X-Git-Url: http://git.samba.org/samba.git/?p=sfrench%2Fcifs-2.6.git;a=blobdiff_plain;f=drivers%2Flightnvm%2Fpblk-core.c;h=6944aac43b015de6625ca08d0b50a8514f13768d;hp=00984b486fea72a953652385c6133468f6f96810;hb=b0b6a28bc4b265aa56cbf4fa8fd27c0a4fa3a49c;hpb=0c4b0f815f20304156f66d47d0c2a6e148f6ffaa diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c index 00984b486fea..6944aac43b01 100644 --- a/drivers/lightnvm/pblk-core.c +++ b/drivers/lightnvm/pblk-core.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2016 CNEX Labs * Initial release: Javier Gonzalez @@ -16,7 +17,10 @@ * */ +#define CREATE_TRACE_POINTS + #include "pblk.h" +#include "pblk-trace.h" static void pblk_line_mark_bb(struct work_struct *work) { @@ -27,12 +31,12 @@ static void pblk_line_mark_bb(struct work_struct *work) struct ppa_addr *ppa = line_ws->priv; int ret; - ret = nvm_set_tgt_bb_tbl(dev, ppa, 1, NVM_BLK_T_GRWN_BAD); + ret = nvm_set_chunk_meta(dev, ppa, 1, NVM_BLK_T_GRWN_BAD); if (ret) { struct pblk_line *line; int pos; - line = &pblk->lines[pblk_ppa_to_line(*ppa)]; + line = pblk_ppa_to_line(pblk, *ppa); pos = pblk_ppa_to_pos(&dev->geo, *ppa); pblk_err(pblk, "failed to mark bb, line:%d, pos:%d\n", @@ -80,19 +84,28 @@ static void __pblk_end_io_erase(struct pblk *pblk, struct nvm_rq *rqd) struct pblk_line *line; int pos; - line = &pblk->lines[pblk_ppa_to_line(rqd->ppa_addr)]; + line = pblk_ppa_to_line(pblk, rqd->ppa_addr); pos = pblk_ppa_to_pos(geo, rqd->ppa_addr); chunk = &line->chks[pos]; atomic_dec(&line->left_seblks); if (rqd->error) { + trace_pblk_chunk_reset(pblk_disk_name(pblk), + &rqd->ppa_addr, PBLK_CHUNK_RESET_FAILED); + chunk->state = NVM_CHK_ST_OFFLINE; pblk_mark_bb(pblk, line, rqd->ppa_addr); } else { + trace_pblk_chunk_reset(pblk_disk_name(pblk), + &rqd->ppa_addr, PBLK_CHUNK_RESET_DONE); + chunk->state = NVM_CHK_ST_FREE; } + trace_pblk_chunk_state(pblk_disk_name(pblk), &rqd->ppa_addr, + chunk->state); + atomic_dec(&pblk->inflight_io); } @@ -108,9 +121,9 @@ static void pblk_end_io_erase(struct nvm_rq *rqd) /* * Get information for all chunks from the device. * - * The caller is responsible for freeing the returned structure + * The caller is responsible for freeing (vmalloc) the returned structure */ -struct nvm_chk_meta *pblk_chunk_get_info(struct pblk *pblk) +struct nvm_chk_meta *pblk_get_chunk_meta(struct pblk *pblk) { struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; @@ -122,11 +135,11 @@ struct nvm_chk_meta *pblk_chunk_get_info(struct pblk *pblk) ppa.ppa = 0; len = geo->all_chunks * sizeof(*meta); - meta = kzalloc(len, GFP_KERNEL); + meta = vzalloc(len); if (!meta) return ERR_PTR(-ENOMEM); - ret = nvm_get_chunk_meta(dev, meta, ppa, geo->all_chunks); + ret = nvm_get_chunk_meta(dev, ppa, geo->all_chunks, meta); if (ret) { kfree(meta); return ERR_PTR(-EIO); @@ -192,7 +205,6 @@ void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa) { struct pblk_line *line; u64 paddr; - int line_id; #ifdef CONFIG_NVM_PBLK_DEBUG /* Callers must ensure that the ppa points to a device address */ @@ -200,8 +212,7 @@ void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa) BUG_ON(pblk_ppa_empty(ppa)); #endif - line_id = pblk_ppa_to_line(ppa); - line = &pblk->lines[line_id]; + line = pblk_ppa_to_line(pblk, ppa); paddr = pblk_dev_ppa_to_line_addr(pblk, ppa); __pblk_map_invalidate(pblk, line, paddr); @@ -227,6 +238,33 @@ static void pblk_invalidate_range(struct pblk *pblk, sector_t slba, spin_unlock(&pblk->trans_lock); } +int pblk_alloc_rqd_meta(struct pblk *pblk, struct nvm_rq *rqd) +{ + struct nvm_tgt_dev *dev = pblk->dev; + + rqd->meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, + &rqd->dma_meta_list); + if (!rqd->meta_list) + return -ENOMEM; + + if (rqd->nr_ppas == 1) + return 0; + + rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size; + rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size; + + return 0; +} + +void pblk_free_rqd_meta(struct pblk *pblk, struct nvm_rq *rqd) +{ + struct nvm_tgt_dev *dev = pblk->dev; + + if (rqd->meta_list) + nvm_dev_dma_free(dev->parent, rqd->meta_list, + rqd->dma_meta_list); +} + /* Caller must guarantee that the request is a valid type */ struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int type) { @@ -258,7 +296,6 @@ struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int type) /* Typically used on completion path. Cannot guarantee request consistency */ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type) { - struct nvm_tgt_dev *dev = pblk->dev; mempool_t *pool; switch (type) { @@ -279,9 +316,7 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type) return; } - if (rqd->meta_list) - nvm_dev_dma_free(dev->parent, rqd->meta_list, - rqd->dma_meta_list); + pblk_free_rqd_meta(pblk, rqd); mempool_free(rqd, pool); } @@ -409,6 +444,9 @@ struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line) } } else { line->state = PBLK_LINESTATE_CORRUPT; + trace_pblk_line_state(pblk_disk_name(pblk), line->id, + line->state); + line->gc_group = PBLK_LINEGC_NONE; move_list = &l_mg->corrupt_list; pblk_err(pblk, "corrupted vsc for line %d, vsc:%d (%d/%d/%d)\n", @@ -479,9 +517,30 @@ int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd) return nvm_submit_io(dev, rqd); } +void pblk_check_chunk_state_update(struct pblk *pblk, struct nvm_rq *rqd) +{ + struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); + + int i; + + for (i = 0; i < rqd->nr_ppas; i++) { + struct ppa_addr *ppa = &ppa_list[i]; + struct nvm_chk_meta *chunk = pblk_dev_ppa_to_chunk(pblk, *ppa); + u64 caddr = pblk_dev_ppa_to_chunk_addr(pblk, *ppa); + + if (caddr == 0) + trace_pblk_chunk_state(pblk_disk_name(pblk), + ppa, NVM_CHK_ST_OPEN); + else if (caddr == chunk->cnlb) + trace_pblk_chunk_state(pblk_disk_name(pblk), + ppa, NVM_CHK_ST_CLOSED); + } +} + int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd) { struct nvm_tgt_dev *dev = pblk->dev; + int ret; atomic_inc(&pblk->inflight_io); @@ -490,7 +549,27 @@ int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd) return NVM_IO_ERR; #endif - return nvm_submit_io_sync(dev, rqd); + ret = nvm_submit_io_sync(dev, rqd); + + if (trace_pblk_chunk_state_enabled() && !ret && + rqd->opcode == NVM_OP_PWRITE) + pblk_check_chunk_state_update(pblk, rqd); + + return ret; +} + +int pblk_submit_io_sync_sem(struct pblk *pblk, struct nvm_rq *rqd) +{ + struct ppa_addr *ppa_list; + int ret; + + ppa_list = (rqd->nr_ppas > 1) ? rqd->ppa_list : &rqd->ppa_addr; + + pblk_down_chunk(pblk, ppa_list[0]); + ret = pblk_submit_io_sync(pblk, rqd); + pblk_up_chunk(pblk, ppa_list[0]); + + return ret; } static void pblk_bio_map_addr_endio(struct bio *bio) @@ -621,262 +700,227 @@ u64 pblk_lookup_page(struct pblk *pblk, struct pblk_line *line) return paddr; } -/* - * Submit emeta to one LUN in the raid line at the time to avoid a deadlock when - * taking the per LUN semaphore. - */ -static int pblk_line_submit_emeta_io(struct pblk *pblk, struct pblk_line *line, - void *emeta_buf, u64 paddr, int dir) +u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line) { struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; struct pblk_line_meta *lm = &pblk->lm; - void *ppa_list, *meta_list; - struct bio *bio; - struct nvm_rq rqd; - dma_addr_t dma_ppa_list, dma_meta_list; - int min = pblk->min_write_pgs; - int left_ppas = lm->emeta_sec[0]; - int id = line->id; - int rq_ppas, rq_len; - int cmd_op, bio_op; - int i, j; - int ret; + int bit; - if (dir == PBLK_WRITE) { - bio_op = REQ_OP_WRITE; - cmd_op = NVM_OP_PWRITE; - } else if (dir == PBLK_READ) { - bio_op = REQ_OP_READ; - cmd_op = NVM_OP_PREAD; - } else - return -EINVAL; + /* This usually only happens on bad lines */ + bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line); + if (bit >= lm->blk_per_line) + return -1; - meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, - &dma_meta_list); - if (!meta_list) - return -ENOMEM; + return bit * geo->ws_opt; +} - ppa_list = meta_list + pblk_dma_meta_size; - dma_ppa_list = dma_meta_list + pblk_dma_meta_size; +int pblk_line_smeta_read(struct pblk *pblk, struct pblk_line *line) +{ + struct nvm_tgt_dev *dev = pblk->dev; + struct pblk_line_meta *lm = &pblk->lm; + struct bio *bio; + struct nvm_rq rqd; + u64 paddr = pblk_line_smeta_start(pblk, line); + int i, ret; -next_rq: memset(&rqd, 0, sizeof(struct nvm_rq)); - rq_ppas = pblk_calc_secs(pblk, left_ppas, 0); - rq_len = rq_ppas * geo->csecs; + ret = pblk_alloc_rqd_meta(pblk, &rqd); + if (ret) + return ret; - bio = pblk_bio_map_addr(pblk, emeta_buf, rq_ppas, rq_len, - l_mg->emeta_alloc_type, GFP_KERNEL); + bio = bio_map_kern(dev->q, line->smeta, lm->smeta_len, GFP_KERNEL); if (IS_ERR(bio)) { ret = PTR_ERR(bio); - goto free_rqd_dma; + goto clear_rqd; } bio->bi_iter.bi_sector = 0; /* internal bio */ - bio_set_op_attrs(bio, bio_op, 0); + bio_set_op_attrs(bio, REQ_OP_READ, 0); rqd.bio = bio; - rqd.meta_list = meta_list; - rqd.ppa_list = ppa_list; - rqd.dma_meta_list = dma_meta_list; - rqd.dma_ppa_list = dma_ppa_list; - rqd.opcode = cmd_op; - rqd.nr_ppas = rq_ppas; - - if (dir == PBLK_WRITE) { - struct pblk_sec_meta *meta_list = rqd.meta_list; - - rqd.flags = pblk_set_progr_mode(pblk, PBLK_WRITE); - for (i = 0; i < rqd.nr_ppas; ) { - spin_lock(&line->lock); - paddr = __pblk_alloc_page(pblk, line, min); - spin_unlock(&line->lock); - for (j = 0; j < min; j++, i++, paddr++) { - meta_list[i].lba = cpu_to_le64(ADDR_EMPTY); - rqd.ppa_list[i] = - addr_to_gen_ppa(pblk, paddr, id); - } - } - } else { - for (i = 0; i < rqd.nr_ppas; ) { - struct ppa_addr ppa = addr_to_gen_ppa(pblk, paddr, id); - int pos = pblk_ppa_to_pos(geo, ppa); - int read_type = PBLK_READ_RANDOM; - - if (pblk_io_aligned(pblk, rq_ppas)) - read_type = PBLK_READ_SEQUENTIAL; - rqd.flags = pblk_set_read_mode(pblk, read_type); - - while (test_bit(pos, line->blk_bitmap)) { - paddr += min; - if (pblk_boundary_paddr_checks(pblk, paddr)) { - pblk_err(pblk, "corrupt emeta line:%d\n", - line->id); - bio_put(bio); - ret = -EINTR; - goto free_rqd_dma; - } - - ppa = addr_to_gen_ppa(pblk, paddr, id); - pos = pblk_ppa_to_pos(geo, ppa); - } - - if (pblk_boundary_paddr_checks(pblk, paddr + min)) { - pblk_err(pblk, "corrupt emeta line:%d\n", - line->id); - bio_put(bio); - ret = -EINTR; - goto free_rqd_dma; - } + rqd.opcode = NVM_OP_PREAD; + rqd.nr_ppas = lm->smeta_sec; + rqd.is_seq = 1; - for (j = 0; j < min; j++, i++, paddr++) - rqd.ppa_list[i] = - addr_to_gen_ppa(pblk, paddr, line->id); - } - } + for (i = 0; i < lm->smeta_sec; i++, paddr++) + rqd.ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id); ret = pblk_submit_io_sync(pblk, &rqd); if (ret) { - pblk_err(pblk, "emeta I/O submission failed: %d\n", ret); + pblk_err(pblk, "smeta I/O submission failed: %d\n", ret); bio_put(bio); - goto free_rqd_dma; + goto clear_rqd; } atomic_dec(&pblk->inflight_io); - if (rqd.error) { - if (dir == PBLK_WRITE) - pblk_log_write_err(pblk, &rqd); - else - pblk_log_read_err(pblk, &rqd); - } + if (rqd.error) + pblk_log_read_err(pblk, &rqd); - emeta_buf += rq_len; - left_ppas -= rq_ppas; - if (left_ppas) - goto next_rq; -free_rqd_dma: - nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_list); +clear_rqd: + pblk_free_rqd_meta(pblk, &rqd); return ret; } -u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line_meta *lm = &pblk->lm; - int bit; - - /* This usually only happens on bad lines */ - bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line); - if (bit >= lm->blk_per_line) - return -1; - - return bit * geo->ws_opt; -} - -static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line, - u64 paddr, int dir) +static int pblk_line_smeta_write(struct pblk *pblk, struct pblk_line *line, + u64 paddr) { struct nvm_tgt_dev *dev = pblk->dev; struct pblk_line_meta *lm = &pblk->lm; struct bio *bio; struct nvm_rq rqd; - __le64 *lba_list = NULL; + __le64 *lba_list = emeta_to_lbas(pblk, line->emeta->buf); + __le64 addr_empty = cpu_to_le64(ADDR_EMPTY); int i, ret; - int cmd_op, bio_op; - int flags; - - if (dir == PBLK_WRITE) { - bio_op = REQ_OP_WRITE; - cmd_op = NVM_OP_PWRITE; - flags = pblk_set_progr_mode(pblk, PBLK_WRITE); - lba_list = emeta_to_lbas(pblk, line->emeta->buf); - } else if (dir == PBLK_READ_RECOV || dir == PBLK_READ) { - bio_op = REQ_OP_READ; - cmd_op = NVM_OP_PREAD; - flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL); - } else - return -EINVAL; memset(&rqd, 0, sizeof(struct nvm_rq)); - rqd.meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, - &rqd.dma_meta_list); - if (!rqd.meta_list) - return -ENOMEM; - - rqd.ppa_list = rqd.meta_list + pblk_dma_meta_size; - rqd.dma_ppa_list = rqd.dma_meta_list + pblk_dma_meta_size; + ret = pblk_alloc_rqd_meta(pblk, &rqd); + if (ret) + return ret; bio = bio_map_kern(dev->q, line->smeta, lm->smeta_len, GFP_KERNEL); if (IS_ERR(bio)) { ret = PTR_ERR(bio); - goto free_ppa_list; + goto clear_rqd; } bio->bi_iter.bi_sector = 0; /* internal bio */ - bio_set_op_attrs(bio, bio_op, 0); + bio_set_op_attrs(bio, REQ_OP_WRITE, 0); rqd.bio = bio; - rqd.opcode = cmd_op; - rqd.flags = flags; + rqd.opcode = NVM_OP_PWRITE; rqd.nr_ppas = lm->smeta_sec; + rqd.is_seq = 1; for (i = 0; i < lm->smeta_sec; i++, paddr++) { struct pblk_sec_meta *meta_list = rqd.meta_list; rqd.ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id); - - if (dir == PBLK_WRITE) { - __le64 addr_empty = cpu_to_le64(ADDR_EMPTY); - - meta_list[i].lba = lba_list[paddr] = addr_empty; - } + meta_list[i].lba = lba_list[paddr] = addr_empty; } - /* - * This I/O is sent by the write thread when a line is replace. Since - * the write thread is the only one sending write and erase commands, - * there is no need to take the LUN semaphore. - */ - ret = pblk_submit_io_sync(pblk, &rqd); + ret = pblk_submit_io_sync_sem(pblk, &rqd); if (ret) { pblk_err(pblk, "smeta I/O submission failed: %d\n", ret); bio_put(bio); - goto free_ppa_list; + goto clear_rqd; } atomic_dec(&pblk->inflight_io); if (rqd.error) { - if (dir == PBLK_WRITE) { - pblk_log_write_err(pblk, &rqd); - ret = 1; - } else if (dir == PBLK_READ) - pblk_log_read_err(pblk, &rqd); + pblk_log_write_err(pblk, &rqd); + ret = -EIO; } -free_ppa_list: - nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_list); - +clear_rqd: + pblk_free_rqd_meta(pblk, &rqd); return ret; } -int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line) +int pblk_line_emeta_read(struct pblk *pblk, struct pblk_line *line, + void *emeta_buf) { - u64 bpaddr = pblk_line_smeta_start(pblk, line); + struct nvm_tgt_dev *dev = pblk->dev; + struct nvm_geo *geo = &dev->geo; + struct pblk_line_mgmt *l_mg = &pblk->l_mg; + struct pblk_line_meta *lm = &pblk->lm; + void *ppa_list, *meta_list; + struct bio *bio; + struct nvm_rq rqd; + u64 paddr = line->emeta_ssec; + dma_addr_t dma_ppa_list, dma_meta_list; + int min = pblk->min_write_pgs; + int left_ppas = lm->emeta_sec[0]; + int line_id = line->id; + int rq_ppas, rq_len; + int i, j; + int ret; - return pblk_line_submit_smeta_io(pblk, line, bpaddr, PBLK_READ_RECOV); -} + meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, + &dma_meta_list); + if (!meta_list) + return -ENOMEM; -int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line, - void *emeta_buf) -{ - return pblk_line_submit_emeta_io(pblk, line, emeta_buf, - line->emeta_ssec, PBLK_READ); + ppa_list = meta_list + pblk_dma_meta_size; + dma_ppa_list = dma_meta_list + pblk_dma_meta_size; + +next_rq: + memset(&rqd, 0, sizeof(struct nvm_rq)); + + rq_ppas = pblk_calc_secs(pblk, left_ppas, 0); + rq_len = rq_ppas * geo->csecs; + + bio = pblk_bio_map_addr(pblk, emeta_buf, rq_ppas, rq_len, + l_mg->emeta_alloc_type, GFP_KERNEL); + if (IS_ERR(bio)) { + ret = PTR_ERR(bio); + goto free_rqd_dma; + } + + bio->bi_iter.bi_sector = 0; /* internal bio */ + bio_set_op_attrs(bio, REQ_OP_READ, 0); + + rqd.bio = bio; + rqd.meta_list = meta_list; + rqd.ppa_list = ppa_list; + rqd.dma_meta_list = dma_meta_list; + rqd.dma_ppa_list = dma_ppa_list; + rqd.opcode = NVM_OP_PREAD; + rqd.nr_ppas = rq_ppas; + + for (i = 0; i < rqd.nr_ppas; ) { + struct ppa_addr ppa = addr_to_gen_ppa(pblk, paddr, line_id); + int pos = pblk_ppa_to_pos(geo, ppa); + + if (pblk_io_aligned(pblk, rq_ppas)) + rqd.is_seq = 1; + + while (test_bit(pos, line->blk_bitmap)) { + paddr += min; + if (pblk_boundary_paddr_checks(pblk, paddr)) { + bio_put(bio); + ret = -EINTR; + goto free_rqd_dma; + } + + ppa = addr_to_gen_ppa(pblk, paddr, line_id); + pos = pblk_ppa_to_pos(geo, ppa); + } + + if (pblk_boundary_paddr_checks(pblk, paddr + min)) { + bio_put(bio); + ret = -EINTR; + goto free_rqd_dma; + } + + for (j = 0; j < min; j++, i++, paddr++) + rqd.ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line_id); + } + + ret = pblk_submit_io_sync(pblk, &rqd); + if (ret) { + pblk_err(pblk, "emeta I/O submission failed: %d\n", ret); + bio_put(bio); + goto free_rqd_dma; + } + + atomic_dec(&pblk->inflight_io); + + if (rqd.error) + pblk_log_read_err(pblk, &rqd); + + emeta_buf += rq_len; + left_ppas -= rq_ppas; + if (left_ppas) + goto next_rq; + +free_rqd_dma: + nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_list); + return ret; } static void pblk_setup_e_rq(struct pblk *pblk, struct nvm_rq *rqd, @@ -885,16 +929,17 @@ static void pblk_setup_e_rq(struct pblk *pblk, struct nvm_rq *rqd, rqd->opcode = NVM_OP_ERASE; rqd->ppa_addr = ppa; rqd->nr_ppas = 1; - rqd->flags = pblk_set_progr_mode(pblk, PBLK_ERASE); + rqd->is_seq = 1; rqd->bio = NULL; } static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa) { - struct nvm_rq rqd; - int ret = 0; + struct nvm_rq rqd = {NULL}; + int ret; - memset(&rqd, 0, sizeof(struct nvm_rq)); + trace_pblk_chunk_reset(pblk_disk_name(pblk), &ppa, + PBLK_CHUNK_RESET_START); pblk_setup_e_rq(pblk, &rqd, ppa); @@ -902,19 +947,6 @@ static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa) * with writes. Thus, there is no need to take the LUN semaphore. */ ret = pblk_submit_io_sync(pblk, &rqd); - if (ret) { - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - - pblk_err(pblk, "could not sync erase line:%d,blk:%d\n", - pblk_ppa_to_line(ppa), - pblk_ppa_to_pos(geo, ppa)); - - rqd.error = ret; - goto out; - } - -out: rqd.private = pblk; __pblk_end_io_erase(pblk, &rqd); @@ -1008,6 +1040,8 @@ static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line, spin_lock(&l_mg->free_lock); spin_lock(&line->lock); line->state = PBLK_LINESTATE_BAD; + trace_pblk_line_state(pblk_disk_name(pblk), line->id, + line->state); spin_unlock(&line->lock); list_add_tail(&line->list, &l_mg->bad_list); @@ -1071,15 +1105,18 @@ static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line, static int pblk_line_alloc_bitmaps(struct pblk *pblk, struct pblk_line *line) { struct pblk_line_meta *lm = &pblk->lm; + struct pblk_line_mgmt *l_mg = &pblk->l_mg; - line->map_bitmap = kzalloc(lm->sec_bitmap_len, GFP_KERNEL); + line->map_bitmap = mempool_alloc(l_mg->bitmap_pool, GFP_KERNEL); if (!line->map_bitmap) return -ENOMEM; + memset(line->map_bitmap, 0, lm->sec_bitmap_len); + /* will be initialized using bb info from map_bitmap */ - line->invalid_bitmap = kmalloc(lm->sec_bitmap_len, GFP_KERNEL); + line->invalid_bitmap = mempool_alloc(l_mg->bitmap_pool, GFP_KERNEL); if (!line->invalid_bitmap) { - kfree(line->map_bitmap); + mempool_free(line->map_bitmap, l_mg->bitmap_pool); line->map_bitmap = NULL; return -ENOMEM; } @@ -1122,7 +1159,7 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line, line->smeta_ssec = off; line->cur_sec = off + lm->smeta_sec; - if (init && pblk_line_submit_smeta_io(pblk, line, off, PBLK_WRITE)) { + if (init && pblk_line_smeta_write(pblk, line, off)) { pblk_debug(pblk, "line smeta I/O failed. Retry\n"); return 0; } @@ -1152,6 +1189,8 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line, bitmap_weight(line->invalid_bitmap, lm->sec_per_line)) { spin_lock(&line->lock); line->state = PBLK_LINESTATE_BAD; + trace_pblk_line_state(pblk_disk_name(pblk), line->id, + line->state); spin_unlock(&line->lock); list_add_tail(&line->list, &l_mg->bad_list); @@ -1204,6 +1243,8 @@ static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line) if (line->state == PBLK_LINESTATE_NEW) { blk_to_erase = pblk_prepare_new_line(pblk, line); line->state = PBLK_LINESTATE_FREE; + trace_pblk_line_state(pblk_disk_name(pblk), line->id, + line->state); } else { blk_to_erase = blk_in_line; } @@ -1221,6 +1262,8 @@ static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line) } line->state = PBLK_LINESTATE_OPEN; + trace_pblk_line_state(pblk_disk_name(pblk), line->id, + line->state); atomic_set(&line->left_eblks, blk_to_erase); atomic_set(&line->left_seblks, blk_to_erase); @@ -1265,7 +1308,9 @@ int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line) void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line) { - kfree(line->map_bitmap); + struct pblk_line_mgmt *l_mg = &pblk->l_mg; + + mempool_free(line->map_bitmap, l_mg->bitmap_pool); line->map_bitmap = NULL; line->smeta = NULL; line->emeta = NULL; @@ -1283,8 +1328,11 @@ static void pblk_line_reinit(struct pblk_line *line) void pblk_line_free(struct pblk_line *line) { - kfree(line->map_bitmap); - kfree(line->invalid_bitmap); + struct pblk *pblk = line->pblk; + struct pblk_line_mgmt *l_mg = &pblk->l_mg; + + mempool_free(line->map_bitmap, l_mg->bitmap_pool); + mempool_free(line->invalid_bitmap, l_mg->bitmap_pool); pblk_line_reinit(line); } @@ -1312,6 +1360,8 @@ retry: if (unlikely(bit >= lm->blk_per_line)) { spin_lock(&line->lock); line->state = PBLK_LINESTATE_BAD; + trace_pblk_line_state(pblk_disk_name(pblk), line->id, + line->state); spin_unlock(&line->lock); list_add_tail(&line->list, &l_mg->bad_list); @@ -1446,12 +1496,32 @@ retry_setup: return line; } +void pblk_ppa_to_line_put(struct pblk *pblk, struct ppa_addr ppa) +{ + struct pblk_line *line; + + line = pblk_ppa_to_line(pblk, ppa); + kref_put(&line->ref, pblk_line_put_wq); +} + +void pblk_rq_to_line_put(struct pblk *pblk, struct nvm_rq *rqd) +{ + struct ppa_addr *ppa_list; + int i; + + ppa_list = (rqd->nr_ppas > 1) ? rqd->ppa_list : &rqd->ppa_addr; + + for (i = 0; i < rqd->nr_ppas; i++) + pblk_ppa_to_line_put(pblk, ppa_list[i]); +} + static void pblk_stop_writes(struct pblk *pblk, struct pblk_line *line) { lockdep_assert_held(&pblk->l_mg.free_lock); pblk_set_space_limit(pblk); pblk->state = PBLK_STATE_STOPPING; + trace_pblk_state(pblk_disk_name(pblk), pblk->state); } static void pblk_line_close_meta_sync(struct pblk *pblk) @@ -1501,6 +1571,7 @@ void __pblk_pipeline_flush(struct pblk *pblk) return; } pblk->state = PBLK_STATE_RECOVERING; + trace_pblk_state(pblk_disk_name(pblk), pblk->state); spin_unlock(&l_mg->free_lock); pblk_flush_writer(pblk); @@ -1522,6 +1593,7 @@ void __pblk_pipeline_stop(struct pblk *pblk) spin_lock(&l_mg->free_lock); pblk->state = PBLK_STATE_STOPPED; + trace_pblk_state(pblk_disk_name(pblk), pblk->state); l_mg->data_line = NULL; l_mg->data_next = NULL; spin_unlock(&l_mg->free_lock); @@ -1539,13 +1611,14 @@ struct pblk_line *pblk_line_replace_data(struct pblk *pblk) struct pblk_line *cur, *new = NULL; unsigned int left_seblks; - cur = l_mg->data_line; new = l_mg->data_next; if (!new) goto out; - l_mg->data_line = new; spin_lock(&l_mg->free_lock); + cur = l_mg->data_line; + l_mg->data_line = new; + pblk_line_setup_metadata(new, l_mg, &pblk->lm); spin_unlock(&l_mg->free_lock); @@ -1612,6 +1685,8 @@ static void __pblk_line_put(struct pblk *pblk, struct pblk_line *line) spin_lock(&line->lock); WARN_ON(line->state != PBLK_LINESTATE_GC); line->state = PBLK_LINESTATE_FREE; + trace_pblk_line_state(pblk_disk_name(pblk), line->id, + line->state); line->gc_group = PBLK_LINEGC_NONE; pblk_line_free(line); @@ -1680,6 +1755,9 @@ int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr ppa) rqd->end_io = pblk_end_io_erase; rqd->private = pblk; + trace_pblk_chunk_reset(pblk_disk_name(pblk), + &ppa, PBLK_CHUNK_RESET_START); + /* The write thread schedules erases so that it minimizes disturbances * with writes. Thus, there is no need to take the LUN semaphore. */ @@ -1689,7 +1767,7 @@ int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr ppa) struct nvm_geo *geo = &dev->geo; pblk_err(pblk, "could not async erase line:%d,blk:%d\n", - pblk_ppa_to_line(ppa), + pblk_ppa_to_line_id(ppa), pblk_ppa_to_pos(geo, ppa)); } @@ -1741,10 +1819,9 @@ void pblk_line_close(struct pblk *pblk, struct pblk_line *line) WARN_ON(line->state != PBLK_LINESTATE_OPEN); line->state = PBLK_LINESTATE_CLOSED; move_list = pblk_line_gc_list(pblk, line); - list_add_tail(&line->list, move_list); - kfree(line->map_bitmap); + mempool_free(line->map_bitmap, l_mg->bitmap_pool); line->map_bitmap = NULL; line->smeta = NULL; line->emeta = NULL; @@ -1760,6 +1837,9 @@ void pblk_line_close(struct pblk *pblk, struct pblk_line *line) spin_unlock(&line->lock); spin_unlock(&l_mg->gc_lock); + + trace_pblk_line_state(pblk_disk_name(pblk), line->id, + line->state); } void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line) @@ -1778,6 +1858,17 @@ void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line) wa->pad = cpu_to_le64(atomic64_read(&pblk->pad_wa)); wa->gc = cpu_to_le64(atomic64_read(&pblk->gc_wa)); + if (le32_to_cpu(emeta_buf->header.identifier) != PBLK_MAGIC) { + emeta_buf->header.identifier = cpu_to_le32(PBLK_MAGIC); + memcpy(emeta_buf->header.uuid, pblk->instance_uuid, 16); + emeta_buf->header.id = cpu_to_le32(line->id); + emeta_buf->header.type = cpu_to_le16(line->type); + emeta_buf->header.version_major = EMETA_VERSION_MAJOR; + emeta_buf->header.version_minor = EMETA_VERSION_MINOR; + emeta_buf->header.crc = cpu_to_le32( + pblk_calc_meta_header_crc(pblk, &emeta_buf->header)); + } + emeta_buf->nr_valid_lbas = cpu_to_le64(line->nr_valid_lbas); emeta_buf->crc = cpu_to_le32(pblk_calc_emeta_crc(pblk, emeta_buf)); @@ -1795,8 +1886,6 @@ void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line) spin_unlock(&l_mg->close_lock); pblk_line_should_sync_meta(pblk); - - } static void pblk_save_lba_list(struct pblk *pblk, struct pblk_line *line) @@ -1847,8 +1936,7 @@ void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv, queue_work(wq, &line_ws->ws); } -static void __pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list, - int nr_ppas, int pos) +static void __pblk_down_chunk(struct pblk *pblk, int pos) { struct pblk_lun *rlun = &pblk->luns[pos]; int ret; @@ -1857,13 +1945,6 @@ static void __pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list, * Only send one inflight I/O per LUN. Since we map at a page * granurality, all ppas in the I/O will map to the same LUN */ -#ifdef CONFIG_NVM_PBLK_DEBUG - int i; - - for (i = 1; i < nr_ppas; i++) - WARN_ON(ppa_list[0].a.lun != ppa_list[i].a.lun || - ppa_list[0].a.ch != ppa_list[i].a.ch); -#endif ret = down_timeout(&rlun->wr_sem, msecs_to_jiffies(30000)); if (ret == -ETIME || ret == -EINTR) @@ -1871,21 +1952,21 @@ static void __pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list, -ret); } -void pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas) +void pblk_down_chunk(struct pblk *pblk, struct ppa_addr ppa) { struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; - int pos = pblk_ppa_to_pos(geo, ppa_list[0]); + int pos = pblk_ppa_to_pos(geo, ppa); - __pblk_down_page(pblk, ppa_list, nr_ppas, pos); + __pblk_down_chunk(pblk, pos); } -void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas, +void pblk_down_rq(struct pblk *pblk, struct ppa_addr ppa, unsigned long *lun_bitmap) { struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; - int pos = pblk_ppa_to_pos(geo, ppa_list[0]); + int pos = pblk_ppa_to_pos(geo, ppa); /* If the LUN has been locked for this same request, do no attempt to * lock it again @@ -1893,30 +1974,21 @@ void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas, if (test_and_set_bit(pos, lun_bitmap)) return; - __pblk_down_page(pblk, ppa_list, nr_ppas, pos); + __pblk_down_chunk(pblk, pos); } -void pblk_up_page(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas) +void pblk_up_chunk(struct pblk *pblk, struct ppa_addr ppa) { struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; struct pblk_lun *rlun; - int pos = pblk_ppa_to_pos(geo, ppa_list[0]); - -#ifdef CONFIG_NVM_PBLK_DEBUG - int i; - - for (i = 1; i < nr_ppas; i++) - WARN_ON(ppa_list[0].a.lun != ppa_list[i].a.lun || - ppa_list[0].a.ch != ppa_list[i].a.ch); -#endif + int pos = pblk_ppa_to_pos(geo, ppa); rlun = &pblk->luns[pos]; up(&rlun->wr_sem); } -void pblk_up_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas, - unsigned long *lun_bitmap) +void pblk_up_rq(struct pblk *pblk, unsigned long *lun_bitmap) { struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; @@ -2060,8 +2132,7 @@ void pblk_lookup_l2p_seq(struct pblk *pblk, struct ppa_addr *ppas, /* If the L2P entry maps to a line, the reference is valid */ if (!pblk_ppa_empty(ppa) && !pblk_addr_in_cache(ppa)) { - int line_id = pblk_ppa_to_line(ppa); - struct pblk_line *line = &pblk->lines[line_id]; + struct pblk_line *line = pblk_ppa_to_line(pblk, ppa); kref_get(&line->ref); }