@@ -109,6 +109,7 @@ struct mmc_blk_data {
#define MMC_BLK_WRITE BIT(1)
#define MMC_BLK_DISCARD BIT(2)
#define MMC_BLK_SECDISCARD BIT(3)
+#define MMC_BLK_CQE_RECOVERY BIT(4)
/*
* Only set in main mmc_blk_data associated
@@ -1659,6 +1660,200 @@ static void mmc_blk_data_prep(struct mmc_queue *mq, struct mmc_queue_req *mqrq,
*do_data_tag_p = do_data_tag;
}
+#define MMC_CQE_RETRIES 2
+
+void mmc_blk_cqe_complete_rq(struct request *req)
+{
+ struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+ struct mmc_request *mrq = &mqrq->brq.mrq;
+ struct request_queue *q = req->q;
+ struct mmc_queue *mq = q->queuedata;
+ struct mmc_host *host = mq->card->host;
+ unsigned long flags;
+ bool put_card;
+ int err;
+
+ mmc_cqe_post_req(host, mrq);
+
+ spin_lock_irqsave(q->queue_lock, flags);
+
+ mq->cqe_in_flight[mmc_cqe_issue_type(host, req)] -= 1;
+
+ put_card = mmc_cqe_tot_in_flight(mq) == 0;
+
+ if (mrq->cmd && mrq->cmd->error)
+ err = mrq->cmd->error;
+ else if (mrq->data && mrq->data->error)
+ err = mrq->data->error;
+ else
+ err = 0;
+
+ if (err) {
+ if (mqrq->retries++ < MMC_CQE_RETRIES)
+ blk_requeue_request(q, req);
+ else
+ __blk_end_request_all(req, BLK_STS_IOERR);
+ } else if (mrq->data) {
+ if (__blk_end_request(req, BLK_STS_OK, mrq->data->bytes_xfered))
+ blk_requeue_request(q, req);
+ } else {
+ __blk_end_request_all(req, BLK_STS_OK);
+ }
+
+ mmc_cqe_kick_queue(mq);
+
+ spin_unlock_irqrestore(q->queue_lock, flags);
+
+ if (put_card)
+ mmc_put_card(mq->card);
+}
+
+void mmc_blk_cqe_recovery(struct mmc_queue *mq)
+{
+ struct mmc_card *card = mq->card;
+ struct mmc_host *host = card->host;
+ int err;
+
+ mmc_get_card(card);
+
+ pr_debug("%s: CQE recovery start\n", mmc_hostname(host));
+
+ mq->cqe_in_recovery = true;
+
+ err = mmc_cqe_recovery(host);
+ if (err)
+ mmc_blk_reset(mq->blkdata, host, MMC_BLK_CQE_RECOVERY);
+ else
+ mmc_blk_reset_success(mq->blkdata, MMC_BLK_CQE_RECOVERY);
+
+ mq->cqe_in_recovery = false;
+
+ pr_debug("%s: CQE recovery done\n", mmc_hostname(host));
+
+ mmc_put_card(card);
+}
+
+static void mmc_blk_cqe_req_done(struct mmc_request *mrq)
+{
+ struct mmc_queue_req *mqrq = container_of(mrq, struct mmc_queue_req,
+ brq.mrq);
+ struct request *req = mmc_queue_req_to_req(mqrq);
+ struct request_queue *q = req->q;
+ struct mmc_queue *mq = q->queuedata;
+
+ /*
+ * Block layer timeouts race with completions which means the normal
+ * completion path cannot be used during recovery.
+ */
+ if (mq->cqe_in_recovery)
+ mmc_blk_cqe_complete_rq(req);
+ else
+ blk_complete_request(req);
+}
+
+static int mmc_blk_cqe_start_req(struct mmc_host *host, struct mmc_request *mrq)
+{
+ mrq->done = mmc_blk_cqe_req_done;
+ mrq->recovery_notifier = mmc_cqe_recovery_notifier;
+
+ return mmc_cqe_start_req(host, mrq);
+}
+
+static struct mmc_request *mmc_blk_cqe_prep_dcmd(struct mmc_queue_req *mqrq,
+ struct request *req)
+{
+ struct mmc_blk_request *brq = &mqrq->brq;
+
+ memset(brq, 0, sizeof(*brq));
+
+ brq->mrq.cmd = &brq->cmd;
+ brq->mrq.tag = req->tag;
+
+ return &brq->mrq;
+}
+
+static int mmc_blk_cqe_issue_flush(struct mmc_queue *mq, struct request *req)
+{
+ struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+ struct mmc_request *mrq = mmc_blk_cqe_prep_dcmd(mqrq, req);
+
+ mrq->cmd->opcode = MMC_SWITCH;
+ mrq->cmd->arg = (MMC_SWITCH_MODE_WRITE_BYTE << 24) |
+ (EXT_CSD_FLUSH_CACHE << 16) |
+ (1 << 8) |
+ EXT_CSD_CMD_SET_NORMAL;
+ mrq->cmd->flags = MMC_CMD_AC | MMC_RSP_R1B;
+
+ return mmc_blk_cqe_start_req(mq->card->host, mrq);
+}
+
+static int mmc_blk_cqe_issue_rw_rq(struct mmc_queue *mq, struct request *req)
+{
+ struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+
+ mmc_blk_data_prep(mq, mqrq, 0, NULL, NULL);
+
+ return mmc_blk_cqe_start_req(mq->card->host, &mqrq->brq.mrq);
+}
+
+enum mmc_issued mmc_blk_cqe_issue_rq(struct mmc_queue *mq, struct request *req)
+{
+ struct mmc_blk_data *md = mq->blkdata;
+ struct mmc_card *card = md->queue.card;
+ struct mmc_host *host = card->host;
+ int ret;
+
+ ret = mmc_blk_part_switch(card, md->part_type);
+ if (ret)
+ return MMC_REQ_FAILED_TO_START;
+
+ switch (mmc_cqe_issue_type(host, req)) {
+ case MMC_ISSUE_SYNC:
+ ret = host->cqe_ops->cqe_wait_for_idle(host);
+ if (ret)
+ return MMC_REQ_BUSY;
+ switch (req_op(req)) {
+ case REQ_OP_DRV_IN:
+ case REQ_OP_DRV_OUT:
+ mmc_blk_issue_drv_op(mq, req);
+ break;
+ case REQ_OP_DISCARD:
+ mmc_blk_issue_discard_rq(mq, req);
+ break;
+ case REQ_OP_SECURE_ERASE:
+ mmc_blk_issue_secdiscard_rq(mq, req);
+ break;
+ case REQ_OP_FLUSH:
+ mmc_blk_issue_flush(mq, req);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ return MMC_REQ_FAILED_TO_START;
+ }
+ return MMC_REQ_FINISHED;
+ case MMC_ISSUE_DCMD:
+ case MMC_ISSUE_ASYNC:
+ switch (req_op(req)) {
+ case REQ_OP_FLUSH:
+ ret = mmc_blk_cqe_issue_flush(mq, req);
+ break;
+ case REQ_OP_READ:
+ case REQ_OP_WRITE:
+ ret = mmc_blk_cqe_issue_rw_rq(mq, req);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ ret = -EINVAL;
+ }
+ if (!ret)
+ return MMC_REQ_STARTED;
+ return ret == -EBUSY ? MMC_REQ_BUSY : MMC_REQ_FAILED_TO_START;
+ default:
+ WARN_ON_ONCE(1);
+ return MMC_REQ_FAILED_TO_START;
+ }
+}
+
static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
struct mmc_card *card,
int disable_multi,
@@ -2082,7 +2277,7 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
INIT_LIST_HEAD(&md->part);
md->usage = 1;
- ret = mmc_init_queue(&md->queue, card, &md->lock, subname);
+ ret = mmc_init_queue(&md->queue, card, &md->lock, subname, area_type);
if (ret)
goto err_putdisk;
@@ -6,4 +6,11 @@
void mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req);
+enum mmc_issued;
+
+enum mmc_issued mmc_blk_cqe_issue_rq(struct mmc_queue *mq,
+ struct request *req);
+void mmc_blk_cqe_complete_rq(struct request *rq);
+void mmc_blk_cqe_recovery(struct mmc_queue *mq);
+
#endif
@@ -36,10 +36,253 @@ static int mmc_prep_request(struct request_queue *q, struct request *req)
return BLKPREP_KILL;
req->rq_flags |= RQF_DONTPREP;
+ req_to_mmc_queue_req(req)->retries = 0;
return BLKPREP_OK;
}
+static void mmc_cqe_request_fn(struct request_queue *q)
+{
+ struct mmc_queue *mq = q->queuedata;
+ struct request *req;
+
+ if (!mq) {
+ while ((req = blk_fetch_request(q)) != NULL) {
+ req->rq_flags |= RQF_QUIET;
+ __blk_end_request_all(req, BLK_STS_IOERR);
+ }
+ return;
+ }
+
+ if (mq->asleep && !mq->cqe_busy)
+ wake_up_process(mq->thread);
+}
+
+static inline bool mmc_cqe_dcmd_busy(struct mmc_queue *mq)
+{
+ /* Allow only 1 DCMD at a time */
+ return mq->cqe_in_flight[MMC_ISSUE_DCMD];
+}
+
+void mmc_cqe_kick_queue(struct mmc_queue *mq)
+{
+ if ((mq->cqe_busy & MMC_CQE_DCMD_BUSY) && !mmc_cqe_dcmd_busy(mq))
+ mq->cqe_busy &= ~MMC_CQE_DCMD_BUSY;
+
+ mq->cqe_busy &= ~MMC_CQE_QUEUE_FULL;
+
+ if (mq->asleep && !mq->cqe_busy)
+ __blk_run_queue(mq->queue);
+}
+
+static inline bool mmc_cqe_can_dcmd(struct mmc_host *host)
+{
+ return host->caps2 & MMC_CAP2_CQE_DCMD;
+}
+
+enum mmc_issue_type mmc_cqe_issue_type(struct mmc_host *host,
+ struct request *req)
+{
+ switch (req_op(req)) {
+ case REQ_OP_DRV_IN:
+ case REQ_OP_DRV_OUT:
+ case REQ_OP_DISCARD:
+ case REQ_OP_SECURE_ERASE:
+ return MMC_ISSUE_SYNC;
+ case REQ_OP_FLUSH:
+ return mmc_cqe_can_dcmd(host) ? MMC_ISSUE_DCMD : MMC_ISSUE_SYNC;
+ default:
+ return MMC_ISSUE_ASYNC;
+ }
+}
+
+static void __mmc_cqe_recovery_notifier(struct mmc_queue *mq)
+{
+ if (!mq->cqe_recovery_needed) {
+ mq->cqe_recovery_needed = true;
+ wake_up_process(mq->thread);
+ }
+}
+
+void mmc_cqe_recovery_notifier(struct mmc_request *mrq)
+{
+ struct mmc_queue_req *mqrq = container_of(mrq, struct mmc_queue_req,
+ brq.mrq);
+ struct request *req = mmc_queue_req_to_req(mqrq);
+ struct request_queue *q = req->q;
+ struct mmc_queue *mq = q->queuedata;
+ unsigned long flags;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ __mmc_cqe_recovery_notifier(mq);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+static int mmc_cqe_thread(void *d)
+{
+ struct mmc_queue *mq = d;
+ struct request_queue *q = mq->queue;
+ struct mmc_card *card = mq->card;
+ struct mmc_host *host = card->host;
+ unsigned long flags;
+ int get_put = 0;
+
+ current->flags |= PF_MEMALLOC;
+
+ down(&mq->thread_sem);
+ spin_lock_irqsave(q->queue_lock, flags);
+ while (1) {
+ struct request *req = NULL;
+ enum mmc_issue_type issue_type;
+ bool retune_ok = false;
+
+ if (mq->cqe_recovery_needed) {
+ spin_unlock_irqrestore(q->queue_lock, flags);
+ mmc_blk_cqe_recovery(mq);
+ spin_lock_irqsave(q->queue_lock, flags);
+ mq->cqe_recovery_needed = false;
+ }
+
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ if (!kthread_should_stop())
+ req = blk_peek_request(q);
+
+ if (req) {
+ issue_type = mmc_cqe_issue_type(host, req);
+ switch (issue_type) {
+ case MMC_ISSUE_DCMD:
+ if (mmc_cqe_dcmd_busy(mq)) {
+ mq->cqe_busy |= MMC_CQE_DCMD_BUSY;
+ req = NULL;
+ break;
+ }
+ /* Fall through */
+ case MMC_ISSUE_ASYNC:
+ if (blk_queue_start_tag(q, req)) {
+ mq->cqe_busy |= MMC_CQE_QUEUE_FULL;
+ req = NULL;
+ }
+ break;
+ default:
+ /*
+ * Timeouts are handled by mmc core, so set a
+ * large value to avoid races.
+ */
+ req->timeout = 600 * HZ;
+ blk_start_request(req);
+ break;
+ }
+ if (req) {
+ mq->cqe_in_flight[issue_type] += 1;
+ if (mmc_cqe_tot_in_flight(mq) == 1)
+ get_put += 1;
+ if (mmc_cqe_qcnt(mq) == 1)
+ retune_ok = true;
+ }
+ }
+
+ mq->asleep = !req;
+
+ spin_unlock_irqrestore(q->queue_lock, flags);
+
+ if (req) {
+ enum mmc_issued issued;
+
+ set_current_state(TASK_RUNNING);
+
+ if (get_put) {
+ get_put = 0;
+ mmc_get_card(card);
+ }
+
+ if (host->need_retune && retune_ok &&
+ !host->hold_retune)
+ host->retune_now = true;
+ else
+ host->retune_now = false;
+
+ issued = mmc_blk_cqe_issue_rq(mq, req);
+
+ cond_resched();
+
+ spin_lock_irqsave(q->queue_lock, flags);
+
+ switch (issued) {
+ case MMC_REQ_STARTED:
+ break;
+ case MMC_REQ_BUSY:
+ blk_requeue_request(q, req);
+ goto finished;
+ case MMC_REQ_FAILED_TO_START:
+ __blk_end_request_all(req, BLK_STS_IOERR);
+ /* Fall through */
+ case MMC_REQ_FINISHED:
+finished:
+ mq->cqe_in_flight[issue_type] -= 1;
+ if (mmc_cqe_tot_in_flight(mq) == 0)
+ get_put = -1;
+ }
+ } else {
+ if (get_put < 0) {
+ get_put = 0;
+ mmc_put_card(card);
+ }
+ /*
+ * Do not stop with requests in flight in case recovery
+ * is needed.
+ */
+ if (kthread_should_stop() &&
+ !mmc_cqe_tot_in_flight(mq)) {
+ set_current_state(TASK_RUNNING);
+ break;
+ }
+ up(&mq->thread_sem);
+ schedule();
+ down(&mq->thread_sem);
+ spin_lock_irqsave(q->queue_lock, flags);
+ }
+ } /* loop */
+ up(&mq->thread_sem);
+
+ return 0;
+}
+
+static enum blk_eh_timer_return __mmc_cqe_timed_out(struct request *req)
+{
+ struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
+ struct mmc_request *mrq = &mqrq->brq.mrq;
+ struct mmc_queue *mq = req->q->queuedata;
+ struct mmc_host *host = mq->card->host;
+ enum mmc_issue_type issue_type = mmc_cqe_issue_type(host, req);
+ bool recovery_needed = false;
+
+ switch (issue_type) {
+ case MMC_ISSUE_ASYNC:
+ case MMC_ISSUE_DCMD:
+ if (host->cqe_ops->cqe_timeout(host, mrq, &recovery_needed)) {
+ if (recovery_needed)
+ __mmc_cqe_recovery_notifier(mq);
+ return BLK_EH_RESET_TIMER;
+ }
+ /* No timeout */
+ return BLK_EH_HANDLED;
+ default:
+ /* Timeout is handled by mmc core */
+ return BLK_EH_RESET_TIMER;
+ }
+}
+
+static enum blk_eh_timer_return mmc_cqe_timed_out(struct request *req)
+{
+ struct mmc_queue *mq = req->q->queuedata;
+
+ if (mq->cqe_recovery_needed)
+ return BLK_EH_RESET_TIMER;
+
+ return __mmc_cqe_timed_out(req);
+}
+
static int mmc_queue_thread(void *d)
{
struct mmc_queue *mq = d;
@@ -233,11 +476,12 @@ static void mmc_exit_request(struct request_queue *q, struct request *req)
* Initialise a MMC card request queue.
*/
int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
- spinlock_t *lock, const char *subname)
+ spinlock_t *lock, const char *subname, int area_type)
{
struct mmc_host *host = card->host;
u64 limit = BLK_BOUNCE_HIGH;
int ret = -ENOMEM;
+ bool use_cqe = host->cqe_enabled && area_type != MMC_BLK_DATA_AREA_RPMB;
if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask)
limit = (u64)dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT;
@@ -247,7 +491,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
if (!mq->queue)
return -ENOMEM;
mq->queue->queue_lock = lock;
- mq->queue->request_fn = mmc_request_fn;
+ mq->queue->request_fn = use_cqe ? mmc_cqe_request_fn : mmc_request_fn;
mq->queue->init_rq_fn = mmc_init_request;
mq->queue->exit_rq_fn = mmc_exit_request;
mq->queue->cmd_size = sizeof(struct mmc_queue_req);
@@ -259,6 +503,22 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
return ret;
}
+ if (use_cqe) {
+ int q_depth = card->ext_csd.cmdq_depth;
+
+ if (q_depth > host->cqe_qdepth)
+ q_depth = host->cqe_qdepth;
+
+ ret = blk_queue_init_tags(mq->queue, q_depth, NULL,
+ BLK_TAG_ALLOC_FIFO);
+ if (ret)
+ goto cleanup_queue;
+
+ blk_queue_softirq_done(mq->queue, mmc_blk_cqe_complete_rq);
+ blk_queue_rq_timed_out(mq->queue, mmc_cqe_timed_out);
+ blk_queue_rq_timeout(mq->queue, 60 * HZ);
+ }
+
blk_queue_prep_rq(mq->queue, mmc_prep_request);
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mq->queue);
queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, mq->queue);
@@ -280,9 +540,9 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
sema_init(&mq->thread_sem, 1);
- mq->thread = kthread_run(mmc_queue_thread, mq, "mmcqd/%d%s",
- host->index, subname ? subname : "");
-
+ mq->thread = kthread_run(use_cqe ? mmc_cqe_thread : mmc_queue_thread,
+ mq, "mmcqd/%d%s", host->index,
+ subname ? subname : "");
if (IS_ERR(mq->thread)) {
ret = PTR_ERR(mq->thread);
goto cleanup_queue;
@@ -7,6 +7,20 @@
#include <linux/mmc/core.h>
#include <linux/mmc/host.h>
+enum mmc_issued {
+ MMC_REQ_STARTED,
+ MMC_REQ_BUSY,
+ MMC_REQ_FAILED_TO_START,
+ MMC_REQ_FINISHED,
+};
+
+enum mmc_issue_type {
+ MMC_ISSUE_SYNC,
+ MMC_ISSUE_DCMD,
+ MMC_ISSUE_ASYNC,
+ MMC_ISSUE_MAX,
+};
+
static inline struct mmc_queue_req *req_to_mmc_queue_req(struct request *rq)
{
return blk_mq_rq_to_pdu(rq);
@@ -57,6 +71,7 @@ struct mmc_queue_req {
int drv_op_result;
void *drv_op_data;
unsigned int ioc_count;
+ int retries;
};
struct mmc_queue {
@@ -74,10 +89,17 @@ struct mmc_queue {
* associated mmc_queue_req data.
*/
int qcnt;
+ /* Following are defined for a Command Queue Engine */
+ int cqe_in_flight[MMC_ISSUE_MAX];
+ unsigned int cqe_busy;
+ bool cqe_recovery_needed;
+ bool cqe_in_recovery;
+#define MMC_CQE_DCMD_BUSY BIT(0)
+#define MMC_CQE_QUEUE_FULL BIT(1)
};
extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *,
- const char *);
+ const char *, int);
extern void mmc_cleanup_queue(struct mmc_queue *);
extern void mmc_queue_suspend(struct mmc_queue *);
extern void mmc_queue_resume(struct mmc_queue *);
@@ -89,4 +111,23 @@ extern unsigned int mmc_queue_map_sg(struct mmc_queue *,
extern int mmc_access_rpmb(struct mmc_queue *);
+void mmc_cqe_kick_queue(struct mmc_queue *mq);
+void mmc_cqe_recovery_notifier(struct mmc_request *mrq);
+
+enum mmc_issue_type mmc_cqe_issue_type(struct mmc_host *host,
+ struct request *req);
+
+static inline int mmc_cqe_tot_in_flight(struct mmc_queue *mq)
+{
+ return mq->cqe_in_flight[MMC_ISSUE_SYNC] +
+ mq->cqe_in_flight[MMC_ISSUE_DCMD] +
+ mq->cqe_in_flight[MMC_ISSUE_ASYNC];
+}
+
+static inline int mmc_cqe_qcnt(struct mmc_queue *mq)
+{
+ return mq->cqe_in_flight[MMC_ISSUE_DCMD] +
+ mq->cqe_in_flight[MMC_ISSUE_ASYNC];
+}
+
#endif
Add CQE support to the block driver, including: - optionally using DCMD for flush requests - "manually" issuing discard requests - issuing read / write requests to the CQE - supporting block-layer timeouts - handling recovery - supporting re-tuning CQE offers 25% - 50% better random multi-threaded I/O. There is a slight (e.g. 2%) drop in sequential read speed but no observable change to sequential write. CQE automatically sends the commands to complete requests. However it only supports reads / writes and so-called "direct commands" (DCMD). Furthermore DCMD is limited to one command at a time, but discards require 3 commands. That makes issuing discards through CQE very awkward, but some CQE's don't support DCMD anyway. So for discards, the existing non-CQE approach is taken, where the mmc core code issues the 3 commands one at a time i.e. mmc_erase(). Where DCMD is used, is for issuing flushes. We need to start with the legacy block API because people want to backport CQ to earlier kernels (we really need to get features upstream more quickly), but blk-mq has been evolving a lot (e.g. elevator support), so backporters face having either something quite different from upstream or trying to backport great chunks of the block layer. We also don't know how blk-mq will perform so it would be prudent to start with support for both the legacy API and blk-mq (as scsi does) so that we can find out first. This implementation for CQE support continues to use a thread to fetch requests from the block layer and issue them. This is slightly complicated by the different ways that requests can be issued (refer mmc_cqe_issue_type() and mmc_blk_cqe_issue_rq()). Also allowance must be made for runtime pm and re-tuning which cannot be performed while CQE is active. Block layer timeouts are useful for CQE. While CQE will detect timeout for a task, the block layer timeouts ensure that the driver will notice if CQE itself gets stuck or somehow does not process a task. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> --- drivers/mmc/core/block.c | 197 +++++++++++++++++++++++++++++++++- drivers/mmc/core/block.h | 7 ++ drivers/mmc/core/queue.c | 270 ++++++++++++++++++++++++++++++++++++++++++++++- drivers/mmc/core/queue.h | 43 +++++++- 4 files changed, 510 insertions(+), 7 deletions(-)