_CFS) || !(csts & NVME_CSTS_RDY);
}
static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
{
struct pci_dev *pdev = to_pci_dev(dev->dev);
bool dead;
mutex_lock(&dev->shutdown_lock);
dead = nvme_pci_ctrl_is_dead(dev);
if (dev->ctrl.state == NVME_CTRL_LIVE ||
dev->ctrl.state == NVME_CTRL_RESETTING) {
if (pci_is_enabled(pdev))
nvme_start_freeze(&dev->ctrl);
if (!dead && shutdown)
nvme_wait_freeze_timeout(&dev->ctrl, NVME_IO_TIMEOUT);
}
nvme_quiesce_io_queues(&dev->ctrl);
if (!dead && dev->ctrl.queue_count > 0) {
nvme_delete_io_queues(dev);
nvme_disable_ctrl(&dev->ctrl, shutdown);
nvme_poll_irqdisable(&dev->queues[0]);
}
nvme_suspend_io_queues(dev);
nvme_suspend_queue(dev, 0);
pci_free_irq_vectors(pdev);
if (pci_is_enabled(pdev))
pci_disable_device(pdev);
nvme_reap_pending_cqes(dev);
nvme_cancel_tagset(&dev->ctrl);
nvme_cancel_admin_tagset(&dev->ctrl);
if (shutdown) {
nvme_unquiesce_io_queues(&dev->ctrl);
if (dev->ctrl.admin_q && !blk_queue_dying(dev->ctrl.admin_q))
nvme_unquiesce_admin_queue(&dev->ctrl);
}
mutex_unlock(&dev->shutdown_lock);
}
static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown)
{
if (!nvme_wait_reset(&dev->ctrl))
return -EBUSY;
nvme_dev_disable(dev, shutdown);
return 0;
}
static int nvme_setup_prp_pools(struct nvme_dev *dev)
{
dev->prp_page_pool = dma_pool_create("prp list page", dev->dev,
NVME_CTRL_PAGE_SIZE,
NVME_CTRL_PAGE_SIZE, 0);
if (!dev->prp_page_pool)
return -ENOMEM;
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 int nvme_pci_alloc_iod_mempool(struct nvme_dev *dev)
{
size_t alloc_size = sizeof(struct scatterlist) * NVME_MAX_SEGS;
dev->iod_mempool = mempool_create_node(1,
mempool_kmalloc, mempool_kfree,
(void *)alloc_size, GFP_KERNEL,
dev_to_node(dev->dev));
if (!dev->iod_mempool)
return -ENOMEM;
return 0;
}
static void nvme_free_tagset(struct nvme_dev *dev)
{
if (dev->tagset.tags)
nvme_remove_io_tag_set(&dev->ctrl);
dev->ctrl.tagset = NULL;
}
static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
{
struct nvme_dev *dev = to_nvme_dev(ctrl);
nvme_free_tagset(dev);
put_device(dev->dev);
kfree(dev->queues);
kfree(dev);
}
static void nvme_reset_work(struct work_struct *work)
{
struct nvme_dev *dev =
container_of(work, struct nvme_dev, ctrl.reset_work);
bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
int result;
if (dev->ctrl.state != NVME_CTRL_RESETTING) {
dev_warn(dev->ctrl.device, "ctrl state %d is not RESETTING\n",
dev->ctrl.state);
result = -ENODEV;
goto out;
}
if (dev->ctrl.ctrl_config & NVME_CC_ENABLE)
nvme_dev_disable(dev, false);
nvme_sync_queues(&dev->ctrl);
mutex_lock(&dev->shutdown_lock);
result = nvme_pci_enable(dev);
if (result)
goto out_unlock;
nvme_unquiesce_admin_queue(&dev->ctrl);
mutex_unlock(&dev->shutdown_lock);
if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) {
dev_warn(dev->ctrl.device,
"failed to mark controller CONNECTING\n");
result = -EBUSY;
goto out;
}
result = nvme_init_ctrl_finish(&dev->ctrl, was_suspend);
if (result)
goto out;
nvme_dbbuf_dma_alloc(dev);
result = nvme_setup_host_mem(dev);
if (result < 0)
goto out;
result = nvme_setup_io_queues(dev);
if (result)
goto out;
if (dev->online_queues > 1) {
nvme_unquiesce_io_queues(&dev->ctrl);
nvme_wait_freeze(&dev->ctrl);
nvme_pci_update_nr_queues(dev);
nvme_dbbuf_set(dev);
nvme_unfreeze(&dev->ctrl);
} else {
dev_warn(dev->ctrl.device, "IO queues lost\n");
nvme_mark_namespaces_dead(&dev->ctrl);
nvme_unquiesce_io_queues(&dev->ctrl);
nvme_remove_namespaces(&dev->ctrl);
nvme_free_tagset(dev);
}
if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_LIVE)) {
dev_warn(dev->ctrl.device,
"failed to mark controller live state\n");
result = -ENODEV;
goto out;
}
nvme_start_ctrl(&dev->ctrl);
return;
out_unlock:
mutex_unlock(&dev->shutdown_lock);
out:
dev_warn(dev->ctrl.device, "Disabling device after reset failure: %d\n",
result);
nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
nvme_dev_disable(dev, true);
nvme_sync_queues(&dev->ctrl);
nvme_mark_namespaces_dead(&dev->ctrl);
nvme_unquiesce_io_queues(&dev->ctrl);
nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DEAD);
}
static int nvme_pci_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
{
*val = readl(to_nvme_dev(ctrl)->bar + off);
return 0;
}
static int nvme_pci_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
{
writel(val, to_nvme_dev(ctrl)->bar + off);
return 0;
}
static int nvme_pci_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
{
*val = lo_hi_readq(to_nvme_dev(ctrl)->bar + off);
return 0;
}
static int nvme_pci_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
{
struct pci_dev *pdev = to_pci_dev(to_nvme_dev(ctrl)->dev);
return snprintf(buf, size, "%s\n", dev_name(&pdev->dev));
}
static void nvme_pci_print_device_info(struct nvme_ctrl *ctrl)
{
struct pci_dev *pdev = to_pci_dev(to_nvme_dev(ctrl)->dev);
struct nvme_subsystem *subsys = ctrl->subsys;
dev_err(ctrl->device,
"VID:DID %04x:%04x model:%.*s firmware:%.*s\n",
pdev->vendor, pdev->device,
nvme_strlen(subsys->model, sizeof(subsys->model)),
subsys->model, nvme_strlen(subsys->firmware_rev,
sizeof(subsys->firmware_rev)),
subsys->firmware_rev);
}
static bool nvme_pci_supports_pci_p2pdma(struct nvme_ctrl *ctrl)
{
struct nvme_dev *dev = to_nvme_dev(ctrl);
return dma_pci_p2pdma_supported(dev->dev);
}
static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
.name = "pcie",
.module = THIS_MODULE,
.flags = NVME_F_METADATA_SUPPORTED,
.dev_attr_groups = nvme_pci_dev_attr_groups,
.reg_read32 = nvme_pci_reg_read32,
.reg_write32 = nvme_pci_reg_write32,
.reg_read64 = nvme_pci_reg_read64,
.free_ctrl = nvme_pci_free_ctrl,
.submit_async_event = nvme_pci_submit_async_event,
.get_address = nvme_pci_get_address,
.print_device_info = nvme_pci_print_device_info,
.supports_pci_p2pdma = nvme_pci_supports_pci_p2pdma,
};
static int nvme_dev_map(struct nvme_dev *dev)
{
struct pci_dev *pdev = to_pci_dev(dev->dev);
if (pci_request_mem_regions(pdev, "nvme"))
return -ENODEV;
if (nvme_remap_bar(dev, NVME_REG_DBS + 4096))
goto release;
return 0;
release:
pci_release_mem_regions(pdev);
return -ENODEV;
}
static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
{
if (pdev->vendor == 0x144d && pdev->device == 0xa802) {
if (dmi_match(DMI_SYS_VENDOR, "Dell Inc.") &&
(dmi_match(DMI_PRODUCT_NAME, "XPS 15 9550") ||
dmi_match(DMI_PRODUCT_NAME, "Precision 5510")))
return NVME_QUIRK_NO_DEEPEST_PS;
} else if (pdev->vendor == 0x144d && pdev->device == 0xa804) {
if (dmi_match(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC.") &&
(dmi_match(DMI_BOARD_NAME, "PRIME B350M-A") ||
dmi_match(DMI_BOARD_NAME, "PRIME Z370-A")))
return NVME_QUIRK_NO_APST;
} else if ((pdev->vendor == 0x144d && (pdev->device == 0xa801 ||
pdev->device == 0xa808 || pdev->device == 0xa809)) ||
(pdev->vendor == 0x1e0f && pdev->device == 0x0001)) {
if ((dmi_match(DMI_BOARD_VENDOR, "LENOVO")) &&
dmi_match(DMI_BOARD_NAME, "LNVNB161216"))
return NVME_QUIRK_SIMPLE_SUSPEND;
}
return 0;
}
static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev,
const struct pci_device_id *id)
{
unsigned long quirks = id->driver_data;
int node = dev_to_node(&pdev->dev);
struct nvme_dev *dev;
int ret = -ENOMEM;
dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
if (!dev)
return ERR_PTR(-ENOMEM);
INIT_WORK(&dev->ctrl.reset_work, nvme_reset_work);
mutex_init(&dev->shutdown_lock);
dev->nr_write_queues = write_queues;
dev->nr_poll_queues = poll_queues;
dev->nr_allocated_queues = nvme_max_io_queues(dev) + 1;
dev->queues = kcalloc_node(dev->nr_allocated_queues,
sizeof(struct nvme_queue), GFP_KERNEL, node);
if (!dev->queues)
goto out_free_dev;
dev->dev = get_device(&pdev->dev);
quirks |= check_vendor_combination_bug(pdev);
if (!noacpi && acpi_storage_d3(&pdev->dev)) {
dev_info(&pdev->dev,
"platform quirk: setting simple suspend\n");
quirks |= NVME_QUIRK_SIMPLE_SUSPEND;
}
ret = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
quirks);
if (ret)
goto out_put_device;
if (dev->ctrl.quirks & NVME_QUIRK_DMA_ADDRESS_BITS_48)
dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(48));
else
dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
dma_set_min_align_mask(&pdev->dev, NVME_CTRL_PAGE_SIZE - 1);
dma_set_max_seg_size(&pdev->dev, 0xffffffff);
dev->ctrl.max_hw_sectors = min_t(u32,
NVME_MAX_KB_SZ << 1, dma_opt_mapping_size(&pdev->dev) >> 9);
dev->ctrl.max_segments = NVME_MAX_SEGS;
dev->ctrl.max_integrity_segments = 1;
return dev;
out_put_device:
put_device(dev->dev);
kfree(dev->queues);
out_free_dev:
kfree(dev);
return ERR_PTR(ret);
}
static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
struct nvme_dev *dev;
int result = -ENOMEM;
dev = nvme_pci_alloc_dev(pdev, id);
if (IS_ERR(dev))
return PTR_ERR(dev);
result = nvme_dev_map(dev);
if (result)
goto out_uninit_ctrl;
result = nvme_setup_prp_pools(dev);
if (result)
goto out_dev_unmap;
result = nvme_pci_alloc_iod_mempool(dev);
if (result)
goto out_release_prp_pools;
dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
result = nvme_pci_enable(dev);
if (result)
goto out_release_iod_mempool;
result = nvme_alloc_admin_tag_set(&dev->ctrl, &dev->admin_tagset,
&nvme_mq_admin_ops, sizeof(struct nvme_iod));
if (result)
goto out_disable;
if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) {
dev_warn(dev->ctrl.device,
"failed to mark controller CONNECTING\n");
result = -EBUSY;
goto out_disable;
}
result = nvme_init_ctrl_finish(&dev->ctrl, false);
if (result)
goto out_disable;
nvme_dbbuf_dma_alloc(dev);
result = nvme_setup_host_mem(dev);
if (result < 0)
goto out_disable;
result = nvme_setup_io_queues(dev);
if (result)
goto out_disable;
if (dev->online_queues > 1) {
nvme_alloc_io_tag_set(&dev->ctrl, &dev->tagset, &nvme_mq_ops,
nvme_pci_nr_maps(dev), sizeof(struct nvme_iod));
nvme_dbbuf_set(dev);
}
if (!dev->ctrl.tagset)
dev_warn(dev->ctrl.device, "IO queues not created\n");
if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_LIVE)) {
dev_warn(dev->ctrl.device,
"failed to mark controller live state\n");
result = -ENODEV;
goto out_disable;
}
pci_set_drvdata(pdev, dev);
nvme_start_ctrl(&dev->ctrl);
nvme_put_ctrl(&dev->ctrl);
flush_work(&dev->ctrl.scan_work);
return 0;
out_disable:
nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
nvme_dev_disable(dev, true);
nvme_free_host_mem(dev);
nvme_dev_remove_admin(dev);
nvme_dbbuf_dma_free(dev);
nvme_free_queues(dev, 0);
out_release_iod_mempool:
mempool_destroy(dev->iod_mempool);
out_release_prp_pools:
nvme_release_prp_pools(dev);
out_dev_unmap:
nvme_dev_unmap(dev);
out_uninit_ctrl:
nvme_uninit_ctrl(&dev->ctrl);
nvme_put_ctrl(&dev->ctrl);
return result;
}
static void nvme_reset_prepare(struct pci_dev *pdev)
{
struct nvme_dev *dev = pci_get_drvdata(pdev);
nvme_disable_prepare_reset(dev, false);
nvme_sync_queues(&dev->ctrl);
}
static void nvme_reset_done(struct pci_dev *pdev)
{
struct nvme_dev *dev = pci_get_drvdata(pdev);
if (!nvme_try_sched_reset(&dev->ctrl))
flush_work(&dev->ctrl.reset_work);
}
static void nvme_shutdown(struct pci_dev *pdev)
{
struct nvme_dev *dev = pci_get_drvdata(pdev);
nvme_disable_prepare_reset(dev, true);
}
static void nvme_remove(struct pci_dev *pdev)
{
struct nvme_dev *dev = pci_get_drvdata(pdev);
nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
pci_set_drvdata(pdev, NULL);
if (!pci_device_is_present(pdev)) {
nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DEAD);
nvme_dev_disable(dev, true);
}
flush_work(&dev->ctrl.reset_work);
nvme_stop_ctrl(&dev->ctrl);
nvme_remove_namespaces(&dev->ctrl);
nvme_dev_disable(dev, true);
nvme_free_host_mem(dev);
nvme_dev_remove_admin(dev);
nvme_dbbuf_dma_free(dev);
nvme_free_queues(dev, 0);
mempool_destroy(dev->iod_mempool);
nvme_release_prp_pools(dev);
nvme_dev_unmap(dev);
nvme_uninit_ctrl(&dev->ctrl);
}
#ifdef CONFIG_PM_SLEEP
static int nvme_get_power_state(struct nvme_ctrl *ctrl, u32 *ps)
{
return nvme_get_features(ctrl, NVME_FEAT_POWER_MGMT, 0, NULL, 0, ps);
}
static int nvme_set_power_state(struct nvme_ctrl *ctrl, u32 ps)
{
return nvme_set_features(ctrl, NVME_FEAT_POWER_MGMT, ps, NULL, 0, NULL);
}
static int nvme_resume(struct device *dev)
{
struct nvme_dev *ndev = pci_get_drvdata(to_pci_dev(dev));
struct nvme_ctrl *ctrl = &ndev->ctrl;
if (ndev->last_ps == U32_MAX ||
nvme_set_power_state(ctrl, ndev->last_ps) != 0)
goto reset;
if (ctrl->hmpre && nvme_setup_host_mem(ndev))
goto reset;
return 0;
reset:
return nvme_try_sched_reset(ctrl);
}
static int nvme_suspend(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
struct nvme_dev *ndev = pci_get_drvdata(pdev);
struct nvme_ctrl *ctrl = &ndev->ctrl;
int ret = -EBUSY;
ndev->last_ps = U32_MAX;
if (pm_suspend_via_firmware() || !ctrl->npss ||
!pcie_aspm_enabled(pdev) ||
(ndev->ctrl.quirks & NVME_QUIRK_SIMPLE_SUSPEND))
return nvme_disable_prepare_reset(ndev, true);
nvme_start_freeze(ctrl);
nvme_wait_freeze(ctrl);
nvme_sync_queues(ctrl);
if (ctrl->state != NVME_CTRL_LIVE)
goto unfreeze;
if (ndev->hmb) {
ret = nvme_set_host_mem(ndev, 0);
if (ret < 0)
goto unfreeze;
}
ret = nvme_get_power_state(ctrl, &ndev->last_ps);
if (ret < 0)
goto unfreeze;
pci_save_state(pdev);
ret = nvme_set_power_state(ctrl, ctrl->npss);
if (ret < 0)
goto unfreeze;
if (ret) {
pci_load_saved_state(pdev, NULL);
ret = nvme_disable_prepare_reset(ndev, true);
ctrl->npss = 0;
}
unfreeze:
nvme_unfreeze(ctrl);
return ret;
}
static int nvme_simple_suspend(struct device *dev)
{
struct nvme_dev *ndev = pci_get_drvdata(to_pci_dev(dev));
return nvme_disable_prepare_reset(ndev, true);
}
static int nvme_simple_resume(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
struct nvme_dev *ndev = pci_get_drvdata(pdev);
return nvme_try_sched_reset(&ndev->ctrl);
}
static const struct dev_pm_ops nvme_dev_pm_ops = {
.suspend = nvme_suspend,
.resume = nvme_resume,
.freeze = nvme_simple_suspend,
.thaw = nvme_simple_resume,
.poweroff = nvme_simple_suspend,
.restore = nvme_simple_resume,
};
#endif /* CONFIG_PM_SLEEP */
static pci_ers_result_t nvme_error_detected(struct pci_dev *pdev,
pci_channel_state_t state)
{
struct nvme_dev *dev = pci_get_drvdata(pdev);
switch (state) {
case pci_channel_io_normal:
return PCI_ERS_RESULT_CAN_RECOVER;
case pci_channel_io_frozen:
dev_warn(dev->ctrl.device,
"frozen state error detected, reset controller\n");
if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING)) {
nvme_dev_disable(dev, true);
return PCI_ERS_RESULT_DISCONNECT;
}
nvme_dev_disable(dev, false);
return PCI_ERS_RESULT_NEED_RESET;
case pci_channel_io_perm_failure:
dev_warn(dev->ctrl.device,
"failure state error detected, request disconnect\n");
return PCI_ERS_RESULT_DISCONNECT;
}
return PCI_ERS_RESULT_NEED_RESET;
}
static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
{
struct nvme_dev *dev = pci_get_drvdata(pdev);
dev_info(dev->ctrl.device, "restart after slot reset\n");
pci_restore_state(pdev);
if (!nvme_try_sched_reset(&dev->ctrl))
nvme_unquiesce_io_queues(&dev->ctrl);
return PCI_ERS_RESULT_RECOVERED;
}
static void nvme_error_resume(struct pci_dev *pdev)
{
struct nvme_dev *dev = pci_get_drvdata(pdev);
flush_work(&dev->ctrl.reset_work);
}
static const struct pci_error_handlers nvme_err_handler = {
.error_detected = nvme_error_detected,
.slot_reset = nvme_slot_reset,
.resume = nvme_error_resume,
.reset_prepare = nvme_reset_prepare,
.reset_done = nvme_reset_done,
};
static const struct pci_device_id nvme_id_table[] = {
{ PCI_VDEVICE(INTEL, 0x0953),
.driver_data = NVME_QUIRK_STRIPE_SIZE |
NVME_QUIRK_DEALLOCATE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0x0a53),
.driver_data = NVME_QUIRK_STRIPE_SIZE |
NVME_QUIRK_DEALLOCATE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0x0a54),
.driver_data = NVME_QUIRK_STRIPE_SIZE |
NVME_QUIRK_DEALLOCATE_ZEROES |
NVME_QUIRK_IGNORE_DEV_SUBNQN |
NVME_QUIRK_BOGUS_NID, },
{ PCI_VDEVICE(INTEL, 0x0a55),
.driver_data = NVME_QUIRK_STRIPE_SIZE |
NVME_QUIRK_DEALLOCATE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0xf1a5),
.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
NVME_QUIRK_MEDIUM_PRIO_SQ |
NVME_QUIRK_NO_TEMP_THRESH_CHANGE |
NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0xf1a6),
.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
{ PCI_VDEVICE(INTEL, 0x5845),
.driver_data = NVME_QUIRK_IDENTIFY_CNS |
NVME_QUIRK_DISABLE_WRITE_ZEROES |
NVME_QUIRK_BOGUS_NID, },
{ PCI_VDEVICE(REDHAT, 0x0010),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x126f, 0x2263),
.driver_data = NVME_QUIRK_NO_NS_DESC_LIST |
NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1bb1, 0x0100),
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY |
NVME_QUIRK_NO_NS_DESC_LIST, },
{ PCI_DEVICE(0x1c58, 0x0003),
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
{ PCI_DEVICE(0x1c58, 0x0023),
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
{ PCI_DEVICE(0x1c5f, 0x0540),
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
{ PCI_DEVICE(0x144d, 0xa821),
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
{ PCI_DEVICE(0x144d, 0xa822),
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY |
NVME_QUIRK_DISABLE_WRITE_ZEROES|
NVME_QUIRK_IGNORE_DEV_SUBNQN, },
{ PCI_DEVICE(0x1987, 0x5012),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1987, 0x5016),
.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN |
NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1987, 0x5019),
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x1987, 0x5021),
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x1b4b, 0x1092),
.driver_data = NVME_QUIRK_NO_NS_DESC_LIST |
NVME_QUIRK_IGNORE_DEV_SUBNQN, },
{ PCI_DEVICE(0x1cc1, 0x33f8),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x10ec, 0x5762),
.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN |
NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x10ec, 0x5763),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1cc1, 0x8201),
.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
NVME_QUIRK_IGNORE_DEV_SUBNQN, },
{ PCI_DEVICE(0x1344, 0x5407),
.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN },
{ PCI_DEVICE(0x1344, 0x6001),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1c5c, 0x1504),
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x1c5c, 0x174a),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x15b7, 0x2001),
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x1d97, 0x2263),
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x144d, 0xa80b),
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES |
NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x144d, 0xa809),
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x144d, 0xa802),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1cc4, 0x6303),
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x1cc4, 0x6302),
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x2646, 0x2262),
.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
{ PCI_DEVICE(0x2646, 0x2263),
.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
{ PCI_DEVICE(0x2646, 0x5013),
.driver_data = NVME_QUIRK_NO_SECONDARY_TEMP_THRESH, },
{ PCI_DEVICE(0x2646, 0x5018),
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x2646, 0x5016),
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x2646, 0x501A),
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x2646, 0x501B),
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x2646, 0x501E),
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x1f40, 0x1202),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1f40, 0x5236),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1e4B, 0x1001),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1e4B, 0x1002),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1e4B, 0x1202),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1e4B, 0x1602),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1cc1, 0x5350),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1dbe, 0x5236),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1e49, 0x0021),
.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
{ PCI_DEVICE(0x1e49, 0x0041),
.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
{ PCI_DEVICE(0xc0a9, 0x540a),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1d97, 0x2263),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1d97, 0x1d97),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1d97, 0x2269),
.driver_data = NVME_QUIRK_BOGUS_NID |
NVME_QUIRK_IGNORE_DEV_SUBNQN, },
{ PCI_DEVICE(0x10ec, 0x5763),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1e4b, 0x1602),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x10ec, 0x5765),
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061),
.driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065),
.driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x8061),
.driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0xcd00),
.driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0xcd01),
.driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0xcd02),
.driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001),
.driver_data = NVME_QUIRK_SINGLE_VECTOR },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2005),
.driver_data = NVME_QUIRK_SINGLE_VECTOR |
NVME_QUIRK_128_BYTES_SQES |
NVME_QUIRK_SHARED_TAGS |
NVME_QUIRK_SKIP_CID_GEN |
NVME_QUIRK_IDENTIFY_CNS },
{ 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 = {
.probe_type = PROBE_PREFER_ASYNCHRONOUS,
#ifdef CONFIG_PM_SLEEP
.pm = &nvme_dev_pm_ops,
#endif
},
.sriov_configure = pci_sriov_configure_simple,
.err_handler = &nvme_err_handler,
};
static int __init nvme_init(void)
{
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(IRQ_AFFINITY_MAX_SETS < 2);
BUILD_BUG_ON(NVME_MAX_SEGS > SGES_PER_PAGE);
BUILD_BUG_ON(sizeof(struct scatterlist) * NVME_MAX_SEGS > PAGE_SIZE);
BUILD_BUG_ON(nvme_pci_npages_prp() > NVME_MAX_NR_ALLOCATIONS);
return pci_register_driver(&nvme_driver);
}
static void __exit nvme_exit(void)
{
pci_unregister_driver(&nvme_driver);
flush_workqueue(nvme_wq);
}
MODULE_AUTHOR("Matthew Wilcox <willy@linux.intel.com>");
MODULE_LICENSE("GPL");
MODULE_VERSION("1.0");
module_init(nvme_init);
module_exit