return 0;
}
-__le64 *pblk_recov_get_lba_list(struct pblk *pblk, struct line_emeta *emeta)
+__le64 *pblk_recov_get_lba_list(struct pblk *pblk, struct line_emeta *emeta_buf)
{
u32 crc;
- crc = pblk_calc_emeta_crc(pblk, emeta);
- if (le32_to_cpu(emeta->crc) != crc)
+ crc = pblk_calc_emeta_crc(pblk, emeta_buf);
+ if (le32_to_cpu(emeta_buf->crc) != crc)
return NULL;
- if (le32_to_cpu(emeta->header.identifier) != PBLK_MAGIC)
+ if (le32_to_cpu(emeta_buf->header.identifier) != PBLK_MAGIC)
return NULL;
- return pblk_line_emeta_to_lbas(emeta);
+ return emeta_to_lbas(pblk, emeta_buf);
}
static int pblk_recov_l2p_from_emeta(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;
- struct line_emeta *emeta = line->emeta;
+ struct pblk_emeta *emeta = line->emeta;
+ struct line_emeta *emeta_buf = emeta->buf;
__le64 *lba_list;
int data_start;
int nr_data_lbas, nr_valid_lbas, nr_lbas = 0;
int i;
- lba_list = pblk_recov_get_lba_list(pblk, emeta);
+ lba_list = pblk_recov_get_lba_list(pblk, emeta_buf);
if (!lba_list)
return 1;
data_start = pblk_line_smeta_start(pblk, line) + lm->smeta_sec;
- nr_data_lbas = lm->sec_per_line - lm->emeta_sec;
- nr_valid_lbas = le64_to_cpu(emeta->nr_valid_lbas);
+ nr_data_lbas = lm->sec_per_line - lm->emeta_sec[0];
+ nr_valid_lbas = le64_to_cpu(emeta_buf->nr_valid_lbas);
for (i = data_start; i < nr_data_lbas && nr_lbas < nr_valid_lbas; i++) {
struct ppa_addr ppa;
if (test_and_set_bit(i, line->invalid_bitmap))
WARN_ONCE(1, "pblk: rec. double invalidate:\n");
else
- line->vsc--;
+ le32_add_cpu(line->vsc, -1);
spin_unlock(&line->lock);
continue;
if (nr_valid_lbas != nr_lbas)
pr_err("pblk: line %d - inconsistent lba list(%llu/%d)\n",
- line->id, line->emeta->nr_valid_lbas, nr_lbas);
+ line->id, emeta_buf->nr_valid_lbas, nr_lbas);
line->left_msecs = 0;
struct pblk_line_meta *lm = &pblk->lm;
int nr_bb = bitmap_weight(line->blk_bitmap, lm->blk_per_line);
- return lm->sec_per_line - lm->smeta_sec - lm->emeta_sec -
+ return lm->sec_per_line - lm->smeta_sec - lm->emeta_sec[0] -
nr_bb * geo->sec_per_blk;
}
r_ptr_int = r_ptr;
next_read_rq:
- memset(rqd, 0, pblk_r_rq_size);
+ memset(rqd, 0, pblk_g_rq_size);
rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
if (!rq_ppas)
rqd->bio = bio;
rqd->opcode = NVM_OP_PREAD;
- rqd->flags = pblk_set_read_mode(pblk);
rqd->meta_list = meta_list;
rqd->nr_ppas = rq_ppas;
rqd->ppa_list = ppa_list;
rqd->end_io = pblk_end_io_sync;
rqd->private = &wait;
+ if (pblk_io_aligned(pblk, rq_ppas))
+ rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL);
+ else
+ rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
+
for (i = 0; i < rqd->nr_ppas; ) {
struct ppa_addr ppa;
int pos;
pr_err("pblk: L2P recovery read timed out\n");
return -EINTR;
}
-
+ atomic_dec(&pblk->inflight_io);
reinit_completion(&wait);
/* At this point, the read should not fail. If it does, it is a problem
return 0;
}
+static void pblk_recov_complete(struct kref *ref)
+{
+ struct pblk_pad_rq *pad_rq = container_of(ref, struct pblk_pad_rq, ref);
+
+ complete(&pad_rq->wait);
+}
+
+static void pblk_end_io_recov(struct nvm_rq *rqd)
+{
+ struct pblk_pad_rq *pad_rq = rqd->private;
+ struct pblk *pblk = pad_rq->pblk;
+ struct nvm_tgt_dev *dev = pblk->dev;
+
+ kref_put(&pad_rq->ref, pblk_recov_complete);
+ nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
+ pblk_free_rqd(pblk, rqd, WRITE);
+}
+
static int pblk_recov_pad_oob(struct pblk *pblk, struct pblk_line *line,
- struct pblk_recov_alloc p, int left_ppas)
+ int left_ppas)
{
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 pblk_pad_rq *pad_rq;
struct nvm_rq *rqd;
struct bio *bio;
void *data;
dma_addr_t dma_ppa_list, dma_meta_list;
- __le64 *lba_list = pblk_line_emeta_to_lbas(line->emeta);
+ __le64 *lba_list = emeta_to_lbas(pblk, line->emeta->buf);
u64 w_ptr = line->cur_sec;
- int left_line_ppas = line->left_msecs;
- int rq_ppas, rq_len;
+ int left_line_ppas, rq_ppas, rq_len;
int i, j;
int ret = 0;
- DECLARE_COMPLETION_ONSTACK(wait);
- 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;
+ spin_lock(&line->lock);
+ left_line_ppas = line->left_msecs;
+ spin_unlock(&line->lock);
+
+ pad_rq = kmalloc(sizeof(struct pblk_pad_rq), GFP_KERNEL);
+ if (!pad_rq)
+ return -ENOMEM;
+
+ data = vzalloc(pblk->max_write_pgs * geo->sec_size);
+ if (!data) {
+ ret = -ENOMEM;
+ goto free_rq;
+ }
+
+ pad_rq->pblk = pblk;
+ init_completion(&pad_rq->wait);
+ kref_init(&pad_rq->ref);
next_pad_rq:
rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
- if (!rq_ppas)
- rq_ppas = pblk->min_write_pgs;
+ if (rq_ppas < pblk->min_write_pgs) {
+ pr_err("pblk: corrupted pad line %d\n", line->id);
+ goto free_rq;
+ }
+
rq_len = rq_ppas * geo->sec_size;
+ meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_meta_list);
+ if (!meta_list) {
+ ret = -ENOMEM;
+ goto free_data;
+ }
+
+ ppa_list = (void *)(meta_list) + pblk_dma_meta_size;
+ dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
+
+ rqd = pblk_alloc_rqd(pblk, WRITE);
+ if (IS_ERR(rqd)) {
+ ret = PTR_ERR(rqd);
+ goto fail_free_meta;
+ }
+ memset(rqd, 0, pblk_w_rq_size);
+
bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
- if (IS_ERR(bio))
- return PTR_ERR(bio);
+ if (IS_ERR(bio)) {
+ ret = PTR_ERR(bio);
+ goto fail_free_rqd;
+ }
bio->bi_iter.bi_sector = 0; /* internal bio */
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
- memset(rqd, 0, pblk_r_rq_size);
-
rqd->bio = bio;
rqd->opcode = NVM_OP_PWRITE;
rqd->flags = pblk_set_progr_mode(pblk, WRITE);
rqd->ppa_list = ppa_list;
rqd->dma_ppa_list = dma_ppa_list;
rqd->dma_meta_list = dma_meta_list;
- rqd->end_io = pblk_end_io_sync;
- rqd->private = &wait;
+ rqd->end_io = pblk_end_io_recov;
+ rqd->private = pad_rq;
for (i = 0; i < rqd->nr_ppas; ) {
struct ppa_addr ppa;
for (j = 0; j < pblk->min_write_pgs; j++, i++, w_ptr++) {
struct ppa_addr dev_ppa;
+ __le64 addr_empty = cpu_to_le64(ADDR_EMPTY);
dev_ppa = addr_to_gen_ppa(pblk, w_ptr, line->id);
pblk_map_invalidate(pblk, dev_ppa);
- meta_list[i].lba = cpu_to_le64(ADDR_EMPTY);
- lba_list[w_ptr] = cpu_to_le64(ADDR_EMPTY);
+ lba_list[w_ptr] = meta_list[i].lba = addr_empty;
rqd->ppa_list[i] = dev_ppa;
}
}
+ kref_get(&pad_rq->ref);
+
ret = pblk_submit_io(pblk, rqd);
if (ret) {
pr_err("pblk: I/O submission failed: %d\n", ret);
- return ret;
+ goto free_data;
}
- if (!wait_for_completion_io_timeout(&wait,
- msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
- pr_err("pblk: L2P recovery write timed out\n");
- }
- reinit_completion(&wait);
+ atomic_dec(&pblk->inflight_io);
left_line_ppas -= rq_ppas;
left_ppas -= rq_ppas;
- if (left_ppas > 0 && left_line_ppas)
+ if (left_ppas && left_line_ppas)
goto next_pad_rq;
- return 0;
+ kref_put(&pad_rq->ref, pblk_recov_complete);
+
+ if (!wait_for_completion_io_timeout(&pad_rq->wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: pad write timed out\n");
+ ret = -ETIME;
+ }
+
+free_rq:
+ kfree(pad_rq);
+free_data:
+ vfree(data);
+ return ret;
+
+fail_free_rqd:
+ pblk_free_rqd(pblk, rqd, WRITE);
+fail_free_meta:
+ nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list);
+ kfree(pad_rq);
+ return ret;
}
/* When this function is called, it means that not all upper pages have been
rec_round = 0;
next_rq:
- memset(rqd, 0, pblk_r_rq_size);
+ memset(rqd, 0, pblk_g_rq_size);
rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
if (!rq_ppas)
rqd->bio = bio;
rqd->opcode = NVM_OP_PREAD;
- rqd->flags = pblk_set_read_mode(pblk);
rqd->meta_list = meta_list;
rqd->nr_ppas = rq_ppas;
rqd->ppa_list = ppa_list;
rqd->end_io = pblk_end_io_sync;
rqd->private = &wait;
+ if (pblk_io_aligned(pblk, rq_ppas))
+ rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL);
+ else
+ rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
+
for (i = 0; i < rqd->nr_ppas; ) {
struct ppa_addr ppa;
int pos;
msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
pr_err("pblk: L2P recovery read timed out\n");
}
+ atomic_dec(&pblk->inflight_io);
reinit_completion(&wait);
/* This should not happen since the read failed during normal recovery,
if (pad_secs > line->left_msecs)
pad_secs = line->left_msecs;
- ret = pblk_recov_pad_oob(pblk, line, p, pad_secs);
+ ret = pblk_recov_pad_oob(pblk, line, pad_secs);
if (ret)
pr_err("pblk: OOB padding failed (err:%d)\n", ret);
if (ret)
pr_err("pblk: OOB read failed (err:%d)\n", ret);
- line->left_ssecs = line->left_msecs;
left_ppas = 0;
}
*done = 1;
next_rq:
- memset(rqd, 0, pblk_r_rq_size);
+ memset(rqd, 0, pblk_g_rq_size);
rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
if (!rq_ppas)
rqd->bio = bio;
rqd->opcode = NVM_OP_PREAD;
- rqd->flags = pblk_set_read_mode(pblk);
rqd->meta_list = meta_list;
rqd->nr_ppas = rq_ppas;
rqd->ppa_list = ppa_list;
rqd->end_io = pblk_end_io_sync;
rqd->private = &wait;
+ if (pblk_io_aligned(pblk, rq_ppas))
+ rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL);
+ else
+ rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
+
for (i = 0; i < rqd->nr_ppas; ) {
struct ppa_addr ppa;
int pos;
msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
pr_err("pblk: L2P recovery read timed out\n");
}
+ atomic_dec(&pblk->inflight_io);
reinit_completion(&wait);
/* Reached the end of the written line */
/* Roll back failed sectors */
line->cur_sec -= nr_error_bits;
line->left_msecs += nr_error_bits;
- line->left_ssecs = line->left_msecs;
bitmap_clear(line->map_bitmap, line->cur_sec, nr_error_bits);
left_ppas = 0;
struct pblk_line_meta *lm = &pblk->lm;
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
struct pblk_line *line, *tline, *data_line = NULL;
- struct line_smeta *smeta;
- struct line_emeta *emeta;
+ struct pblk_smeta *smeta;
+ struct pblk_emeta *emeta;
+ struct line_smeta *smeta_buf;
int found_lines = 0, recovered_lines = 0, open_lines = 0;
int is_next = 0;
int meta_line;
spin_lock(&l_mg->free_lock);
meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES);
set_bit(meta_line, &l_mg->meta_bitmap);
- smeta = l_mg->sline_meta[meta_line].meta;
- emeta = l_mg->eline_meta[meta_line].meta;
+ smeta = l_mg->sline_meta[meta_line];
+ emeta = l_mg->eline_meta[meta_line];
+ smeta_buf = (struct line_smeta *)smeta;
spin_unlock(&l_mg->free_lock);
/* Order data lines using their sequence number */
memset(smeta, 0, lm->smeta_len);
line->smeta = smeta;
- line->lun_bitmap = ((void *)(smeta)) +
+ line->lun_bitmap = ((void *)(smeta_buf)) +
sizeof(struct line_smeta);
/* Lines that cannot be read are assumed as not written here */
if (pblk_line_read_smeta(pblk, line))
continue;
- crc = pblk_calc_smeta_crc(pblk, smeta);
- if (le32_to_cpu(smeta->crc) != crc)
+ crc = pblk_calc_smeta_crc(pblk, smeta_buf);
+ if (le32_to_cpu(smeta_buf->crc) != crc)
continue;
- if (le32_to_cpu(smeta->header.identifier) != PBLK_MAGIC)
+ if (le32_to_cpu(smeta_buf->header.identifier) != PBLK_MAGIC)
continue;
- if (le16_to_cpu(smeta->header.version) != 1) {
+ if (le16_to_cpu(smeta_buf->header.version) != 1) {
pr_err("pblk: found incompatible line version %u\n",
- smeta->header.version);
+ smeta_buf->header.version);
return ERR_PTR(-EINVAL);
}
/* The first valid instance uuid is used for initialization */
if (!valid_uuid) {
- memcpy(pblk->instance_uuid, smeta->header.uuid, 16);
+ memcpy(pblk->instance_uuid, smeta_buf->header.uuid, 16);
valid_uuid = 1;
}
- if (memcmp(pblk->instance_uuid, smeta->header.uuid, 16)) {
+ if (memcmp(pblk->instance_uuid, smeta_buf->header.uuid, 16)) {
pr_debug("pblk: ignore line %u due to uuid mismatch\n",
i);
continue;
/* Update line metadata */
spin_lock(&line->lock);
- line->id = le32_to_cpu(line->smeta->header.id);
- line->type = le16_to_cpu(line->smeta->header.type);
- line->seq_nr = le64_to_cpu(line->smeta->seq_nr);
+ line->id = le32_to_cpu(smeta_buf->header.id);
+ line->type = le16_to_cpu(smeta_buf->header.type);
+ line->seq_nr = le64_to_cpu(smeta_buf->seq_nr);
spin_unlock(&line->lock);
/* Update general metadata */
pblk_recov_line_add_ordered(&recov_list, line);
found_lines++;
pr_debug("pblk: recovering data line %d, seq:%llu\n",
- line->id, smeta->seq_nr);
+ line->id, smeta_buf->seq_nr);
}
if (!found_lines) {
recovered_lines++;
/* Calculate where emeta starts based on the line bb */
- off = lm->sec_per_line - lm->emeta_sec;
+ off = lm->sec_per_line - lm->emeta_sec[0];
nr_bb = bitmap_weight(line->blk_bitmap, lm->blk_per_line);
off -= nr_bb * geo->sec_per_pl;
- memset(emeta, 0, lm->emeta_len);
- line->emeta = emeta;
line->emeta_ssec = off;
+ line->emeta = emeta;
+ memset(line->emeta->buf, 0, lm->emeta_len[0]);
- if (pblk_line_read_emeta(pblk, line)) {
+ if (pblk_line_read_emeta(pblk, line, line->emeta->buf)) {
pblk_recov_l2p_from_oob(pblk, line);
goto next;
}
}
/*
- * Pad until smeta can be read on current data line
+ * Pad current line
*/
-void pblk_recov_pad(struct pblk *pblk)
+int pblk_recov_pad(struct pblk *pblk)
{
- struct nvm_tgt_dev *dev = pblk->dev;
- struct nvm_geo *geo = &dev->geo;
struct pblk_line *line;
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
- struct nvm_rq *rqd;
- struct pblk_recov_alloc p;
- struct ppa_addr *ppa_list;
- struct pblk_sec_meta *meta_list;
- void *data;
- dma_addr_t dma_ppa_list, dma_meta_list;
+ int left_msecs;
+ int ret = 0;
spin_lock(&l_mg->free_lock);
line = l_mg->data_line;
+ left_msecs = line->left_msecs;
spin_unlock(&l_mg->free_lock);
- rqd = pblk_alloc_rqd(pblk, READ);
- if (IS_ERR(rqd))
- return;
-
- meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_meta_list);
- if (!meta_list)
- goto free_rqd;
-
- ppa_list = (void *)(meta_list) + pblk_dma_meta_size;
- dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
-
- data = kcalloc(pblk->max_write_pgs, geo->sec_size, GFP_KERNEL);
- if (!data)
- goto free_meta_list;
-
- p.ppa_list = ppa_list;
- p.meta_list = meta_list;
- p.rqd = rqd;
- p.data = data;
- p.dma_ppa_list = dma_ppa_list;
- p.dma_meta_list = dma_meta_list;
-
- if (pblk_recov_pad_oob(pblk, line, p, line->left_msecs)) {
- pr_err("pblk: Tear down padding failed\n");
- goto free_data;
+ ret = pblk_recov_pad_oob(pblk, line, left_msecs);
+ if (ret) {
+ pr_err("pblk: Tear down padding failed (%d)\n", ret);
+ return ret;
}
- pblk_line_close(pblk, line);
-
-free_data:
- kfree(data);
-free_meta_list:
- nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list);
-free_rqd:
- pblk_free_rqd(pblk, rqd, READ);
+ pblk_line_close_meta(pblk, line);
+ return ret;
}
projects / linux.git / blobdiff