*/
#include "pblk.h"
-#include <linux/time.h>
static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
struct ppa_addr *ppa)
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_line_run_ws(pblk, NULL, ppa, pblk_line_mark_bb, pblk->bb_wq);
}
static void __pblk_end_io_erase(struct pblk *pblk, struct nvm_rq *rqd)
*ppa = rqd->ppa_addr;
pblk_mark_bb(pblk, line, ppa);
}
+
+ atomic_dec(&pblk->inflight_io);
}
/* Erase completion assumes that only one block is erased at the time */
complete(waiting);
}
-void pblk_flush_writer(struct pblk *pblk)
+void pblk_wait_for_meta(struct pblk *pblk)
{
- struct bio *bio;
- int ret;
- DECLARE_COMPLETION_ONSTACK(wait);
-
- bio = bio_alloc(GFP_KERNEL, 1);
- if (!bio)
- return;
-
- bio->bi_iter.bi_sector = 0; /* internal bio */
- bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_OP_FLUSH);
- bio->bi_private = &wait;
- bio->bi_end_io = pblk_end_bio_sync;
+ do {
+ if (!atomic_read(&pblk->inflight_io))
+ break;
- ret = pblk_write_to_cache(pblk, bio, 0);
- if (ret == NVM_IO_OK) {
- if (!wait_for_completion_io_timeout(&wait,
- msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
- pr_err("pblk: flush cache timed out\n");
- }
- } else if (ret != NVM_IO_DONE) {
- pr_err("pblk: tear down bio failed\n");
- }
+ schedule();
+ } while (1);
+}
- if (bio->bi_status)
- pr_err("pblk: flush sync write failed (%u)\n", bio->bi_status);
+static void pblk_flush_writer(struct pblk *pblk)
+{
+ pblk_rb_flush(&pblk->rwb);
+ do {
+ if (!pblk_rb_read_count(&pblk->rwb))
+ break;
- bio_put(bio);
+ schedule();
+ } while (1);
}
struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
struct list_head *move_list = NULL;
int vsc = le32_to_cpu(*line->vsc);
+ lockdep_assert_held(&line->lock);
+
if (!vsc) {
if (line->gc_group != PBLK_LINEGC_FULL) {
line->gc_group = PBLK_LINEGC_FULL;
move_list = &l_mg->gc_full_list;
}
- } else if (vsc < lm->mid_thrs) {
+ } else if (vsc < lm->high_thrs) {
if (line->gc_group != PBLK_LINEGC_HIGH) {
line->gc_group = PBLK_LINEGC_HIGH;
move_list = &l_mg->gc_high_list;
}
- } else if (vsc < lm->high_thrs) {
+ } else if (vsc < lm->mid_thrs) {
if (line->gc_group != PBLK_LINEGC_MID) {
line->gc_group = PBLK_LINEGC_MID;
move_list = &l_mg->gc_mid_list;
}
}
#endif
+
+ atomic_inc(&pblk->inflight_io);
+
return nvm_submit_io(dev, rqd);
}
struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
unsigned int nr_secs, unsigned int len,
- gfp_t gfp_mask)
+ int alloc_type, gfp_t gfp_mask)
{
struct nvm_tgt_dev *dev = pblk->dev;
- struct pblk_line_mgmt *l_mg = &pblk->l_mg;
void *kaddr = data;
struct page *page;
struct bio *bio;
int i, ret;
- if (l_mg->emeta_alloc_type == PBLK_KMALLOC_META)
+ if (alloc_type == PBLK_KMALLOC_META)
return bio_map_kern(dev->q, kaddr, len, gfp_mask);
bio = bio_kmalloc(gfp_mask, nr_secs);
u64 addr;
int i;
+ lockdep_assert_held(&line->lock);
+
/* logic error: ppa out-of-bounds. Prevent generating bad address */
if (line->cur_sec + nr_secs > pblk->lm.sec_per_line) {
WARN(1, "pblk: page allocation out of bounds\n");
{
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;
rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
rq_len = rq_ppas * geo->sec_size;
- bio = pblk_bio_map_addr(pblk, emeta_buf, rq_ppas, rq_len, GFP_KERNEL);
+ 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;
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))
rqd.ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id);
if (dir == WRITE) {
- u64 addr_empty = cpu_to_le64(ADDR_EMPTY);
+ __le64 addr_empty = cpu_to_le64(ADDR_EMPTY);
meta_list[i].lba = lba_list[paddr] = addr_empty;
}
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)
static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa)
{
struct nvm_rq rqd;
- int ret;
+ int ret = 0;
DECLARE_COMPLETION_ONSTACK(wait);
memset(&rqd, 0, sizeof(struct nvm_rq));
rqd.private = pblk;
__pblk_end_io_erase(pblk, &rqd);
- return 0;
+ return ret;
}
int pblk_line_erase(struct pblk *pblk, struct pblk_line *line)
{
struct pblk_line_meta *lm = &pblk->lm;
struct ppa_addr ppa;
- int bit = -1;
+ int ret, bit = -1;
/* Erase only good blocks, one at a time */
do {
WARN_ON(test_and_set_bit(bit, line->erase_bitmap));
spin_unlock(&line->lock);
- if (pblk_blk_erase_sync(pblk, ppa)) {
+ ret = pblk_blk_erase_sync(pblk, ppa);
+ if (ret) {
pr_err("pblk: failed to erase line %d\n", line->id);
- return -ENOMEM;
+ return ret;
}
} while (1);
{
int meta_line;
+ lockdep_assert_held(&l_mg->free_lock);
+
retry_meta:
meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES);
if (meta_line == PBLK_DATA_LINES) {
/* Mark smeta metadata sectors as bad sectors */
bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line);
off = bit * geo->sec_per_pl;
-retry_smeta:
bitmap_set(line->map_bitmap, off, lm->smeta_sec);
line->sec_in_line -= lm->smeta_sec;
line->smeta_ssec = off;
if (init && pblk_line_submit_smeta_io(pblk, line, off, WRITE)) {
pr_debug("pblk: line smeta I/O failed. Retry\n");
- off += geo->sec_per_pl;
- goto retry_smeta;
+ return 1;
}
bitmap_copy(line->invalid_bitmap, line->map_bitmap, lm->sec_per_line);
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);
spin_unlock(&line->lock);
- WARN(1, "pblk: corrupted line state\n");
- return -EINTR;
+ WARN(1, "pblk: corrupted line %d, state %d\n",
+ line->id, line->state);
+ return -EAGAIN;
}
+
line->state = PBLK_LINESTATE_OPEN;
atomic_set(&line->left_eblks, blk_in_line);
{
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
struct pblk_line_meta *lm = &pblk->lm;
- struct pblk_line *line = NULL;
- int bit;
+ struct pblk_line *line;
+ int ret, bit;
lockdep_assert_held(&l_mg->free_lock);
-retry_get:
+retry:
if (list_empty(&l_mg->free_list)) {
pr_err("pblk: no free lines\n");
- goto out;
+ return NULL;
}
line = list_first_entry(&l_mg->free_list, struct pblk_line, list);
list_add_tail(&line->list, &l_mg->bad_list);
pr_debug("pblk: line %d is bad\n", line->id);
- goto retry_get;
+ goto retry;
}
- if (pblk_line_prepare(pblk, line)) {
- pr_err("pblk: failed to prepare line %d\n", line->id);
- list_add(&line->list, &l_mg->free_list);
- return NULL;
+ ret = pblk_line_prepare(pblk, line);
+ if (ret) {
+ if (ret == -EAGAIN) {
+ list_add(&line->list, &l_mg->corrupt_list);
+ goto retry;
+ } else {
+ pr_err("pblk: failed to prepare line %d\n", line->id);
+ list_add(&line->list, &l_mg->free_list);
+ l_mg->nr_free_lines++;
+ return NULL;
+ }
}
-out:
return line;
}
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
struct pblk_line *retry_line;
+retry:
spin_lock(&l_mg->free_lock);
retry_line = pblk_line_get(pblk);
if (!retry_line) {
l_mg->data_line = retry_line;
spin_unlock(&l_mg->free_lock);
- if (pblk_line_erase(pblk, retry_line)) {
- spin_lock(&l_mg->free_lock);
- l_mg->data_line = NULL;
- spin_unlock(&l_mg->free_lock);
- return NULL;
- }
-
pblk_rl_free_lines_dec(&pblk->rl, retry_line);
+ if (pblk_line_erase(pblk, retry_line))
+ goto retry;
+
return retry_line;
}
+static void pblk_set_space_limit(struct pblk *pblk)
+{
+ struct pblk_rl *rl = &pblk->rl;
+
+ atomic_set(&rl->rb_space, 0);
+}
+
struct pblk_line *pblk_line_get_first_data(struct pblk *pblk)
{
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
/* Allocate next line for preparation */
l_mg->data_next = pblk_line_get(pblk);
- if (l_mg->data_next) {
+ if (!l_mg->data_next) {
+ /* If we cannot get a new line, we need to stop the pipeline.
+ * Only allow as many writes in as we can store safely and then
+ * fail gracefully
+ */
+ pblk_set_space_limit(pblk);
+
+ l_mg->data_next = NULL;
+ } else {
l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
l_mg->data_next->type = PBLK_LINETYPE_DATA;
is_next = 1;
}
spin_unlock(&l_mg->free_lock);
+ if (pblk_line_erase(pblk, line)) {
+ line = pblk_line_retry(pblk, line);
+ if (!line)
+ return NULL;
+ }
+
pblk_rl_free_lines_dec(&pblk->rl, line);
if (is_next)
pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
- if (pblk_line_erase(pblk, line))
- return NULL;
-
retry_setup:
if (!pblk_line_init_metadata(pblk, line, NULL)) {
line = pblk_line_retry(pblk, line);
return line;
}
-struct pblk_line *pblk_line_replace_data(struct pblk *pblk)
+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;
+}
+
+void pblk_pipeline_stop(struct pblk *pblk)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ int ret;
+
+ spin_lock(&l_mg->free_lock);
+ if (pblk->state == PBLK_STATE_RECOVERING ||
+ pblk->state == PBLK_STATE_STOPPED) {
+ spin_unlock(&l_mg->free_lock);
+ return;
+ }
+ pblk->state = PBLK_STATE_RECOVERING;
+ spin_unlock(&l_mg->free_lock);
+
+ pblk_flush_writer(pblk);
+ pblk_wait_for_meta(pblk);
+
+ ret = pblk_recov_pad(pblk);
+ if (ret) {
+ pr_err("pblk: could not close data on teardown(%d)\n", ret);
+ return;
+ }
+
+ pblk_line_close_meta_sync(pblk);
+
+ spin_lock(&l_mg->free_lock);
+ pblk->state = PBLK_STATE_STOPPED;
+ l_mg->data_line = NULL;
+ l_mg->data_next = NULL;
+ spin_unlock(&l_mg->free_lock);
+}
+
+void pblk_line_replace_data(struct pblk *pblk)
{
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
struct pblk_line *cur, *new;
cur = l_mg->data_line;
new = l_mg->data_next;
if (!new)
- return NULL;
+ return;
l_mg->data_line = new;
-retry_line:
+ spin_lock(&l_mg->free_lock);
+ if (pblk->state != PBLK_STATE_RUNNING) {
+ l_mg->data_line = NULL;
+ l_mg->data_next = NULL;
+ spin_unlock(&l_mg->free_lock);
+ return;
+ }
+
+ pblk_line_setup_metadata(new, l_mg, &pblk->lm);
+ spin_unlock(&l_mg->free_lock);
+
+retry_erase:
left_seblks = atomic_read(&new->left_seblks);
if (left_seblks) {
/* If line is not fully erased, erase it */
if (atomic_read(&new->left_eblks)) {
if (pblk_line_erase(pblk, new))
- return NULL;
+ return;
} else {
io_schedule();
}
- goto retry_line;
- }
-
- spin_lock(&l_mg->free_lock);
- /* Allocate next line for preparation */
- l_mg->data_next = pblk_line_get(pblk);
- if (l_mg->data_next) {
- l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
- l_mg->data_next->type = PBLK_LINETYPE_DATA;
- is_next = 1;
+ goto retry_erase;
}
- pblk_line_setup_metadata(new, l_mg, &pblk->lm);
- spin_unlock(&l_mg->free_lock);
-
- if (is_next)
- pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
-
retry_setup:
if (!pblk_line_init_metadata(pblk, new, cur)) {
new = pblk_line_retry(pblk, new);
if (!new)
- return NULL;
+ return;
goto retry_setup;
}
if (!pblk_line_init_bb(pblk, new, 1)) {
new = pblk_line_retry(pblk, new);
if (!new)
- return NULL;
+ return;
goto retry_setup;
}
- return new;
+ /* Allocate next line for preparation */
+ spin_lock(&l_mg->free_lock);
+ l_mg->data_next = pblk_line_get(pblk);
+ if (!l_mg->data_next) {
+ /* If we cannot get a new line, we need to stop the pipeline.
+ * Only allow as many writes in as we can store safely and then
+ * fail gracefully
+ */
+ pblk_stop_writes(pblk, new);
+ l_mg->data_next = NULL;
+ } else {
+ l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
+ l_mg->data_next->type = PBLK_LINETYPE_DATA;
+ is_next = 1;
+ }
+ spin_unlock(&l_mg->free_lock);
+
+ if (is_next)
+ pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
}
void pblk_line_free(struct pblk *pblk, struct pblk_line *line)
return (line->left_msecs == 0);
}
+void pblk_line_close_meta_sync(struct pblk *pblk)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line *line, *tline;
+ LIST_HEAD(list);
+
+ spin_lock(&l_mg->close_lock);
+ if (list_empty(&l_mg->emeta_list)) {
+ spin_unlock(&l_mg->close_lock);
+ return;
+ }
+
+ list_cut_position(&list, &l_mg->emeta_list, l_mg->emeta_list.prev);
+ spin_unlock(&l_mg->close_lock);
+
+ list_for_each_entry_safe(line, tline, &list, list) {
+ struct pblk_emeta *emeta = line->emeta;
+
+ while (emeta->mem < lm->emeta_len[0]) {
+ int ret;
+
+ ret = pblk_submit_meta_io(pblk, line);
+ if (ret) {
+ pr_err("pblk: sync meta line %d failed (%d)\n",
+ line->id, ret);
+ return;
+ }
+ }
+ }
+
+ pblk_wait_for_meta(pblk);
+}
+
+static void pblk_line_should_sync_meta(struct pblk *pblk)
+{
+ if (pblk_rl_is_limit(&pblk->rl))
+ pblk_line_close_meta_sync(pblk);
+}
+
void pblk_line_close(struct pblk *pblk, struct pblk_line *line)
{
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
spin_unlock(&line->lock);
spin_unlock(&l_mg->gc_lock);
+
+ pblk_gc_should_kick(pblk);
}
void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line)
struct pblk_emeta *emeta = line->emeta;
struct line_emeta *emeta_buf = emeta->buf;
- /* No need for exact vsc value; avoid a big line lock and tak aprox. */
+ /* No need for exact vsc value; avoid a big line lock and take aprox. */
memcpy(emeta_to_vsc(pblk, emeta_buf), l_mg->vsc_list, lm->vsc_list_len);
memcpy(emeta_to_bb(emeta_buf), line->blk_bitmap, lm->blk_bitmap_len);
list_add_tail(&line->list, &l_mg->emeta_list);
spin_unlock(&line->lock);
spin_unlock(&l_mg->close_lock);
+
+ pblk_line_should_sync_meta(pblk);
}
void pblk_line_close_ws(struct work_struct *work)
}
void pblk_line_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
- void (*work)(struct work_struct *))
+ void (*work)(struct work_struct *),
+ struct workqueue_struct *wq)
{
struct pblk_line_ws *line_ws;
line_ws->priv = priv;
INIT_WORK(&line_ws->ws, work);
- queue_work(pblk->kw_wq, &line_ws->ws);
+ queue_work(wq, &line_ws->ws);
}
void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
projects / linux.git / blobdiff