*/
#include <linux/nvme.h>
-#include <linux/bio.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/module.h>
#include <linux/moduleparam.h>
#include <linux/pci.h>
-#include <linux/percpu.h>
#include <linux/poison.h>
#include <linux/ptrace.h>
#include <linux/sched.h>
#include <scsi/sg.h>
#include <asm-generic/io-64-nonatomic-lo-hi.h>
-#include <trace/events/block.h>
-
#define NVME_Q_DEPTH 1024
+#define NVME_AQ_DEPTH 64
#define SQ_SIZE(depth) (depth * sizeof(struct nvme_command))
#define CQ_SIZE(depth) (depth * sizeof(struct nvme_completion))
#define ADMIN_TIMEOUT (admin_timeout * HZ)
static struct notifier_block nvme_nb;
static void nvme_reset_failed_dev(struct work_struct *ws);
+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;
volatile struct nvme_completion *cqes;
dma_addr_t sq_dma_addr;
dma_addr_t cq_dma_addr;
- wait_queue_head_t sq_full;
- wait_queue_t sq_cong_wait;
- struct bio_list sq_cong;
- struct list_head iod_bio;
u32 __iomem *q_db;
u16 q_depth;
u16 cq_vector;
u16 qid;
u8 cq_phase;
u8 cqe_seen;
- u8 q_suspended;
- cpumask_var_t cpu_mask;
struct async_cmd_info cmdinfo;
- unsigned long cmdid_data[];
+ struct blk_mq_hw_ctx *hctx;
};
/*
struct nvme_cmd_info {
nvme_completion_fn fn;
void *ctx;
- unsigned long timeout;
int aborted;
+ struct nvme_queue *nvmeq;
};
-static struct nvme_cmd_info *nvme_cmd_info(struct nvme_queue *nvmeq)
+static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+ unsigned int hctx_idx)
{
- return (void *)&nvmeq->cmdid_data[BITS_TO_LONGS(nvmeq->q_depth)];
+ struct nvme_dev *dev = data;
+ struct nvme_queue *nvmeq = dev->queues[0];
+
+ WARN_ON(nvmeq->hctx);
+ nvmeq->hctx = hctx;
+ hctx->driver_data = nvmeq;
+ return 0;
}
-static unsigned nvme_queue_extra(int depth)
+static int nvme_admin_init_request(void *data, struct request *req,
+ unsigned int hctx_idx, unsigned int rq_idx,
+ unsigned int numa_node)
{
- return DIV_ROUND_UP(depth, 8) + (depth * sizeof(struct nvme_cmd_info));
+ 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;
}
-/**
- * alloc_cmdid() - Allocate a Command ID
- * @nvmeq: The queue that will be used for this command
- * @ctx: A pointer that will be passed to the handler
- * @handler: The function to call on completion
- *
- * Allocate a Command ID for a queue. The data passed in will
- * be passed to the completion handler. This is implemented by using
- * the bottom two bits of the ctx pointer to store the handler ID.
- * Passing in a pointer that's not 4-byte aligned will cause a BUG.
- * We can change this if it becomes a problem.
- *
- * May be called with local interrupts disabled and the q_lock held,
- * or with interrupts enabled and no locks held.
- */
-static int alloc_cmdid(struct nvme_queue *nvmeq, void *ctx,
- nvme_completion_fn handler, unsigned timeout)
+static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+ unsigned int hctx_idx)
{
- int depth = nvmeq->q_depth - 1;
- struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
- int cmdid;
+ struct nvme_dev *dev = data;
+ struct nvme_queue *nvmeq = dev->queues[
+ (hctx_idx % dev->queue_count) + 1];
- do {
- cmdid = find_first_zero_bit(nvmeq->cmdid_data, depth);
- if (cmdid >= depth)
- return -EBUSY;
- } while (test_and_set_bit(cmdid, nvmeq->cmdid_data));
+ if (!nvmeq->hctx)
+ nvmeq->hctx = hctx;
+
+ /* nvmeq queues are shared between namespaces. We assume here that
+ * blk-mq map the tags so they match up with the nvme queue tags. */
+ WARN_ON(nvmeq->hctx->tags != hctx->tags);
- info[cmdid].fn = handler;
- info[cmdid].ctx = ctx;
- info[cmdid].timeout = jiffies + timeout;
- info[cmdid].aborted = 0;
- return cmdid;
+ hctx->driver_data = nvmeq;
+ return 0;
}
-static int alloc_cmdid_killable(struct nvme_queue *nvmeq, void *ctx,
- nvme_completion_fn handler, unsigned timeout)
+static int nvme_init_request(void *data, struct request *req,
+ unsigned int hctx_idx, unsigned int rq_idx,
+ unsigned int numa_node)
{
- int cmdid;
- wait_event_killable(nvmeq->sq_full,
- (cmdid = alloc_cmdid(nvmeq, ctx, handler, timeout)) >= 0);
- return (cmdid < 0) ? -EINTR : cmdid;
+ 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;
}
/* Special values must be less than 0x1000 */
#define CMD_CTX_CANCELLED (0x30C + CMD_CTX_BASE)
#define CMD_CTX_COMPLETED (0x310 + CMD_CTX_BASE)
#define CMD_CTX_INVALID (0x314 + CMD_CTX_BASE)
-#define CMD_CTX_ABORT (0x318 + CMD_CTX_BASE)
-#define CMD_CTX_ASYNC (0x31C + 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_ABORT) {
- ++nvmeq->dev->abort_limit;
- 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_ASYNC) {
- 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)
- dev_warn(nvmeq->q_dmadev,
- "async event result %08x\n", result);
- return;
- }
-
dev_warn(nvmeq->q_dmadev, "Unknown special completion %p\n", ctx);
}
-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);
-}
-
-/*
- * Called with local interrupts disabled and the q_lock held. May not sleep.
- */
-static void *free_cmdid(struct nvme_queue *nvmeq, int cmdid,
- nvme_completion_fn *fn)
+static void *cancel_cmd_info(struct nvme_cmd_info *cmd, nvme_completion_fn *fn)
{
void *ctx;
- struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
- if (cmdid >= nvmeq->q_depth || !info[cmdid].fn) {
- if (fn)
- *fn = special_completion;
- return CMD_CTX_INVALID;
- }
if (fn)
- *fn = info[cmdid].fn;
- ctx = info[cmdid].ctx;
- info[cmdid].fn = special_completion;
- info[cmdid].ctx = CMD_CTX_COMPLETED;
- clear_bit(cmdid, nvmeq->cmdid_data);
- wake_up(&nvmeq->sq_full);
+ *fn = cmd->fn;
+ ctx = cmd->ctx;
+ cmd->fn = special_completion;
+ cmd->ctx = CMD_CTX_CANCELLED;
return ctx;
}
-static void *cancel_cmdid(struct nvme_queue *nvmeq, int cmdid,
- nvme_completion_fn *fn)
+static void async_req_completion(struct nvme_queue *nvmeq, void *ctx,
+ struct nvme_completion *cqe)
{
- void *ctx;
- struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
- if (fn)
- *fn = info[cmdid].fn;
- ctx = info[cmdid].ctx;
- info[cmdid].fn = special_completion;
- info[cmdid].ctx = CMD_CTX_CANCELLED;
- return ctx;
-}
+ struct request *req = ctx;
-static struct nvme_queue *raw_nvmeq(struct nvme_dev *dev, int qid)
-{
- return rcu_dereference_raw(dev->queues[qid]);
+ 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)
+ dev_warn(nvmeq->q_dmadev,
+ "async event result %08x\n", result);
+
+ blk_put_request(req);
}
-static struct nvme_queue *get_nvmeq(struct nvme_dev *dev) __acquires(RCU)
+static void abort_completion(struct nvme_queue *nvmeq, void *ctx,
+ struct nvme_completion *cqe)
{
- struct nvme_queue *nvmeq;
- unsigned queue_id = get_cpu_var(*dev->io_queue);
+ struct request *req = ctx;
+
+ u16 status = le16_to_cpup(&cqe->status) >> 1;
+ u32 result = le32_to_cpup(&cqe->result);
- rcu_read_lock();
- nvmeq = rcu_dereference(dev->queues[queue_id]);
- if (nvmeq)
- return nvmeq;
+ blk_put_request(req);
- rcu_read_unlock();
- put_cpu_var(*dev->io_queue);
- return NULL;
+ dev_warn(nvmeq->q_dmadev, "Abort status:%x result:%x", status, result);
+ ++nvmeq->dev->abort_limit;
}
-static void put_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
+static void async_completion(struct nvme_queue *nvmeq, void *ctx,
+ struct nvme_completion *cqe)
{
- rcu_read_unlock();
- put_cpu_var(nvmeq->dev->io_queue);
+ 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_put_request(cmdinfo->req);
}
-static struct nvme_queue *lock_nvmeq(struct nvme_dev *dev, int q_idx)
- __acquires(RCU)
+static inline struct nvme_cmd_info *get_cmd_from_tag(struct nvme_queue *nvmeq,
+ unsigned int tag)
{
- struct nvme_queue *nvmeq;
-
- rcu_read_lock();
- nvmeq = rcu_dereference(dev->queues[q_idx]);
- if (nvmeq)
- return nvmeq;
+ struct blk_mq_hw_ctx *hctx = nvmeq->hctx;
+ struct request *req = blk_mq_tag_to_rq(hctx->tags, tag);
- rcu_read_unlock();
- return NULL;
+ return blk_mq_rq_to_pdu(req);
}
-static void unlock_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
+/*
+ * 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)
{
- rcu_read_unlock();
+ 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;
}
/**
*
* Safe to use from interrupt context
*/
-static int nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
+static int __nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
{
- unsigned long flags;
- u16 tail;
- spin_lock_irqsave(&nvmeq->q_lock, flags);
- if (nvmeq->q_suspended) {
- spin_unlock_irqrestore(&nvmeq->q_lock, flags);
- return -EBUSY;
- }
- tail = nvmeq->sq_tail;
+ u16 tail = nvmeq->sq_tail;
+
memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
if (++tail == nvmeq->q_depth)
tail = 0;
writel(tail, nvmeq->q_db);
nvmeq->sq_tail = tail;
- spin_unlock_irqrestore(&nvmeq->q_lock, flags);
return 0;
}
+static int nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
+{
+ unsigned long flags;
+ int ret;
+ spin_lock_irqsave(&nvmeq->q_lock, flags);
+ ret = __nvme_submit_cmd(nvmeq, cmd);
+ spin_unlock_irqrestore(&nvmeq->q_lock, flags);
+ return ret;
+}
+
static __le64 **iod_list(struct nvme_iod *iod)
{
return ((void *)iod) + iod->offset;
iod->length = nbytes;
iod->nents = 0;
iod->first_dma = 0ULL;
- iod->start_time = jiffies;
}
return iod;
kfree(iod);
}
-static void nvme_start_io_acct(struct bio *bio)
-{
- struct gendisk *disk = bio->bi_bdev->bd_disk;
- if (blk_queue_io_stat(disk->queue)) {
- const int rw = bio_data_dir(bio);
- int cpu = part_stat_lock();
- part_round_stats(cpu, &disk->part0);
- part_stat_inc(cpu, &disk->part0, ios[rw]);
- part_stat_add(cpu, &disk->part0, sectors[rw],
- bio_sectors(bio));
- part_inc_in_flight(&disk->part0, rw);
- part_stat_unlock();
- }
-}
-
-static void nvme_end_io_acct(struct bio *bio, unsigned long start_time)
-{
- struct gendisk *disk = bio->bi_bdev->bd_disk;
- if (blk_queue_io_stat(disk->queue)) {
- const int rw = bio_data_dir(bio);
- unsigned long duration = jiffies - start_time;
- int cpu = part_stat_lock();
- part_stat_add(cpu, &disk->part0, ticks[rw], duration);
- part_round_stats(cpu, &disk->part0);
- part_dec_in_flight(&disk->part0, rw);
- part_stat_unlock();
- }
-}
-
static int nvme_error_status(u16 status)
{
switch (status & 0x7ff) {
}
}
-static void bio_completion(struct nvme_queue *nvmeq, void *ctx,
+static void req_completion(struct nvme_queue *nvmeq, void *ctx,
struct nvme_completion *cqe)
{
struct nvme_iod *iod = ctx;
- struct bio *bio = iod->private;
+ struct request *req = iod->private;
+ struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
+
u16 status = le16_to_cpup(&cqe->status) >> 1;
- int error = 0;
if (unlikely(status)) {
- if (!(status & NVME_SC_DNR ||
- bio->bi_rw & REQ_FAILFAST_MASK) &&
- (jiffies - iod->start_time) < IOD_TIMEOUT) {
- if (!waitqueue_active(&nvmeq->sq_full))
- add_wait_queue(&nvmeq->sq_full,
- &nvmeq->sq_cong_wait);
- list_add_tail(&iod->node, &nvmeq->iod_bio);
- wake_up(&nvmeq->sq_full);
+ if (!(status & NVME_SC_DNR || blk_noretry_request(req))
+ && (jiffies - req->start_time) < req->timeout) {
+ blk_mq_requeue_request(req);
+ blk_mq_kick_requeue_list(req->q);
return;
}
- error = nvme_error_status(status);
- }
- if (iod->nents) {
- dma_unmap_sg(nvmeq->q_dmadev, iod->sg, iod->nents,
- bio_data_dir(bio) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
- nvme_end_io_acct(bio, iod->start_time);
- }
+ req->errors = nvme_error_status(status);
+ } else
+ req->errors = 0;
+
+ if (cmd_rq->aborted)
+ dev_warn(&nvmeq->dev->pci_dev->dev,
+ "completing aborted command with status:%04x\n",
+ status);
+
+ if (iod->nents)
+ dma_unmap_sg(&nvmeq->dev->pci_dev->dev, iod->sg, iod->nents,
+ rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
nvme_free_iod(nvmeq->dev, iod);
- trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio, error);
- bio_endio(bio, error);
+ blk_mq_complete_request(req);
}
/* length is in bytes. gfp flags indicates whether we may sleep. */
return total_len;
}
-static int nvme_split_and_submit(struct bio *bio, struct nvme_queue *nvmeq,
- int len)
-{
- struct bio *split = bio_split(bio, len >> 9, GFP_ATOMIC, NULL);
- if (!split)
- return -ENOMEM;
-
- trace_block_split(bdev_get_queue(bio->bi_bdev), bio,
- split->bi_iter.bi_sector);
- bio_chain(split, bio);
-
- if (!waitqueue_active(&nvmeq->sq_full))
- add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
- bio_list_add(&nvmeq->sq_cong, split);
- bio_list_add(&nvmeq->sq_cong, bio);
- wake_up(&nvmeq->sq_full);
-
- return 0;
-}
-
-/* NVMe scatterlists require no holes in the virtual address */
-#define BIOVEC_NOT_VIRT_MERGEABLE(vec1, vec2) ((vec2)->bv_offset || \
- (((vec1)->bv_offset + (vec1)->bv_len) % PAGE_SIZE))
-
-static int nvme_map_bio(struct nvme_queue *nvmeq, struct nvme_iod *iod,
- struct bio *bio, enum dma_data_direction dma_dir, int psegs)
-{
- struct bio_vec bvec, bvprv;
- struct bvec_iter iter;
- struct scatterlist *sg = NULL;
- int length = 0, nsegs = 0, split_len = bio->bi_iter.bi_size;
- int first = 1;
-
- if (nvmeq->dev->stripe_size)
- split_len = nvmeq->dev->stripe_size -
- ((bio->bi_iter.bi_sector << 9) &
- (nvmeq->dev->stripe_size - 1));
-
- sg_init_table(iod->sg, psegs);
- bio_for_each_segment(bvec, bio, iter) {
- if (!first && BIOVEC_PHYS_MERGEABLE(&bvprv, &bvec)) {
- sg->length += bvec.bv_len;
- } else {
- if (!first && BIOVEC_NOT_VIRT_MERGEABLE(&bvprv, &bvec))
- return nvme_split_and_submit(bio, nvmeq,
- length);
-
- sg = sg ? sg + 1 : iod->sg;
- sg_set_page(sg, bvec.bv_page,
- bvec.bv_len, bvec.bv_offset);
- nsegs++;
- }
-
- if (split_len - length < bvec.bv_len)
- return nvme_split_and_submit(bio, nvmeq, split_len);
- length += bvec.bv_len;
- bvprv = bvec;
- first = 0;
- }
- iod->nents = nsegs;
- sg_mark_end(sg);
- if (dma_map_sg(nvmeq->q_dmadev, iod->sg, iod->nents, dma_dir) == 0)
- return -ENOMEM;
-
- BUG_ON(length != bio->bi_iter.bi_size);
- return length;
-}
-
-static int nvme_submit_discard(struct nvme_queue *nvmeq, struct nvme_ns *ns,
- struct bio *bio, struct nvme_iod *iod, int cmdid)
+/*
+ * 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 = &nvmeq->sq_cmds[nvmeq->sq_tail];
range->cattr = cpu_to_le32(0);
- range->nlb = cpu_to_le32(bio->bi_iter.bi_size >> ns->lba_shift);
- range->slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_iter.bi_sector));
+ 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 = cmdid;
+ 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;
if (++nvmeq->sq_tail == nvmeq->q_depth)
nvmeq->sq_tail = 0;
writel(nvmeq->sq_tail, nvmeq->q_db);
-
- return 0;
}
-static int nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns,
+static void nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns,
int cmdid)
{
struct nvme_command *cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
if (++nvmeq->sq_tail == nvmeq->q_depth)
nvmeq->sq_tail = 0;
writel(nvmeq->sq_tail, nvmeq->q_db);
-
- return 0;
}
-static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod)
+static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod,
+ struct nvme_ns *ns)
{
- struct bio *bio = iod->private;
- struct nvme_ns *ns = bio->bi_bdev->bd_disk->private_data;
+ struct request *req = iod->private;
struct nvme_command *cmnd;
- int cmdid;
- u16 control;
- u32 dsmgmt;
+ u16 control = 0;
+ u32 dsmgmt = 0;
- cmdid = alloc_cmdid(nvmeq, iod, bio_completion, NVME_IO_TIMEOUT);
- if (unlikely(cmdid < 0))
- return cmdid;
-
- if (bio->bi_rw & REQ_DISCARD)
- return nvme_submit_discard(nvmeq, ns, bio, iod, cmdid);
- if (bio->bi_rw & REQ_FLUSH)
- return nvme_submit_flush(nvmeq, ns, cmdid);
-
- control = 0;
- if (bio->bi_rw & REQ_FUA)
+ if (req->cmd_flags & REQ_FUA)
control |= NVME_RW_FUA;
- if (bio->bi_rw & (REQ_FAILFAST_DEV | REQ_RAHEAD))
+ if (req->cmd_flags & (REQ_FAILFAST_DEV | REQ_RAHEAD))
control |= NVME_RW_LR;
- dsmgmt = 0;
- if (bio->bi_rw & REQ_RAHEAD)
+ if (req->cmd_flags & REQ_RAHEAD)
dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
memset(cmnd, 0, sizeof(*cmnd));
- cmnd->rw.opcode = bio_data_dir(bio) ? nvme_cmd_write : nvme_cmd_read;
- cmnd->rw.command_id = cmdid;
+ 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, bio->bi_iter.bi_sector));
- cmnd->rw.length =
- cpu_to_le16((bio->bi_iter.bi_size >> ns->lba_shift) - 1);
+ 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);
cmnd->rw.control = cpu_to_le16(control);
cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
return 0;
}
-static int nvme_split_flush_data(struct nvme_queue *nvmeq, struct bio *bio)
-{
- struct bio *split = bio_clone(bio, GFP_ATOMIC);
- if (!split)
- return -ENOMEM;
-
- split->bi_iter.bi_size = 0;
- split->bi_phys_segments = 0;
- bio->bi_rw &= ~REQ_FLUSH;
- bio_chain(split, bio);
-
- if (!waitqueue_active(&nvmeq->sq_full))
- add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
- bio_list_add(&nvmeq->sq_cong, split);
- bio_list_add(&nvmeq->sq_cong, bio);
- wake_up_process(nvme_thread);
-
- return 0;
-}
-
-/*
- * Called with local interrupts disabled and the q_lock held. May not sleep.
- */
-static int nvme_submit_bio_queue(struct nvme_queue *nvmeq, struct nvme_ns *ns,
- struct bio *bio)
+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 request *req = bd->rq;
+ struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
struct nvme_iod *iod;
- int psegs = bio_phys_segments(ns->queue, bio);
- int result;
- unsigned size = !(bio->bi_rw & REQ_DISCARD) ? bio->bi_iter.bi_size :
+ int psegs = req->nr_phys_segments;
+ int result = BLK_MQ_RQ_QUEUE_BUSY;
+ enum dma_data_direction dma_dir;
+ unsigned size = !(req->cmd_flags & REQ_DISCARD) ? blk_rq_bytes(req) :
sizeof(struct nvme_dsm_range);
- if ((bio->bi_rw & REQ_FLUSH) && psegs)
- return nvme_split_flush_data(nvmeq, bio);
+ /*
+ * Requeued IO has already been prepped
+ */
+ iod = req->special;
+ if (iod)
+ goto submit_iod;
iod = nvme_alloc_iod(psegs, size, ns->dev, GFP_ATOMIC);
if (!iod)
- return -ENOMEM;
+ return result;
+
+ iod->private = req;
+ req->special = iod;
- iod->private = bio;
- if (bio->bi_rw & REQ_DISCARD) {
+ nvme_set_info(cmd, iod, req_completion);
+
+ if (req->cmd_flags & REQ_DISCARD) {
void *range;
/*
* We reuse the small pool to allocate the 16-byte range here
range = dma_pool_alloc(nvmeq->dev->prp_small_pool,
GFP_ATOMIC,
&iod->first_dma);
- if (!range) {
- result = -ENOMEM;
- goto free_iod;
- }
+ if (!range)
+ goto finish_cmd;
iod_list(iod)[0] = (__le64 *)range;
iod->npages = 0;
} else if (psegs) {
- result = nvme_map_bio(nvmeq, iod, bio,
- bio_data_dir(bio) ? DMA_TO_DEVICE : DMA_FROM_DEVICE,
- psegs);
- if (result <= 0)
- goto free_iod;
- if (nvme_setup_prps(nvmeq->dev, iod, result, GFP_ATOMIC) !=
- result) {
- result = -ENOMEM;
- goto free_iod;
+ dma_dir = rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
+
+ sg_init_table(iod->sg, psegs);
+ iod->nents = blk_rq_map_sg(req->q, req, iod->sg);
+ if (!iod->nents) {
+ result = BLK_MQ_RQ_QUEUE_ERROR;
+ goto finish_cmd;
}
- nvme_start_io_acct(bio);
- }
- if (unlikely(nvme_submit_iod(nvmeq, iod))) {
- if (!waitqueue_active(&nvmeq->sq_full))
- add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
- list_add_tail(&iod->node, &nvmeq->iod_bio);
+
+ if (!dma_map_sg(nvmeq->q_dmadev, iod->sg, iod->nents, dma_dir))
+ goto finish_cmd;
+
+ if (blk_rq_bytes(req) != nvme_setup_prps(nvmeq->dev, iod,
+ blk_rq_bytes(req), GFP_ATOMIC))
+ goto finish_cmd;
}
- return 0;
- free_iod:
+ blk_mq_start_request(req);
+
+ submit_iod:
+ spin_lock_irq(&nvmeq->q_lock);
+ 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;
+
+ finish_cmd:
+ nvme_finish_cmd(nvmeq, req->tag, NULL);
nvme_free_iod(nvmeq->dev, iod);
return result;
}
head = 0;
phase = !phase;
}
-
- ctx = free_cmdid(nvmeq, cqe.command_id, &fn);
+ ctx = nvme_finish_cmd(nvmeq, cqe.command_id, &fn);
fn(nvmeq, ctx, &cqe);
}
return 1;
}
-static void nvme_make_request(struct request_queue *q, struct bio *bio)
+/* Admin queue isn't initialized as a request queue. If at some point this
+ * happens anyway, make sure to notify the user */
+static int nvme_admin_queue_rq(struct blk_mq_hw_ctx *hctx,
+ const struct blk_mq_queue_data *bd)
{
- struct nvme_ns *ns = q->queuedata;
- struct nvme_queue *nvmeq = get_nvmeq(ns->dev);
- int result = -EBUSY;
-
- if (!nvmeq) {
- bio_endio(bio, -EIO);
- return;
- }
-
- spin_lock_irq(&nvmeq->q_lock);
- if (!nvmeq->q_suspended && bio_list_empty(&nvmeq->sq_cong))
- result = nvme_submit_bio_queue(nvmeq, ns, bio);
- if (unlikely(result)) {
- if (!waitqueue_active(&nvmeq->sq_full))
- add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
- bio_list_add(&nvmeq->sq_cong, bio);
- }
-
- nvme_process_cq(nvmeq);
- spin_unlock_irq(&nvmeq->q_lock);
- put_nvmeq(nvmeq);
+ WARN_ON_ONCE(1);
+ return BLK_MQ_RQ_QUEUE_ERROR;
}
static irqreturn_t nvme_irq(int irq, void *data)
return IRQ_WAKE_THREAD;
}
-static void nvme_abort_command(struct nvme_queue *nvmeq, int cmdid)
+static void nvme_abort_cmd_info(struct nvme_queue *nvmeq, struct nvme_cmd_info *
+ cmd_info)
{
spin_lock_irq(&nvmeq->q_lock);
- cancel_cmdid(nvmeq, cmdid, NULL);
+ cancel_cmd_info(cmd_info, NULL);
spin_unlock_irq(&nvmeq->q_lock);
}
* 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
*/
-static int nvme_submit_sync_cmd(struct nvme_dev *dev, int q_idx,
- struct nvme_command *cmd,
+static int nvme_submit_sync_cmd(struct request *req, struct nvme_command *cmd,
u32 *result, unsigned timeout)
{
- int cmdid, ret;
+ int ret;
struct sync_cmd_info cmdinfo;
- struct nvme_queue *nvmeq;
-
- nvmeq = lock_nvmeq(dev, q_idx);
- if (!nvmeq)
- return -ENODEV;
+ struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
+ struct nvme_queue *nvmeq = cmd_rq->nvmeq;
cmdinfo.task = current;
cmdinfo.status = -EINTR;
- cmdid = alloc_cmdid(nvmeq, &cmdinfo, sync_completion, timeout);
- if (cmdid < 0) {
- unlock_nvmeq(nvmeq);
- return cmdid;
- }
- cmd->common.command_id = cmdid;
+ cmd->common.command_id = req->tag;
+
+ nvme_set_info(cmd_rq, &cmdinfo, sync_completion);
set_current_state(TASK_KILLABLE);
ret = nvme_submit_cmd(nvmeq, cmd);
if (ret) {
- free_cmdid(nvmeq, cmdid, NULL);
- unlock_nvmeq(nvmeq);
+ nvme_finish_cmd(nvmeq, req->tag, NULL);
set_current_state(TASK_RUNNING);
- return ret;
}
- unlock_nvmeq(nvmeq);
schedule_timeout(timeout);
if (cmdinfo.status == -EINTR) {
- nvmeq = lock_nvmeq(dev, q_idx);
- if (nvmeq) {
- nvme_abort_command(nvmeq, cmdid);
- unlock_nvmeq(nvmeq);
- }
+ nvme_abort_cmd_info(nvmeq, blk_mq_rq_to_pdu(req));
return -EINTR;
}
return cmdinfo.status;
}
-static int nvme_submit_async_cmd(struct nvme_queue *nvmeq,
+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_KERNEL, false);
+ if (!req)
+ return -ENOMEM;
+
+ cmd_info = blk_mq_rq_to_pdu(req);
+ nvme_set_info(cmd_info, req, async_req_completion);
+
+ memset(&c, 0, sizeof(c));
+ c.common.opcode = nvme_admin_async_event;
+ c.common.command_id = req->tag;
+
+ return __nvme_submit_cmd(nvmeq, &c);
+}
+
+static int nvme_submit_admin_async_cmd(struct nvme_dev *dev,
struct nvme_command *cmd,
struct async_cmd_info *cmdinfo, unsigned timeout)
{
- int cmdid;
+ struct nvme_queue *nvmeq = dev->queues[0];
+ struct request *req;
+ struct nvme_cmd_info *cmd_rq;
- cmdid = alloc_cmdid_killable(nvmeq, cmdinfo, async_completion, timeout);
- if (cmdid < 0)
- return cmdid;
+ req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_KERNEL, false);
+ if (!req)
+ return -ENOMEM;
+
+ 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 = cmdid;
+
+ cmd->common.command_id = req->tag;
+
return nvme_submit_cmd(nvmeq, cmd);
}
-int nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
- u32 *result)
+int __nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
+ u32 *result, unsigned timeout)
{
- return nvme_submit_sync_cmd(dev, 0, cmd, result, ADMIN_TIMEOUT);
+ int res;
+ struct request *req;
+
+ req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_KERNEL, false);
+ if (!req)
+ return -ENOMEM;
+ res = nvme_submit_sync_cmd(req, cmd, result, timeout);
+ blk_put_request(req);
+ return res;
}
-int nvme_submit_io_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
+int nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
u32 *result)
{
- return nvme_submit_sync_cmd(dev, this_cpu_read(*dev->io_queue), cmd,
- result, NVME_IO_TIMEOUT);
+ return __nvme_submit_admin_cmd(dev, cmd, result, ADMIN_TIMEOUT);
}
-static int nvme_submit_admin_cmd_async(struct nvme_dev *dev,
- struct nvme_command *cmd, struct async_cmd_info *cmdinfo)
+int nvme_submit_io_cmd(struct nvme_dev *dev, struct nvme_ns *ns,
+ struct nvme_command *cmd, u32 *result)
{
- return nvme_submit_async_cmd(raw_nvmeq(dev, 0), cmd, cmdinfo,
- ADMIN_TIMEOUT);
+ int res;
+ struct request *req;
+
+ req = blk_mq_alloc_request(ns->queue, WRITE, (GFP_KERNEL|__GFP_WAIT),
+ false);
+ if (!req)
+ return -ENOMEM;
+ res = nvme_submit_sync_cmd(req, cmd, result, NVME_IO_TIMEOUT);
+ blk_put_request(req);
+ return res;
}
static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
{
- int status;
struct nvme_command c;
memset(&c, 0, sizeof(c));
c.delete_queue.opcode = opcode;
c.delete_queue.qid = cpu_to_le16(id);
- status = nvme_submit_admin_cmd(dev, &c, NULL);
- if (status)
- return -EIO;
- return 0;
+ return nvme_submit_admin_cmd(dev, &c, NULL);
}
static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
struct nvme_queue *nvmeq)
{
- int status;
struct nvme_command c;
int flags = NVME_QUEUE_PHYS_CONTIG | NVME_CQ_IRQ_ENABLED;
c.create_cq.cq_flags = cpu_to_le16(flags);
c.create_cq.irq_vector = cpu_to_le16(nvmeq->cq_vector);
- status = nvme_submit_admin_cmd(dev, &c, NULL);
- if (status)
- return -EIO;
- return 0;
+ return nvme_submit_admin_cmd(dev, &c, NULL);
}
static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
struct nvme_queue *nvmeq)
{
- int status;
struct nvme_command c;
int flags = NVME_QUEUE_PHYS_CONTIG | NVME_SQ_PRIO_MEDIUM;
c.create_sq.sq_flags = cpu_to_le16(flags);
c.create_sq.cqid = cpu_to_le16(qid);
- status = nvme_submit_admin_cmd(dev, &c, NULL);
- if (status)
- return -EIO;
- return 0;
+ return nvme_submit_admin_cmd(dev, &c, NULL);
}
static int adapter_delete_cq(struct nvme_dev *dev, u16 cqid)
}
/**
- * nvme_abort_cmd - Attempt aborting a command
- * @cmdid: Command id of a timed out IO
- * @queue: The queue with timed out IO
+ * 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_cmd(int cmdid, struct nvme_queue *nvmeq)
+static void nvme_abort_req(struct request *req)
{
- int a_cmdid;
- struct nvme_command cmd;
+ 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 nvme_cmd_info *info = nvme_cmd_info(nvmeq);
- struct nvme_queue *adminq;
+ struct request *abort_req;
+ struct nvme_cmd_info *abort_cmd;
+ struct nvme_command cmd;
- if (!nvmeq->qid || info[cmdid].aborted) {
+ if (!nvmeq->qid || cmd_rq->aborted) {
if (work_busy(&dev->reset_work))
return;
list_del_init(&dev->node);
dev_warn(&dev->pci_dev->dev,
- "I/O %d QID %d timeout, reset controller\n", cmdid,
- nvmeq->qid);
+ "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);
return;
if (!dev->abort_limit)
return;
- adminq = rcu_dereference(dev->queues[0]);
- a_cmdid = alloc_cmdid(adminq, CMD_CTX_ABORT, special_completion,
- ADMIN_TIMEOUT);
- if (a_cmdid < 0)
+ abort_req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_ATOMIC,
+ false);
+ if (!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 = cmdid;
+ cmd.abort.cid = req->tag;
cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
- cmd.abort.command_id = a_cmdid;
+ cmd.abort.command_id = abort_req->tag;
--dev->abort_limit;
- info[cmdid].aborted = 1;
- info[cmdid].timeout = jiffies + ADMIN_TIMEOUT;
+ cmd_rq->aborted = 1;
- dev_warn(nvmeq->q_dmadev, "Aborting I/O %d QID %d\n", cmdid,
+ dev_warn(nvmeq->q_dmadev, "Aborting I/O %d QID %d\n", req->tag,
nvmeq->qid);
- nvme_submit_cmd(adminq, &cmd);
+ if (nvme_submit_cmd(dev->queues[0], &cmd) < 0) {
+ dev_warn(nvmeq->q_dmadev,
+ "Could not abort I/O %d QID %d",
+ req->tag, nvmeq->qid);
+ blk_put_request(req);
+ }
}
-/**
- * nvme_cancel_ios - Cancel outstanding I/Os
- * @queue: The queue to cancel I/Os on
- * @timeout: True to only cancel I/Os which have timed out
- */
-static void nvme_cancel_ios(struct nvme_queue *nvmeq, bool timeout)
+static void nvme_cancel_queue_ios(struct blk_mq_hw_ctx *hctx,
+ struct request *req, void *data, bool reserved)
{
- int depth = nvmeq->q_depth - 1;
- struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
- unsigned long now = jiffies;
- int cmdid;
+ struct nvme_queue *nvmeq = data;
+ void *ctx;
+ nvme_completion_fn fn;
+ struct nvme_cmd_info *cmd;
+ static struct nvme_completion cqe = {
+ .status = cpu_to_le16(NVME_SC_ABORT_REQ << 1),
+ };
- for_each_set_bit(cmdid, nvmeq->cmdid_data, depth) {
- void *ctx;
- nvme_completion_fn fn;
- static struct nvme_completion cqe = {
- .status = cpu_to_le16(NVME_SC_ABORT_REQ << 1),
- };
+ cmd = blk_mq_rq_to_pdu(req);
- if (timeout && !time_after(now, info[cmdid].timeout))
- continue;
- if (info[cmdid].ctx == CMD_CTX_CANCELLED)
- continue;
- if (timeout && info[cmdid].ctx == CMD_CTX_ASYNC)
- continue;
- if (timeout && nvmeq->dev->initialized) {
- nvme_abort_cmd(cmdid, nvmeq);
- continue;
- }
- dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d QID %d\n", cmdid,
- nvmeq->qid);
- ctx = cancel_cmdid(nvmeq, cmdid, &fn);
- fn(nvmeq, ctx, &cqe);
- }
+ if (cmd->ctx == CMD_CTX_CANCELLED)
+ return;
+
+ 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 void nvme_free_queue(struct nvme_queue *nvmeq)
+static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
{
- spin_lock_irq(&nvmeq->q_lock);
- while (bio_list_peek(&nvmeq->sq_cong)) {
- struct bio *bio = bio_list_pop(&nvmeq->sq_cong);
- bio_endio(bio, -EIO);
- }
- while (!list_empty(&nvmeq->iod_bio)) {
- static struct nvme_completion cqe = {
- .status = cpu_to_le16(
- (NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1),
- };
- struct nvme_iod *iod = list_first_entry(&nvmeq->iod_bio,
- struct nvme_iod,
- node);
- list_del(&iod->node);
- bio_completion(nvmeq, iod, &cqe);
- }
- spin_unlock_irq(&nvmeq->q_lock);
+ 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);
+ if (nvmeq->dev->initialized)
+ nvme_abort_req(req);
+
+ /*
+ * 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);
dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
nvmeq->sq_cmds, nvmeq->sq_dma_addr);
- if (nvmeq->qid)
- free_cpumask_var(nvmeq->cpu_mask);
kfree(nvmeq);
}
int i;
for (i = dev->queue_count - 1; i >= lowest; i--) {
- nvmeq = raw_nvmeq(dev, i);
- RCU_INIT_POINTER(dev->queues[i], NULL);
+ struct nvme_queue *nvmeq = dev->queues[i];
llist_add(&nvmeq->node, &q_list);
dev->queue_count--;
+ dev->queues[i] = NULL;
}
synchronize_rcu();
entry = llist_del_all(&q_list);
/**
* nvme_suspend_queue - put queue into suspended state
* @nvmeq - queue to suspend
- *
- * Returns 1 if already suspended, 0 otherwise.
*/
static int nvme_suspend_queue(struct nvme_queue *nvmeq)
{
int vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
spin_lock_irq(&nvmeq->q_lock);
- if (nvmeq->q_suspended) {
- spin_unlock_irq(&nvmeq->q_lock);
- return 1;
- }
- nvmeq->q_suspended = 1;
nvmeq->dev->online_queues--;
spin_unlock_irq(&nvmeq->q_lock);
static void nvme_clear_queue(struct nvme_queue *nvmeq)
{
+ struct blk_mq_hw_ctx *hctx = nvmeq->hctx;
+
spin_lock_irq(&nvmeq->q_lock);
nvme_process_cq(nvmeq);
- nvme_cancel_ios(nvmeq, false);
+ if (hctx && hctx->tags)
+ blk_mq_tag_busy_iter(hctx, 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 = raw_nvmeq(dev, qid);
+ struct nvme_queue *nvmeq = dev->queues[qid];
if (!nvmeq)
return;
int depth, int vector)
{
struct device *dmadev = &dev->pci_dev->dev;
- unsigned extra = nvme_queue_extra(depth);
- struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq) + extra, GFP_KERNEL);
+ struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq), GFP_KERNEL);
if (!nvmeq)
return NULL;
if (!nvmeq->sq_cmds)
goto free_cqdma;
- if (qid && !zalloc_cpumask_var(&nvmeq->cpu_mask, GFP_KERNEL))
- goto free_sqdma;
-
nvmeq->q_dmadev = dmadev;
nvmeq->dev = dev;
snprintf(nvmeq->irqname, sizeof(nvmeq->irqname), "nvme%dq%d",
spin_lock_init(&nvmeq->q_lock);
nvmeq->cq_head = 0;
nvmeq->cq_phase = 1;
- init_waitqueue_head(&nvmeq->sq_full);
- bio_list_init(&nvmeq->sq_cong);
- INIT_LIST_HEAD(&nvmeq->iod_bio);
nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
nvmeq->q_depth = depth;
nvmeq->cq_vector = vector;
nvmeq->qid = qid;
- nvmeq->q_suspended = 1;
dev->queue_count++;
- rcu_assign_pointer(dev->queues[qid], nvmeq);
+ dev->queues[qid] = nvmeq;
return nvmeq;
- free_sqdma:
- dma_free_coherent(dmadev, SQ_SIZE(depth), (void *)nvmeq->sq_cmds,
- nvmeq->sq_dma_addr);
free_cqdma:
dma_free_coherent(dmadev, CQ_SIZE(depth), (void *)nvmeq->cqes,
nvmeq->cq_dma_addr);
static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
{
struct nvme_dev *dev = nvmeq->dev;
- unsigned extra = nvme_queue_extra(nvmeq->q_depth);
spin_lock_irq(&nvmeq->q_lock);
- init_waitqueue_entry(&nvmeq->sq_cong_wait, nvme_thread);
nvmeq->sq_tail = 0;
nvmeq->cq_head = 0;
nvmeq->cq_phase = 1;
nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
- memset(nvmeq->cmdid_data, 0, extra);
memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
- nvme_cancel_ios(nvmeq, false);
- nvmeq->q_suspended = 0;
dev->online_queues++;
spin_unlock_irq(&nvmeq->q_lock);
}
return 0;
}
+static struct blk_mq_ops nvme_mq_admin_ops = {
+ .queue_rq = nvme_admin_queue_rq,
+ .map_queue = blk_mq_map_queue,
+ .init_hctx = nvme_admin_init_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 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.timeout = ADMIN_TIMEOUT;
+ dev->admin_tagset.numa_node = dev_to_node(&dev->pci_dev->dev);
+ dev->admin_tagset.cmd_size = sizeof(struct nvme_cmd_info);
+ 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 (!dev->admin_q) {
+ blk_mq_free_tag_set(&dev->admin_tagset);
+ return -ENOMEM;
+ }
+ }
+
+ return 0;
+}
+
+static void nvme_free_admin_tags(struct nvme_dev *dev)
+{
+ if (dev->admin_q)
+ blk_mq_free_tag_set(&dev->admin_tagset);
+}
+
static int nvme_configure_admin_queue(struct nvme_dev *dev)
{
int result;
if (result < 0)
return result;
- nvmeq = raw_nvmeq(dev, 0);
+ nvmeq = dev->queues[0];
if (!nvmeq) {
- nvmeq = nvme_alloc_queue(dev, 0, 64, 0);
+ nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH, 0);
if (!nvmeq)
return -ENOMEM;
}
result = nvme_enable_ctrl(dev, cap);
if (result)
- return result;
+ goto free_nvmeq;
+
+ result = nvme_alloc_admin_tags(dev);
+ if (result)
+ goto free_nvmeq;
result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
if (result)
- return result;
+ goto free_tags;
return result;
+
+ free_tags:
+ nvme_free_admin_tags(dev);
+ free_nvmeq:
+ nvme_free_queues(dev, 0);
+ return result;
}
struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
if (length != (io.nblocks + 1) << ns->lba_shift)
status = -ENOMEM;
else
- status = nvme_submit_io_cmd(dev, &c, NULL);
+ status = nvme_submit_io_cmd(dev, ns, &c, NULL);
if (meta_len) {
if (status == NVME_SC_SUCCESS && !(io.opcode & 1)) {
return status;
}
-static int nvme_user_cmd(struct nvme_dev *dev,
- struct nvme_passthru_cmd __user *ucmd, bool ioq)
+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;
timeout = cmd.timeout_ms ? msecs_to_jiffies(cmd.timeout_ms) :
ADMIN_TIMEOUT;
+
if (length != cmd.data_len)
status = -ENOMEM;
- else if (ioq)
- status = nvme_submit_sync_cmd(dev, this_cpu_read(*dev->io_queue), &c,
- &cmd.result, timeout);
- else
- status = nvme_submit_sync_cmd(dev, 0, &c, &cmd.result, timeout);
+ else if (ns) {
+ struct request *req;
+
+ req = blk_mq_alloc_request(ns->queue, WRITE,
+ (GFP_KERNEL|__GFP_WAIT), false);
+ if (!req)
+ status = -ENOMEM;
+ else {
+ status = nvme_submit_sync_cmd(req, &c, &cmd.result,
+ timeout);
+ blk_put_request(req);
+ }
+ } else
+ status = __nvme_submit_admin_cmd(dev, &c, &cmd.result, timeout);
if (cmd.data_len) {
nvme_unmap_user_pages(dev, cmd.opcode & 1, iod);
force_successful_syscall_return();
return ns->ns_id;
case NVME_IOCTL_ADMIN_CMD:
- return nvme_user_cmd(ns->dev, (void __user *)arg, false);
+ return nvme_user_cmd(ns->dev, NULL, (void __user *)arg);
case NVME_IOCTL_IO_CMD:
- return nvme_user_cmd(ns->dev, (void __user *)arg, true);
+ 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:
.revalidate_disk= nvme_revalidate_disk,
};
-static void nvme_resubmit_iods(struct nvme_queue *nvmeq)
-{
- struct nvme_iod *iod, *next;
-
- list_for_each_entry_safe(iod, next, &nvmeq->iod_bio, node) {
- if (unlikely(nvme_submit_iod(nvmeq, iod)))
- break;
- list_del(&iod->node);
- if (bio_list_empty(&nvmeq->sq_cong) &&
- list_empty(&nvmeq->iod_bio))
- remove_wait_queue(&nvmeq->sq_full,
- &nvmeq->sq_cong_wait);
- }
-}
-
-static void nvme_resubmit_bios(struct nvme_queue *nvmeq)
-{
- while (bio_list_peek(&nvmeq->sq_cong)) {
- struct bio *bio = bio_list_pop(&nvmeq->sq_cong);
- struct nvme_ns *ns = bio->bi_bdev->bd_disk->private_data;
-
- if (bio_list_empty(&nvmeq->sq_cong) &&
- list_empty(&nvmeq->iod_bio))
- remove_wait_queue(&nvmeq->sq_full,
- &nvmeq->sq_cong_wait);
- if (nvme_submit_bio_queue(nvmeq, ns, bio)) {
- if (!waitqueue_active(&nvmeq->sq_full))
- add_wait_queue(&nvmeq->sq_full,
- &nvmeq->sq_cong_wait);
- bio_list_add_head(&nvmeq->sq_cong, bio);
- break;
- }
- }
-}
-
-static int nvme_submit_async_req(struct nvme_queue *nvmeq)
-{
- struct nvme_command *c;
- int cmdid;
-
- cmdid = alloc_cmdid(nvmeq, CMD_CTX_ASYNC, special_completion, 0);
- if (cmdid < 0)
- return cmdid;
-
- c = &nvmeq->sq_cmds[nvmeq->sq_tail];
- memset(c, 0, sizeof(*c));
- c->common.opcode = nvme_admin_async_event;
- c->common.command_id = cmdid;
-
- if (++nvmeq->sq_tail == nvmeq->q_depth)
- nvmeq->sq_tail = 0;
- writel(nvmeq->sq_tail, nvmeq->q_db);
-
- return 0;
-}
-
static int nvme_kthread(void *data)
{
struct nvme_dev *dev, *next;
continue;
list_del_init(&dev->node);
dev_warn(&dev->pci_dev->dev,
- "Failed status, reset controller\n");
+ "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;
}
- rcu_read_lock();
for (i = 0; i < dev->queue_count; i++) {
- struct nvme_queue *nvmeq =
- rcu_dereference(dev->queues[i]);
+ struct nvme_queue *nvmeq = dev->queues[i];
if (!nvmeq)
continue;
spin_lock_irq(&nvmeq->q_lock);
- if (nvmeq->q_suspended)
- goto unlock;
nvme_process_cq(nvmeq);
- nvme_cancel_ios(nvmeq, true);
- nvme_resubmit_bios(nvmeq);
- nvme_resubmit_iods(nvmeq);
while ((i == 0) && (dev->event_limit > 0)) {
- if (nvme_submit_async_req(nvmeq))
+ if (nvme_submit_async_admin_req(dev))
break;
dev->event_limit--;
}
- unlock:
spin_unlock_irq(&nvmeq->q_lock);
}
- rcu_read_unlock();
}
spin_unlock(&dev_list_lock);
schedule_timeout(round_jiffies_relative(HZ));
{
struct nvme_ns *ns;
struct gendisk *disk;
+ int node = dev_to_node(&dev->pci_dev->dev);
int lbaf;
if (rt->attributes & NVME_LBART_ATTRIB_HIDE)
return NULL;
- ns = kzalloc(sizeof(*ns), GFP_KERNEL);
+ ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
if (!ns)
return NULL;
- ns->queue = blk_alloc_queue(GFP_KERNEL);
+ ns->queue = blk_mq_init_queue(&dev->tagset);
if (!ns->queue)
goto out_free_ns;
- ns->queue->queue_flags = QUEUE_FLAG_DEFAULT;
- queue_flag_clear_unlocked(QUEUE_FLAG_STACKABLE, ns->queue);
queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, ns->queue);
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue);
- queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, ns->queue);
- blk_queue_make_request(ns->queue, nvme_make_request);
+ queue_flag_set_unlocked(QUEUE_FLAG_SG_GAPS, ns->queue);
+ queue_flag_clear_unlocked(QUEUE_FLAG_IO_STAT, ns->queue);
ns->dev = dev;
ns->queue->queuedata = ns;
- disk = alloc_disk(0);
+ disk = alloc_disk_node(0, node);
if (!disk)
goto out_free_queue;
+
ns->ns_id = nsid;
ns->disk = disk;
lbaf = id->flbas & 0xf;
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);
+ 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);
return NULL;
}
-static int nvme_find_closest_node(int node)
-{
- int n, val, min_val = INT_MAX, best_node = node;
-
- for_each_online_node(n) {
- if (n == node)
- continue;
- val = node_distance(node, n);
- if (val < min_val) {
- min_val = val;
- best_node = n;
- }
- }
- return best_node;
-}
-
-static void nvme_set_queue_cpus(cpumask_t *qmask, struct nvme_queue *nvmeq,
- int count)
-{
- int cpu;
- for_each_cpu(cpu, qmask) {
- if (cpumask_weight(nvmeq->cpu_mask) >= count)
- break;
- if (!cpumask_test_and_set_cpu(cpu, nvmeq->cpu_mask))
- *per_cpu_ptr(nvmeq->dev->io_queue, cpu) = nvmeq->qid;
- }
-}
-
-static void nvme_add_cpus(cpumask_t *mask, const cpumask_t *unassigned_cpus,
- const cpumask_t *new_mask, struct nvme_queue *nvmeq, int cpus_per_queue)
-{
- int next_cpu;
- for_each_cpu(next_cpu, new_mask) {
- cpumask_or(mask, mask, get_cpu_mask(next_cpu));
- cpumask_or(mask, mask, topology_thread_cpumask(next_cpu));
- cpumask_and(mask, mask, unassigned_cpus);
- nvme_set_queue_cpus(mask, nvmeq, cpus_per_queue);
- }
-}
-
static void nvme_create_io_queues(struct nvme_dev *dev)
{
- unsigned i, max;
+ unsigned i;
- max = min(dev->max_qid, num_online_cpus());
- for (i = dev->queue_count; i <= max; i++)
+ for (i = dev->queue_count; i <= dev->max_qid; i++)
if (!nvme_alloc_queue(dev, i, dev->q_depth, i - 1))
break;
- max = min(dev->queue_count - 1, num_online_cpus());
- for (i = dev->online_queues; i <= max; i++)
- if (nvme_create_queue(raw_nvmeq(dev, i), i))
+ for (i = dev->online_queues; i <= dev->queue_count - 1; i++)
+ if (nvme_create_queue(dev->queues[i], i))
break;
}
-/*
- * If there are fewer queues than online cpus, this will try to optimally
- * assign a queue to multiple cpus by grouping cpus that are "close" together:
- * thread siblings, core, socket, closest node, then whatever else is
- * available.
- */
-static void nvme_assign_io_queues(struct nvme_dev *dev)
-{
- unsigned cpu, cpus_per_queue, queues, remainder, i;
- cpumask_var_t unassigned_cpus;
-
- nvme_create_io_queues(dev);
-
- queues = min(dev->online_queues - 1, num_online_cpus());
- if (!queues)
- return;
-
- cpus_per_queue = num_online_cpus() / queues;
- remainder = queues - (num_online_cpus() - queues * cpus_per_queue);
-
- if (!alloc_cpumask_var(&unassigned_cpus, GFP_KERNEL))
- return;
-
- cpumask_copy(unassigned_cpus, cpu_online_mask);
- cpu = cpumask_first(unassigned_cpus);
- for (i = 1; i <= queues; i++) {
- struct nvme_queue *nvmeq = lock_nvmeq(dev, i);
- cpumask_t mask;
-
- cpumask_clear(nvmeq->cpu_mask);
- if (!cpumask_weight(unassigned_cpus)) {
- unlock_nvmeq(nvmeq);
- break;
- }
-
- mask = *get_cpu_mask(cpu);
- nvme_set_queue_cpus(&mask, nvmeq, cpus_per_queue);
- if (cpus_weight(mask) < cpus_per_queue)
- nvme_add_cpus(&mask, unassigned_cpus,
- topology_thread_cpumask(cpu),
- nvmeq, cpus_per_queue);
- if (cpus_weight(mask) < cpus_per_queue)
- nvme_add_cpus(&mask, unassigned_cpus,
- topology_core_cpumask(cpu),
- nvmeq, cpus_per_queue);
- if (cpus_weight(mask) < cpus_per_queue)
- nvme_add_cpus(&mask, unassigned_cpus,
- cpumask_of_node(cpu_to_node(cpu)),
- nvmeq, cpus_per_queue);
- if (cpus_weight(mask) < cpus_per_queue)
- nvme_add_cpus(&mask, unassigned_cpus,
- cpumask_of_node(
- nvme_find_closest_node(
- cpu_to_node(cpu))),
- nvmeq, cpus_per_queue);
- if (cpus_weight(mask) < cpus_per_queue)
- nvme_add_cpus(&mask, unassigned_cpus,
- unassigned_cpus,
- nvmeq, cpus_per_queue);
-
- WARN(cpumask_weight(nvmeq->cpu_mask) != cpus_per_queue,
- "nvme%d qid:%d mis-matched queue-to-cpu assignment\n",
- dev->instance, i);
-
- irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
- nvmeq->cpu_mask);
- cpumask_andnot(unassigned_cpus, unassigned_cpus,
- nvmeq->cpu_mask);
- cpu = cpumask_next(cpu, unassigned_cpus);
- if (remainder && !--remainder)
- cpus_per_queue++;
- unlock_nvmeq(nvmeq);
- }
- WARN(cpumask_weight(unassigned_cpus), "nvme%d unassigned online cpus\n",
- dev->instance);
- i = 0;
- cpumask_andnot(unassigned_cpus, cpu_possible_mask, cpu_online_mask);
- for_each_cpu(cpu, unassigned_cpus)
- *per_cpu_ptr(dev->io_queue, cpu) = (i++ % queues) + 1;
- free_cpumask_var(unassigned_cpus);
-}
-
static int set_queue_count(struct nvme_dev *dev, int count)
{
int status;
return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride);
}
-static void nvme_cpu_workfn(struct work_struct *work)
-{
- struct nvme_dev *dev = container_of(work, struct nvme_dev, cpu_work);
- if (dev->initialized)
- nvme_assign_io_queues(dev);
-}
-
-static int nvme_cpu_notify(struct notifier_block *self,
- unsigned long action, void *hcpu)
-{
- struct nvme_dev *dev;
-
- switch (action) {
- case CPU_ONLINE:
- case CPU_DEAD:
- spin_lock(&dev_list_lock);
- list_for_each_entry(dev, &dev_list, node)
- schedule_work(&dev->cpu_work);
- spin_unlock(&dev_list_lock);
- break;
- }
- return NOTIFY_OK;
-}
-
static int nvme_setup_io_queues(struct nvme_dev *dev)
{
- struct nvme_queue *adminq = raw_nvmeq(dev, 0);
+ struct nvme_queue *adminq = dev->queues[0];
struct pci_dev *pdev = dev->pci_dev;
int result, i, vecs, nr_io_queues, size;
dev->max_qid = nr_io_queues;
result = queue_request_irq(dev, adminq, adminq->irqname);
- if (result) {
- adminq->q_suspended = 1;
+ if (result)
goto free_queues;
- }
/* Free previously allocated queues that are no longer usable */
nvme_free_queues(dev, nr_io_queues + 1);
- nvme_assign_io_queues(dev);
+ nvme_create_io_queues(dev);
return 0;
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])
+ (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;
+ }
+
+ 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->pci_dev->dev);
+ dev->tagset.queue_depth =
+ min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1;
+ dev->tagset.cmd_size = sizeof(struct nvme_cmd_info);
+ dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
+ dev->tagset.driver_data = dev;
+
+ if (blk_mq_alloc_tag_set(&dev->tagset))
+ goto out;
id_ns = mem;
for (i = 1; i <= nn; i++) {
c.delete_queue.qid = cpu_to_le16(nvmeq->qid);
init_kthread_work(&nvmeq->cmdinfo.work, fn);
- return nvme_submit_admin_cmd_async(nvmeq->dev, &c, &nvmeq->cmdinfo);
+ return nvme_submit_admin_async_cmd(nvmeq->dev, &c, &nvmeq->cmdinfo,
+ ADMIN_TIMEOUT);
}
static void nvme_del_cq_work_handler(struct kthread_work *work)
atomic_set(&dq.refcount, 0);
dq.worker = &worker;
for (i = dev->queue_count - 1; i > 0; i--) {
- struct nvme_queue *nvmeq = raw_nvmeq(dev, i);
+ struct nvme_queue *nvmeq = dev->queues[i];
if (nvme_suspend_queue(nvmeq))
continue;
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 = raw_nvmeq(dev, i);
+ struct nvme_queue *nvmeq = dev->queues[i];
nvme_suspend_queue(nvmeq);
nvme_clear_queue(nvmeq);
}
nvme_dev_unmap(dev);
}
+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);
+}
+
static void nvme_dev_remove(struct nvme_dev *dev)
{
struct nvme_ns *ns;
pci_dev_put(dev->pci_dev);
nvme_free_namespaces(dev);
- free_percpu(dev->io_queue);
+ blk_mq_free_tag_set(&dev->tagset);
kfree(dev->queues);
kfree(dev->entry);
kfree(dev);
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, (void __user *)arg, false);
+ return nvme_user_cmd(dev, NULL, (void __user *)arg);
case NVME_IOCTL_IO_CMD:
- return nvme_user_cmd(dev, (void __user *)arg, true);
+ 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);
default:
return -ENOTTY;
}
.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->hctx)
+ continue;
+
+ irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
+ nvmeq->hctx->cpumask);
+ }
+}
+
static int nvme_dev_start(struct nvme_dev *dev)
{
int result;
result = nvme_thread ? PTR_ERR(nvme_thread) : -EINTR;
goto disable;
}
- nvme_init_queue(raw_nvmeq(dev, 0), 0);
+
+ nvme_init_queue(dev->queues[0], 0);
result = nvme_setup_io_queues(dev);
if (result)
goto disable;
+ nvme_set_irq_hints(dev);
+
return result;
disable:
{
nvme_dev_shutdown(dev);
if (nvme_dev_resume(dev)) {
- dev_err(&dev->pci_dev->dev, "Device failed to resume\n");
+ dev_warn(&dev->pci_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))) {
static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
- int result = -ENOMEM;
+ int node, result = -ENOMEM;
struct nvme_dev *dev;
- dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+ 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 = kcalloc(num_possible_cpus(), sizeof(*dev->entry),
- GFP_KERNEL);
+ dev->entry = kzalloc_node(num_possible_cpus() * sizeof(*dev->entry),
+ GFP_KERNEL, node);
if (!dev->entry)
goto free;
- dev->queues = kcalloc(num_possible_cpus() + 1, sizeof(void *),
- GFP_KERNEL);
+ dev->queues = kzalloc_node((num_possible_cpus() + 1) * sizeof(void *),
+ GFP_KERNEL, node);
if (!dev->queues)
goto free;
- dev->io_queue = alloc_percpu(unsigned short);
- if (!dev->io_queue)
- goto free;
INIT_LIST_HEAD(&dev->namespaces);
dev->reset_workfn = nvme_reset_failed_dev;
INIT_WORK(&dev->reset_work, nvme_reset_workfn);
- INIT_WORK(&dev->cpu_work, nvme_cpu_workfn);
dev->pci_dev = pci_dev_get(pdev);
pci_set_drvdata(pdev, dev);
result = nvme_set_instance(dev);
if (result)
goto remove;
+ nvme_set_irq_hints(dev);
+
dev->initialized = 1;
return 0;
remove:
nvme_dev_remove(dev);
+ nvme_dev_remove_admin(dev);
nvme_free_namespaces(dev);
shutdown:
nvme_dev_shutdown(dev);
put_pci:
pci_dev_put(dev->pci_dev);
free:
- free_percpu(dev->io_queue);
kfree(dev->queues);
kfree(dev->entry);
kfree(dev);
pci_set_drvdata(pdev, NULL);
flush_work(&dev->reset_work);
- flush_work(&dev->cpu_work);
misc_deregister(&dev->miscdev);
+ nvme_dev_remove(dev);
nvme_dev_shutdown(dev);
+ nvme_dev_remove_admin(dev);
nvme_free_queues(dev, 0);
- nvme_dev_remove(dev);
+ nvme_free_admin_tags(dev);
nvme_release_instance(dev);
nvme_release_prp_pools(dev);
kref_put(&dev->kref, nvme_free_dev);
else if (result > 0)
nvme_major = result;
- nvme_nb.notifier_call = &nvme_cpu_notify;
- result = register_hotcpu_notifier(&nvme_nb);
- if (result)
- goto unregister_blkdev;
-
result = pci_register_driver(&nvme_driver);
if (result)
- goto unregister_hotcpu;
+ goto unregister_blkdev;
return 0;
- unregister_hotcpu:
- unregister_hotcpu_notifier(&nvme_nb);
unregister_blkdev:
unregister_blkdev(nvme_major, "nvme");
kill_workq:
projects / openwrt / staging / blogic.git / commitdiff