diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-14 15:32:19 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-14 15:32:19 -0800 |
commit | e2c5923c349c1738fe8fda980874d93f6fb2e5b6 (patch) | |
tree | b97a90170c45211bcc437761653aa8016c34afcd /drivers/lightnvm | |
parent | abc36be236358162202e86ad88616ff95a755101 (diff) | |
parent | a04b5de5050ab8b891128eb2c47a0916fe8622e1 (diff) |
Merge branch 'for-4.15/block' of git://git.kernel.dk/linux-block
Pull core block layer updates from Jens Axboe:
"This is the main pull request for block storage for 4.15-rc1.
Nothing out of the ordinary in here, and no API changes or anything
like that. Just various new features for drivers, core changes, etc.
In particular, this pull request contains:
- A patch series from Bart, closing the whole on blk/scsi-mq queue
quescing.
- A series from Christoph, building towards hidden gendisks (for
multipath) and ability to move bio chains around.
- NVMe
- Support for native multipath for NVMe (Christoph).
- Userspace notifications for AENs (Keith).
- Command side-effects support (Keith).
- SGL support (Chaitanya Kulkarni)
- FC fixes and improvements (James Smart)
- Lots of fixes and tweaks (Various)
- bcache
- New maintainer (Michael Lyle)
- Writeback control improvements (Michael)
- Various fixes (Coly, Elena, Eric, Liang, et al)
- lightnvm updates, mostly centered around the pblk interface
(Javier, Hans, and Rakesh).
- Removal of unused bio/bvec kmap atomic interfaces (me, Christoph)
- Writeback series that fix the much discussed hundreds of millions
of sync-all units. This goes all the way, as discussed previously
(me).
- Fix for missing wakeup on writeback timer adjustments (Yafang
Shao).
- Fix laptop mode on blk-mq (me).
- {mq,name} tupple lookup for IO schedulers, allowing us to have
alias names. This means you can use 'deadline' on both !mq and on
mq (where it's called mq-deadline). (me).
- blktrace race fix, oopsing on sg load (me).
- blk-mq optimizations (me).
- Obscure waitqueue race fix for kyber (Omar).
- NBD fixes (Josef).
- Disable writeback throttling by default on bfq, like we do on cfq
(Luca Miccio).
- Series from Ming that enable us to treat flush requests on blk-mq
like any other request. This is a really nice cleanup.
- Series from Ming that improves merging on blk-mq with schedulers,
getting us closer to flipping the switch on scsi-mq again.
- BFQ updates (Paolo).
- blk-mq atomic flags memory ordering fixes (Peter Z).
- Loop cgroup support (Shaohua).
- Lots of minor fixes from lots of different folks, both for core and
driver code"
* 'for-4.15/block' of git://git.kernel.dk/linux-block: (294 commits)
nvme: fix visibility of "uuid" ns attribute
blk-mq: fixup some comment typos and lengths
ide: ide-atapi: fix compile error with defining macro DEBUG
blk-mq: improve tag waiting setup for non-shared tags
brd: remove unused brd_mutex
blk-mq: only run the hardware queue if IO is pending
block: avoid null pointer dereference on null disk
fs: guard_bio_eod() needs to consider partitions
xtensa/simdisk: fix compile error
nvme: expose subsys attribute to sysfs
nvme: create 'slaves' and 'holders' entries for hidden controllers
block: create 'slaves' and 'holders' entries for hidden gendisks
nvme: also expose the namespace identification sysfs files for mpath nodes
nvme: implement multipath access to nvme subsystems
nvme: track shared namespaces
nvme: introduce a nvme_ns_ids structure
nvme: track subsystems
block, nvme: Introduce blk_mq_req_flags_t
block, scsi: Make SCSI quiesce and resume work reliably
block: Add the QUEUE_FLAG_PREEMPT_ONLY request queue flag
...
Diffstat (limited to 'drivers/lightnvm')
-rw-r--r-- | drivers/lightnvm/Kconfig | 3 | ||||
-rw-r--r-- | drivers/lightnvm/core.c | 176 | ||||
-rw-r--r-- | drivers/lightnvm/pblk-cache.c | 24 | ||||
-rw-r--r-- | drivers/lightnvm/pblk-core.c | 512 | ||||
-rw-r--r-- | drivers/lightnvm/pblk-gc.c | 289 | ||||
-rw-r--r-- | drivers/lightnvm/pblk-init.c | 197 | ||||
-rw-r--r-- | drivers/lightnvm/pblk-map.c | 28 | ||||
-rw-r--r-- | drivers/lightnvm/pblk-rb.c | 30 | ||||
-rw-r--r-- | drivers/lightnvm/pblk-read.c | 274 | ||||
-rw-r--r-- | drivers/lightnvm/pblk-recovery.c | 129 | ||||
-rw-r--r-- | drivers/lightnvm/pblk-rl.c | 43 | ||||
-rw-r--r-- | drivers/lightnvm/pblk-sysfs.c | 2 | ||||
-rw-r--r-- | drivers/lightnvm/pblk-write.c | 229 | ||||
-rw-r--r-- | drivers/lightnvm/pblk.h | 132 |
14 files changed, 1079 insertions, 989 deletions
diff --git a/drivers/lightnvm/Kconfig b/drivers/lightnvm/Kconfig index ead61a93cb4e..2a953efec4e1 100644 --- a/drivers/lightnvm/Kconfig +++ b/drivers/lightnvm/Kconfig @@ -4,7 +4,8 @@ menuconfig NVM bool "Open-Channel SSD target support" - depends on BLOCK && HAS_DMA + depends on BLOCK && HAS_DMA && PCI + select BLK_DEV_NVME help Say Y here to get to enable Open-channel SSDs. diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c index ddae430b6eae..83249b43dd06 100644 --- a/drivers/lightnvm/core.c +++ b/drivers/lightnvm/core.c @@ -22,6 +22,7 @@ #include <linux/types.h> #include <linux/sem.h> #include <linux/bitmap.h> +#include <linux/module.h> #include <linux/moduleparam.h> #include <linux/miscdevice.h> #include <linux/lightnvm.h> @@ -138,7 +139,6 @@ static struct nvm_tgt_dev *nvm_create_tgt_dev(struct nvm_dev *dev, int prev_nr_luns; int i, j; - nr_chnls = nr_luns / dev->geo.luns_per_chnl; nr_chnls = (nr_chnls_mod == 0) ? nr_chnls : nr_chnls + 1; dev_map = kmalloc(sizeof(struct nvm_dev_map), GFP_KERNEL); @@ -226,6 +226,24 @@ static const struct block_device_operations nvm_fops = { .owner = THIS_MODULE, }; +static struct nvm_tgt_type *nvm_find_target_type(const char *name, int lock) +{ + struct nvm_tgt_type *tmp, *tt = NULL; + + if (lock) + down_write(&nvm_tgtt_lock); + + list_for_each_entry(tmp, &nvm_tgt_types, list) + if (!strcmp(name, tmp->name)) { + tt = tmp; + break; + } + + if (lock) + up_write(&nvm_tgtt_lock); + return tt; +} + static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create) { struct nvm_ioctl_create_simple *s = &create->conf.s; @@ -316,6 +334,8 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create) list_add_tail(&t->list, &dev->targets); mutex_unlock(&dev->mlock); + __module_get(tt->owner); + return 0; err_sysfs: if (tt->exit) @@ -351,6 +371,7 @@ static void __nvm_remove_target(struct nvm_target *t) nvm_remove_tgt_dev(t->dev, 1); put_disk(tdisk); + module_put(t->type->owner); list_del(&t->list); kfree(t); @@ -532,25 +553,6 @@ void nvm_part_to_tgt(struct nvm_dev *dev, sector_t *entries, } EXPORT_SYMBOL(nvm_part_to_tgt); -struct nvm_tgt_type *nvm_find_target_type(const char *name, int lock) -{ - struct nvm_tgt_type *tmp, *tt = NULL; - - if (lock) - down_write(&nvm_tgtt_lock); - - list_for_each_entry(tmp, &nvm_tgt_types, list) - if (!strcmp(name, tmp->name)) { - tt = tmp; - break; - } - - if (lock) - up_write(&nvm_tgtt_lock); - return tt; -} -EXPORT_SYMBOL(nvm_find_target_type); - int nvm_register_tgt_type(struct nvm_tgt_type *tt) { int ret = 0; @@ -571,9 +573,9 @@ void nvm_unregister_tgt_type(struct nvm_tgt_type *tt) if (!tt) return; - down_write(&nvm_lock); + down_write(&nvm_tgtt_lock); list_del(&tt->list); - up_write(&nvm_lock); + up_write(&nvm_tgtt_lock); } EXPORT_SYMBOL(nvm_unregister_tgt_type); @@ -602,6 +604,52 @@ static struct nvm_dev *nvm_find_nvm_dev(const char *name) return NULL; } +static int nvm_set_rqd_ppalist(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd, + const struct ppa_addr *ppas, int nr_ppas) +{ + struct nvm_dev *dev = tgt_dev->parent; + struct nvm_geo *geo = &tgt_dev->geo; + int i, plane_cnt, pl_idx; + struct ppa_addr ppa; + + if (geo->plane_mode == NVM_PLANE_SINGLE && nr_ppas == 1) { + rqd->nr_ppas = nr_ppas; + rqd->ppa_addr = ppas[0]; + + return 0; + } + + rqd->nr_ppas = nr_ppas; + rqd->ppa_list = nvm_dev_dma_alloc(dev, GFP_KERNEL, &rqd->dma_ppa_list); + if (!rqd->ppa_list) { + pr_err("nvm: failed to allocate dma memory\n"); + return -ENOMEM; + } + + plane_cnt = geo->plane_mode; + rqd->nr_ppas *= plane_cnt; + + for (i = 0; i < nr_ppas; i++) { + for (pl_idx = 0; pl_idx < plane_cnt; pl_idx++) { + ppa = ppas[i]; + ppa.g.pl = pl_idx; + rqd->ppa_list[(pl_idx * nr_ppas) + i] = ppa; + } + } + + return 0; +} + +static void nvm_free_rqd_ppalist(struct nvm_tgt_dev *tgt_dev, + struct nvm_rq *rqd) +{ + if (!rqd->ppa_list) + return; + + nvm_dev_dma_free(tgt_dev->parent, rqd->ppa_list, rqd->dma_ppa_list); +} + + int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas, int nr_ppas, int type) { @@ -616,7 +664,7 @@ int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas, memset(&rqd, 0, sizeof(struct nvm_rq)); - nvm_set_rqd_ppalist(tgt_dev, &rqd, ppas, nr_ppas, 1); + nvm_set_rqd_ppalist(tgt_dev, &rqd, ppas, nr_ppas); nvm_rq_tgt_to_dev(tgt_dev, &rqd); ret = dev->ops->set_bb_tbl(dev, &rqd.ppa_addr, rqd.nr_ppas, type); @@ -658,12 +706,25 @@ int nvm_submit_io(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd) } EXPORT_SYMBOL(nvm_submit_io); -static void nvm_end_io_sync(struct nvm_rq *rqd) +int nvm_submit_io_sync(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd) { - struct completion *waiting = rqd->private; + struct nvm_dev *dev = tgt_dev->parent; + int ret; - complete(waiting); + if (!dev->ops->submit_io_sync) + return -ENODEV; + + nvm_rq_tgt_to_dev(tgt_dev, rqd); + + rqd->dev = tgt_dev; + + /* In case of error, fail with right address format */ + ret = dev->ops->submit_io_sync(dev, rqd); + nvm_rq_dev_to_tgt(tgt_dev, rqd); + + return ret; } +EXPORT_SYMBOL(nvm_submit_io_sync); int nvm_erase_sync(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas, int nr_ppas) @@ -671,25 +732,21 @@ int nvm_erase_sync(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas, struct nvm_geo *geo = &tgt_dev->geo; struct nvm_rq rqd; int ret; - DECLARE_COMPLETION_ONSTACK(wait); memset(&rqd, 0, sizeof(struct nvm_rq)); rqd.opcode = NVM_OP_ERASE; - rqd.end_io = nvm_end_io_sync; - rqd.private = &wait; rqd.flags = geo->plane_mode >> 1; - ret = nvm_set_rqd_ppalist(tgt_dev, &rqd, ppas, nr_ppas, 1); + ret = nvm_set_rqd_ppalist(tgt_dev, &rqd, ppas, nr_ppas); if (ret) return ret; - ret = nvm_submit_io(tgt_dev, &rqd); + ret = nvm_submit_io_sync(tgt_dev, &rqd); if (ret) { pr_err("rrpr: erase I/O submission failed: %d\n", ret); goto free_ppa_list; } - wait_for_completion_io(&wait); free_ppa_list: nvm_free_rqd_ppalist(tgt_dev, &rqd); @@ -775,57 +832,6 @@ void nvm_put_area(struct nvm_tgt_dev *tgt_dev, sector_t begin) } EXPORT_SYMBOL(nvm_put_area); -int nvm_set_rqd_ppalist(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd, - const struct ppa_addr *ppas, int nr_ppas, int vblk) -{ - struct nvm_dev *dev = tgt_dev->parent; - struct nvm_geo *geo = &tgt_dev->geo; - int i, plane_cnt, pl_idx; - struct ppa_addr ppa; - - if ((!vblk || geo->plane_mode == NVM_PLANE_SINGLE) && nr_ppas == 1) { - rqd->nr_ppas = nr_ppas; - rqd->ppa_addr = ppas[0]; - - return 0; - } - - rqd->nr_ppas = nr_ppas; - rqd->ppa_list = nvm_dev_dma_alloc(dev, GFP_KERNEL, &rqd->dma_ppa_list); - if (!rqd->ppa_list) { - pr_err("nvm: failed to allocate dma memory\n"); - return -ENOMEM; - } - - if (!vblk) { - for (i = 0; i < nr_ppas; i++) - rqd->ppa_list[i] = ppas[i]; - } else { - plane_cnt = geo->plane_mode; - rqd->nr_ppas *= plane_cnt; - - for (i = 0; i < nr_ppas; i++) { - for (pl_idx = 0; pl_idx < plane_cnt; pl_idx++) { - ppa = ppas[i]; - ppa.g.pl = pl_idx; - rqd->ppa_list[(pl_idx * nr_ppas) + i] = ppa; - } - } - } - - return 0; -} -EXPORT_SYMBOL(nvm_set_rqd_ppalist); - -void nvm_free_rqd_ppalist(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd) -{ - if (!rqd->ppa_list) - return; - - nvm_dev_dma_free(tgt_dev->parent, rqd->ppa_list, rqd->dma_ppa_list); -} -EXPORT_SYMBOL(nvm_free_rqd_ppalist); - void nvm_end_io(struct nvm_rq *rqd) { struct nvm_tgt_dev *tgt_dev = rqd->dev; @@ -1177,7 +1183,7 @@ static long nvm_ioctl_info(struct file *file, void __user *arg) info->version[1] = NVM_VERSION_MINOR; info->version[2] = NVM_VERSION_PATCH; - down_write(&nvm_lock); + down_write(&nvm_tgtt_lock); list_for_each_entry(tt, &nvm_tgt_types, list) { struct nvm_ioctl_info_tgt *tgt = &info->tgts[tgt_iter]; @@ -1190,7 +1196,7 @@ static long nvm_ioctl_info(struct file *file, void __user *arg) } info->tgtsize = tgt_iter; - up_write(&nvm_lock); + up_write(&nvm_tgtt_lock); if (copy_to_user(arg, info, sizeof(struct nvm_ioctl_info))) { kfree(info); diff --git a/drivers/lightnvm/pblk-cache.c b/drivers/lightnvm/pblk-cache.c index 024a8fc93069..0d227ef7d1b9 100644 --- a/drivers/lightnvm/pblk-cache.c +++ b/drivers/lightnvm/pblk-cache.c @@ -43,8 +43,10 @@ retry: if (unlikely(!bio_has_data(bio))) goto out; - w_ctx.flags = flags; pblk_ppa_set_empty(&w_ctx.ppa); + w_ctx.flags = flags; + if (bio->bi_opf & REQ_PREFLUSH) + w_ctx.flags |= PBLK_FLUSH_ENTRY; for (i = 0; i < nr_entries; i++) { void *data = bio_data(bio); @@ -73,12 +75,11 @@ out: * On GC the incoming lbas are not necessarily sequential. Also, some of the * lbas might not be valid entries, which are marked as empty by the GC thread */ -int pblk_write_gc_to_cache(struct pblk *pblk, void *data, u64 *lba_list, - unsigned int nr_entries, unsigned int nr_rec_entries, - struct pblk_line *gc_line, unsigned long flags) +int pblk_write_gc_to_cache(struct pblk *pblk, struct pblk_gc_rq *gc_rq) { struct pblk_w_ctx w_ctx; unsigned int bpos, pos; + void *data = gc_rq->data; int i, valid_entries; /* Update the write buffer head (mem) with the entries that we can @@ -86,28 +87,29 @@ int pblk_write_gc_to_cache(struct pblk *pblk, void *data, u64 *lba_list, * rollback from here on. */ retry: - if (!pblk_rb_may_write_gc(&pblk->rwb, nr_rec_entries, &bpos)) { + if (!pblk_rb_may_write_gc(&pblk->rwb, gc_rq->secs_to_gc, &bpos)) { io_schedule(); goto retry; } - w_ctx.flags = flags; + w_ctx.flags = PBLK_IOTYPE_GC; pblk_ppa_set_empty(&w_ctx.ppa); - for (i = 0, valid_entries = 0; i < nr_entries; i++) { - if (lba_list[i] == ADDR_EMPTY) + for (i = 0, valid_entries = 0; i < gc_rq->nr_secs; i++) { + if (gc_rq->lba_list[i] == ADDR_EMPTY) continue; - w_ctx.lba = lba_list[i]; + w_ctx.lba = gc_rq->lba_list[i]; pos = pblk_rb_wrap_pos(&pblk->rwb, bpos + valid_entries); - pblk_rb_write_entry_gc(&pblk->rwb, data, w_ctx, gc_line, pos); + pblk_rb_write_entry_gc(&pblk->rwb, data, w_ctx, gc_rq->line, + gc_rq->paddr_list[i], pos); data += PBLK_EXPOSED_PAGE_SIZE; valid_entries++; } - WARN_ONCE(nr_rec_entries != valid_entries, + WARN_ONCE(gc_rq->secs_to_gc != valid_entries, "pblk: inconsistent GC write\n"); #ifdef CONFIG_NVM_DEBUG diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c index 81501644fb15..ce90213a42fa 100644 --- a/drivers/lightnvm/pblk-core.c +++ b/drivers/lightnvm/pblk-core.c @@ -18,6 +18,31 @@ #include "pblk.h" +static void pblk_line_mark_bb(struct work_struct *work) +{ + struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws, + ws); + struct pblk *pblk = line_ws->pblk; + struct nvm_tgt_dev *dev = pblk->dev; + struct ppa_addr *ppa = line_ws->priv; + int ret; + + ret = nvm_set_tgt_bb_tbl(dev, ppa, 1, NVM_BLK_T_GRWN_BAD); + if (ret) { + struct pblk_line *line; + int pos; + + line = &pblk->lines[pblk_dev_ppa_to_line(*ppa)]; + pos = pblk_dev_ppa_to_pos(&dev->geo, *ppa); + + pr_err("pblk: failed to mark bb, line:%d, pos:%d\n", + line->id, pos); + } + + kfree(ppa); + mempool_free(line_ws, pblk->gen_ws_pool); +} + static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line, struct ppa_addr *ppa) { @@ -33,7 +58,8 @@ static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line, pr_err("pblk: attempted to erase bb: line:%d, pos:%d\n", line->id, pos); - pblk_line_run_ws(pblk, NULL, ppa, pblk_line_mark_bb, pblk->bb_wq); + pblk_gen_run_ws(pblk, NULL, ppa, pblk_line_mark_bb, + GFP_ATOMIC, pblk->bb_wq); } static void __pblk_end_io_erase(struct pblk *pblk, struct nvm_rq *rqd) @@ -63,7 +89,7 @@ static void pblk_end_io_erase(struct nvm_rq *rqd) struct pblk *pblk = rqd->private; __pblk_end_io_erase(pblk, rqd); - mempool_free(rqd, pblk->g_rq_pool); + mempool_free(rqd, pblk->e_rq_pool); } void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line, @@ -77,11 +103,7 @@ void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line, * that newer updates are not overwritten. */ spin_lock(&line->lock); - if (line->state == PBLK_LINESTATE_GC || - line->state == PBLK_LINESTATE_FREE) { - spin_unlock(&line->lock); - return; - } + WARN_ON(line->state == PBLK_LINESTATE_FREE); if (test_and_set_bit(paddr, line->invalid_bitmap)) { WARN_ONCE(1, "pblk: double invalidate\n"); @@ -98,8 +120,7 @@ void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line, spin_lock(&l_mg->gc_lock); spin_lock(&line->lock); /* Prevent moving a line that has just been chosen for GC */ - if (line->state == PBLK_LINESTATE_GC || - line->state == PBLK_LINESTATE_FREE) { + if (line->state == PBLK_LINESTATE_GC) { spin_unlock(&line->lock); spin_unlock(&l_mg->gc_lock); return; @@ -150,17 +171,25 @@ static void pblk_invalidate_range(struct pblk *pblk, sector_t slba, spin_unlock(&pblk->trans_lock); } -struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw) +/* Caller must guarantee that the request is a valid type */ +struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int type) { mempool_t *pool; struct nvm_rq *rqd; int rq_size; - if (rw == WRITE) { + switch (type) { + case PBLK_WRITE: + case PBLK_WRITE_INT: pool = pblk->w_rq_pool; rq_size = pblk_w_rq_size; - } else { - pool = pblk->g_rq_pool; + break; + case PBLK_READ: + pool = pblk->r_rq_pool; + rq_size = pblk_g_rq_size; + break; + default: + pool = pblk->e_rq_pool; rq_size = pblk_g_rq_size; } @@ -170,15 +199,30 @@ struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw) return rqd; } -void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int rw) +/* 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; - if (rw == WRITE) + switch (type) { + case PBLK_WRITE: + kfree(((struct pblk_c_ctx *)nvm_rq_to_pdu(rqd))->lun_bitmap); + case PBLK_WRITE_INT: pool = pblk->w_rq_pool; - else - pool = pblk->g_rq_pool; + break; + case PBLK_READ: + pool = pblk->r_rq_pool; + break; + case PBLK_ERASE: + pool = pblk->e_rq_pool; + break; + default: + pr_err("pblk: trying to free unknown rqd type\n"); + return; + } + nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list); mempool_free(rqd, pool); } @@ -190,10 +234,9 @@ void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off, WARN_ON(off + nr_pages != bio->bi_vcnt); - bio_advance(bio, off * PBLK_EXPOSED_PAGE_SIZE); for (i = off; i < nr_pages + off; i++) { bv = bio->bi_io_vec[i]; - mempool_free(bv.bv_page, pblk->page_pool); + mempool_free(bv.bv_page, pblk->page_bio_pool); } } @@ -205,14 +248,12 @@ int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags, int i, ret; for (i = 0; i < nr_pages; i++) { - page = mempool_alloc(pblk->page_pool, flags); - if (!page) - goto err; + page = mempool_alloc(pblk->page_bio_pool, flags); ret = bio_add_pc_page(q, bio, page, PBLK_EXPOSED_PAGE_SIZE, 0); if (ret != PBLK_EXPOSED_PAGE_SIZE) { pr_err("pblk: could not add page to bio\n"); - mempool_free(page, pblk->page_pool); + mempool_free(page, pblk->page_bio_pool); goto err; } } @@ -245,13 +286,6 @@ void pblk_write_should_kick(struct pblk *pblk) pblk_write_kick(pblk); } -void pblk_end_bio_sync(struct bio *bio) -{ - struct completion *waiting = bio->bi_private; - - complete(waiting); -} - void pblk_end_io_sync(struct nvm_rq *rqd) { struct completion *waiting = rqd->private; @@ -259,7 +293,7 @@ void pblk_end_io_sync(struct nvm_rq *rqd) complete(waiting); } -void pblk_wait_for_meta(struct pblk *pblk) +static void pblk_wait_for_meta(struct pblk *pblk) { do { if (!atomic_read(&pblk->inflight_io)) @@ -336,17 +370,6 @@ void pblk_discard(struct pblk *pblk, struct bio *bio) pblk_invalidate_range(pblk, slba, nr_secs); } -struct ppa_addr pblk_get_lba_map(struct pblk *pblk, sector_t lba) -{ - struct ppa_addr ppa; - - spin_lock(&pblk->trans_lock); - ppa = pblk_trans_map_get(pblk, lba); - spin_unlock(&pblk->trans_lock); - - return ppa; -} - void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd) { atomic_long_inc(&pblk->write_failed); @@ -389,39 +412,38 @@ int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd) struct nvm_tgt_dev *dev = pblk->dev; #ifdef CONFIG_NVM_DEBUG - struct ppa_addr *ppa_list; + int ret; - ppa_list = (rqd->nr_ppas > 1) ? rqd->ppa_list : &rqd->ppa_addr; - if (pblk_boundary_ppa_checks(dev, ppa_list, rqd->nr_ppas)) { - WARN_ON(1); - return -EINVAL; - } + ret = pblk_check_io(pblk, rqd); + if (ret) + return ret; +#endif - if (rqd->opcode == NVM_OP_PWRITE) { - struct pblk_line *line; - struct ppa_addr ppa; - int i; + atomic_inc(&pblk->inflight_io); - for (i = 0; i < rqd->nr_ppas; i++) { - ppa = ppa_list[i]; - line = &pblk->lines[pblk_dev_ppa_to_line(ppa)]; + return nvm_submit_io(dev, rqd); +} - spin_lock(&line->lock); - if (line->state != PBLK_LINESTATE_OPEN) { - pr_err("pblk: bad ppa: line:%d,state:%d\n", - line->id, line->state); - WARN_ON(1); - spin_unlock(&line->lock); - return -EINVAL; - } - spin_unlock(&line->lock); - } - } +int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd) +{ + struct nvm_tgt_dev *dev = pblk->dev; + +#ifdef CONFIG_NVM_DEBUG + int ret; + + ret = pblk_check_io(pblk, rqd); + if (ret) + return ret; #endif atomic_inc(&pblk->inflight_io); - return nvm_submit_io(dev, rqd); + return nvm_submit_io_sync(dev, rqd); +} + +static void pblk_bio_map_addr_endio(struct bio *bio) +{ + bio_put(bio); } struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data, @@ -460,6 +482,8 @@ struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data, kaddr += PAGE_SIZE; } + + bio->bi_end_io = pblk_bio_map_addr_endio; out: return bio; } @@ -486,12 +510,14 @@ void pblk_dealloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs) u64 addr; int i; + spin_lock(&line->lock); addr = find_next_zero_bit(line->map_bitmap, pblk->lm.sec_per_line, line->cur_sec); line->cur_sec = addr - nr_secs; for (i = 0; i < nr_secs; i++, line->cur_sec--) WARN_ON(!test_and_clear_bit(line->cur_sec, line->map_bitmap)); + spin_unlock(&line->lock); } u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs) @@ -565,12 +591,11 @@ static int pblk_line_submit_emeta_io(struct pblk *pblk, struct pblk_line *line, int cmd_op, bio_op; int i, j; int ret; - DECLARE_COMPLETION_ONSTACK(wait); - if (dir == WRITE) { + if (dir == PBLK_WRITE) { bio_op = REQ_OP_WRITE; cmd_op = NVM_OP_PWRITE; - } else if (dir == READ) { + } else if (dir == PBLK_READ) { bio_op = REQ_OP_READ; cmd_op = NVM_OP_PREAD; } else @@ -607,13 +632,11 @@ next_rq: rqd.dma_ppa_list = dma_ppa_list; rqd.opcode = cmd_op; rqd.nr_ppas = rq_ppas; - rqd.end_io = pblk_end_io_sync; - rqd.private = &wait; - if (dir == WRITE) { + if (dir == PBLK_WRITE) { struct pblk_sec_meta *meta_list = rqd.meta_list; - rqd.flags = pblk_set_progr_mode(pblk, WRITE); + 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); @@ -662,25 +685,17 @@ next_rq: } } - ret = pblk_submit_io(pblk, &rqd); + ret = pblk_submit_io_sync(pblk, &rqd); if (ret) { pr_err("pblk: emeta I/O submission failed: %d\n", ret); bio_put(bio); goto free_rqd_dma; } - if (!wait_for_completion_io_timeout(&wait, - msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) { - pr_err("pblk: emeta I/O timed out\n"); - } atomic_dec(&pblk->inflight_io); - reinit_completion(&wait); - - if (likely(pblk->l_mg.emeta_alloc_type == PBLK_VMALLOC_META)) - bio_put(bio); if (rqd.error) { - if (dir == WRITE) + if (dir == PBLK_WRITE) pblk_log_write_err(pblk, &rqd); else pblk_log_read_err(pblk, &rqd); @@ -721,14 +736,13 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line, int i, ret; int cmd_op, bio_op; int flags; - DECLARE_COMPLETION_ONSTACK(wait); - if (dir == WRITE) { + if (dir == PBLK_WRITE) { bio_op = REQ_OP_WRITE; cmd_op = NVM_OP_PWRITE; - flags = pblk_set_progr_mode(pblk, WRITE); + flags = pblk_set_progr_mode(pblk, PBLK_WRITE); lba_list = emeta_to_lbas(pblk, line->emeta->buf); - } else if (dir == READ) { + } else if (dir == PBLK_READ) { bio_op = REQ_OP_READ; cmd_op = NVM_OP_PREAD; flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL); @@ -758,15 +772,13 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line, rqd.opcode = cmd_op; rqd.flags = flags; rqd.nr_ppas = lm->smeta_sec; - rqd.end_io = pblk_end_io_sync; - rqd.private = &wait; 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 == WRITE) { + if (dir == PBLK_WRITE) { __le64 addr_empty = cpu_to_le64(ADDR_EMPTY); meta_list[i].lba = lba_list[paddr] = addr_empty; @@ -778,21 +790,17 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line, * 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(pblk, &rqd); + ret = pblk_submit_io_sync(pblk, &rqd); if (ret) { pr_err("pblk: smeta I/O submission failed: %d\n", ret); bio_put(bio); goto free_ppa_list; } - if (!wait_for_completion_io_timeout(&wait, - msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) { - pr_err("pblk: smeta I/O timed out\n"); - } atomic_dec(&pblk->inflight_io); if (rqd.error) { - if (dir == WRITE) + if (dir == PBLK_WRITE) pblk_log_write_err(pblk, &rqd); else pblk_log_read_err(pblk, &rqd); @@ -808,14 +816,14 @@ int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line) { u64 bpaddr = pblk_line_smeta_start(pblk, line); - return pblk_line_submit_smeta_io(pblk, line, bpaddr, READ); + return pblk_line_submit_smeta_io(pblk, line, bpaddr, PBLK_READ); } 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, READ); + line->emeta_ssec, PBLK_READ); } static void pblk_setup_e_rq(struct pblk *pblk, struct nvm_rq *rqd, @@ -824,7 +832,7 @@ 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, ERASE); + rqd->flags = pblk_set_progr_mode(pblk, PBLK_ERASE); rqd->bio = NULL; } @@ -832,19 +840,15 @@ static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa) { struct nvm_rq rqd; int ret = 0; - DECLARE_COMPLETION_ONSTACK(wait); memset(&rqd, 0, sizeof(struct nvm_rq)); pblk_setup_e_rq(pblk, &rqd, ppa); - rqd.end_io = pblk_end_io_sync; - rqd.private = &wait; - /* The write thread schedules erases so that it minimizes disturbances * with writes. Thus, there is no need to take the LUN semaphore. */ - ret = pblk_submit_io(pblk, &rqd); + ret = pblk_submit_io_sync(pblk, &rqd); if (ret) { struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; @@ -857,11 +861,6 @@ static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa) goto out; } - if (!wait_for_completion_io_timeout(&wait, - msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) { - pr_err("pblk: sync erase timed out\n"); - } - out: rqd.private = pblk; __pblk_end_io_erase(pblk, &rqd); @@ -976,7 +975,7 @@ static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line, memcpy(smeta_buf->header.uuid, pblk->instance_uuid, 16); smeta_buf->header.id = cpu_to_le32(line->id); smeta_buf->header.type = cpu_to_le16(line->type); - smeta_buf->header.version = cpu_to_le16(1); + smeta_buf->header.version = SMETA_VERSION; /* Start metadata */ smeta_buf->seq_nr = cpu_to_le64(line->seq_nr); @@ -1046,7 +1045,7 @@ 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, WRITE)) { + if (init && pblk_line_submit_smeta_io(pblk, line, off, PBLK_WRITE)) { pr_debug("pblk: line smeta I/O failed. Retry\n"); return 1; } @@ -1056,7 +1055,6 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line, /* Mark emeta metadata sectors as bad sectors. We need to consider bad * blocks to make sure that there are enough sectors to store emeta */ - bit = lm->sec_per_line; off = lm->sec_per_line - lm->emeta_sec[0]; bitmap_set(line->invalid_bitmap, off, lm->emeta_sec[0]); while (nr_bb) { @@ -1093,25 +1091,21 @@ static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line) struct pblk_line_meta *lm = &pblk->lm; int blk_in_line = atomic_read(&line->blk_in_line); - line->map_bitmap = mempool_alloc(pblk->line_meta_pool, GFP_ATOMIC); + line->map_bitmap = kzalloc(lm->sec_bitmap_len, GFP_ATOMIC); if (!line->map_bitmap) return -ENOMEM; - memset(line->map_bitmap, 0, lm->sec_bitmap_len); - /* invalid_bitmap is special since it is used when line is closed. No - * need to zeroized; it will be initialized using bb info form - * map_bitmap - */ - line->invalid_bitmap = mempool_alloc(pblk->line_meta_pool, GFP_ATOMIC); + /* will be initialized using bb info from map_bitmap */ + line->invalid_bitmap = kmalloc(lm->sec_bitmap_len, GFP_ATOMIC); if (!line->invalid_bitmap) { - mempool_free(line->map_bitmap, pblk->line_meta_pool); + kfree(line->map_bitmap); return -ENOMEM; } spin_lock(&line->lock); if (line->state != PBLK_LINESTATE_FREE) { - mempool_free(line->invalid_bitmap, pblk->line_meta_pool); - mempool_free(line->map_bitmap, pblk->line_meta_pool); + kfree(line->map_bitmap); + kfree(line->invalid_bitmap); spin_unlock(&line->lock); WARN(1, "pblk: corrupted line %d, state %d\n", line->id, line->state); @@ -1163,7 +1157,7 @@ int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line) void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line) { - mempool_free(line->map_bitmap, pblk->line_meta_pool); + kfree(line->map_bitmap); line->map_bitmap = NULL; line->smeta = NULL; line->emeta = NULL; @@ -1328,6 +1322,41 @@ static void pblk_stop_writes(struct pblk *pblk, struct pblk_line *line) pblk->state = PBLK_STATE_STOPPING; } +static void pblk_line_close |