mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-29 23:53:32 +00:00
d624f371d5
Erase I/Os are scheduled with the following goals in mind: (i) minimize LUNs collisions with write I/Os, and (ii) even out the price of erasing on every write, instead of putting all the burden on when garbage collection runs. This works well on the current design, but is specific to the default mapping algorithm. This patch generalizes the erase path so that other mapping algorithms can select an arbitrary line to be erased instead. It also gets rid of the erase semaphore since it creates jittering for user writes. Signed-off-by: Javier González <javier@cnexlabs.com> Signed-off-by: Matias Bjørling <matias@cnexlabs.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
155 lines
4.7 KiB
C
155 lines
4.7 KiB
C
/*
|
|
* 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 void pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
|
|
struct ppa_addr *ppa_list,
|
|
unsigned long *lun_bitmap,
|
|
struct pblk_sec_meta *meta_list,
|
|
unsigned int valid_secs)
|
|
{
|
|
struct pblk_line *line = pblk_line_get_data(pblk);
|
|
struct line_emeta *emeta = line->emeta;
|
|
struct pblk_w_ctx *w_ctx;
|
|
__le64 *lba_list = pblk_line_emeta_to_lbas(emeta);
|
|
u64 paddr;
|
|
int nr_secs = pblk->min_write_pgs;
|
|
int i;
|
|
|
|
paddr = pblk_alloc_page(pblk, line, nr_secs);
|
|
|
|
for (i = 0; i < nr_secs; i++, paddr++) {
|
|
/* 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);
|
|
w_ctx = pblk_rb_w_ctx(&pblk->rwb, sentry + i);
|
|
w_ctx->ppa = ppa_list[i];
|
|
meta_list[i].lba = cpu_to_le64(w_ctx->lba);
|
|
lba_list[paddr] = cpu_to_le64(w_ctx->lba);
|
|
le64_add_cpu(&line->emeta->nr_valid_lbas, 1);
|
|
} else {
|
|
u64 addr_empty = cpu_to_le64(ADDR_EMPTY);
|
|
|
|
lba_list[paddr] = meta_list[i].lba = addr_empty;
|
|
pblk_map_pad_invalidate(pblk, line, paddr);
|
|
}
|
|
}
|
|
|
|
if (pblk_line_is_full(line)) {
|
|
line = pblk_line_replace_data(pblk);
|
|
if (!line)
|
|
return;
|
|
}
|
|
|
|
pblk_down_rq(pblk, ppa_list, nr_secs, lun_bitmap);
|
|
}
|
|
|
|
void pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
|
|
unsigned long *lun_bitmap, unsigned int valid_secs,
|
|
unsigned int off)
|
|
{
|
|
struct pblk_sec_meta *meta_list = rqd->meta_list;
|
|
unsigned int map_secs;
|
|
int min = pblk->min_write_pgs;
|
|
int i;
|
|
|
|
for (i = off; i < rqd->nr_ppas; i += min) {
|
|
map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
|
|
pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
|
|
lun_bitmap, &meta_list[i], map_secs);
|
|
}
|
|
}
|
|
|
|
/* only if erase_ppa is set, acquire erase semaphore */
|
|
void 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;
|
|
struct pblk_sec_meta *meta_list = rqd->meta_list;
|
|
struct pblk_line *e_line, *d_line;
|
|
unsigned int map_secs;
|
|
int min = pblk->min_write_pgs;
|
|
int i, erase_lun;
|
|
|
|
for (i = 0; i < rqd->nr_ppas; i += min) {
|
|
map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
|
|
pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
|
|
lun_bitmap, &meta_list[i], map_secs);
|
|
|
|
erase_lun = rqd->ppa_list[i].g.lun * geo->nr_chnls +
|
|
rqd->ppa_list[i].g.ch;
|
|
|
|
/* line can change after page map */
|
|
e_line = pblk_line_get_erase(pblk);
|
|
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 = rqd->ppa_list[i];
|
|
erase_ppa->g.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);
|
|
}
|
|
|
|
e_line = pblk_line_get_erase(pblk);
|
|
d_line = pblk_line_get_data(pblk);
|
|
|
|
/* Erase blocks that are bad in this line but might not be in next */
|
|
if (unlikely(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;
|
|
|
|
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->g.blk = e_line->id;
|
|
}
|
|
}
|