From b4cdc4260edf7e03d8b6fabb88aec2cdda95917e Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 11 Feb 2019 13:25:08 +0100 Subject: lightnvm: pblk: prevent stall due to wb threshold In order to respect mw_cuinits, pblk's write buffer maintains a backpointer to protect data not yet persisted; when writing to the write buffer, this backpointer defines a threshold that pblk's rate-limiter enforces. On small PU configurations, the following scenarios might take place: (i) the threshold is larger than the write buffer and (ii) the threshold is smaller than the write buffer, but larger than the maximun allowed split bio - 256KB at this moment (Note that writes are not always split - we only do this when we the size of the buffer is smaller than the buffer). In both cases, pblk's rate-limiter prevents the I/O to be written to the buffer, thus stalling. This patch fixes the original backpointer implementation by considering the threshold both on buffer creation and on the rate-limiters path, when bio_split is triggered (case (ii) above). Fixes: 766c8ceb16fc ("lightnvm: pblk: guarantee that backpointer is respected on writer stall") Signed-off-by: Javier González Reviewed-by: Hans Holmberg Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- drivers/lightnvm/pblk-rb.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) (limited to 'drivers/lightnvm/pblk-rb.c') diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c index d4ca8c64ee0f..a6133b50ed9c 100644 --- a/drivers/lightnvm/pblk-rb.c +++ b/drivers/lightnvm/pblk-rb.c @@ -45,10 +45,23 @@ void pblk_rb_free(struct pblk_rb *rb) /* * pblk_rb_calculate_size -- calculate the size of the write buffer */ -static unsigned int pblk_rb_calculate_size(unsigned int nr_entries) +static unsigned int pblk_rb_calculate_size(unsigned int nr_entries, + unsigned int threshold) { - /* Alloc a write buffer that can at least fit 128 entries */ - return (1 << max(get_count_order(nr_entries), 7)); + unsigned int thr_sz = 1 << (get_count_order(threshold + NVM_MAX_VLBA)); + unsigned int max_sz = max(thr_sz, nr_entries); + unsigned int max_io; + + /* Alloc a write buffer that can (i) fit at least two split bios + * (considering max I/O size NVM_MAX_VLBA, and (ii) guarantee that the + * threshold will be respected + */ + max_io = (1 << max((int)(get_count_order(max_sz)), + (int)(get_count_order(NVM_MAX_VLBA << 1)))); + if ((threshold + NVM_MAX_VLBA) >= max_io) + max_io <<= 1; + + return max_io; } /* @@ -67,12 +80,12 @@ int pblk_rb_init(struct pblk_rb *rb, unsigned int size, unsigned int threshold, unsigned int alloc_order, order, iter; unsigned int nr_entries; - nr_entries = pblk_rb_calculate_size(size); + nr_entries = pblk_rb_calculate_size(size, threshold); entries = vzalloc(array_size(nr_entries, sizeof(struct pblk_rb_entry))); if (!entries) return -ENOMEM; - power_size = get_count_order(size); + power_size = get_count_order(nr_entries); power_seg_sz = get_count_order(seg_size); down_write(&pblk_rb_lock); @@ -149,7 +162,7 @@ int pblk_rb_init(struct pblk_rb *rb, unsigned int size, unsigned int threshold, * Initialize rate-limiter, which controls access to the write buffer * by user and GC I/O */ - pblk_rl_init(&pblk->rl, rb->nr_entries); + pblk_rl_init(&pblk->rl, rb->nr_entries, threshold); return 0; } -- cgit v1.2.3-55-g7522 From 0586942f03b71bc95b0ee356ff6b09d53acbad06 Mon Sep 17 00:00:00 2001 From: Heiner Litz Date: Mon, 11 Feb 2019 13:25:09 +0100 Subject: lightnvm: pblk: fix race condition on GC This patch fixes a race condition where a write is mapped to the last sectors of a line. The write is synced to the device but the L2P is not updated yet. When the line is garbage collected before the L2P update is performed, the sectors are ignored by the GC logic and the line is freed before all sectors are moved. When the L2P is finally updated, it contains a mapping to a freed line, subsequent reads of the corresponding LBAs fail. This patch introduces a per line counter specifying the number of sectors that are synced to the device but have not been updated in the L2P. Lines with a counter of greater than zero will not be selected for GC. Signed-off-by: Heiner Litz Reviewed-by: Hans Holmberg Reviewed-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- drivers/lightnvm/pblk-core.c | 1 + drivers/lightnvm/pblk-gc.c | 20 +++++++++++++------- drivers/lightnvm/pblk-map.c | 1 + drivers/lightnvm/pblk-rb.c | 1 + drivers/lightnvm/pblk-write.c | 1 + drivers/lightnvm/pblk.h | 1 + 6 files changed, 18 insertions(+), 7 deletions(-) (limited to 'drivers/lightnvm/pblk-rb.c') diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c index 2a9e9facf44f..6ca868868fee 100644 --- a/drivers/lightnvm/pblk-core.c +++ b/drivers/lightnvm/pblk-core.c @@ -1278,6 +1278,7 @@ static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line) spin_unlock(&line->lock); kref_init(&line->ref); + atomic_set(&line->sec_to_update, 0); return 0; } diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c index 2fa118c8eb71..26a52ea7ec45 100644 --- a/drivers/lightnvm/pblk-gc.c +++ b/drivers/lightnvm/pblk-gc.c @@ -365,16 +365,22 @@ static struct pblk_line *pblk_gc_get_victim_line(struct pblk *pblk, struct list_head *group_list) { struct pblk_line *line, *victim; - int line_vsc, victim_vsc; + unsigned int line_vsc = ~0x0L, victim_vsc = ~0x0L; victim = list_first_entry(group_list, struct pblk_line, list); + list_for_each_entry(line, group_list, list) { - line_vsc = le32_to_cpu(*line->vsc); - victim_vsc = le32_to_cpu(*victim->vsc); - if (line_vsc < victim_vsc) + if (!atomic_read(&line->sec_to_update)) + line_vsc = le32_to_cpu(*line->vsc); + if (line_vsc < victim_vsc) { victim = line; + victim_vsc = le32_to_cpu(*victim->vsc); + } } + if (victim_vsc == ~0x0) + return NULL; + return victim; } @@ -448,13 +454,13 @@ next_gc_group: do { spin_lock(&l_mg->gc_lock); - if (list_empty(group_list)) { + + line = pblk_gc_get_victim_line(pblk, group_list); + if (!line) { spin_unlock(&l_mg->gc_lock); break; } - line = pblk_gc_get_victim_line(pblk, group_list); - spin_lock(&line->lock); WARN_ON(line->state != PBLK_LINESTATE_CLOSED); line->state = PBLK_LINESTATE_GC; diff --git a/drivers/lightnvm/pblk-map.c b/drivers/lightnvm/pblk-map.c index 79df583ea709..7fbc99b60cac 100644 --- a/drivers/lightnvm/pblk-map.c +++ b/drivers/lightnvm/pblk-map.c @@ -73,6 +73,7 @@ static int pblk_map_page_data(struct pblk *pblk, unsigned int sentry, */ if (i < valid_secs) { kref_get(&line->ref); + atomic_inc(&line->sec_to_update); w_ctx = pblk_rb_w_ctx(&pblk->rwb, sentry + i); w_ctx->ppa = ppa_list[i]; meta->lba = cpu_to_le64(w_ctx->lba); diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c index a6133b50ed9c..03c241b340ea 100644 --- a/drivers/lightnvm/pblk-rb.c +++ b/drivers/lightnvm/pblk-rb.c @@ -260,6 +260,7 @@ static int __pblk_rb_update_l2p(struct pblk_rb *rb, unsigned int to_update) entry->cacheline); line = pblk_ppa_to_line(pblk, w_ctx->ppa); + atomic_dec(&line->sec_to_update); kref_put(&line->ref, pblk_line_put); clean_wctx(w_ctx); rb->l2p_update = pblk_rb_ptr_wrap(rb, rb->l2p_update, 1); diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c index 06d56deb645d..6593deab52da 100644 --- a/drivers/lightnvm/pblk-write.c +++ b/drivers/lightnvm/pblk-write.c @@ -177,6 +177,7 @@ static void pblk_prepare_resubmit(struct pblk *pblk, unsigned int sentry, * re-map these entries */ line = pblk_ppa_to_line(pblk, w_ctx->ppa); + atomic_dec(&line->sec_to_update); kref_put(&line->ref, pblk_line_put); } spin_unlock(&pblk->trans_lock); diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h index a6386d5acd73..ac3ab778e976 100644 --- a/drivers/lightnvm/pblk.h +++ b/drivers/lightnvm/pblk.h @@ -487,6 +487,7 @@ struct pblk_line { __le32 *vsc; /* Valid sector count in line */ struct kref ref; /* Write buffer L2P references */ + atomic_t sec_to_update; /* Outstanding L2P updates to ppa */ struct pblk_w_err_gc *w_err_gc; /* Write error gc recovery metadata */ -- cgit v1.2.3-55-g7522