mirror of
https://github.com/torvalds/linux.git
synced 2024-11-18 18:11:56 +00:00
0586942f03
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 <hlitz@ucsc.edu> Reviewed-by: Hans Holmberg <hans.holmberg@cnexlabs.com> Reviewed-by: Javier González <javier@javigon.com> Signed-off-by: Matias Bjørling <mb@lightnvm.io> Signed-off-by: Jens Axboe <axboe@kernel.dk>
210 lines
5.7 KiB
C
210 lines
5.7 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Copyright (C) 2016 CNEX Labs
|
|
* Initial release: Javier Gonzalez <javier@cnexlabs.com>
|
|
* Matias Bjorling <matias@cnexlabs.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License version
|
|
* 2 as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it will be useful, but
|
|
* WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
* General Public License for more details.
|
|
*
|
|
* pblk-map.c - pblk's lba-ppa mapping strategy
|
|
*
|
|
*/
|
|
|
|
#include "pblk.h"
|
|
|
|
static int pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
|
|
struct ppa_addr *ppa_list,
|
|
unsigned long *lun_bitmap,
|
|
void *meta_list,
|
|
unsigned int valid_secs)
|
|
{
|
|
struct pblk_line *line = pblk_line_get_data(pblk);
|
|
struct pblk_emeta *emeta;
|
|
struct pblk_w_ctx *w_ctx;
|
|
__le64 *lba_list;
|
|
u64 paddr;
|
|
int nr_secs = pblk->min_write_pgs;
|
|
int i;
|
|
|
|
if (!line)
|
|
return -ENOSPC;
|
|
|
|
if (pblk_line_is_full(line)) {
|
|
struct pblk_line *prev_line = line;
|
|
|
|
/* If we cannot allocate a new line, make sure to store metadata
|
|
* on current line and then fail
|
|
*/
|
|
line = pblk_line_replace_data(pblk);
|
|
pblk_line_close_meta(pblk, prev_line);
|
|
|
|
if (!line) {
|
|
pblk_pipeline_stop(pblk);
|
|
return -ENOSPC;
|
|
}
|
|
|
|
}
|
|
|
|
emeta = line->emeta;
|
|
lba_list = emeta_to_lbas(pblk, emeta->buf);
|
|
|
|
paddr = pblk_alloc_page(pblk, line, nr_secs);
|
|
|
|
for (i = 0; i < nr_secs; i++, paddr++) {
|
|
struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i);
|
|
__le64 addr_empty = cpu_to_le64(ADDR_EMPTY);
|
|
|
|
/* ppa to be sent to the device */
|
|
ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id);
|
|
|
|
/* Write context for target bio completion on write buffer. Note
|
|
* that the write buffer is protected by the sync backpointer,
|
|
* and a single writer thread have access to each specific entry
|
|
* at a time. Thus, it is safe to modify the context for the
|
|
* entry we are setting up for submission without taking any
|
|
* lock or memory barrier.
|
|
*/
|
|
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);
|
|
lba_list[paddr] = cpu_to_le64(w_ctx->lba);
|
|
if (lba_list[paddr] != addr_empty)
|
|
line->nr_valid_lbas++;
|
|
else
|
|
atomic64_inc(&pblk->pad_wa);
|
|
} else {
|
|
lba_list[paddr] = addr_empty;
|
|
meta->lba = addr_empty;
|
|
__pblk_map_invalidate(pblk, line, paddr);
|
|
}
|
|
}
|
|
|
|
pblk_down_rq(pblk, ppa_list[0], lun_bitmap);
|
|
return 0;
|
|
}
|
|
|
|
int pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
|
|
unsigned long *lun_bitmap, unsigned int valid_secs,
|
|
unsigned int off)
|
|
{
|
|
void *meta_list = pblk_get_meta_for_writes(pblk, rqd);
|
|
void *meta_buffer;
|
|
struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd);
|
|
unsigned int map_secs;
|
|
int min = pblk->min_write_pgs;
|
|
int i;
|
|
int ret;
|
|
|
|
for (i = off; i < rqd->nr_ppas; i += min) {
|
|
map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
|
|
meta_buffer = pblk_get_meta(pblk, meta_list, i);
|
|
|
|
ret = pblk_map_page_data(pblk, sentry + i, &ppa_list[i],
|
|
lun_bitmap, meta_buffer, map_secs);
|
|
if (ret)
|
|
return ret;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
/* only if erase_ppa is set, acquire erase semaphore */
|
|
int pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
|
|
unsigned int sentry, unsigned long *lun_bitmap,
|
|
unsigned int valid_secs, struct ppa_addr *erase_ppa)
|
|
{
|
|
struct nvm_tgt_dev *dev = pblk->dev;
|
|
struct nvm_geo *geo = &dev->geo;
|
|
struct pblk_line_meta *lm = &pblk->lm;
|
|
void *meta_list = pblk_get_meta_for_writes(pblk, rqd);
|
|
void *meta_buffer;
|
|
struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd);
|
|
struct pblk_line *e_line, *d_line;
|
|
unsigned int map_secs;
|
|
int min = pblk->min_write_pgs;
|
|
int i, erase_lun;
|
|
int ret;
|
|
|
|
|
|
for (i = 0; i < rqd->nr_ppas; i += min) {
|
|
map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
|
|
meta_buffer = pblk_get_meta(pblk, meta_list, i);
|
|
|
|
ret = pblk_map_page_data(pblk, sentry + i, &ppa_list[i],
|
|
lun_bitmap, meta_buffer, map_secs);
|
|
if (ret)
|
|
return ret;
|
|
|
|
erase_lun = pblk_ppa_to_pos(geo, ppa_list[i]);
|
|
|
|
/* line can change after page map. We might also be writing the
|
|
* last line.
|
|
*/
|
|
e_line = pblk_line_get_erase(pblk);
|
|
if (!e_line)
|
|
return pblk_map_rq(pblk, rqd, sentry, lun_bitmap,
|
|
valid_secs, i + min);
|
|
|
|
spin_lock(&e_line->lock);
|
|
if (!test_bit(erase_lun, e_line->erase_bitmap)) {
|
|
set_bit(erase_lun, e_line->erase_bitmap);
|
|
atomic_dec(&e_line->left_eblks);
|
|
|
|
*erase_ppa = ppa_list[i];
|
|
erase_ppa->a.blk = e_line->id;
|
|
|
|
spin_unlock(&e_line->lock);
|
|
|
|
/* Avoid evaluating e_line->left_eblks */
|
|
return pblk_map_rq(pblk, rqd, sentry, lun_bitmap,
|
|
valid_secs, i + min);
|
|
}
|
|
spin_unlock(&e_line->lock);
|
|
}
|
|
|
|
d_line = pblk_line_get_data(pblk);
|
|
|
|
/* line can change after page map. We might also be writing the
|
|
* last line.
|
|
*/
|
|
e_line = pblk_line_get_erase(pblk);
|
|
if (!e_line)
|
|
return -ENOSPC;
|
|
|
|
/* Erase blocks that are bad in this line but might not be in next */
|
|
if (unlikely(pblk_ppa_empty(*erase_ppa)) &&
|
|
bitmap_weight(d_line->blk_bitmap, lm->blk_per_line)) {
|
|
int bit = -1;
|
|
|
|
retry:
|
|
bit = find_next_bit(d_line->blk_bitmap,
|
|
lm->blk_per_line, bit + 1);
|
|
if (bit >= lm->blk_per_line)
|
|
return 0;
|
|
|
|
spin_lock(&e_line->lock);
|
|
if (test_bit(bit, e_line->erase_bitmap)) {
|
|
spin_unlock(&e_line->lock);
|
|
goto retry;
|
|
}
|
|
spin_unlock(&e_line->lock);
|
|
|
|
set_bit(bit, e_line->erase_bitmap);
|
|
atomic_dec(&e_line->left_eblks);
|
|
*erase_ppa = pblk->luns[bit].bppa; /* set ch and lun */
|
|
erase_ppa->a.blk = e_line->id;
|
|
}
|
|
|
|
return 0;
|
|
}
|