dasharo/linux
0
0
Fork 0
mirror of https://github.com/Dasharo/linux.git synced 2026-03-06 15:25:10 -08:00
Code Issues Packages Projects Releases Wiki Activity

Merge tag 'for-5.7/drivers-2020-03-29' of git://git.kernel.dk/linux-block

Browse Source 
Pull block driver updates from Jens Axboe:

 - floppy driver cleanup series from Willy

 - NVMe updates and fixes (Various)

 - null_blk trace improvements (Chaitanya)

 - bcache fixes (Coly)

 - md fixes (via Song)

 - loop block size change optimizations (Martijn)

 - scnprintf() use (Takashi)

* tag 'for-5.7/drivers-2020-03-29' of git://git.kernel.dk/linux-block: (81 commits)
  null_blk: add trace in null_blk_zoned.c
  null_blk: add tracepoint helpers for zoned mode
  block: add a zone condition debug helper
  nvme: cleanup namespace identifier reporting in nvme_init_ns_head
  nvme: rename __nvme_find_ns_head to nvme_find_ns_head
  nvme: refactor nvme_identify_ns_descs error handling
  nvme-tcp: Add warning on state change failure at nvme_tcp_setup_ctrl
  nvme-rdma: Add warning on state change failure at nvme_rdma_setup_ctrl
  nvme: Fix controller creation races with teardown flow
  nvme: Make nvme_uninit_ctrl symmetric to nvme_init_ctrl
  nvme: Fix ctrl use-after-free during sysfs deletion
  nvme-pci: Re-order nvme_pci_free_ctrl
  nvme: Remove unused return code from nvme_delete_ctrl_sync
  nvme: Use nvme_state_terminal helper
  nvme: release ida resources
  nvme: Add compat_ioctl handler for NVME_IOCTL_SUBMIT_IO
  nvmet-tcp: optimize tcp stack TX when data digest is used
  nvme-fabrics: Use scnprintf() for avoiding potential buffer overflow
  nvme-multipath: do not reset on unknown status
  nvmet-rdma: allocate RW ctxs according to mdts
  ...
This commit is contained in:
Linus Torvalds
2020-03-30 11:43:51 -07:00
parent 10f36b1e80 766c3297d7
commit 1592614838
39 changed files with 1773 additions and 975 deletions
Download Patch File Download Diff File Expand all files Collapse all files

88
arch/arm/include/asm/floppy.h
View File

@@ -8,16 +8,18 @@
*/
#ifndef __ASM_ARM_FLOPPY_H
#define __ASM_ARM_FLOPPY_H
#if 0
#include <mach/floppy.h>
#endif
#define fd_outb(val,port) \
do { \
if ((port) == (u32)FD_DOR) \
fd_setdor((val)); \
else \
outb((val),(port)); \
#define fd_outb(val,port) \
do { \
int new_val = (val); \
if (((port) & 7) == FD_DOR) { \
if (new_val & 0xf0) \
new_val = (new_val & 0x0c) | \
floppy_selects[new_val & 3]; \
else \
new_val &= 0x0c; \
} \
outb(new_val, (port)); \
} while(0)
#define fd_inb(port) inb((port))
@@ -53,69 +55,7 @@ static inline int fd_dma_setup(void *data, unsigned int length,
* to a non-zero track, and then restoring it to track 0. If an error occurs,
* then there is no floppy drive present. [to be put back in again]
*/
static unsigned char floppy_selects[2][4] =
{
{ 0x10, 0x21, 0x23, 0x33 },
{ 0x10, 0x21, 0x23, 0x33 }
};
#define fd_setdor(dor) \
do { \
int new_dor = (dor); \
if (new_dor & 0xf0) \
new_dor = (new_dor & 0x0c) | floppy_selects[fdc][new_dor & 3]; \
else \
new_dor &= 0x0c; \
outb(new_dor, FD_DOR); \
} while (0)
/*
* Someday, we'll automatically detect which drives are present...
*/
static inline void fd_scandrives (void)
{
#if 0
int floppy, drive_count;
fd_disable_irq();
raw_cmd = &default_raw_cmd;
raw_cmd->flags = FD_RAW_SPIN | FD_RAW_NEED_SEEK;
raw_cmd->track = 0;
raw_cmd->rate = ?;
drive_count = 0;
for (floppy = 0; floppy < 4; floppy ++) {
current_drive = drive_count;
/*
* Turn on floppy motor
*/
if (start_motor(redo_fd_request))
continue;
/*
* Set up FDC
*/
fdc_specify();
/*
* Tell FDC to recalibrate
*/
output_byte(FD_RECALIBRATE);
LAST_OUT(UNIT(floppy));
/* wait for command to complete */
if (!successful) {
int i;
for (i = drive_count; i < 3; i--)
floppy_selects[fdc][i] = floppy_selects[fdc][i + 1];
floppy_selects[fdc][3] = 0;
floppy -= 1;
} else
drive_count++;
}
#else
floppy_selects[0][0] = 0x10;
floppy_selects[0][1] = 0x21;
floppy_selects[0][2] = 0x23;
floppy_selects[0][3] = 0x33;
#endif
}
static unsigned char floppy_selects[4] = { 0x10, 0x21, 0x23, 0x33 };
#define FDC1 (0x3f0)
@@ -135,9 +75,7 @@ static inline void fd_scandrives (void)
*/
static void driveswap(int *ints, int dummy, int dummy2)
{
floppy_selects[0][0] ^= floppy_selects[0][1];
floppy_selects[0][1] ^= floppy_selects[0][0];
floppy_selects[0][0] ^= floppy_selects[0][1];
swap(floppy_selects[0], floppy_selects[1]);
}
#define EXTRA_FLOPPY_PARAMS ,{ "driveswap", &driveswap, NULL, 0, 0 }

3
block/blk-settings.c
View File

@@ -628,6 +628,9 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
printk(KERN_NOTICE "%s: Warning: Device %s is misaligned\n",
top, bottom);
}
t->backing_dev_info->io_pages =
t->limits.max_sectors >> (PAGE_SHIFT - 9);
}
EXPORT_SYMBOL(disk_stack_limits);

32
block/blk-zoned.c
View File

@@ -20,6 +20,38 @@
#include "blk.h"
#define ZONE_COND_NAME(name) [BLK_ZONE_COND_##name] = #name
static const char *const zone_cond_name[] = {
ZONE_COND_NAME(NOT_WP),
ZONE_COND_NAME(EMPTY),
ZONE_COND_NAME(IMP_OPEN),
ZONE_COND_NAME(EXP_OPEN),
ZONE_COND_NAME(CLOSED),
ZONE_COND_NAME(READONLY),
ZONE_COND_NAME(FULL),
ZONE_COND_NAME(OFFLINE),
};
#undef ZONE_COND_NAME
/**
* blk_zone_cond_str - Return string XXX in BLK_ZONE_COND_XXX.
* @zone_cond: BLK_ZONE_COND_XXX.
*
* Description: Centralize block layer function to convert BLK_ZONE_COND_XXX
* into string format. Useful in the debugging and tracing zone conditions. For
* invalid BLK_ZONE_COND_XXX it returns string "UNKNOWN".
*/
const char *blk_zone_cond_str(enum blk_zone_cond zone_cond)
{
static const char *zone_cond_str = "UNKNOWN";
if (zone_cond < ARRAY_SIZE(zone_cond_name) && zone_cond_name[zone_cond])
zone_cond_str = zone_cond_name[zone_cond];
return zone_cond_str;
}
EXPORT_SYMBOL_GPL(blk_zone_cond_str);
static inline sector_t blk_zone_start(struct request_queue *q,
sector_t sector)
{

6
drivers/block/Makefile
View File

@@ -6,6 +6,9 @@
# Rewritten to use lists instead of if-statements.
#
# needed for trace events
ccflags-y += -I$(src)
obj-$(CONFIG_MAC_FLOPPY) += swim3.o
obj-$(CONFIG_BLK_DEV_SWIM) += swim_mod.o
obj-$(CONFIG_BLK_DEV_FD) += floppy.o
@@ -39,6 +42,9 @@ obj-$(CONFIG_ZRAM) += zram/
obj-$(CONFIG_BLK_DEV_NULL_BLK) += null_blk.o
null_blk-objs := null_blk_main.o
ifeq ($(CONFIG_BLK_DEV_ZONED), y)
null_blk-$(CONFIG_TRACING) += null_blk_trace.o
endif
null_blk-$(CONFIG_BLK_DEV_ZONED) += null_blk_zoned.o
skd-y := skd_main.o

4
drivers/block/aoe/aoeblk.c
View File

@@ -87,9 +87,9 @@ static ssize_t aoedisk_show_netif(struct device *dev,
if (*nd == NULL)
return snprintf(page, PAGE_SIZE, "none\n");
for (p = page; nd < ne; nd++)
p += snprintf(p, PAGE_SIZE - (p-page), "%s%s",
p += scnprintf(p, PAGE_SIZE - (p-page), "%s%s",
p == page ? "" : ",", (*nd)->name);
p += snprintf(p, PAGE_SIZE - (p-page), "\n");
p += scnprintf(p, PAGE_SIZE - (p-page), "\n");
return p-page;
}
/* firmware version */

11
drivers/block/drbd/drbd_main.c
View File

@@ -3413,22 +3413,11 @@ int drbd_md_read(struct drbd_device *device, struct drbd_backing_dev *bdev)
* the meta-data super block. This function sets MD_DIRTY, and starts a
* timer that ensures that within five seconds you have to call drbd_md_sync().
*/
#ifdef DEBUG
void drbd_md_mark_dirty_(struct drbd_device *device, unsigned int line, const char *func)
{
if (!test_and_set_bit(MD_DIRTY, &device->flags)) {
mod_timer(&device->md_sync_timer, jiffies + HZ);
device->last_md_mark_dirty.line = line;
device->last_md_mark_dirty.func = func;
}
}
#else
void drbd_md_mark_dirty(struct drbd_device *device)
{
if (!test_and_set_bit(MD_DIRTY, &device->flags))
mod_timer(&device->md_sync_timer, jiffies + 5*HZ);
}
#endif
void drbd_uuid_move_history(struct drbd_device *device) __must_hold(local)
{

1091
drivers/block/floppy.c
View File

File diff suppressed because it is too large Load Diff

18
drivers/block/loop.c
View File

@@ -214,7 +214,8 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
* LO_FLAGS_READ_ONLY, both are set from kernel, and losetup
* will get updated by ioctl(LOOP_GET_STATUS)
*/
blk_mq_freeze_queue(lo->lo_queue);
if (lo->lo_state == Lo_bound)
blk_mq_freeze_queue(lo->lo_queue);
lo->use_dio = use_dio;
if (use_dio) {
blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, lo->lo_queue);
@@ -223,7 +224,8 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue);
lo->lo_flags &= ~LO_FLAGS_DIRECT_IO;
}
blk_mq_unfreeze_queue(lo->lo_queue);
if (lo->lo_state == Lo_bound)
blk_mq_unfreeze_queue(lo->lo_queue);
}
static int
@@ -1539,16 +1541,16 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
if (arg < 512 || arg > PAGE_SIZE || !is_power_of_2(arg))
return -EINVAL;
if (lo->lo_queue->limits.logical_block_size != arg) {
sync_blockdev(lo->lo_device);
kill_bdev(lo->lo_device);
}
if (lo->lo_queue->limits.logical_block_size == arg)
return 0;
sync_blockdev(lo->lo_device);
kill_bdev(lo->lo_device);
blk_mq_freeze_queue(lo->lo_queue);
/* kill_bdev should have truncated all the pages */
if (lo->lo_queue->limits.logical_block_size != arg &&
lo->lo_device->bd_inode->i_mapping->nrpages) {
if (lo->lo_device->bd_inode->i_mapping->nrpages) {
err = -EAGAIN;
pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n",
__func__, lo->lo_number, lo->lo_file_name,

27
drivers/block/nbd.c
View File

@@ -395,16 +395,19 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
}
config = nbd->config;
if (config->num_connections > 1) {
if (config->num_connections > 1 ||
(config->num_connections == 1 && nbd->tag_set.timeout)) {
dev_err_ratelimited(nbd_to_dev(nbd),
"Connection timed out, retrying (%d/%d alive)\n",
atomic_read(&config->live_connections),
config->num_connections);
/*
* Hooray we have more connections, requeue this IO, the submit
* path will put it on a real connection.
* path will put it on a real connection. Or if only one
* connection is configured, the submit path will wait util
* a new connection is reconfigured or util dead timeout.
*/
if (config->socks && config->num_connections > 1) {
if (config->socks) {
if (cmd->index < config->num_connections) {
struct nbd_sock *nsock =
config->socks[cmd->index];
@@ -431,12 +434,22 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
* Userspace sets timeout=0 to disable socket disconnection,
* so just warn and reset the timer.
*/
struct nbd_sock *nsock = config->socks[cmd->index];
cmd->retries++;
dev_info(nbd_to_dev(nbd), "Possible stuck request %p: control (%s@%llu,%uB). Runtime %u seconds\n",
req, nbdcmd_to_ascii(req_to_nbd_cmd_type(req)),
(unsigned long long)blk_rq_pos(req) << 9,
blk_rq_bytes(req), (req->timeout / HZ) * cmd->retries);
mutex_lock(&nsock->tx_lock);
if (cmd->cookie != nsock->cookie) {
nbd_requeue_cmd(cmd);
mutex_unlock(&nsock->tx_lock);
mutex_unlock(&cmd->lock);
nbd_config_put(nbd);
return BLK_EH_DONE;
}
mutex_unlock(&nsock->tx_lock);
mutex_unlock(&cmd->lock);
nbd_config_put(nbd);
return BLK_EH_RESET_TIMER;
@@ -741,14 +754,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n",
result);
/*
* If we've disconnected or we only have 1
* connection then we need to make sure we
* If we've disconnected, we need to make sure we
* complete this request, otherwise error out
* and let the timeout stuff handle resubmitting
* this request onto another connection.
*/
if (nbd_disconnected(config) ||
config->num_connections <= 1) {
if (nbd_disconnected(config)) {
cmd->status = BLK_STS_IOERR;
goto out;
}
@@ -825,7 +836,7 @@ static int find_fallback(struct nbd_device *nbd, int index)
if (config->num_connections <= 1) {
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Attempted send on invalid socket\n");
"Dead connection, failed to find a fallback\n");
return new_index;
}

9
drivers/block/null_blk_main.c
View File

@@ -97,14 +97,21 @@ module_param_named(home_node, g_home_node, int, 0444);
MODULE_PARM_DESC(home_node, "Home node for the device");
#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
/*
* For more details about fault injection, please refer to
* Documentation/fault-injection/fault-injection.rst.
*/
static char g_timeout_str[80];
module_param_string(timeout, g_timeout_str, sizeof(g_timeout_str), 0444);
MODULE_PARM_DESC(timeout, "Fault injection. timeout=<interval>,<probability>,<space>,<times>");
static char g_requeue_str[80];
module_param_string(requeue, g_requeue_str, sizeof(g_requeue_str), 0444);
MODULE_PARM_DESC(requeue, "Fault injection. requeue=<interval>,<probability>,<space>,<times>");
static char g_init_hctx_str[80];
module_param_string(init_hctx, g_init_hctx_str, sizeof(g_init_hctx_str), 0444);
MODULE_PARM_DESC(init_hctx, "Fault injection to fail hctx init. init_hctx=<interval>,<probability>,<space>,<times>");
#endif
static int g_queue_mode = NULL_Q_MQ;
@@ -615,6 +622,7 @@ static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq)
if (tag != -1U) {
cmd = &nq->cmds[tag];
cmd->tag = tag;
cmd->error = BLK_STS_OK;
cmd->nq = nq;
if (nq->dev->irqmode == NULL_IRQ_TIMER) {
hrtimer_init(&cmd->timer, CLOCK_MONOTONIC,
@@ -1395,6 +1403,7 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
cmd->timer.function = null_cmd_timer_expired;
}
cmd->rq = bd->rq;
cmd->error = BLK_STS_OK;
cmd->nq = nq;
blk_mq_start_request(bd->rq);

21
drivers/block/null_blk_trace.c Normal file
View File

@@ -0,0 +1,21 @@
// SPDX-License-Identifier: GPL-2.0
/*
* null_blk trace related helpers.
*
* Copyright (C) 2020 Western Digital Corporation or its affiliates.
*/
#include "null_blk_trace.h"
/*
* Helper to use for all null_blk traces to extract disk name.
*/
const char *nullb_trace_disk_name(struct trace_seq *p, char *name)
{
const char *ret = trace_seq_buffer_ptr(p);
if (name && *name)
trace_seq_printf(p, "disk=%s, ", name);
trace_seq_putc(p, 0);
return ret;
}

79
drivers/block/null_blk_trace.h Normal file
View File

@@ -0,0 +1,79 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* null_blk device driver tracepoints.
*
* Copyright (C) 2020 Western Digital Corporation or its affiliates.
*/
#undef TRACE_SYSTEM
#define TRACE_SYSTEM nullb
#if !defined(_TRACE_NULLB_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_NULLB_H
#include <linux/tracepoint.h>
#include <linux/trace_seq.h>
#include "null_blk.h"
const char *nullb_trace_disk_name(struct trace_seq *p, char *name);
#define __print_disk_name(name) nullb_trace_disk_name(p, name)
#ifndef TRACE_HEADER_MULTI_READ
static inline void __assign_disk_name(char *name, struct gendisk *disk)
{
if (disk)
memcpy(name, disk->disk_name, DISK_NAME_LEN);
else
memset(name, 0, DISK_NAME_LEN);
}
#endif
TRACE_EVENT(nullb_zone_op,
TP_PROTO(struct nullb_cmd *cmd, unsigned int zone_no,
unsigned int zone_cond),
TP_ARGS(cmd, zone_no, zone_cond),
TP_STRUCT__entry(
__array(char, disk, DISK_NAME_LEN)
__field(enum req_opf, op)
__field(unsigned int, zone_no)
__field(unsigned int, zone_cond)
),
TP_fast_assign(
__entry->op = req_op(cmd->rq);
__entry->zone_no = zone_no;
__entry->zone_cond = zone_cond;
__assign_disk_name(__entry->disk, cmd->rq->rq_disk);
),
TP_printk("%s req=%-15s zone_no=%u zone_cond=%-10s",
__print_disk_name(__entry->disk),
blk_op_str(__entry->op),
__entry->zone_no,
blk_zone_cond_str(__entry->zone_cond))
);
TRACE_EVENT(nullb_report_zones,
TP_PROTO(struct nullb *nullb, unsigned int nr_zones),
TP_ARGS(nullb, nr_zones),
TP_STRUCT__entry(
__array(char, disk, DISK_NAME_LEN)
__field(unsigned int, nr_zones)
),
TP_fast_assign(
__entry->nr_zones = nr_zones;
__assign_disk_name(__entry->disk, nullb->disk);
),
TP_printk("%s nr_zones=%u",
__print_disk_name(__entry->disk), __entry->nr_zones)
);
#endif /* _TRACE_NULLB_H */
#undef TRACE_INCLUDE_PATH
#define TRACE_INCLUDE_PATH .
#undef TRACE_INCLUDE_FILE
#define TRACE_INCLUDE_FILE null_blk_trace
/* This part must be outside protection */
#include <trace/define_trace.h>

12
drivers/block/null_blk_zoned.c
View File

@@ -2,6 +2,9 @@
#include <linux/vmalloc.h>
#include "null_blk.h"
#define CREATE_TRACE_POINTS
#include "null_blk_trace.h"
/* zone_size in MBs to sectors. */
#define ZONE_SIZE_SHIFT 11
@@ -80,6 +83,8 @@ int null_report_zones(struct gendisk *disk, sector_t sector,
return 0;
nr_zones = min(nr_zones, dev->nr_zones - first_zone);
trace_nullb_report_zones(nullb, nr_zones);
for (i = 0; i < nr_zones; i++) {
/*
* Stacked DM target drivers will remap the zone information by
@@ -148,6 +153,8 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
/* Invalid zone condition */
return BLK_STS_IOERR;
}
trace_nullb_zone_op(cmd, zno, zone->cond);
return BLK_STS_OK;
}
@@ -155,7 +162,8 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
sector_t sector)
{
struct nullb_device *dev = cmd->nq->dev;
struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)];
unsigned int zone_no = null_zone_no(dev, sector);
struct blk_zone *zone = &dev->zones[zone_no];
size_t i;
switch (op) {
@@ -203,6 +211,8 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
default:
return BLK_STS_NOTSUPP;
}
trace_nullb_zone_op(cmd, zone_no, zone->cond);
return BLK_STS_OK;
}

2
drivers/block/rsxx/dma.c
View File

@@ -80,7 +80,7 @@ struct dma_tracker {
struct dma_tracker_list {
spinlock_t lock;
int head;
struct dma_tracker list[0];
struct dma_tracker list[];
};

42
drivers/lightnvm/pblk-sysfs.c
View File

@@ -37,7 +37,7 @@ static ssize_t pblk_sysfs_luns_show(struct pblk *pblk, char *page)
active = 0;
up(&rlun->wr_sem);
}
sz += snprintf(page + sz, PAGE_SIZE - sz,
sz += scnprintf(page + sz, PAGE_SIZE - sz,
"pblk: pos:%d, ch:%d, lun:%d - %d\n",
i,
rlun->bppa.a.ch,
@@ -120,7 +120,7 @@ static ssize_t pblk_sysfs_ppaf(struct pblk *pblk, char *page)
struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)&pblk->addrf;
struct nvm_addrf_12 *gppaf = (struct nvm_addrf_12 *)&geo->addrf;
sz = snprintf(page, PAGE_SIZE,
sz = scnprintf(page, PAGE_SIZE,
"g:(b:%d)blk:%d/%d,pg:%d/%d,lun:%d/%d,ch:%d/%d,pl:%d/%d,sec:%d/%d\n",
pblk->addrf_len,
ppaf->blk_offset, ppaf->blk_len,
@@ -130,7 +130,7 @@ static ssize_t pblk_sysfs_ppaf(struct pblk *pblk, char *page)
ppaf->pln_offset, ppaf->pln_len,
ppaf->sec_offset, ppaf->sec_len);
sz += snprintf(page + sz, PAGE_SIZE - sz,
sz += scnprintf(page + sz, PAGE_SIZE - sz,
"d:blk:%d/%d,pg:%d/%d,lun:%d/%d,ch:%d/%d,pl:%d/%d,sec:%d/%d\n",
gppaf->blk_offset, gppaf->blk_len,
gppaf->pg_offset, gppaf->pg_len,
@@ -142,7 +142,7 @@ static ssize_t pblk_sysfs_ppaf(struct pblk *pblk, char *page)
struct nvm_addrf *ppaf = &pblk->addrf;
struct nvm_addrf *gppaf = &geo->addrf;
sz = snprintf(page, PAGE_SIZE,
sz = scnprintf(page, PAGE_SIZE,
"pblk:(s:%d)ch:%d/%d,lun:%d/%d,chk:%d/%d/sec:%d/%d\n",
pblk->addrf_len,
ppaf->ch_offset, ppaf->ch_len,
@@ -150,7 +150,7 @@ static ssize_t pblk_sysfs_ppaf(struct pblk *pblk, char *page)
ppaf->chk_offset, ppaf->chk_len,
ppaf->sec_offset, ppaf->sec_len);
sz += snprintf(page + sz, PAGE_SIZE - sz,
sz += scnprintf(page + sz, PAGE_SIZE - sz,
"device:ch:%d/%d,lun:%d/%d,chk:%d/%d,sec:%d/%d\n",
gppaf->ch_offset, gppaf->ch_len,
gppaf->lun_offset, gppaf->lun_len,
@@ -278,11 +278,11 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
pblk_err(pblk, "corrupted free line list:%d/%d\n",
nr_free_lines, free_line_cnt);
sz = snprintf(page, PAGE_SIZE - sz,
sz = scnprintf(page, PAGE_SIZE - sz,
"line: nluns:%d, nblks:%d, nsecs:%d\n",
geo->all_luns, lm->blk_per_line, lm->sec_per_line);
sz += snprintf(page + sz, PAGE_SIZE - sz,
sz += scnprintf(page + sz, PAGE_SIZE - sz,
"lines:d:%d,l:%d-f:%d,m:%d/%d,c:%d,b:%d,co:%d(d:%d,l:%d)t:%d\n",
cur_data, cur_log,
nr_free_lines,
@@ -292,12 +292,12 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
d_line_cnt, l_line_cnt,
l_mg->nr_lines);
sz += snprintf(page + sz, PAGE_SIZE - sz,
sz += scnprintf(page + sz, PAGE_SIZE - sz,
"GC: full:%d, high:%d, mid:%d, low:%d, empty:%d, werr: %d, queue:%d\n",
gc_full, gc_high, gc_mid, gc_low, gc_empty, gc_werr,
atomic_read(&pblk->gc.read_inflight_gc));
sz += snprintf(page + sz, PAGE_SIZE - sz,
sz += scnprintf(page + sz, PAGE_SIZE - sz,
"data (%d) cur:%d, left:%d, vsc:%d, s:%d, map:%d/%d (%d)\n",
cur_data, cur_sec, msecs, vsc, sec_in_line,
map_weight, lm->sec_per_line,
@@ -313,19 +313,19 @@ static ssize_t pblk_sysfs_lines_info(struct pblk *pblk, char *page)
struct pblk_line_meta *lm = &pblk->lm;
ssize_t sz = 0;
sz = snprintf(page, PAGE_SIZE - sz,
sz = scnprintf(page, PAGE_SIZE - sz,
"smeta - len:%d, secs:%d\n",
lm->smeta_len, lm->smeta_sec);
sz += snprintf(page + sz, PAGE_SIZE - sz,
sz += scnprintf(page + sz, PAGE_SIZE - sz,
"emeta - len:%d, sec:%d, bb_start:%d\n",
lm->emeta_len[0], lm->emeta_sec[0],
lm->emeta_bb);
sz += snprintf(page + sz, PAGE_SIZE - sz,
sz += scnprintf(page + sz, PAGE_SIZE - sz,
"bitmap lengths: sec:%d, blk:%d, lun:%d\n",
lm->sec_bitmap_len,
lm->blk_bitmap_len,
lm->lun_bitmap_len);
sz += snprintf(page + sz, PAGE_SIZE - sz,
sz += scnprintf(page + sz, PAGE_SIZE - sz,
"blk_line:%d, sec_line:%d, sec_blk:%d\n",
lm->blk_per_line,
lm->sec_per_line,
@@ -344,12 +344,12 @@ static ssize_t pblk_get_write_amp(u64 user, u64 gc, u64 pad,
{
int sz;
sz = snprintf(page, PAGE_SIZE,
sz = scnprintf(page, PAGE_SIZE,
"user:%lld gc:%lld pad:%lld WA:",
user, gc, pad);
if (!user) {
sz += snprintf(page + sz, PAGE_SIZE - sz, "NaN\n");
sz += scnprintf(page + sz, PAGE_SIZE - sz, "NaN\n");
} else {
u64 wa_int;
u32 wa_frac;
@@ -358,7 +358,7 @@ static ssize_t pblk_get_write_amp(u64 user, u64 gc, u64 pad,
wa_int = div64_u64(wa_int, user);
wa_int = div_u64_rem(wa_int, 100000, &wa_frac);
sz += snprintf(page + sz, PAGE_SIZE - sz, "%llu.%05u\n",
sz += scnprintf(page + sz, PAGE_SIZE - sz, "%llu.%05u\n",
wa_int, wa_frac);
}
@@ -401,9 +401,9 @@ static ssize_t pblk_sysfs_get_padding_dist(struct pblk *pblk, char *page)
total = atomic64_read(&pblk->nr_flush) - pblk->nr_flush_rst;
if (!total) {
for (i = 0; i < (buckets + 1); i++)
sz += snprintf(page + sz, PAGE_SIZE - sz,
sz += scnprintf(page + sz, PAGE_SIZE - sz,
"%d:0 ", i);
sz += snprintf(page + sz, PAGE_SIZE - sz, "\n");
sz += scnprintf(page + sz, PAGE_SIZE - sz, "\n");
return sz;
}
@@ -411,7 +411,7 @@ static ssize_t pblk_sysfs_get_padding_dist(struct pblk *pblk, char *page)
for (i = 0; i < buckets; i++)
total_buckets += atomic64_read(&pblk->pad_dist[i]);
sz += snprintf(page + sz, PAGE_SIZE - sz, "0:%lld%% ",
sz += scnprintf(page + sz, PAGE_SIZE - sz, "0:%lld%% ",
bucket_percentage(total - total_buckets, total));
for (i = 0; i < buckets; i++) {
@@ -419,10 +419,10 @@ static ssize_t pblk_sysfs_get_padding_dist(struct pblk *pblk, char *page)
p = bucket_percentage(atomic64_read(&pblk->pad_dist[i]),
total);
sz += snprintf(page + sz, PAGE_SIZE - sz, "%d:%lld%% ",
sz += scnprintf(page + sz, PAGE_SIZE - sz, "%d:%lld%% ",
i + 1, p);
}
sz += snprintf(page + sz, PAGE_SIZE - sz, "\n");
sz += scnprintf(page + sz, PAGE_SIZE - sz, "\n");
return sz;
}

242
drivers/md/bcache/btree.c
View File

@@ -101,64 +101,6 @@
#define insert_lock(s, b) ((b)->level <= (s)->lock)
/*
* These macros are for recursing down the btree - they handle the details of
* locking and looking up nodes in the cache for you. They're best treated as
* mere syntax when reading code that uses them.
*
* op->lock determines whether we take a read or a write lock at a given depth.
* If you've got a read lock and find that you need a write lock (i.e. you're
* going to have to split), set op->lock and return -EINTR; btree_root() will
* call you again and you'll have the correct lock.
*/
/**
* btree - recurse down the btree on a specified key
* @fn: function to call, which will be passed the child node
* @key: key to recurse on
* @b: parent btree node
* @op: pointer to struct btree_op
*/
#define btree(fn, key, b, op, ...) \
({ \
int _r, l = (b)->level - 1; \
bool _w = l <= (op)->lock; \
struct btree *_child = bch_btree_node_get((b)->c, op, key, l, \
_w, b); \
if (!IS_ERR(_child)) { \
_r = bch_btree_ ## fn(_child, op, ##__VA_ARGS__); \
rw_unlock(_w, _child); \
} else \
_r = PTR_ERR(_child); \
_r; \
})
/**
* btree_root - call a function on the root of the btree
* @fn: function to call, which will be passed the child node
* @c: cache set
* @op: pointer to struct btree_op
*/
#define btree_root(fn, c, op, ...) \
({ \
int _r = -EINTR; \
do { \
struct btree *_b = (c)->root; \
bool _w = insert_lock(op, _b); \
rw_lock(_w, _b, _b->level); \
if (_b == (c)->root && \
_w == insert_lock(op, _b)) { \
_r = bch_btree_ ## fn(_b, op, ##__VA_ARGS__); \
} \
rw_unlock(_w, _b); \
bch_cannibalize_unlock(c); \
if (_r == -EINTR) \
schedule(); \
} while (_r == -EINTR); \
\
finish_wait(&(c)->btree_cache_wait, &(op)->wait); \
_r; \
})
static inline struct bset *write_block(struct btree *b)
{
@@ -1848,7 +1790,7 @@ static void bch_btree_gc(struct cache_set *c)
/* if CACHE_SET_IO_DISABLE set, gc thread should stop too */
do {
ret = btree_root(gc_root, c, &op, &writes, &stats);
ret = bcache_btree_root(gc_root, c, &op, &writes, &stats);
closure_sync(&writes);
cond_resched();
@@ -1946,7 +1888,7 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
}
if (p)
ret = btree(check_recurse, p, b, op);
ret = bcache_btree(check_recurse, p, b, op);
p = k;
} while (p && !ret);
@@ -1955,13 +1897,176 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
return ret;
}
static int bch_btree_check_thread(void *arg)
{
int ret;
struct btree_check_info *info = arg;
struct btree_check_state *check_state = info->state;
struct cache_set *c = check_state->c;
struct btree_iter iter;
struct bkey *k, *p;
int cur_idx, prev_idx, skip_nr;
int i, n;
k = p = NULL;
i = n = 0;
cur_idx = prev_idx = 0;
ret = 0;
/* root node keys are checked before thread created */
bch_btree_iter_init(&c->root->keys, &iter, NULL);
k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
BUG_ON(!k);
p = k;
while (k) {
/*
* Fetch a root node key index, skip the keys which
* should be fetched by other threads, then check the
* sub-tree indexed by the fetched key.
*/
spin_lock(&check_state->idx_lock);
cur_idx = check_state->key_idx;
check_state->key_idx++;
spin_unlock(&check_state->idx_lock);
skip_nr = cur_idx - prev_idx;
while (skip_nr) {
k = bch_btree_iter_next_filter(&iter,
&c->root->keys,
bch_ptr_bad);
if (k)
p = k;
else {
/*
* No more keys to check in root node,
* current checking threads are enough,
* stop creating more.
*/
atomic_set(&check_state->enough, 1);
/* Update check_state->enough earlier */
smp_mb__after_atomic();
goto out;
}
skip_nr--;
cond_resched();
}
if (p) {
struct btree_op op;
btree_node_prefetch(c->root, p);
c->gc_stats.nodes++;
bch_btree_op_init(&op, 0);
ret = bcache_btree(check_recurse, p, c->root, &op);
if (ret)
goto out;
}
p = NULL;
prev_idx = cur_idx;
cond_resched();
}
out:
info->result = ret;
/* update check_state->started among all CPUs */
smp_mb__before_atomic();
if (atomic_dec_and_test(&check_state->started))
wake_up(&check_state->wait);
return ret;
}
static int bch_btree_chkthread_nr(void)
{
int n = num_online_cpus()/2;
if (n == 0)
n = 1;
else if (n > BCH_BTR_CHKTHREAD_MAX)
n = BCH_BTR_CHKTHREAD_MAX;
return n;
}
int bch_btree_check(struct cache_set *c)
{
struct btree_op op;
int ret = 0;
int i;
struct bkey *k = NULL;
struct btree_iter iter;
struct btree_check_state *check_state;
char name[32];
bch_btree_op_init(&op, SHRT_MAX);
/* check and mark root node keys */
for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid)
bch_initial_mark_key(c, c->root->level, k);
return btree_root(check_recurse, c, &op);
bch_initial_mark_key(c, c->root->level + 1, &c->root->key);
if (c->root->level == 0)
return 0;
check_state = kzalloc(sizeof(struct btree_check_state), GFP_KERNEL);
if (!check_state)
return -ENOMEM;
check_state->c = c;
check_state->total_threads = bch_btree_chkthread_nr();
check_state->key_idx = 0;
spin_lock_init(&check_state->idx_lock);
atomic_set(&check_state->started, 0);
atomic_set(&check_state->enough, 0);
init_waitqueue_head(&check_state->wait);
/*
* Run multiple threads to check btree nodes in parallel,
* if check_state->enough is non-zero, it means current
* running check threads are enough, unncessary to create
* more.
*/
for (i = 0; i < check_state->total_threads; i++) {
/* fetch latest check_state->enough earlier */
smp_mb__before_atomic();
if (atomic_read(&check_state->enough))
break;
check_state->infos[i].result = 0;
check_state->infos[i].state = check_state;
snprintf(name, sizeof(name), "bch_btrchk[%u]", i);
atomic_inc(&check_state->started);
check_state->infos[i].thread =
kthread_run(bch_btree_check_thread,
&check_state->infos[i],
name);
if (IS_ERR(check_state->infos[i].thread)) {
pr_err("fails to run thread bch_btrchk[%d]", i);
for (--i; i >= 0; i--)
kthread_stop(check_state->infos[i].thread);
ret = -ENOMEM;
goto out;
}
}
wait_event_interruptible(check_state->wait,
atomic_read(&check_state->started) == 0 ||
test_bit(CACHE_SET_IO_DISABLE, &c->flags));
for (i = 0; i < check_state->total_threads; i++) {
if (check_state->infos[i].result) {
ret = check_state->infos[i].result;
goto out;
}
}
out:
kfree(check_state);
return ret;
}
void bch_initial_gc_finish(struct cache_set *c)
@@ -2401,7 +2506,7 @@ static int bch_btree_map_nodes_recurse(struct btree *b, struct btree_op *op,
while ((k = bch_btree_iter_next_filter(&iter, &b->keys,
bch_ptr_bad))) {
ret = btree(map_nodes_recurse, k, b,
ret = bcache_btree(map_nodes_recurse, k, b,
op, from, fn, flags);
from = NULL;
@@ -2419,10 +2524,10 @@ static int bch_btree_map_nodes_recurse(struct btree *b, struct btree_op *op,
int __bch_btree_map_nodes(struct btree_op *op, struct cache_set *c,
struct bkey *from, btree_map_nodes_fn *fn, int flags)
{
return btree_root(map_nodes_recurse, c, op, from, fn, flags);
return bcache_btree_root(map_nodes_recurse, c, op, from, fn, flags);
}
static int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
struct bkey *from, btree_map_keys_fn *fn,
int flags)
{
@@ -2435,7 +2540,8 @@ static int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
while ((k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad))) {
ret = !b->level
? fn(op, b, k)
: btree(map_keys_recurse, k, b, op, from, fn, flags);
: bcache_btree(map_keys_recurse, k,
b, op, from, fn, flags);
from = NULL;
if (ret != MAP_CONTINUE)
@@ -2452,7 +2558,7 @@ static int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
int bch_btree_map_keys(struct btree_op *op, struct cache_set *c,
struct bkey *from, btree_map_keys_fn *fn, int flags)
{
return btree_root(map_keys_recurse, c, op, from, fn, flags);
return bcache_btree_root(map_keys_recurse, c, op, from, fn, flags);
}
/* Keybuf code */

84
drivers/md/bcache/btree.h
View File

@@ -145,6 +145,9 @@ struct btree {
struct bio *bio;
};
#define BTREE_FLAG(flag) \
static inline bool btree_node_ ## flag(struct btree *b) \
{ return test_bit(BTREE_NODE_ ## flag, &b->flags); } \
@@ -216,6 +219,25 @@ struct btree_op {
unsigned int insert_collision:1;
};
struct btree_check_state;
struct btree_check_info {
struct btree_check_state *state;
struct task_struct *thread;
int result;
};
#define BCH_BTR_CHKTHREAD_MAX 64
struct btree_check_state {
struct cache_set *c;
int total_threads;
int key_idx;
spinlock_t idx_lock;
atomic_t started;
atomic_t enough;
wait_queue_head_t wait;
struct btree_check_info infos[BCH_BTR_CHKTHREAD_MAX];
};
static inline void bch_btree_op_init(struct btree_op *op, int write_lock_level)
{
memset(op, 0, sizeof(struct btree_op));
@@ -284,6 +306,65 @@ static inline void force_wake_up_gc(struct cache_set *c)
wake_up_gc(c);
}
/*
* These macros are for recursing down the btree - they handle the details of
* locking and looking up nodes in the cache for you. They're best treated as
* mere syntax when reading code that uses them.
*
* op->lock determines whether we take a read or a write lock at a given depth.
* If you've got a read lock and find that you need a write lock (i.e. you're
* going to have to split), set op->lock and return -EINTR; btree_root() will
* call you again and you'll have the correct lock.
*/
/**
* btree - recurse down the btree on a specified key
* @fn: function to call, which will be passed the child node
* @key: key to recurse on
* @b: parent btree node
* @op: pointer to struct btree_op
*/
#define bcache_btree(fn, key, b, op, ...) \
({ \
int _r, l = (b)->level - 1; \
bool _w = l <= (op)->lock; \
struct btree *_child = bch_btree_node_get((b)->c, op, key, l, \
_w, b); \
if (!IS_ERR(_child)) { \
_r = bch_btree_ ## fn(_child, op, ##__VA_ARGS__); \
rw_unlock(_w, _child); \
} else \
_r = PTR_ERR(_child); \
_r; \
})
/**
* btree_root - call a function on the root of the btree
* @fn: function to call, which will be passed the child node
* @c: cache set
* @op: pointer to struct btree_op
*/
#define bcache_btree_root(fn, c, op, ...) \
({ \
int _r = -EINTR; \
do { \
struct btree *_b = (c)->root; \
bool _w = insert_lock(op, _b); \
rw_lock(_w, _b, _b->level); \
if (_b == (c)->root && \
_w == insert_lock(op, _b)) { \
_r = bch_btree_ ## fn(_b, op, ##__VA_ARGS__); \
} \
rw_unlock(_w, _b); \
bch_cannibalize_unlock(c); \
if (_r == -EINTR) \
schedule(); \
} while (_r == -EINTR); \
\
finish_wait(&(c)->btree_cache_wait, &(op)->wait); \
_r; \
})
#define MAP_DONE 0
#define MAP_CONTINUE 1
@@ -314,6 +395,9 @@ typedef int (btree_map_keys_fn)(struct btree_op *op, struct btree *b,
struct bkey *k);
int bch_btree_map_keys(struct btree_op *op, struct cache_set *c,
struct bkey *from, btree_map_keys_fn *fn, int flags);
int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
struct bkey *from, btree_map_keys_fn *fn,
int flags);
typedef bool (keybuf_pred_fn)(struct keybuf *buf, struct bkey *k);

2
drivers/md/bcache/sysfs.c
View File

@@ -154,7 +154,7 @@ static ssize_t bch_snprint_string_list(char *buf,
size_t i;
for (i = 0; list[i]; i++)
out += snprintf(out, buf + size - out,
out += scnprintf(out, buf + size - out,
i == selected ? "[%s] " : "%s ", list[i]);
out[-1] = '\n';

164
drivers/md/bcache/writeback.c
View File

@@ -183,7 +183,7 @@ static void update_writeback_rate(struct work_struct *work)
*/
set_bit(BCACHE_DEV_RATE_DW_RUNNING, &dc->disk.flags);
/* paired with where BCACHE_DEV_RATE_DW_RUNNING is tested */
smp_mb();
smp_mb__after_atomic();
/*
* CACHE_SET_IO_DISABLE might be set via sysfs interface,
@@ -193,7 +193,7 @@ static void update_writeback_rate(struct work_struct *work)
test_bit(CACHE_SET_IO_DISABLE, &c->flags)) {
clear_bit(BCACHE_DEV_RATE_DW_RUNNING, &dc->disk.flags);
/* paired with where BCACHE_DEV_RATE_DW_RUNNING is tested */
smp_mb();
smp_mb__after_atomic();
return;
}
@@ -229,7 +229,7 @@ static void update_writeback_rate(struct work_struct *work)
*/
clear_bit(BCACHE_DEV_RATE_DW_RUNNING, &dc->disk.flags);
/* paired with where BCACHE_DEV_RATE_DW_RUNNING is tested */
smp_mb();
smp_mb__after_atomic();
}
static unsigned int writeback_delay(struct cached_dev *dc,
@@ -785,7 +785,9 @@ static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
return MAP_CONTINUE;
}
void bch_sectors_dirty_init(struct bcache_device *d)
static int bch_root_node_dirty_init(struct cache_set *c,
struct bcache_device *d,
struct bkey *k)
{
struct sectors_dirty_init op;
int ret;
@@ -796,8 +798,13 @@ void bch_sectors_dirty_init(struct bcache_device *d)
op.start = KEY(op.inode, 0, 0);
do {
ret = bch_btree_map_keys(&op.op, d->c, &op.start,
sectors_dirty_init_fn, 0);
ret = bcache_btree(map_keys_recurse,
k,
c->root,
&op.op,
&op.start,
sectors_dirty_init_fn,
0);
if (ret == -EAGAIN)
schedule_timeout_interruptible(
msecs_to_jiffies(INIT_KEYS_SLEEP_MS));
@@ -806,6 +813,151 @@ void bch_sectors_dirty_init(struct bcache_device *d)
break;
}
} while (ret == -EAGAIN);
return ret;
}
static int bch_dirty_init_thread(void *arg)
{
struct dirty_init_thrd_info *info = arg;
struct bch_dirty_init_state *state = info->state;
struct cache_set *c = state->c;
struct btree_iter iter;
struct bkey *k, *p;
int cur_idx, prev_idx, skip_nr;
int i;
k = p = NULL;
i = 0;
cur_idx = prev_idx = 0;
bch_btree_iter_init(&c->root->keys, &iter, NULL);
k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
BUG_ON(!k);
p = k;
while (k) {
spin_lock(&state->idx_lock);
cur_idx = state->key_idx;
state->key_idx++;
spin_unlock(&state->idx_lock);
skip_nr = cur_idx - prev_idx;
while (skip_nr) {
k = bch_btree_iter_next_filter(&iter,
&c->root->keys,
bch_ptr_bad);
if (k)
p = k;
else {
atomic_set(&state->enough, 1);
/* Update state->enough earlier */
smp_mb__after_atomic();
goto out;
}
skip_nr--;
cond_resched();
}
if (p) {
if (bch_root_node_dirty_init(c, state->d, p) < 0)
goto out;
}
p = NULL;
prev_idx = cur_idx;
cond_resched();
}
out:
/* In order to wake up state->wait in time */
smp_mb__before_atomic();
if (atomic_dec_and_test(&state->started))
wake_up(&state->wait);
return 0;
}
static int bch_btre_dirty_init_thread_nr(void)
{
int n = num_online_cpus()/2;
if (n == 0)
n = 1;
else if (n > BCH_DIRTY_INIT_THRD_MAX)
n = BCH_DIRTY_INIT_THRD_MAX;
return n;
}
void bch_sectors_dirty_init(struct bcache_device *d)
{
int i;
struct bkey *k = NULL;
struct btree_iter iter;
struct sectors_dirty_init op;
struct cache_set *c = d->c;
struct bch_dirty_init_state *state;
char name[32];
/* Just count root keys if no leaf node */
if (c->root->level == 0) {
bch_btree_op_init(&op.op, -1);
op.inode = d->id;
op.count = 0;
op.start = KEY(op.inode, 0, 0);
for_each_key_filter(&c->root->keys,
k, &iter, bch_ptr_invalid)
sectors_dirty_init_fn(&op.op, c->root, k);
return;
}
state = kzalloc(sizeof(struct bch_dirty_init_state), GFP_KERNEL);
if (!state) {
pr_warn("sectors dirty init failed: cannot allocate memory");
return;
}
state->c = c;
state->d = d;
state->total_threads = bch_btre_dirty_init_thread_nr();
state->key_idx = 0;
spin_lock_init(&state->idx_lock);
atomic_set(&state->started, 0);
atomic_set(&state->enough, 0);
init_waitqueue_head(&state->wait);
for (i = 0; i < state->total_threads; i++) {
/* Fetch latest state->enough earlier */
smp_mb__before_atomic();
if (atomic_read(&state->enough))
break;
state->infos[i].state = state;
atomic_inc(&state->started);
snprintf(name, sizeof(name), "bch_dirty_init[%d]", i);
state->infos[i].thread =
kthread_run(bch_dirty_init_thread,
&state->infos[i],
name);
if (IS_ERR(state->infos[i].thread)) {
pr_err("fails to run thread bch_dirty_init[%d]", i);
for (--i; i >= 0; i--)
kthread_stop(state->infos[i].thread);
goto out;
}
}
wait_event_interruptible(state->wait,
atomic_read(&state->started) == 0 ||
test_bit(CACHE_SET_IO_DISABLE, &c->flags));
out:
kfree(state);
}
void bch_cached_dev_writeback_init(struct cached_dev *dc)

19
drivers/md/bcache/writeback.h
View File

@@ -16,6 +16,7 @@
#define BCH_AUTO_GC_DIRTY_THRESHOLD 50
#define BCH_DIRTY_INIT_THRD_MAX 64
/*
* 14 (16384ths) is chosen here as something that each backing device
* should be a reasonable fraction of the share, and not to blow up
@@ -23,6 +24,24 @@
*/
#define WRITEBACK_SHARE_SHIFT 14
struct bch_dirty_init_state;
struct dirty_init_thrd_info {
struct bch_dirty_init_state *state;
struct task_struct *thread;
};
struct bch_dirty_init_state {
struct cache_set *c;
struct bcache_device *d;
int total_threads;
int key_idx;
spinlock_t idx_lock;
atomic_t started;
atomic_t enough;
wait_queue_head_t wait;
struct dirty_init_thrd_info infos[BCH_DIRTY_INIT_THRD_MAX];
};
static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d)
{
uint64_t i, ret = 0;

Some files were not shown because too many files have changed in this diff Show More