| Message ID | 1480066500-4983-1-git-send-email-linus.walleij@linaro.org |
|---|---|
| State | New |
| Headers | show |
On 25 November 2016 at 10:35, Linus Walleij <linus.walleij@linaro.org> wrote: > I've had it with this code now. > > The packed command support is a complex hurdle in the MMC/SD block > layer, around 500+ lines of code which was introduced in 2013 in > commits > > ce39f9d17c14 ("mmc: support packed write command for eMMC4.5 devices") > abd9ac144947 ("mmc: add packed command feature of eMMC4.5") > > ...and since then it has been rotting. The original author of the > code has disappeared from the community and the mail address is > bouncing. > > For the code to be exercised the host must flag that it supports > packed commands, so in mmc_blk_prep_packed_list() which is called for > every single request, the following construction appears: > > u8 max_packed_rw = 0; > > if ((rq_data_dir(cur) == WRITE) && > mmc_host_packed_wr(card->host)) > max_packed_rw = card->ext_csd.max_packed_writes; > > if (max_packed_rw == 0) > goto no_packed; > > This has the following logical deductions: > > - Only WRITE commands can really be packed, so the solution is > only half-done: we support packed WRITE but not packed READ. > The packed command support has not been finalized by supporting > reads in three years! > > - mmc_host_packed_wr() is just a static inline that checks > host->caps2 & MMC_CAP2_PACKED_WR. The problem with this is > that NO upstream host sets this capability flag! No driver > in the kernel is using it, and we can't test it. Packed > command may be supported in out-of-tree code, but I doubt > it. I doubt that the code is even working anymore due to > other refactorings in the MMC block layer, who would > notice if patches affecting it broke packed commands? > No one. > > - There is no Device Tree binding or code to mark a host as > supporting packed read or write commands, just this flag > in caps2, so for sure there are not any DT systems using > it either. > > It has other problems as well: mmc_blk_prep_packed_list() is > speculatively picking requests out of the request queue with > blk_fetch_request() making the MMC/SD stack harder to convert > to the multiqueue block layer. By this we get rid of an > obstacle. > > The way I see it this is just cruft littering the MMC/SD > stack. > > Cc: Namjae Jeon <namjae.jeon@samsung.com> > Cc: Maya Erez <qca_merez@qca.qualcomm.com> > Acked-by: Jaehoon Chung <jh80.chung@samsung.com> > Signed-off-by: Linus Walleij <linus.walleij@linaro.org> Thanks, applied for next! Kind regards Uffe > --- > ChangeLog v2->v3: > - Remove unused "reqs" variable, found by the build robot. > ChangeLog v1->v2: > - Rebased on Ulf's next branch > - Added Jaehoon's ACK > --- > drivers/mmc/card/block.c | 483 ++--------------------------------------------- > drivers/mmc/card/queue.c | 53 +----- > drivers/mmc/card/queue.h | 19 -- > include/linux/mmc/host.h | 5 - > 4 files changed, 20 insertions(+), 540 deletions(-) > > diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c > index 6618126fcb9f..86ff28f84698 100644 > --- a/drivers/mmc/card/block.c > +++ b/drivers/mmc/card/block.c > @@ -66,9 +66,6 @@ MODULE_ALIAS("mmc:block"); > > #define mmc_req_rel_wr(req) ((req->cmd_flags & REQ_FUA) && \ > (rq_data_dir(req) == WRITE)) > -#define PACKED_CMD_VER 0x01 > -#define PACKED_CMD_WR 0x02 > - > static DEFINE_MUTEX(block_mutex); > > /* > @@ -102,7 +99,6 @@ struct mmc_blk_data { > unsigned int flags; > #define MMC_BLK_CMD23 (1 << 0) /* Can do SET_BLOCK_COUNT for multiblock */ > #define MMC_BLK_REL_WR (1 << 1) /* MMC Reliable write support */ > -#define MMC_BLK_PACKED_CMD (1 << 2) /* MMC packed command support */ > > unsigned int usage; > unsigned int read_only; > @@ -126,12 +122,6 @@ struct mmc_blk_data { > > static DEFINE_MUTEX(open_lock); > > -enum { > - MMC_PACKED_NR_IDX = -1, > - MMC_PACKED_NR_ZERO, > - MMC_PACKED_NR_SINGLE, > -}; > - > module_param(perdev_minors, int, 0444); > MODULE_PARM_DESC(perdev_minors, "Minors numbers to allocate per device"); > > @@ -139,17 +129,6 @@ static inline int mmc_blk_part_switch(struct mmc_card *card, > struct mmc_blk_data *md); > static int get_card_status(struct mmc_card *card, u32 *status, int retries); > > -static inline void mmc_blk_clear_packed(struct mmc_queue_req *mqrq) > -{ > - struct mmc_packed *packed = mqrq->packed; > - > - mqrq->cmd_type = MMC_PACKED_NONE; > - packed->nr_entries = MMC_PACKED_NR_ZERO; > - packed->idx_failure = MMC_PACKED_NR_IDX; > - packed->retries = 0; > - packed->blocks = 0; > -} > - > static struct mmc_blk_data *mmc_blk_get(struct gendisk *disk) > { > struct mmc_blk_data *md; > @@ -1420,111 +1399,12 @@ static enum mmc_blk_status mmc_blk_err_check(struct mmc_card *card, > if (!brq->data.bytes_xfered) > return MMC_BLK_RETRY; > > - if (mmc_packed_cmd(mq_mrq->cmd_type)) { > - if (unlikely(brq->data.blocks << 9 != brq->data.bytes_xfered)) > - return MMC_BLK_PARTIAL; > - else > - return MMC_BLK_SUCCESS; > - } > - > if (blk_rq_bytes(req) != brq->data.bytes_xfered) > return MMC_BLK_PARTIAL; > > return MMC_BLK_SUCCESS; > } > > -static int mmc_packed_init(struct mmc_queue *mq, struct mmc_card *card) > -{ > - struct mmc_queue_req *mqrq_cur = &mq->mqrq[0]; > - struct mmc_queue_req *mqrq_prev = &mq->mqrq[1]; > - int ret = 0; > - > - > - mqrq_cur->packed = kzalloc(sizeof(struct mmc_packed), GFP_KERNEL); > - if (!mqrq_cur->packed) { > - pr_warn("%s: unable to allocate packed cmd for mqrq_cur\n", > - mmc_card_name(card)); > - ret = -ENOMEM; > - goto out; > - } > - > - mqrq_prev->packed = kzalloc(sizeof(struct mmc_packed), GFP_KERNEL); > - if (!mqrq_prev->packed) { > - pr_warn("%s: unable to allocate packed cmd for mqrq_prev\n", > - mmc_card_name(card)); > - kfree(mqrq_cur->packed); > - mqrq_cur->packed = NULL; > - ret = -ENOMEM; > - goto out; > - } > - > - INIT_LIST_HEAD(&mqrq_cur->packed->list); > - INIT_LIST_HEAD(&mqrq_prev->packed->list); > - > -out: > - return ret; > -} > - > -static void mmc_packed_clean(struct mmc_queue *mq) > -{ > - struct mmc_queue_req *mqrq_cur = &mq->mqrq[0]; > - struct mmc_queue_req *mqrq_prev = &mq->mqrq[1]; > - > - kfree(mqrq_cur->packed); > - mqrq_cur->packed = NULL; > - kfree(mqrq_prev->packed); > - mqrq_prev->packed = NULL; > -} > - > -static enum mmc_blk_status mmc_blk_packed_err_check(struct mmc_card *card, > - struct mmc_async_req *areq) > -{ > - struct mmc_queue_req *mq_rq = container_of(areq, struct mmc_queue_req, > - mmc_active); > - struct request *req = mq_rq->req; > - struct mmc_packed *packed = mq_rq->packed; > - enum mmc_blk_status status, check; > - int err; > - u8 *ext_csd; > - > - packed->retries--; > - check = mmc_blk_err_check(card, areq); > - err = get_card_status(card, &status, 0); > - if (err) { > - pr_err("%s: error %d sending status command\n", > - req->rq_disk->disk_name, err); > - return MMC_BLK_ABORT; > - } > - > - if (status & R1_EXCEPTION_EVENT) { > - err = mmc_get_ext_csd(card, &ext_csd); > - if (err) { > - pr_err("%s: error %d sending ext_csd\n", > - req->rq_disk->disk_name, err); > - return MMC_BLK_ABORT; > - } > - > - if ((ext_csd[EXT_CSD_EXP_EVENTS_STATUS] & > - EXT_CSD_PACKED_FAILURE) && > - (ext_csd[EXT_CSD_PACKED_CMD_STATUS] & > - EXT_CSD_PACKED_GENERIC_ERROR)) { > - if (ext_csd[EXT_CSD_PACKED_CMD_STATUS] & > - EXT_CSD_PACKED_INDEXED_ERROR) { > - packed->idx_failure = > - ext_csd[EXT_CSD_PACKED_FAILURE_INDEX] - 1; > - check = MMC_BLK_PARTIAL; > - } > - pr_err("%s: packed cmd failed, nr %u, sectors %u, " > - "failure index: %d\n", > - req->rq_disk->disk_name, packed->nr_entries, > - packed->blocks, packed->idx_failure); > - } > - kfree(ext_csd); > - } > - > - return check; > -} > - > static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq, > struct mmc_card *card, > int disable_multi, > @@ -1685,222 +1565,6 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq, > mmc_queue_bounce_pre(mqrq); > } > > -static inline u8 mmc_calc_packed_hdr_segs(struct request_queue *q, > - struct mmc_card *card) > -{ > - unsigned int hdr_sz = mmc_large_sector(card) ? 4096 : 512; > - unsigned int max_seg_sz = queue_max_segment_size(q); > - unsigned int len, nr_segs = 0; > - > - do { > - len = min(hdr_sz, max_seg_sz); > - hdr_sz -= len; > - nr_segs++; > - } while (hdr_sz); > - > - return nr_segs; > -} > - > -static u8 mmc_blk_prep_packed_list(struct mmc_queue *mq, struct request *req) > -{ > - struct request_queue *q = mq->queue; > - struct mmc_card *card = mq->card; > - struct request *cur = req, *next = NULL; > - struct mmc_blk_data *md = mq->blkdata; > - struct mmc_queue_req *mqrq = mq->mqrq_cur; > - bool en_rel_wr = card->ext_csd.rel_param & EXT_CSD_WR_REL_PARAM_EN; > - unsigned int req_sectors = 0, phys_segments = 0; > - unsigned int max_blk_count, max_phys_segs; > - bool put_back = true; > - u8 max_packed_rw = 0; > - u8 reqs = 0; > - > - /* > - * We don't need to check packed for any further > - * operation of packed stuff as we set MMC_PACKED_NONE > - * and return zero for reqs if geting null packed. Also > - * we clean the flag of MMC_BLK_PACKED_CMD to avoid doing > - * it again when removing blk req. > - */ > - if (!mqrq->packed) { > - md->flags &= (~MMC_BLK_PACKED_CMD); > - goto no_packed; > - } > - > - if (!(md->flags & MMC_BLK_PACKED_CMD)) > - goto no_packed; > - > - if ((rq_data_dir(cur) == WRITE) && > - mmc_host_packed_wr(card->host)) > - max_packed_rw = card->ext_csd.max_packed_writes; > - > - if (max_packed_rw == 0) > - goto no_packed; > - > - if (mmc_req_rel_wr(cur) && > - (md->flags & MMC_BLK_REL_WR) && !en_rel_wr) > - goto no_packed; > - > - if (mmc_large_sector(card) && > - !IS_ALIGNED(blk_rq_sectors(cur), 8)) > - goto no_packed; > - > - mmc_blk_clear_packed(mqrq); > - > - max_blk_count = min(card->host->max_blk_count, > - card->host->max_req_size >> 9); > - if (unlikely(max_blk_count > 0xffff)) > - max_blk_count = 0xffff; > - > - max_phys_segs = queue_max_segments(q); > - req_sectors += blk_rq_sectors(cur); > - phys_segments += cur->nr_phys_segments; > - > - if (rq_data_dir(cur) == WRITE) { > - req_sectors += mmc_large_sector(card) ? 8 : 1; > - phys_segments += mmc_calc_packed_hdr_segs(q, card); > - } > - > - do { > - if (reqs >= max_packed_rw - 1) { > - put_back = false; > - break; > - } > - > - spin_lock_irq(q->queue_lock); > - next = blk_fetch_request(q); > - spin_unlock_irq(q->queue_lock); > - if (!next) { > - put_back = false; > - break; > - } > - > - if (mmc_large_sector(card) && > - !IS_ALIGNED(blk_rq_sectors(next), 8)) > - break; > - > - if (mmc_req_is_special(next)) > - break; > - > - if (rq_data_dir(cur) != rq_data_dir(next)) > - break; > - > - if (mmc_req_rel_wr(next) && > - (md->flags & MMC_BLK_REL_WR) && !en_rel_wr) > - break; > - > - req_sectors += blk_rq_sectors(next); > - if (req_sectors > max_blk_count) > - break; > - > - phys_segments += next->nr_phys_segments; > - if (phys_segments > max_phys_segs) > - break; > - > - list_add_tail(&next->queuelist, &mqrq->packed->list); > - cur = next; > - reqs++; > - } while (1); > - > - if (put_back) { > - spin_lock_irq(q->queue_lock); > - blk_requeue_request(q, next); > - spin_unlock_irq(q->queue_lock); > - } > - > - if (reqs > 0) { > - list_add(&req->queuelist, &mqrq->packed->list); > - mqrq->packed->nr_entries = ++reqs; > - mqrq->packed->retries = reqs; > - return reqs; > - } > - > -no_packed: > - mqrq->cmd_type = MMC_PACKED_NONE; > - return 0; > -} > - > -static void mmc_blk_packed_hdr_wrq_prep(struct mmc_queue_req *mqrq, > - struct mmc_card *card, > - struct mmc_queue *mq) > -{ > - struct mmc_blk_request *brq = &mqrq->brq; > - struct request *req = mqrq->req; > - struct request *prq; > - struct mmc_blk_data *md = mq->blkdata; > - struct mmc_packed *packed = mqrq->packed; > - bool do_rel_wr, do_data_tag; > - __le32 *packed_cmd_hdr; > - u8 hdr_blocks; > - u8 i = 1; > - > - mqrq->cmd_type = MMC_PACKED_WRITE; > - packed->blocks = 0; > - packed->idx_failure = MMC_PACKED_NR_IDX; > - > - packed_cmd_hdr = packed->cmd_hdr; > - memset(packed_cmd_hdr, 0, sizeof(packed->cmd_hdr)); > - packed_cmd_hdr[0] = cpu_to_le32((packed->nr_entries << 16) | > - (PACKED_CMD_WR << 8) | PACKED_CMD_VER); > - hdr_blocks = mmc_large_sector(card) ? 8 : 1; > - > - /* > - * Argument for each entry of packed group > - */ > - list_for_each_entry(prq, &packed->list, queuelist) { > - do_rel_wr = mmc_req_rel_wr(prq) && (md->flags & MMC_BLK_REL_WR); > - do_data_tag = (card->ext_csd.data_tag_unit_size) && > - (prq->cmd_flags & REQ_META) && > - (rq_data_dir(prq) == WRITE) && > - blk_rq_bytes(prq) >= card->ext_csd.data_tag_unit_size; > - /* Argument of CMD23 */ > - packed_cmd_hdr[(i * 2)] = cpu_to_le32( > - (do_rel_wr ? MMC_CMD23_ARG_REL_WR : 0) | > - (do_data_tag ? MMC_CMD23_ARG_TAG_REQ : 0) | > - blk_rq_sectors(prq)); > - /* Argument of CMD18 or CMD25 */ > - packed_cmd_hdr[((i * 2)) + 1] = cpu_to_le32( > - mmc_card_blockaddr(card) ? > - blk_rq_pos(prq) : blk_rq_pos(prq) << 9); > - packed->blocks += blk_rq_sectors(prq); > - i++; > - } > - > - memset(brq, 0, sizeof(struct mmc_blk_request)); > - brq->mrq.cmd = &brq->cmd; > - brq->mrq.data = &brq->data; > - brq->mrq.sbc = &brq->sbc; > - brq->mrq.stop = &brq->stop; > - > - brq->sbc.opcode = MMC_SET_BLOCK_COUNT; > - brq->sbc.arg = MMC_CMD23_ARG_PACKED | (packed->blocks + hdr_blocks); > - brq->sbc.flags = MMC_RSP_R1 | MMC_CMD_AC; > - > - brq->cmd.opcode = MMC_WRITE_MULTIPLE_BLOCK; > - brq->cmd.arg = blk_rq_pos(req); > - if (!mmc_card_blockaddr(card)) > - brq->cmd.arg <<= 9; > - brq->cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_ADTC; > - > - brq->data.blksz = 512; > - brq->data.blocks = packed->blocks + hdr_blocks; > - brq->data.flags = MMC_DATA_WRITE; > - > - brq->stop.opcode = MMC_STOP_TRANSMISSION; > - brq->stop.arg = 0; > - brq->stop.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC; > - > - mmc_set_data_timeout(&brq->data, card); > - > - brq->data.sg = mqrq->sg; > - brq->data.sg_len = mmc_queue_map_sg(mq, mqrq); > - > - mqrq->mmc_active.mrq = &brq->mrq; > - mqrq->mmc_active.err_check = mmc_blk_packed_err_check; > - > - mmc_queue_bounce_pre(mqrq); > -} > - > static int mmc_blk_cmd_err(struct mmc_blk_data *md, struct mmc_card *card, > struct mmc_blk_request *brq, struct request *req, > int ret) > @@ -1923,79 +1587,10 @@ static int mmc_blk_cmd_err(struct mmc_blk_data *md, struct mmc_card *card, > if (blocks != (u32)-1) { > ret = blk_end_request(req, 0, blocks << 9); > } > - } else { > - if (!mmc_packed_cmd(mq_rq->cmd_type)) > - ret = blk_end_request(req, 0, brq->data.bytes_xfered); > - } > - return ret; > -} > - > -static int mmc_blk_end_packed_req(struct mmc_queue_req *mq_rq) > -{ > - struct request *prq; > - struct mmc_packed *packed = mq_rq->packed; > - int idx = packed->idx_failure, i = 0; > - int ret = 0; > - > - while (!list_empty(&packed->list)) { > - prq = list_entry_rq(packed->list.next); > - if (idx == i) { > - /* retry from error index */ > - packed->nr_entries -= idx; > - mq_rq->req = prq; > - ret = 1; > - > - if (packed->nr_entries == MMC_PACKED_NR_SINGLE) { > - list_del_init(&prq->queuelist); > - mmc_blk_clear_packed(mq_rq); > - } > - return ret; > - } > - list_del_init(&prq->queuelist); > - blk_end_request(prq, 0, blk_rq_bytes(prq)); > - i++; > } > - > - mmc_blk_clear_packed(mq_rq); > return ret; > } > > -static void mmc_blk_abort_packed_req(struct mmc_queue_req *mq_rq) > -{ > - struct request *prq; > - struct mmc_packed *packed = mq_rq->packed; > - > - while (!list_empty(&packed->list)) { > - prq = list_entry_rq(packed->list.next); > - list_del_init(&prq->queuelist); > - blk_end_request(prq, -EIO, blk_rq_bytes(prq)); > - } > - > - mmc_blk_clear_packed(mq_rq); > -} > - > -static void mmc_blk_revert_packed_req(struct mmc_queue *mq, > - struct mmc_queue_req *mq_rq) > -{ > - struct request *prq; > - struct request_queue *q = mq->queue; > - struct mmc_packed *packed = mq_rq->packed; > - > - while (!list_empty(&packed->list)) { > - prq = list_entry_rq(packed->list.prev); > - if (prq->queuelist.prev != &packed->list) { > - list_del_init(&prq->queuelist); > - spin_lock_irq(q->queue_lock); > - blk_requeue_request(mq->queue, prq); > - spin_unlock_irq(q->queue_lock); > - } else { > - list_del_init(&prq->queuelist); > - } > - } > - > - mmc_blk_clear_packed(mq_rq); > -} > - > static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) > { > struct mmc_blk_data *md = mq->blkdata; > @@ -2006,15 +1601,10 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) > struct mmc_queue_req *mq_rq; > struct request *req = rqc; > struct mmc_async_req *areq; > - const u8 packed_nr = 2; > - u8 reqs = 0; > > if (!rqc && !mq->mqrq_prev->req) > return 0; > > - if (rqc) > - reqs = mmc_blk_prep_packed_list(mq, rqc); > - > do { > if (rqc) { > /* > @@ -2029,11 +1619,7 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) > goto cmd_abort; > } > > - if (reqs >= packed_nr) > - mmc_blk_packed_hdr_wrq_prep(mq->mqrq_cur, > - card, mq); > - else > - mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq); > + mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq); > areq = &mq->mqrq_cur->mmc_active; > } else > areq = NULL; > @@ -2058,13 +1644,8 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) > */ > mmc_blk_reset_success(md, type); > > - if (mmc_packed_cmd(mq_rq->cmd_type)) { > - ret = mmc_blk_end_packed_req(mq_rq); > - break; > - } else { > - ret = blk_end_request(req, 0, > - brq->data.bytes_xfered); > - } > + ret = blk_end_request(req, 0, > + brq->data.bytes_xfered); > > /* > * If the blk_end_request function returns non-zero even > @@ -2101,8 +1682,7 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) > err = mmc_blk_reset(md, card->host, type); > if (!err) > break; > - if (err == -ENODEV || > - mmc_packed_cmd(mq_rq->cmd_type)) > + if (err == -ENODEV) > goto cmd_abort; > /* Fall through */ > } > @@ -2133,23 +1713,14 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) > } > > if (ret) { > - if (mmc_packed_cmd(mq_rq->cmd_type)) { > - if (!mq_rq->packed->retries) > - goto cmd_abort; > - mmc_blk_packed_hdr_wrq_prep(mq_rq, card, mq); > - mmc_start_req(card->host, > - &mq_rq->mmc_active, NULL); > - } else { > - > - /* > - * In case of a incomplete request > - * prepare it again and resend. > - */ > - mmc_blk_rw_rq_prep(mq_rq, card, > - disable_multi, mq); > - mmc_start_req(card->host, > - &mq_rq->mmc_active, NULL); > - } > + /* > + * In case of a incomplete request > + * prepare it again and resend. > + */ > + mmc_blk_rw_rq_prep(mq_rq, card, > + disable_multi, mq); > + mmc_start_req(card->host, > + &mq_rq->mmc_active, NULL); > mq_rq->brq.retune_retry_done = retune_retry_done; > } > } while (ret); > @@ -2157,15 +1728,11 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) > return 1; > > cmd_abort: > - if (mmc_packed_cmd(mq_rq->cmd_type)) { > - mmc_blk_abort_packed_req(mq_rq); > - } else { > - if (mmc_card_removed(card)) > - req->cmd_flags |= REQ_QUIET; > - while (ret) > - ret = blk_end_request(req, -EIO, > - blk_rq_cur_bytes(req)); > - } > + if (mmc_card_removed(card)) > + req->cmd_flags |= REQ_QUIET; > + while (ret) > + ret = blk_end_request(req, -EIO, > + blk_rq_cur_bytes(req)); > > start_new_req: > if (rqc) { > @@ -2173,12 +1740,6 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) > rqc->cmd_flags |= REQ_QUIET; > blk_end_request_all(rqc, -EIO); > } else { > - /* > - * If current request is packed, it needs to put back. > - */ > - if (mmc_packed_cmd(mq->mqrq_cur->cmd_type)) > - mmc_blk_revert_packed_req(mq, mq->mqrq_cur); > - > mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq); > mmc_start_req(card->host, > &mq->mqrq_cur->mmc_active, NULL); > @@ -2361,14 +1922,6 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, > blk_queue_write_cache(md->queue.queue, true, true); > } > > - if (mmc_card_mmc(card) && > - (area_type == MMC_BLK_DATA_AREA_MAIN) && > - (md->flags & MMC_BLK_CMD23) && > - card->ext_csd.packed_event_en) { > - if (!mmc_packed_init(&md->queue, card)) > - md->flags |= MMC_BLK_PACKED_CMD; > - } > - > return md; > > err_putdisk: > @@ -2472,8 +2025,6 @@ static void mmc_blk_remove_req(struct mmc_blk_data *md) > */ > card = md->queue.card; > mmc_cleanup_queue(&md->queue); > - if (md->flags & MMC_BLK_PACKED_CMD) > - mmc_packed_clean(&md->queue); > if (md->disk->flags & GENHD_FL_UP) { > device_remove_file(disk_to_dev(md->disk), &md->force_ro); > if ((md->area_type & MMC_BLK_DATA_AREA_BOOT) && > diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c > index 3f6a2463ab30..7dacf2744fbd 100644 > --- a/drivers/mmc/card/queue.c > +++ b/drivers/mmc/card/queue.c > @@ -406,41 +406,6 @@ void mmc_queue_resume(struct mmc_queue *mq) > } > } > > -static unsigned int mmc_queue_packed_map_sg(struct mmc_queue *mq, > - struct mmc_packed *packed, > - struct scatterlist *sg, > - enum mmc_packed_type cmd_type) > -{ > - struct scatterlist *__sg = sg; > - unsigned int sg_len = 0; > - struct request *req; > - > - if (mmc_packed_wr(cmd_type)) { > - unsigned int hdr_sz = mmc_large_sector(mq->card) ? 4096 : 512; > - unsigned int max_seg_sz = queue_max_segment_size(mq->queue); > - unsigned int len, remain, offset = 0; > - u8 *buf = (u8 *)packed->cmd_hdr; > - > - remain = hdr_sz; > - do { > - len = min(remain, max_seg_sz); > - sg_set_buf(__sg, buf + offset, len); > - offset += len; > - remain -= len; > - sg_unmark_end(__sg++); > - sg_len++; > - } while (remain); > - } > - > - list_for_each_entry(req, &packed->list, queuelist) { > - sg_len += blk_rq_map_sg(mq->queue, req, __sg); > - __sg = sg + (sg_len - 1); > - sg_unmark_end(__sg++); > - } > - sg_mark_end(sg + (sg_len - 1)); > - return sg_len; > -} > - > /* > * Prepare the sg list(s) to be handed of to the host driver > */ > @@ -449,26 +414,14 @@ unsigned int mmc_queue_map_sg(struct mmc_queue *mq, struct mmc_queue_req *mqrq) > unsigned int sg_len; > size_t buflen; > struct scatterlist *sg; > - enum mmc_packed_type cmd_type; > int i; > > - cmd_type = mqrq->cmd_type; > - > - if (!mqrq->bounce_buf) { > - if (mmc_packed_cmd(cmd_type)) > - return mmc_queue_packed_map_sg(mq, mqrq->packed, > - mqrq->sg, cmd_type); > - else > - return blk_rq_map_sg(mq->queue, mqrq->req, mqrq->sg); > - } > + if (!mqrq->bounce_buf) > + return blk_rq_map_sg(mq->queue, mqrq->req, mqrq->sg); > > BUG_ON(!mqrq->bounce_sg); > > - if (mmc_packed_cmd(cmd_type)) > - sg_len = mmc_queue_packed_map_sg(mq, mqrq->packed, > - mqrq->bounce_sg, cmd_type); > - else > - sg_len = blk_rq_map_sg(mq->queue, mqrq->req, mqrq->bounce_sg); > + sg_len = blk_rq_map_sg(mq->queue, mqrq->req, mqrq->bounce_sg); > > mqrq->bounce_sg_len = sg_len; > > diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h > index 334c9306070f..47f5532b5776 100644 > --- a/drivers/mmc/card/queue.h > +++ b/drivers/mmc/card/queue.h > @@ -22,23 +22,6 @@ struct mmc_blk_request { > int retune_retry_done; > }; > > -enum mmc_packed_type { > - MMC_PACKED_NONE = 0, > - MMC_PACKED_WRITE, > -}; > - > -#define mmc_packed_cmd(type) ((type) != MMC_PACKED_NONE) > -#define mmc_packed_wr(type) ((type) == MMC_PACKED_WRITE) > - > -struct mmc_packed { > - struct list_head list; > - __le32 cmd_hdr[1024]; > - unsigned int blocks; > - u8 nr_entries; > - u8 retries; > - s16 idx_failure; > -}; > - > struct mmc_queue_req { > struct request *req; > struct mmc_blk_request brq; > @@ -47,8 +30,6 @@ struct mmc_queue_req { > struct scatterlist *bounce_sg; > unsigned int bounce_sg_len; > struct mmc_async_req mmc_active; > - enum mmc_packed_type cmd_type; > - struct mmc_packed *packed; > }; > > struct mmc_queue { > diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h > index 2a6418d0c343..2ce32fefb41c 100644 > --- a/include/linux/mmc/host.h > +++ b/include/linux/mmc/host.h > @@ -494,11 +494,6 @@ static inline int mmc_host_uhs(struct mmc_host *host) > MMC_CAP_UHS_DDR50); > } > > -static inline int mmc_host_packed_wr(struct mmc_host *host) > -{ > - return host->caps2 & MMC_CAP2_PACKED_WR; > -} > - > static inline int mmc_card_hs(struct mmc_card *card) > { > return card->host->ios.timing == MMC_TIMING_SD_HS || > -- > 2.7.4 > -- To unsubscribe from this list: send the line "unsubscribe linux-mmc" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Hi Ulf and Linus, I understand your concerns about the current packed commands support and the problem of transition to blk_mq. But as I mentioned in previous email thread, the packed commands feature is still in use on eMMC4.5 or eMMC5.1 devices on hosts without SW/HW CMDQ support. Taking this feature out meaning stop supporting one of important performance features of eMMC devices. Looking forward this feature is replaced with a CMDQ, but should we kill it for those who doesn’t have a CMDQ? Thanks, Alex On 11/25/16, 3:30 PM, "linux-mmc-owner@vger.kernel.org on behalf of Ulf Hansson" <linux-mmc-owner@vger.kernel.org on behalf of ulf.hansson@linaro.org> wrote: >On 25 November 2016 at 10:35, Linus Walleij <linus.walleij@linaro.org> wrote: >> I've had it with this code now. >> >> The packed command support is a complex hurdle in the MMC/SD block >> layer, around 500+ lines of code which was introduced in 2013 in >> commits >> >> ce39f9d17c14 ("mmc: support packed write command for eMMC4.5 devices") >> abd9ac144947 ("mmc: add packed command feature of eMMC4.5") >> >> ...and since then it has been rotting. The original author of the >> code has disappeared from the community and the mail address is >> bouncing. >> >> For the code to be exercised the host must flag that it supports >> packed commands, so in mmc_blk_prep_packed_list() which is called for >> every single request, the following construction appears: >> >> u8 max_packed_rw = 0; >> >> if ((rq_data_dir(cur) == WRITE) && >> mmc_host_packed_wr(card->host)) >> max_packed_rw = card->ext_csd.max_packed_writes; >> >> if (max_packed_rw == 0) >> goto no_packed; >> >> This has the following logical deductions: >> >> - Only WRITE commands can really be packed, so the solution is >> only half-done: we support packed WRITE but not packed READ. >> The packed command support has not been finalized by supporting >> reads in three years! >> >> - mmc_host_packed_wr() is just a static inline that checks >> host->caps2 & MMC_CAP2_PACKED_WR. The problem with this is >> that NO upstream host sets this capability flag! No driver >> in the kernel is using it, and we can't test it. Packed >> command may be supported in out-of-tree code, but I doubt >> it. I doubt that the code is even working anymore due to >> other refactorings in the MMC block layer, who would >> notice if patches affecting it broke packed commands? >> No one. >> >> - There is no Device Tree binding or code to mark a host as >> supporting packed read or write commands, just this flag >> in caps2, so for sure there are not any DT systems using >> it either. >> >> It has other problems as well: mmc_blk_prep_packed_list() is >> speculatively picking requests out of the request queue with >> blk_fetch_request() making the MMC/SD stack harder to convert >> to the multiqueue block layer. By this we get rid of an >> obstacle. >> >> The way I see it this is just cruft littering the MMC/SD >> stack. >> >> Cc: Namjae Jeon <namjae.jeon@samsung.com> >> Cc: Maya Erez <qca_merez@qca.qualcomm.com> >> Acked-by: Jaehoon Chung <jh80.chung@samsung.com> >> Signed-off-by: Linus Walleij <linus.walleij@linaro.org> > >Thanks, applied for next! > >Kind regards >Uffe >
On Sun, Nov 27, 2016 at 02:25:15PM +0000, Alex Lemberg wrote: > I understand your concerns about the current packed commands > support and the problem of transition to blk_mq. > But as I mentioned in previous email thread, the packed commands > feature is still in use on eMMC4.5 or eMMC5.1 devices on hosts > without SW/HW CMDQ support. > Taking this feature out meaning stop supporting one of important > performance features of eMMC devices. > Looking forward this feature is replaced with a CMDQ, but should we > kill it for those who doesn’t have a CMDQ? No driver actually uses it, as-is it's simply dead code. -- To unsubscribe from this list: send the line "unsubscribe linux-mmc" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On 27 November 2016 at 15:25, Alex Lemberg <Alex.Lemberg@sandisk.com> wrote: > Hi Ulf and Linus, > > I understand your concerns about the current packed commands > support and the problem of transition to blk_mq. > But as I mentioned in previous email thread, the packed commands > feature is still in use on eMMC4.5 or eMMC5.1 devices on hosts > without SW/HW CMDQ support. > Taking this feature out meaning stop supporting one of important > performance features of eMMC devices. How do we get an improved performance from using packed-command? If this is about decreasing communication overhead, as the JEDEC spec states, we should compare against using the asynchronous request mechanism. Then is there really any noticeable improvement? > Looking forward this feature is replaced with a CMDQ, but should we > kill it for those who doesn’t have a CMDQ? Yes, I think so. From the performance perspective, but also from that there are no users of the code, except in some vendor trees - then there are just no justification for keep maintaining this messy piece of code. [...] Kind regards Uffe -- To unsubscribe from this list: send the line "unsubscribe linux-mmc" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Sun, Nov 27, 2016 at 3:25 PM, Alex Lemberg <Alex.Lemberg@sandisk.com> wrote: > I understand your concerns about the current packed commands > support and the problem of transition to blk_mq. It may be possible to re-implement the feature later, but then only if we get some queue inspection features in blk-mq. Do you agree with my assessment in the thread that this feature can only really make an improvement on random writes, i.e. it will not improve reads (even random reads) and it will not improve sequential writes? > But as I mentioned in previous email thread, the packed commands > feature is still in use on eMMC4.5 or eMMC5.1 devices on hosts > without SW/HW CMDQ support. True. In the market place of devices, sure. But noone is maintaining or testing the code in the Linux kernel. Noone bothered to enable it for their platform so we can test it. > Taking this feature out meaning stop supporting one of important > performance features of eMMC devices. > Looking forward this feature is replaced with a CMDQ, but should we > kill it for those who doesn’t have a CMDQ? What we need from memory card vendors like you (SanDisk) is a target test rig. That is: a board with an SoC that we developers can get hold of (for reasonable cost) and where both the host controller and the eMMC card has the desired features so we can test it. Also that this board has support in the upstream kernel. There are too many vendor trees with too much forked code out there, I know this is common, but we cannot develop important core features in the kernel that have no in-kernel user and no way for us to test it if we need to re-write the code, it is just unmaintainable. Yours, Linus Walleij -- To unsubscribe from this list: send the line "unsubscribe linux-mmc" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 6618126fcb9f..86ff28f84698 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -66,9 +66,6 @@ MODULE_ALIAS("mmc:block"); #define mmc_req_rel_wr(req) ((req->cmd_flags & REQ_FUA) && \ (rq_data_dir(req) == WRITE)) -#define PACKED_CMD_VER 0x01 -#define PACKED_CMD_WR 0x02 - static DEFINE_MUTEX(block_mutex); /* @@ -102,7 +99,6 @@ struct mmc_blk_data { unsigned int flags; #define MMC_BLK_CMD23 (1 << 0) /* Can do SET_BLOCK_COUNT for multiblock */ #define MMC_BLK_REL_WR (1 << 1) /* MMC Reliable write support */ -#define MMC_BLK_PACKED_CMD (1 << 2) /* MMC packed command support */ unsigned int usage; unsigned int read_only; @@ -126,12 +122,6 @@ struct mmc_blk_data { static DEFINE_MUTEX(open_lock); -enum { - MMC_PACKED_NR_IDX = -1, - MMC_PACKED_NR_ZERO, - MMC_PACKED_NR_SINGLE, -}; - module_param(perdev_minors, int, 0444); MODULE_PARM_DESC(perdev_minors, "Minors numbers to allocate per device"); @@ -139,17 +129,6 @@ static inline int mmc_blk_part_switch(struct mmc_card *card, struct mmc_blk_data *md); static int get_card_status(struct mmc_card *card, u32 *status, int retries); -static inline void mmc_blk_clear_packed(struct mmc_queue_req *mqrq) -{ - struct mmc_packed *packed = mqrq->packed; - - mqrq->cmd_type = MMC_PACKED_NONE; - packed->nr_entries = MMC_PACKED_NR_ZERO; - packed->idx_failure = MMC_PACKED_NR_IDX; - packed->retries = 0; - packed->blocks = 0; -} - static struct mmc_blk_data *mmc_blk_get(struct gendisk *disk) { struct mmc_blk_data *md; @@ -1420,111 +1399,12 @@ static enum mmc_blk_status mmc_blk_err_check(struct mmc_card *card, if (!brq->data.bytes_xfered) return MMC_BLK_RETRY; - if (mmc_packed_cmd(mq_mrq->cmd_type)) { - if (unlikely(brq->data.blocks << 9 != brq->data.bytes_xfered)) - return MMC_BLK_PARTIAL; - else - return MMC_BLK_SUCCESS; - } - if (blk_rq_bytes(req) != brq->data.bytes_xfered) return MMC_BLK_PARTIAL; return MMC_BLK_SUCCESS; } -static int mmc_packed_init(struct mmc_queue *mq, struct mmc_card *card) -{ - struct mmc_queue_req *mqrq_cur = &mq->mqrq[0]; - struct mmc_queue_req *mqrq_prev = &mq->mqrq[1]; - int ret = 0; - - - mqrq_cur->packed = kzalloc(sizeof(struct mmc_packed), GFP_KERNEL); - if (!mqrq_cur->packed) { - pr_warn("%s: unable to allocate packed cmd for mqrq_cur\n", - mmc_card_name(card)); - ret = -ENOMEM; - goto out; - } - - mqrq_prev->packed = kzalloc(sizeof(struct mmc_packed), GFP_KERNEL); - if (!mqrq_prev->packed) { - pr_warn("%s: unable to allocate packed cmd for mqrq_prev\n", - mmc_card_name(card)); - kfree(mqrq_cur->packed); - mqrq_cur->packed = NULL; - ret = -ENOMEM; - goto out; - } - - INIT_LIST_HEAD(&mqrq_cur->packed->list); - INIT_LIST_HEAD(&mqrq_prev->packed->list); - -out: - return ret; -} - -static void mmc_packed_clean(struct mmc_queue *mq) -{ - struct mmc_queue_req *mqrq_cur = &mq->mqrq[0]; - struct mmc_queue_req *mqrq_prev = &mq->mqrq[1]; - - kfree(mqrq_cur->packed); - mqrq_cur->packed = NULL; - kfree(mqrq_prev->packed); - mqrq_prev->packed = NULL; -} - -static enum mmc_blk_status mmc_blk_packed_err_check(struct mmc_card *card, - struct mmc_async_req *areq) -{ - struct mmc_queue_req *mq_rq = container_of(areq, struct mmc_queue_req, - mmc_active); - struct request *req = mq_rq->req; - struct mmc_packed *packed = mq_rq->packed; - enum mmc_blk_status status, check; - int err; - u8 *ext_csd; - - packed->retries--; - check = mmc_blk_err_check(card, areq); - err = get_card_status(card, &status, 0); - if (err) { - pr_err("%s: error %d sending status command\n", - req->rq_disk->disk_name, err); - return MMC_BLK_ABORT; - } - - if (status & R1_EXCEPTION_EVENT) { - err = mmc_get_ext_csd(card, &ext_csd); - if (err) { - pr_err("%s: error %d sending ext_csd\n", - req->rq_disk->disk_name, err); - return MMC_BLK_ABORT; - } - - if ((ext_csd[EXT_CSD_EXP_EVENTS_STATUS] & - EXT_CSD_PACKED_FAILURE) && - (ext_csd[EXT_CSD_PACKED_CMD_STATUS] & - EXT_CSD_PACKED_GENERIC_ERROR)) { - if (ext_csd[EXT_CSD_PACKED_CMD_STATUS] & - EXT_CSD_PACKED_INDEXED_ERROR) { - packed->idx_failure = - ext_csd[EXT_CSD_PACKED_FAILURE_INDEX] - 1; - check = MMC_BLK_PARTIAL; - } - pr_err("%s: packed cmd failed, nr %u, sectors %u, " - "failure index: %d\n", - req->rq_disk->disk_name, packed->nr_entries, - packed->blocks, packed->idx_failure); - } - kfree(ext_csd); - } - - return check; -} - static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq, struct mmc_card *card, int disable_multi, @@ -1685,222 +1565,6 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq, mmc_queue_bounce_pre(mqrq); } -static inline u8 mmc_calc_packed_hdr_segs(struct request_queue *q, - struct mmc_card *card) -{ - unsigned int hdr_sz = mmc_large_sector(card) ? 4096 : 512; - unsigned int max_seg_sz = queue_max_segment_size(q); - unsigned int len, nr_segs = 0; - - do { - len = min(hdr_sz, max_seg_sz); - hdr_sz -= len; - nr_segs++; - } while (hdr_sz); - - return nr_segs; -} - -static u8 mmc_blk_prep_packed_list(struct mmc_queue *mq, struct request *req) -{ - struct request_queue *q = mq->queue; - struct mmc_card *card = mq->card; - struct request *cur = req, *next = NULL; - struct mmc_blk_data *md = mq->blkdata; - struct mmc_queue_req *mqrq = mq->mqrq_cur; - bool en_rel_wr = card->ext_csd.rel_param & EXT_CSD_WR_REL_PARAM_EN; - unsigned int req_sectors = 0, phys_segments = 0; - unsigned int max_blk_count, max_phys_segs; - bool put_back = true; - u8 max_packed_rw = 0; - u8 reqs = 0; - - /* - * We don't need to check packed for any further - * operation of packed stuff as we set MMC_PACKED_NONE - * and return zero for reqs if geting null packed. Also - * we clean the flag of MMC_BLK_PACKED_CMD to avoid doing - * it again when removing blk req. - */ - if (!mqrq->packed) { - md->flags &= (~MMC_BLK_PACKED_CMD); - goto no_packed; - } - - if (!(md->flags & MMC_BLK_PACKED_CMD)) - goto no_packed; - - if ((rq_data_dir(cur) == WRITE) && - mmc_host_packed_wr(card->host)) - max_packed_rw = card->ext_csd.max_packed_writes; - - if (max_packed_rw == 0) - goto no_packed; - - if (mmc_req_rel_wr(cur) && - (md->flags & MMC_BLK_REL_WR) && !en_rel_wr) - goto no_packed; - - if (mmc_large_sector(card) && - !IS_ALIGNED(blk_rq_sectors(cur), 8)) - goto no_packed; - - mmc_blk_clear_packed(mqrq); - - max_blk_count = min(card->host->max_blk_count, - card->host->max_req_size >> 9); - if (unlikely(max_blk_count > 0xffff)) - max_blk_count = 0xffff; - - max_phys_segs = queue_max_segments(q); - req_sectors += blk_rq_sectors(cur); - phys_segments += cur->nr_phys_segments; - - if (rq_data_dir(cur) == WRITE) { - req_sectors += mmc_large_sector(card) ? 8 : 1; - phys_segments += mmc_calc_packed_hdr_segs(q, card); - } - - do { - if (reqs >= max_packed_rw - 1) { - put_back = false; - break; - } - - spin_lock_irq(q->queue_lock); - next = blk_fetch_request(q); - spin_unlock_irq(q->queue_lock); - if (!next) { - put_back = false; - break; - } - - if (mmc_large_sector(card) && - !IS_ALIGNED(blk_rq_sectors(next), 8)) - break; - - if (mmc_req_is_special(next)) - break; - - if (rq_data_dir(cur) != rq_data_dir(next)) - break; - - if (mmc_req_rel_wr(next) && - (md->flags & MMC_BLK_REL_WR) && !en_rel_wr) - break; - - req_sectors += blk_rq_sectors(next); - if (req_sectors > max_blk_count) - break; - - phys_segments += next->nr_phys_segments; - if (phys_segments > max_phys_segs) - break; - - list_add_tail(&next->queuelist, &mqrq->packed->list); - cur = next; - reqs++; - } while (1); - - if (put_back) { - spin_lock_irq(q->queue_lock); - blk_requeue_request(q, next); - spin_unlock_irq(q->queue_lock); - } - - if (reqs > 0) { - list_add(&req->queuelist, &mqrq->packed->list); - mqrq->packed->nr_entries = ++reqs; - mqrq->packed->retries = reqs; - return reqs; - } - -no_packed: - mqrq->cmd_type = MMC_PACKED_NONE; - return 0; -} - -static void mmc_blk_packed_hdr_wrq_prep(struct mmc_queue_req *mqrq, - struct mmc_card *card, - struct mmc_queue *mq) -{ - struct mmc_blk_request *brq = &mqrq->brq; - struct request *req = mqrq->req; - struct request *prq; - struct mmc_blk_data *md = mq->blkdata; - struct mmc_packed *packed = mqrq->packed; - bool do_rel_wr, do_data_tag; - __le32 *packed_cmd_hdr; - u8 hdr_blocks; - u8 i = 1; - - mqrq->cmd_type = MMC_PACKED_WRITE; - packed->blocks = 0; - packed->idx_failure = MMC_PACKED_NR_IDX; - - packed_cmd_hdr = packed->cmd_hdr; - memset(packed_cmd_hdr, 0, sizeof(packed->cmd_hdr)); - packed_cmd_hdr[0] = cpu_to_le32((packed->nr_entries << 16) | - (PACKED_CMD_WR << 8) | PACKED_CMD_VER); - hdr_blocks = mmc_large_sector(card) ? 8 : 1; - - /* - * Argument for each entry of packed group - */ - list_for_each_entry(prq, &packed->list, queuelist) { - do_rel_wr = mmc_req_rel_wr(prq) && (md->flags & MMC_BLK_REL_WR); - do_data_tag = (card->ext_csd.data_tag_unit_size) && - (prq->cmd_flags & REQ_META) && - (rq_data_dir(prq) == WRITE) && - blk_rq_bytes(prq) >= card->ext_csd.data_tag_unit_size; - /* Argument of CMD23 */ - packed_cmd_hdr[(i * 2)] = cpu_to_le32( - (do_rel_wr ? MMC_CMD23_ARG_REL_WR : 0) | - (do_data_tag ? MMC_CMD23_ARG_TAG_REQ : 0) | - blk_rq_sectors(prq)); - /* Argument of CMD18 or CMD25 */ - packed_cmd_hdr[((i * 2)) + 1] = cpu_to_le32( - mmc_card_blockaddr(card) ? - blk_rq_pos(prq) : blk_rq_pos(prq) << 9); - packed->blocks += blk_rq_sectors(prq); - i++; - } - - memset(brq, 0, sizeof(struct mmc_blk_request)); - brq->mrq.cmd = &brq->cmd; - brq->mrq.data = &brq->data; - brq->mrq.sbc = &brq->sbc; - brq->mrq.stop = &brq->stop; - - brq->sbc.opcode = MMC_SET_BLOCK_COUNT; - brq->sbc.arg = MMC_CMD23_ARG_PACKED | (packed->blocks + hdr_blocks); - brq->sbc.flags = MMC_RSP_R1 | MMC_CMD_AC; - - brq->cmd.opcode = MMC_WRITE_MULTIPLE_BLOCK; - brq->cmd.arg = blk_rq_pos(req); - if (!mmc_card_blockaddr(card)) - brq->cmd.arg <<= 9; - brq->cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_ADTC; - - brq->data.blksz = 512; - brq->data.blocks = packed->blocks + hdr_blocks; - brq->data.flags = MMC_DATA_WRITE; - - brq->stop.opcode = MMC_STOP_TRANSMISSION; - brq->stop.arg = 0; - brq->stop.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC; - - mmc_set_data_timeout(&brq->data, card); - - brq->data.sg = mqrq->sg; - brq->data.sg_len = mmc_queue_map_sg(mq, mqrq); - - mqrq->mmc_active.mrq = &brq->mrq; - mqrq->mmc_active.err_check = mmc_blk_packed_err_check; - - mmc_queue_bounce_pre(mqrq); -} - static int mmc_blk_cmd_err(struct mmc_blk_data *md, struct mmc_card *card, struct mmc_blk_request *brq, struct request *req, int ret) @@ -1923,79 +1587,10 @@ static int mmc_blk_cmd_err(struct mmc_blk_data *md, struct mmc_card *card, if (blocks != (u32)-1) { ret = blk_end_request(req, 0, blocks << 9); } - } else { - if (!mmc_packed_cmd(mq_rq->cmd_type)) - ret = blk_end_request(req, 0, brq->data.bytes_xfered); - } - return ret; -} - -static int mmc_blk_end_packed_req(struct mmc_queue_req *mq_rq) -{ - struct request *prq; - struct mmc_packed *packed = mq_rq->packed; - int idx = packed->idx_failure, i = 0; - int ret = 0; - - while (!list_empty(&packed->list)) { - prq = list_entry_rq(packed->list.next); - if (idx == i) { - /* retry from error index */ - packed->nr_entries -= idx; - mq_rq->req = prq; - ret = 1; - - if (packed->nr_entries == MMC_PACKED_NR_SINGLE) { - list_del_init(&prq->queuelist); - mmc_blk_clear_packed(mq_rq); - } - return ret; - } - list_del_init(&prq->queuelist); - blk_end_request(prq, 0, blk_rq_bytes(prq)); - i++; } - - mmc_blk_clear_packed(mq_rq); return ret; } -static void mmc_blk_abort_packed_req(struct mmc_queue_req *mq_rq) -{ - struct request *prq; - struct mmc_packed *packed = mq_rq->packed; - - while (!list_empty(&packed->list)) { - prq = list_entry_rq(packed->list.next); - list_del_init(&prq->queuelist); - blk_end_request(prq, -EIO, blk_rq_bytes(prq)); - } - - mmc_blk_clear_packed(mq_rq); -} - -static void mmc_blk_revert_packed_req(struct mmc_queue *mq, - struct mmc_queue_req *mq_rq) -{ - struct request *prq; - struct request_queue *q = mq->queue; - struct mmc_packed *packed = mq_rq->packed; - - while (!list_empty(&packed->list)) { - prq = list_entry_rq(packed->list.prev); - if (prq->queuelist.prev != &packed->list) { - list_del_init(&prq->queuelist); - spin_lock_irq(q->queue_lock); - blk_requeue_request(mq->queue, prq); - spin_unlock_irq(q->queue_lock); - } else { - list_del_init(&prq->queuelist); - } - } - - mmc_blk_clear_packed(mq_rq); -} - static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) { struct mmc_blk_data *md = mq->blkdata; @@ -2006,15 +1601,10 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) struct mmc_queue_req *mq_rq; struct request *req = rqc; struct mmc_async_req *areq; - const u8 packed_nr = 2; - u8 reqs = 0; if (!rqc && !mq->mqrq_prev->req) return 0; - if (rqc) - reqs = mmc_blk_prep_packed_list(mq, rqc); - do { if (rqc) { /* @@ -2029,11 +1619,7 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) goto cmd_abort; } - if (reqs >= packed_nr) - mmc_blk_packed_hdr_wrq_prep(mq->mqrq_cur, - card, mq); - else - mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq); + mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq); areq = &mq->mqrq_cur->mmc_active; } else areq = NULL; @@ -2058,13 +1644,8 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) */ mmc_blk_reset_success(md, type); - if (mmc_packed_cmd(mq_rq->cmd_type)) { - ret = mmc_blk_end_packed_req(mq_rq); - break; - } else { - ret = blk_end_request(req, 0, - brq->data.bytes_xfered); - } + ret = blk_end_request(req, 0, + brq->data.bytes_xfered); /* * If the blk_end_request function returns non-zero even @@ -2101,8 +1682,7 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) err = mmc_blk_reset(md, card->host, type); if (!err) break; - if (err == -ENODEV || - mmc_packed_cmd(mq_rq->cmd_type)) + if (err == -ENODEV) goto cmd_abort; /* Fall through */ } @@ -2133,23 +1713,14 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) } if (ret) { - if (mmc_packed_cmd(mq_rq->cmd_type)) { - if (!mq_rq->packed->retries) - goto cmd_abort; - mmc_blk_packed_hdr_wrq_prep(mq_rq, card, mq); - mmc_start_req(card->host, - &mq_rq->mmc_active, NULL); - } else { - - /* - * In case of a incomplete request - * prepare it again and resend. - */ - mmc_blk_rw_rq_prep(mq_rq, card, - disable_multi, mq); - mmc_start_req(card->host, - &mq_rq->mmc_active, NULL); - } + /* + * In case of a incomplete request + * prepare it again and resend. + */ + mmc_blk_rw_rq_prep(mq_rq, card, + disable_multi, mq); + mmc_start_req(card->host, + &mq_rq->mmc_active, NULL); mq_rq->brq.retune_retry_done = retune_retry_done; } } while (ret); @@ -2157,15 +1728,11 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) return 1; cmd_abort: - if (mmc_packed_cmd(mq_rq->cmd_type)) { - mmc_blk_abort_packed_req(mq_rq); - } else { - if (mmc_card_removed(card)) - req->cmd_flags |= REQ_QUIET; - while (ret) - ret = blk_end_request(req, -EIO, - blk_rq_cur_bytes(req)); - } + if (mmc_card_removed(card)) + req->cmd_flags |= REQ_QUIET; + while (ret) + ret = blk_end_request(req, -EIO, + blk_rq_cur_bytes(req)); start_new_req: if (rqc) { @@ -2173,12 +1740,6 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) rqc->cmd_flags |= REQ_QUIET; blk_end_request_all(rqc, -EIO); } else { - /* - * If current request is packed, it needs to put back. - */ - if (mmc_packed_cmd(mq->mqrq_cur->cmd_type)) - mmc_blk_revert_packed_req(mq, mq->mqrq_cur); - mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq); mmc_start_req(card->host, &mq->mqrq_cur->mmc_active, NULL); @@ -2361,14 +1922,6 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, blk_queue_write_cache(md->queue.queue, true, true); } - if (mmc_card_mmc(card) && - (area_type == MMC_BLK_DATA_AREA_MAIN) && - (md->flags & MMC_BLK_CMD23) && - card->ext_csd.packed_event_en) { - if (!mmc_packed_init(&md->queue, card)) - md->flags |= MMC_BLK_PACKED_CMD; - } - return md; err_putdisk: @@ -2472,8 +2025,6 @@ static void mmc_blk_remove_req(struct mmc_blk_data *md) */ card = md->queue.card; mmc_cleanup_queue(&md->queue); - if (md->flags & MMC_BLK_PACKED_CMD) - mmc_packed_clean(&md->queue); if (md->disk->flags & GENHD_FL_UP) { device_remove_file(disk_to_dev(md->disk), &md->force_ro); if ((md->area_type & MMC_BLK_DATA_AREA_BOOT) && diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index 3f6a2463ab30..7dacf2744fbd 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -406,41 +406,6 @@ void mmc_queue_resume(struct mmc_queue *mq) } } -static unsigned int mmc_queue_packed_map_sg(struct mmc_queue *mq, - struct mmc_packed *packed, - struct scatterlist *sg, - enum mmc_packed_type cmd_type) -{ - struct scatterlist *__sg = sg; - unsigned int sg_len = 0; - struct request *req; - - if (mmc_packed_wr(cmd_type)) { - unsigned int hdr_sz = mmc_large_sector(mq->card) ? 4096 : 512; - unsigned int max_seg_sz = queue_max_segment_size(mq->queue); - unsigned int len, remain, offset = 0; - u8 *buf = (u8 *)packed->cmd_hdr; - - remain = hdr_sz; - do { - len = min(remain, max_seg_sz); - sg_set_buf(__sg, buf + offset, len); - offset += len; - remain -= len; - sg_unmark_end(__sg++); - sg_len++; - } while (remain); - } - - list_for_each_entry(req, &packed->list, queuelist) { - sg_len += blk_rq_map_sg(mq->queue, req, __sg); - __sg = sg + (sg_len - 1); - sg_unmark_end(__sg++); - } - sg_mark_end(sg + (sg_len - 1)); - return sg_len; -} - /* * Prepare the sg list(s) to be handed of to the host driver */ @@ -449,26 +414,14 @@ unsigned int mmc_queue_map_sg(struct mmc_queue *mq, struct mmc_queue_req *mqrq) unsigned int sg_len; size_t buflen; struct scatterlist *sg; - enum mmc_packed_type cmd_type; int i; - cmd_type = mqrq->cmd_type; - - if (!mqrq->bounce_buf) { - if (mmc_packed_cmd(cmd_type)) - return mmc_queue_packed_map_sg(mq, mqrq->packed, - mqrq->sg, cmd_type); - else - return blk_rq_map_sg(mq->queue, mqrq->req, mqrq->sg); - } + if (!mqrq->bounce_buf) + return blk_rq_map_sg(mq->queue, mqrq->req, mqrq->sg); BUG_ON(!mqrq->bounce_sg); - if (mmc_packed_cmd(cmd_type)) - sg_len = mmc_queue_packed_map_sg(mq, mqrq->packed, - mqrq->bounce_sg, cmd_type); - else - sg_len = blk_rq_map_sg(mq->queue, mqrq->req, mqrq->bounce_sg); + sg_len = blk_rq_map_sg(mq->queue, mqrq->req, mqrq->bounce_sg); mqrq->bounce_sg_len = sg_len; diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h index 334c9306070f..47f5532b5776 100644 --- a/drivers/mmc/card/queue.h +++ b/drivers/mmc/card/queue.h @@ -22,23 +22,6 @@ struct mmc_blk_request { int retune_retry_done; }; -enum mmc_packed_type { - MMC_PACKED_NONE = 0, - MMC_PACKED_WRITE, -}; - -#define mmc_packed_cmd(type) ((type) != MMC_PACKED_NONE) -#define mmc_packed_wr(type) ((type) == MMC_PACKED_WRITE) - -struct mmc_packed { - struct list_head list; - __le32 cmd_hdr[1024]; - unsigned int blocks; - u8 nr_entries; - u8 retries; - s16 idx_failure; -}; - struct mmc_queue_req { struct request *req; struct mmc_blk_request brq; @@ -47,8 +30,6 @@ struct mmc_queue_req { struct scatterlist *bounce_sg; unsigned int bounce_sg_len; struct mmc_async_req mmc_active; - enum mmc_packed_type cmd_type; - struct mmc_packed *packed; }; struct mmc_queue { diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 2a6418d0c343..2ce32fefb41c 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -494,11 +494,6 @@ static inline int mmc_host_uhs(struct mmc_host *host) MMC_CAP_UHS_DDR50); } -static inline int mmc_host_packed_wr(struct mmc_host *host) -{ - return host->caps2 & MMC_CAP2_PACKED_WR; -} - static inline int mmc_card_hs(struct mmc_card *card) { return card->host->ios.timing == MMC_TIMING_SD_HS ||
I've had it with this code now. The packed command support is a complex hurdle in the MMC/SD block layer, around 500+ lines of code which was introduced in 2013 in commits ce39f9d17c14 ("mmc: support packed write command for eMMC4.5 devices") abd9ac144947 ("mmc: add packed command feature of eMMC4.5") ...and since then it has been rotting. The original author of the code has disappeared from the community and the mail address is bouncing. For the code to be exercised the host must flag that it supports packed commands, so in mmc_blk_prep_packed_list() which is called for every single request, the following construction appears: u8 max_packed_rw = 0; if ((rq_data_dir(cur) == WRITE) && mmc_host_packed_wr(card->host)) max_packed_rw = card->ext_csd.max_packed_writes; if (max_packed_rw == 0) goto no_packed; This has the following logical deductions: - Only WRITE commands can really be packed, so the solution is only half-done: we support packed WRITE but not packed READ. The packed command support has not been finalized by supporting reads in three years! - mmc_host_packed_wr() is just a static inline that checks host->caps2 & MMC_CAP2_PACKED_WR. The problem with this is that NO upstream host sets this capability flag! No driver in the kernel is using it, and we can't test it. Packed command may be supported in out-of-tree code, but I doubt it. I doubt that the code is even working anymore due to other refactorings in the MMC block layer, who would notice if patches affecting it broke packed commands? No one. - There is no Device Tree binding or code to mark a host as supporting packed read or write commands, just this flag in caps2, so for sure there are not any DT systems using it either. It has other problems as well: mmc_blk_prep_packed_list() is speculatively picking requests out of the request queue with blk_fetch_request() making the MMC/SD stack harder to convert to the multiqueue block layer. By this we get rid of an obstacle. The way I see it this is just cruft littering the MMC/SD stack. Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Maya Erez <qca_merez@qca.qualcomm.com> Acked-by: Jaehoon Chung <jh80.chung@samsung.com> Signed-off-by: Linus Walleij <linus.walleij@linaro.org> --- ChangeLog v2->v3: - Remove unused "reqs" variable, found by the build robot. ChangeLog v1->v2: - Rebased on Ulf's next branch - Added Jaehoon's ACK --- drivers/mmc/card/block.c | 483 ++--------------------------------------------- drivers/mmc/card/queue.c | 53 +----- drivers/mmc/card/queue.h | 19 -- include/linux/mmc/host.h | 5 - 4 files changed, 20 insertions(+), 540 deletions(-) -- 2.7.4 -- To unsubscribe from this list: send the line "unsubscribe linux-mmc" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html