return 0;
}
-static int pblk_calc_sec_in_line(struct pblk *pblk, struct pblk_line *line)
+static void pblk_update_line_wp(struct pblk *pblk, struct pblk_line *line,
+ u64 written_secs)
+{
+ int i;
+
+ for (i = 0; i < written_secs; i += pblk->min_write_pgs)
+ pblk_alloc_page(pblk, line, pblk->min_write_pgs);
+}
+
+static u64 pblk_sec_in_open_line(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 nr_bb = bitmap_weight(line->blk_bitmap, lm->blk_per_line);
+ u64 written_secs = 0;
+ int valid_chunks = 0;
+ int i;
+
+ for (i = 0; i < lm->blk_per_line; i++) {
+ struct nvm_chk_meta *chunk = &line->chks[i];
- return lm->sec_per_line - lm->smeta_sec - lm->emeta_sec[0] -
- nr_bb * geo->clba;
+ if (chunk->state & NVM_CHK_ST_OFFLINE)
+ continue;
+
+ written_secs += chunk->wp;
+ valid_chunks++;
+ }
+
+ if (lm->blk_per_line - nr_bb != valid_chunks)
+ pblk_err(pblk, "recovery line %d is bad\n", line->id);
+
+ pblk_update_line_wp(pblk, line, written_secs - lm->smeta_sec);
+
+ return written_secs;
}
struct pblk_recov_alloc {
dma_addr_t dma_meta_list;
};
-static int pblk_recov_read_oob(struct pblk *pblk, struct pblk_line *line,
- struct pblk_recov_alloc p, u64 r_ptr)
-{
- struct nvm_tgt_dev *dev = pblk->dev;
- struct nvm_geo *geo = &dev->geo;
- struct ppa_addr *ppa_list;
- struct pblk_sec_meta *meta_list;
- struct nvm_rq *rqd;
- struct bio *bio;
- void *data;
- dma_addr_t dma_ppa_list, dma_meta_list;
- u64 r_ptr_int;
- int left_ppas;
- int rq_ppas, rq_len;
- int i, j;
- int ret = 0;
-
- ppa_list = p.ppa_list;
- meta_list = p.meta_list;
- rqd = p.rqd;
- data = p.data;
- dma_ppa_list = p.dma_ppa_list;
- dma_meta_list = p.dma_meta_list;
-
- left_ppas = line->cur_sec - r_ptr;
- if (!left_ppas)
- return 0;
-
- r_ptr_int = r_ptr;
-
-next_read_rq:
- memset(rqd, 0, pblk_g_rq_size);
-
- rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
- if (!rq_ppas)
- rq_ppas = pblk->min_write_pgs;
- rq_len = rq_ppas * geo->csecs;
-
- bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
- if (IS_ERR(bio))
- return PTR_ERR(bio);
-
- bio->bi_iter.bi_sector = 0; /* internal bio */
- bio_set_op_attrs(bio, REQ_OP_READ, 0);
-
- rqd->bio = bio;
- rqd->opcode = NVM_OP_PREAD;
- rqd->meta_list = meta_list;
- rqd->nr_ppas = rq_ppas;
- rqd->ppa_list = ppa_list;
- rqd->dma_ppa_list = dma_ppa_list;
- rqd->dma_meta_list = dma_meta_list;
-
- if (pblk_io_aligned(pblk, rq_ppas))
- rqd->is_seq = 1;
-
- ppa_list = nvm_rq_to_ppa_list(rqd);
-
- for (i = 0; i < rqd->nr_ppas; ) {
- struct ppa_addr ppa;
- int pos;
-
- ppa = addr_to_gen_ppa(pblk, r_ptr_int, line->id);
- pos = pblk_ppa_to_pos(geo, ppa);
-
- while (test_bit(pos, line->blk_bitmap)) {
- r_ptr_int += pblk->min_write_pgs;
- ppa = addr_to_gen_ppa(pblk, r_ptr_int, line->id);
- pos = pblk_ppa_to_pos(geo, ppa);
- }
-
- for (j = 0; j < pblk->min_write_pgs; j++, i++, r_ptr_int++)
- ppa_list[i] =
- addr_to_gen_ppa(pblk, r_ptr_int, line->id);
- }
-
- /* If read fails, more padding is needed */
- ret = pblk_submit_io_sync(pblk, rqd);
- if (ret) {
- pblk_err(pblk, "I/O submission failed: %d\n", ret);
- return ret;
- }
-
- atomic_dec(&pblk->inflight_io);
-
- /* At this point, the read should not fail. If it does, it is a problem
- * we cannot recover from here. Need FTL log.
- */
- if (rqd->error && rqd->error != NVM_RSP_WARN_HIGHECC) {
- pblk_err(pblk, "L2P recovery failed (%d)\n", rqd->error);
- return -EINTR;
- }
-
- for (i = 0; i < rqd->nr_ppas; i++) {
- u64 lba = le64_to_cpu(meta_list[i].lba);
-
- if (lba == ADDR_EMPTY || lba > pblk->rl.nr_secs)
- continue;
-
- pblk_update_map(pblk, lba, ppa_list[i]);
- }
-
- left_ppas -= rq_ppas;
- if (left_ppas > 0)
- goto next_read_rq;
-
- return 0;
-}
-
static void pblk_recov_complete(struct kref *ref)
{
struct pblk_pad_rq *pad_rq = container_of(ref, struct pblk_pad_rq, ref);
kref_put(&pad_rq->ref, pblk_recov_complete);
}
-static int pblk_recov_pad_oob(struct pblk *pblk, struct pblk_line *line,
- int left_ppas)
+/* pad line using line bitmap. */
+static int pblk_recov_pad_line(struct pblk *pblk, struct pblk_line *line,
+ int left_ppas)
{
struct nvm_tgt_dev *dev = pblk->dev;
struct nvm_geo *geo = &dev->geo;
return (distance > line->left_msecs) ? line->left_msecs : distance;
}
-/* When this function is called, it means that not all upper pages have been
- * written in a page that contains valid data. In order to recover this data, we
- * first find the write pointer on the device, then we pad all necessary
- * sectors, and finally attempt to read the valid data
- */
-static int pblk_recov_scan_all_oob(struct pblk *pblk, struct pblk_line *line,
- struct pblk_recov_alloc p)
+static int pblk_line_wp_is_unbalanced(struct pblk *pblk,
+ struct pblk_line *line)
{
struct nvm_tgt_dev *dev = pblk->dev;
struct nvm_geo *geo = &dev->geo;
- struct ppa_addr *ppa_list;
- struct pblk_sec_meta *meta_list;
- struct nvm_rq *rqd;
- struct bio *bio;
- void *data;
- dma_addr_t dma_ppa_list, dma_meta_list;
- u64 w_ptr = 0, r_ptr;
- int rq_ppas, rq_len;
- int i, j;
- int ret = 0;
- int rec_round;
- int left_ppas = pblk_calc_sec_in_line(pblk, line) - line->cur_sec;
-
- ppa_list = p.ppa_list;
- meta_list = p.meta_list;
- rqd = p.rqd;
- data = p.data;
- dma_ppa_list = p.dma_ppa_list;
- dma_meta_list = p.dma_meta_list;
-
- /* we could recover up until the line write pointer */
- r_ptr = line->cur_sec;
- rec_round = 0;
-
-next_rq:
- memset(rqd, 0, pblk_g_rq_size);
-
- rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
- if (!rq_ppas)
- rq_ppas = pblk->min_write_pgs;
- rq_len = rq_ppas * geo->csecs;
-
- bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
- if (IS_ERR(bio))
- return PTR_ERR(bio);
-
- bio->bi_iter.bi_sector = 0; /* internal bio */
- bio_set_op_attrs(bio, REQ_OP_READ, 0);
-
- rqd->bio = bio;
- rqd->opcode = NVM_OP_PREAD;
- rqd->meta_list = meta_list;
- rqd->nr_ppas = rq_ppas;
- rqd->ppa_list = ppa_list;
- rqd->dma_ppa_list = dma_ppa_list;
- rqd->dma_meta_list = dma_meta_list;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_lun *rlun;
+ struct nvm_chk_meta *chunk;
+ struct ppa_addr ppa;
+ u64 line_wp;
+ int pos, i;
- if (pblk_io_aligned(pblk, rq_ppas))
- rqd->is_seq = 1;
+ rlun = &pblk->luns[0];
+ ppa = rlun->bppa;
+ pos = pblk_ppa_to_pos(geo, ppa);
+ chunk = &line->chks[pos];
- for (i = 0; i < rqd->nr_ppas; ) {
- struct ppa_addr ppa;
- int pos;
+ line_wp = chunk->wp;
- w_ptr = pblk_alloc_page(pblk, line, pblk->min_write_pgs);
- ppa = addr_to_gen_ppa(pblk, w_ptr, line->id);
+ for (i = 1; i < lm->blk_per_line; i++) {
+ rlun = &pblk->luns[i];
+ ppa = rlun->bppa;
pos = pblk_ppa_to_pos(geo, ppa);
+ chunk = &line->chks[pos];
- while (test_bit(pos, line->blk_bitmap)) {
- w_ptr += pblk->min_write_pgs;
- ppa = addr_to_gen_ppa(pblk, w_ptr, line->id);
- pos = pblk_ppa_to_pos(geo, ppa);
- }
-
- for (j = 0; j < pblk->min_write_pgs; j++, i++, w_ptr++)
- rqd->ppa_list[i] =
- addr_to_gen_ppa(pblk, w_ptr, line->id);
- }
-
- ret = pblk_submit_io_sync(pblk, rqd);
- if (ret) {
- pblk_err(pblk, "I/O submission failed: %d\n", ret);
- return ret;
- }
-
- atomic_dec(&pblk->inflight_io);
-
- /* This should not happen since the read failed during normal recovery,
- * but the media works funny sometimes...
- */
- if (!rec_round++ && !rqd->error) {
- rec_round = 0;
- for (i = 0; i < rqd->nr_ppas; i++, r_ptr++) {
- u64 lba = le64_to_cpu(meta_list[i].lba);
-
- if (lba == ADDR_EMPTY || lba > pblk->rl.nr_secs)
- continue;
-
- pblk_update_map(pblk, lba, rqd->ppa_list[i]);
- }
- }
-
- /* Reached the end of the written line */
- if (rqd->error == NVM_RSP_ERR_EMPTYPAGE) {
- int pad_secs, nr_error_bits, bit;
- int ret;
-
- bit = find_first_bit((void *)&rqd->ppa_status, rqd->nr_ppas);
- nr_error_bits = rqd->nr_ppas - bit;
-
- /* Roll back failed sectors */
- line->cur_sec -= nr_error_bits;
- line->left_msecs += nr_error_bits;
- bitmap_clear(line->map_bitmap, line->cur_sec, nr_error_bits);
-
- pad_secs = pblk_pad_distance(pblk, line);
-
- ret = pblk_recov_pad_oob(pblk, line, pad_secs);
- if (ret)
- pblk_err(pblk, "OOB padding failed (err:%d)\n", ret);
-
- ret = pblk_recov_read_oob(pblk, line, p, r_ptr);
- if (ret)
- pblk_err(pblk, "OOB read failed (err:%d)\n", ret);
-
- left_ppas = 0;
+ if (chunk->wp > line_wp)
+ return 1;
+ else if (chunk->wp < line_wp)
+ line_wp = chunk->wp;
}
- left_ppas -= rq_ppas;
- if (left_ppas > 0)
- goto next_rq;
-
- return ret;
+ return 0;
}
static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line,
- struct pblk_recov_alloc p, int *done)
+ struct pblk_recov_alloc p)
{
struct nvm_tgt_dev *dev = pblk->dev;
struct nvm_geo *geo = &dev->geo;
struct bio *bio;
void *data;
dma_addr_t dma_ppa_list, dma_meta_list;
- u64 paddr;
+ __le64 *lba_list;
+ u64 paddr = 0;
+ bool padded = false;
int rq_ppas, rq_len;
int i, j;
- int ret = 0;
- int left_ppas = pblk_calc_sec_in_line(pblk, line);
+ int ret;
+ u64 left_ppas = pblk_sec_in_open_line(pblk, line);
+
+ if (pblk_line_wp_is_unbalanced(pblk, line))
+ pblk_warn(pblk, "recovering unbalanced line (%d)\n", line->id);
ppa_list = p.ppa_list;
meta_list = p.meta_list;
dma_ppa_list = p.dma_ppa_list;
dma_meta_list = p.dma_meta_list;
- *done = 1;
+ lba_list = emeta_to_lbas(pblk, line->emeta->buf);
next_rq:
memset(rqd, 0, pblk_g_rq_size);
if (pblk_io_aligned(pblk, rq_ppas))
rqd->is_seq = 1;
+retry_rq:
for (i = 0; i < rqd->nr_ppas; ) {
struct ppa_addr ppa;
int pos;
- paddr = pblk_alloc_page(pblk, line, pblk->min_write_pgs);
ppa = addr_to_gen_ppa(pblk, paddr, line->id);
pos = pblk_ppa_to_pos(geo, ppa);
pos = pblk_ppa_to_pos(geo, ppa);
}
- for (j = 0; j < pblk->min_write_pgs; j++, i++, paddr++)
+ for (j = 0; j < pblk->min_write_pgs; j++, i++)
rqd->ppa_list[i] =
- addr_to_gen_ppa(pblk, paddr, line->id);
+ addr_to_gen_ppa(pblk, paddr + j, line->id);
}
ret = pblk_submit_io_sync(pblk, rqd);
atomic_dec(&pblk->inflight_io);
- /* Reached the end of the written line */
+ /* If a read fails, do a best effort by padding the line and retrying */
if (rqd->error) {
- int nr_error_bits, bit;
-
- bit = find_first_bit((void *)&rqd->ppa_status, rqd->nr_ppas);
- nr_error_bits = rqd->nr_ppas - bit;
+ int pad_distance, ret;
- /* Roll back failed sectors */
- line->cur_sec -= nr_error_bits;
- line->left_msecs += nr_error_bits;
- bitmap_clear(line->map_bitmap, line->cur_sec, nr_error_bits);
+ if (padded) {
+ pblk_log_read_err(pblk, rqd);
+ return -EINTR;
+ }
- left_ppas = 0;
- rqd->nr_ppas = bit;
+ pad_distance = pblk_pad_distance(pblk, line);
+ ret = pblk_recov_pad_line(pblk, line, pad_distance);
+ if (ret)
+ return ret;
- if (rqd->error != NVM_RSP_ERR_EMPTYPAGE)
- *done = 0;
+ padded = true;
+ goto retry_rq;
}
for (i = 0; i < rqd->nr_ppas; i++) {
u64 lba = le64_to_cpu(meta_list[i].lba);
+ lba_list[paddr++] = cpu_to_le64(lba);
+
if (lba == ADDR_EMPTY || lba > pblk->rl.nr_secs)
continue;
+ line->nr_valid_lbas++;
pblk_update_map(pblk, lba, rqd->ppa_list[i]);
}
if (left_ppas > 0)
goto next_rq;
- return ret;
+#ifdef CONFIG_NVM_PBLK_DEBUG
+ WARN_ON(padded && !pblk_line_is_full(line));
+#endif
+
+ return 0;
}
/* Scan line for lbas on out of bound area */
struct pblk_recov_alloc p;
void *data;
dma_addr_t dma_ppa_list, dma_meta_list;
- int done, ret = 0;
+ int ret = 0;
meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_meta_list);
if (!meta_list)
goto free_meta_list;
}
- rqd = pblk_alloc_rqd(pblk, PBLK_READ);
+ rqd = mempool_alloc(&pblk->r_rq_pool, GFP_KERNEL);
+ memset(rqd, 0, pblk_g_rq_size);
p.ppa_list = ppa_list;
p.meta_list = meta_list;
p.dma_ppa_list = dma_ppa_list;
p.dma_meta_list = dma_meta_list;
- ret = pblk_recov_scan_oob(pblk, line, p, &done);
+ ret = pblk_recov_scan_oob(pblk, line, p);
if (ret) {
- pblk_err(pblk, "could not recover L2P from OOB\n");
+ pblk_err(pblk, "could not recover L2P form OOB\n");
goto out;
}
- if (!done) {
- ret = pblk_recov_scan_all_oob(pblk, line, p);
- if (ret) {
- pblk_err(pblk, "could not recover L2P from OOB\n");
- goto out;
- }
- }
-
if (pblk_line_is_full(line))
pblk_line_recov_close(pblk, line);
out:
+ mempool_free(rqd, &pblk->r_rq_pool);
kfree(data);
free_meta_list:
nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list);
}
static int pblk_line_was_written(struct pblk_line *line,
- struct pblk *pblk)
+ struct pblk *pblk)
{
struct pblk_line_meta *lm = &pblk->lm;
return 1;
}
+static bool pblk_line_is_open(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ int i;
+
+ for (i = 0; i < lm->blk_per_line; i++)
+ if (line->chks[i].state & NVM_CHK_ST_OPEN)
+ return true;
+
+ return false;
+}
+
struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
{
struct pblk_line_meta *lm = &pblk->lm;
line->emeta = emeta;
memset(line->emeta->buf, 0, lm->emeta_len[0]);
+ if (pblk_line_is_open(pblk, line)) {
+ pblk_recov_l2p_from_oob(pblk, line);
+ goto next;
+ }
+
if (pblk_line_emeta_read(pblk, line, line->emeta->buf)) {
pblk_recov_l2p_from_oob(pblk, line);
goto next;
line->smeta = NULL;
line->emeta = NULL;
} else {
- if (open_lines > 1)
- pblk_err(pblk, "failed to recover L2P\n");
+ spin_lock(&line->lock);
+ line->state = PBLK_LINESTATE_OPEN;
+ spin_unlock(&line->lock);
+
+ line->emeta->mem = 0;
+ atomic_set(&line->emeta->sync, 0);
trace_pblk_line_state(pblk_disk_name(pblk), line->id,
line->state);
- open_lines++;
- line->meta_line = meta_line;
data_line = line;
+ line->meta_line = meta_line;
+
+ open_lines++;
}
}
left_msecs = line->left_msecs;
spin_unlock(&l_mg->free_lock);
- ret = pblk_recov_pad_oob(pblk, line, left_msecs);
+ ret = pblk_recov_pad_line(pblk, line, left_msecs);
if (ret) {
pblk_err(pblk, "tear down padding failed (%d)\n", ret);
return ret;