diff options
author | Igor Konopko <igor.j.konopko@intel.com> | 2019-05-04 20:38:10 +0200 |
---|---|---|
committer | Jens Axboe <axboe@kernel.dk> | 2019-05-06 10:19:19 -0600 |
commit | a96de64a24e5035018c5a912f2b877da8797277e (patch) | |
tree | 3d3a80a71cce270dca5ebed4cbe6c9133e0d7752 /drivers/lightnvm/pblk-read.c | |
parent | 843f2edbdde085b4d2764baf6fd8a1fccb1ab26a (diff) | |
download | linux-a96de64a24e5035018c5a912f2b877da8797277e.tar.gz linux-a96de64a24e5035018c5a912f2b877da8797277e.tar.bz2 linux-a96de64a24e5035018c5a912f2b877da8797277e.zip |
lightnvm: pblk: simplify partial read path
This patch changes the approach to handling partial read path.
In old approach merging of data from round buffer and drive was fully
made by drive. This had some disadvantages - code was complex and
relies on bio internals, so it was hard to maintain and was strongly
dependent on bio changes.
In new approach most of the handling is done mostly by block layer
functions such as bio_split(), bio_chain() and generic_make request()
and generally is less complex and easier to maintain. Below some more
details of the new approach.
When read bio arrives, it is cloned for pblk internal purposes. All
the L2P mapping, which includes copying data from round buffer to bio
and thus bio_advance() calls is done on the cloned bio, so the original
bio is untouched. If we found that we have partial read case, we
still have original bio untouched, so we can split it and continue to
process only first part of it in current context, when the rest will be
called as separate bio request which is passed to generic_make_request()
for further processing.
Signed-off-by: Igor Konopko <igor.j.konopko@intel.com>
Reviewed-by: Heiner Litz <hlitz@ucsc.edu>
Reviewed-by: Javier González <javier@javigon.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'drivers/lightnvm/pblk-read.c')
-rw-r--r-- | drivers/lightnvm/pblk-read.c | 339 |
1 files changed, 85 insertions, 254 deletions
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c index f5f155d540e2..d98ea392fe33 100644 --- a/drivers/lightnvm/pblk-read.c +++ b/drivers/lightnvm/pblk-read.c @@ -26,8 +26,7 @@ * issued. */ static int pblk_read_from_cache(struct pblk *pblk, struct bio *bio, - sector_t lba, struct ppa_addr ppa, - int bio_iter, bool advanced_bio) + sector_t lba, struct ppa_addr ppa) { #ifdef CONFIG_NVM_PBLK_DEBUG /* Callers must ensure that the ppa points to a cache address */ @@ -35,73 +34,75 @@ static int pblk_read_from_cache(struct pblk *pblk, struct bio *bio, BUG_ON(!pblk_addr_in_cache(ppa)); #endif - return pblk_rb_copy_to_bio(&pblk->rwb, bio, lba, ppa, - bio_iter, advanced_bio); + return pblk_rb_copy_to_bio(&pblk->rwb, bio, lba, ppa); } -static void pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd, +static int pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd, struct bio *bio, sector_t blba, - unsigned long *read_bitmap) + bool *from_cache) { void *meta_list = rqd->meta_list; - struct ppa_addr ppas[NVM_MAX_VLBA]; - int nr_secs = rqd->nr_ppas; - bool advanced_bio = false; - int i, j = 0; + int nr_secs, i; - pblk_lookup_l2p_seq(pblk, ppas, blba, nr_secs); +retry: + nr_secs = pblk_lookup_l2p_seq(pblk, rqd->ppa_list, blba, rqd->nr_ppas, + from_cache); + + if (!*from_cache) + goto end; for (i = 0; i < nr_secs; i++) { - struct ppa_addr p = ppas[i]; struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i); sector_t lba = blba + i; -retry: - if (pblk_ppa_empty(p)) { + if (pblk_ppa_empty(rqd->ppa_list[i])) { __le64 addr_empty = cpu_to_le64(ADDR_EMPTY); - WARN_ON(test_and_set_bit(i, read_bitmap)); meta->lba = addr_empty; - - if (unlikely(!advanced_bio)) { - bio_advance(bio, (i) * PBLK_EXPOSED_PAGE_SIZE); - advanced_bio = true; + } else if (pblk_addr_in_cache(rqd->ppa_list[i])) { + /* + * Try to read from write buffer. The address is later + * checked on the write buffer to prevent retrieving + * overwritten data. + */ + if (!pblk_read_from_cache(pblk, bio, lba, + rqd->ppa_list[i])) { + if (i == 0) { + /* + * We didn't call with bio_advance() + * yet, so we can just retry. + */ + goto retry; + } else { + /* + * We already call bio_advance() + * so we cannot retry and we need + * to quit that function in order + * to allow caller to handle the bio + * splitting in the current sector + * position. + */ + nr_secs = i; + goto end; + } } - - goto next; - } - - /* Try to read from write buffer. The address is later checked - * on the write buffer to prevent retrieving overwritten data. - */ - if (pblk_addr_in_cache(p)) { - if (!pblk_read_from_cache(pblk, bio, lba, p, i, - advanced_bio)) { - pblk_lookup_l2p_seq(pblk, &p, lba, 1); - goto retry; - } - WARN_ON(test_and_set_bit(i, read_bitmap)); meta->lba = cpu_to_le64(lba); - advanced_bio = true; #ifdef CONFIG_NVM_PBLK_DEBUG atomic_long_inc(&pblk->cache_reads); #endif - } else { - /* Read from media non-cached sectors */ - rqd->ppa_list[j++] = p; } - -next: - if (advanced_bio) - bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE); + bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE); } +end: if (pblk_io_aligned(pblk, nr_secs)) rqd->is_seq = 1; #ifdef CONFIG_NVM_PBLK_DEBUG atomic_long_add(nr_secs, &pblk->inflight_reads); #endif + + return nr_secs; } @@ -197,9 +198,7 @@ static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd, pblk_log_read_err(pblk, rqd); pblk_read_check_seq(pblk, rqd, r_ctx->lba); - - if (int_bio) - bio_put(int_bio); + bio_put(int_bio); if (put_line) pblk_rq_to_line_put(pblk, rqd); @@ -223,183 +222,13 @@ static void pblk_end_io_read(struct nvm_rq *rqd) __pblk_end_io_read(pblk, rqd, true); } -static void pblk_end_partial_read(struct nvm_rq *rqd) -{ - struct pblk *pblk = rqd->private; - struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd); - struct pblk_pr_ctx *pr_ctx = r_ctx->private; - struct pblk_sec_meta *meta; - struct bio *new_bio = rqd->bio; - struct bio *bio = pr_ctx->orig_bio; - void *meta_list = rqd->meta_list; - unsigned long *read_bitmap = pr_ctx->bitmap; - struct bvec_iter orig_iter = BVEC_ITER_ALL_INIT; - struct bvec_iter new_iter = BVEC_ITER_ALL_INIT; - int nr_secs = pr_ctx->orig_nr_secs; - int nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs); - void *src_p, *dst_p; - int bit, i; - - if (unlikely(nr_holes == 1)) { - struct ppa_addr ppa; - - ppa = rqd->ppa_addr; - rqd->ppa_list = pr_ctx->ppa_ptr; - rqd->dma_ppa_list = pr_ctx->dma_ppa_list; - rqd->ppa_list[0] = ppa; - } - - for (i = 0; i < nr_secs; i++) { - meta = pblk_get_meta(pblk, meta_list, i); - pr_ctx->lba_list_media[i] = le64_to_cpu(meta->lba); - meta->lba = cpu_to_le64(pr_ctx->lba_list_mem[i]); - } - - /* Fill the holes in the original bio */ - i = 0; - for (bit = 0; bit < nr_secs; bit++) { - if (!test_bit(bit, read_bitmap)) { - struct bio_vec dst_bv, src_bv; - struct pblk_line *line; - - line = pblk_ppa_to_line(pblk, rqd->ppa_list[i]); - kref_put(&line->ref, pblk_line_put); - - meta = pblk_get_meta(pblk, meta_list, bit); - meta->lba = cpu_to_le64(pr_ctx->lba_list_media[i]); - - dst_bv = bio_iter_iovec(bio, orig_iter); - src_bv = bio_iter_iovec(new_bio, new_iter); - - src_p = kmap_atomic(src_bv.bv_page); - dst_p = kmap_atomic(dst_bv.bv_page); - - memcpy(dst_p + dst_bv.bv_offset, - src_p + src_bv.bv_offset, - PBLK_EXPOSED_PAGE_SIZE); - - kunmap_atomic(src_p); - kunmap_atomic(dst_p); - - flush_dcache_page(dst_bv.bv_page); - mempool_free(src_bv.bv_page, &pblk->page_bio_pool); - - bio_advance_iter(new_bio, &new_iter, - PBLK_EXPOSED_PAGE_SIZE); - i++; - } - bio_advance_iter(bio, &orig_iter, PBLK_EXPOSED_PAGE_SIZE); - } - - bio_put(new_bio); - kfree(pr_ctx); - - /* restore original request */ - rqd->bio = NULL; - rqd->nr_ppas = nr_secs; - - pblk_end_user_read(bio, rqd->error); - __pblk_end_io_read(pblk, rqd, false); -} - -static int pblk_setup_partial_read(struct pblk *pblk, struct nvm_rq *rqd, - unsigned int bio_init_idx, - unsigned long *read_bitmap, - int nr_holes) -{ - void *meta_list = rqd->meta_list; - struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd); - struct pblk_pr_ctx *pr_ctx; - struct bio *new_bio, *bio = r_ctx->private; - int nr_secs = rqd->nr_ppas; - int i; - - new_bio = bio_alloc(GFP_KERNEL, nr_holes); - - if (pblk_bio_add_pages(pblk, new_bio, GFP_KERNEL, nr_holes)) - goto fail_bio_put; - - if (nr_holes != new_bio->bi_vcnt) { - WARN_ONCE(1, "pblk: malformed bio\n"); - goto fail_free_pages; - } - - pr_ctx = kzalloc(sizeof(struct pblk_pr_ctx), GFP_KERNEL); - if (!pr_ctx) - goto fail_free_pages; - - for (i = 0; i < nr_secs; i++) { - struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i); - - pr_ctx->lba_list_mem[i] = le64_to_cpu(meta->lba); - } - - new_bio->bi_iter.bi_sector = 0; /* internal bio */ - bio_set_op_attrs(new_bio, REQ_OP_READ, 0); - - rqd->bio = new_bio; - rqd->nr_ppas = nr_holes; - - pr_ctx->orig_bio = bio; - bitmap_copy(pr_ctx->bitmap, read_bitmap, NVM_MAX_VLBA); - pr_ctx->bio_init_idx = bio_init_idx; - pr_ctx->orig_nr_secs = nr_secs; - r_ctx->private = pr_ctx; - - if (unlikely(nr_holes == 1)) { - pr_ctx->ppa_ptr = rqd->ppa_list; - pr_ctx->dma_ppa_list = rqd->dma_ppa_list; - rqd->ppa_addr = rqd->ppa_list[0]; - } - return 0; - -fail_free_pages: - pblk_bio_free_pages(pblk, new_bio, 0, new_bio->bi_vcnt); -fail_bio_put: - bio_put(new_bio); - - return -ENOMEM; -} - -static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd, - unsigned int bio_init_idx, - unsigned long *read_bitmap, int nr_secs) -{ - int nr_holes; - int ret; - - nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs); - - if (pblk_setup_partial_read(pblk, rqd, bio_init_idx, read_bitmap, - nr_holes)) - return NVM_IO_ERR; - - rqd->end_io = pblk_end_partial_read; - - ret = pblk_submit_io(pblk, rqd); - if (ret) { - bio_put(rqd->bio); - pblk_err(pblk, "partial read IO submission failed\n"); - goto err; - } - - return NVM_IO_OK; - -err: - pblk_err(pblk, "failed to perform partial read\n"); - - /* Free allocated pages in new bio */ - pblk_bio_free_pages(pblk, rqd->bio, 0, rqd->bio->bi_vcnt); - return NVM_IO_ERR; -} - static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd, struct bio *bio, - sector_t lba, unsigned long *read_bitmap) + sector_t lba, bool *from_cache) { struct pblk_sec_meta *meta = pblk_get_meta(pblk, rqd->meta_list, 0); struct ppa_addr ppa; - pblk_lookup_l2p_seq(pblk, &ppa, lba, 1); + pblk_lookup_l2p_seq(pblk, &ppa, lba, 1, from_cache); #ifdef CONFIG_NVM_PBLK_DEBUG atomic_long_inc(&pblk->inflight_reads); @@ -409,7 +238,6 @@ retry: if (pblk_ppa_empty(ppa)) { __le64 addr_empty = cpu_to_le64(ADDR_EMPTY); - WARN_ON(test_and_set_bit(0, read_bitmap)); meta->lba = addr_empty; return; } @@ -418,12 +246,11 @@ retry: * write buffer to prevent retrieving overwritten data. */ if (pblk_addr_in_cache(ppa)) { - if (!pblk_read_from_cache(pblk, bio, lba, ppa, 0, 1)) { - pblk_lookup_l2p_seq(pblk, &ppa, lba, 1); + if (!pblk_read_from_cache(pblk, bio, lba, ppa)) { + pblk_lookup_l2p_seq(pblk, &ppa, lba, 1, from_cache); goto retry; } - WARN_ON(test_and_set_bit(0, read_bitmap)); meta->lba = cpu_to_le64(lba); #ifdef CONFIG_NVM_PBLK_DEBUG @@ -440,17 +267,14 @@ void pblk_submit_read(struct pblk *pblk, struct bio *bio) struct request_queue *q = dev->q; sector_t blba = pblk_get_lba(bio); unsigned int nr_secs = pblk_get_secs(bio); + bool from_cache; struct pblk_g_ctx *r_ctx; struct nvm_rq *rqd; - struct bio *int_bio; - unsigned int bio_init_idx; - DECLARE_BITMAP(read_bitmap, NVM_MAX_VLBA); + struct bio *int_bio, *split_bio; generic_start_io_acct(q, REQ_OP_READ, bio_sectors(bio), &pblk->disk->part0); - bitmap_zero(read_bitmap, nr_secs); - rqd = pblk_alloc_rqd(pblk, PBLK_READ); rqd->opcode = NVM_OP_PREAD; @@ -462,11 +286,6 @@ void pblk_submit_read(struct pblk *pblk, struct bio *bio) r_ctx->start_time = jiffies; r_ctx->lba = blba; - /* Save the index for this bio's start. This is needed in case - * we need to fill a partial read. - */ - bio_init_idx = pblk_get_bi_idx(bio); - if (pblk_alloc_rqd_meta(pblk, rqd)) { bio_io_error(bio); pblk_free_rqd(pblk, rqd, PBLK_READ); @@ -475,46 +294,58 @@ void pblk_submit_read(struct pblk *pblk, struct bio *bio) /* Clone read bio to deal internally with: * -read errors when reading from drive - * -bio_advance() calls during l2p lookup and cache reads + * -bio_advance() calls during cache reads */ int_bio = bio_clone_fast(bio, GFP_KERNEL, &pblk_bio_set); if (nr_secs > 1) - pblk_read_ppalist_rq(pblk, rqd, bio, blba, read_bitmap); + nr_secs = pblk_read_ppalist_rq(pblk, rqd, int_bio, blba, + &from_cache); else - pblk_read_rq(pblk, rqd, bio, blba, read_bitmap); + pblk_read_rq(pblk, rqd, int_bio, blba, &from_cache); +split_retry: r_ctx->private = bio; /* original bio */ rqd->bio = int_bio; /* internal bio */ - if (bitmap_full(read_bitmap, nr_secs)) { + if (from_cache && nr_secs == rqd->nr_ppas) { + /* All data was read from cache, we can complete the IO. */ pblk_end_user_read(bio, 0); atomic_inc(&pblk->inflight_io); __pblk_end_io_read(pblk, rqd, false); - return; - } - - if (!bitmap_empty(read_bitmap, rqd->nr_ppas)) { + } else if (nr_secs != rqd->nr_ppas) { /* The read bio request could be partially filled by the write * buffer, but there are some holes that need to be read from - * the drive. + * the drive. In order to handle this, we will use block layer + * mechanism to split this request in to smaller ones and make + * a chain of it. */ - bio_put(int_bio); - rqd->bio = NULL; - if (pblk_partial_read_bio(pblk, rqd, bio_init_idx, read_bitmap, - nr_secs)) { - pblk_err(pblk, "read IO submission failed\n"); - bio_io_error(bio); - __pblk_end_io_read(pblk, rqd, false); - } - return; - } + split_bio = bio_split(bio, nr_secs * NR_PHY_IN_LOG, GFP_KERNEL, + &pblk_bio_set); + bio_chain(split_bio, bio); + generic_make_request(bio); + + /* New bio contains first N sectors of the previous one, so + * we can continue to use existing rqd, but we need to shrink + * the number of PPAs in it. New bio is also guaranteed that + * it contains only either data from cache or from drive, newer + * mix of them. + */ + bio = split_bio; + rqd->nr_ppas = nr_secs; + if (rqd->nr_ppas == 1) + rqd->ppa_addr = rqd->ppa_list[0]; - /* All sectors are to be read from the device */ - if (pblk_submit_io(pblk, rqd)) { - pblk_err(pblk, "read IO submission failed\n"); - bio_io_error(bio); - __pblk_end_io_read(pblk, rqd, false); + /* Recreate int_bio - existing might have some needed internal + * fields modified already. + */ + bio_put(int_bio); + int_bio = bio_clone_fast(bio, GFP_KERNEL, &pblk_bio_set); + goto split_retry; + } else if (pblk_submit_io(pblk, rqd)) { + /* Submitting IO to drive failed, let's report an error */ + rqd->error = -ENODEV; + pblk_end_io_read(rqd); } } |