mirrors
/
linux-stable
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
1
0
Fork 0
Code Issues Releases Wiki Activity

for-5.7/drivers-2020-03-29 

-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAl6BJDYQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgplhMD/95jd4nlVetHAo54z+Zk2ExE13+yDamRKyh
 vc7t2tz1reqFOimtVr5aVuTXCTgOx4CpiIox5qcn6qAExN4JtCChOBRGize/0u8S
 ckxnhHbN2C0rfnGldvrYYeNRonFI+7QKimnurWUSYYGN0xqbo21BxJ7dFaohMseo
 q4K8sIW0ctE6AOlw28Jerkg614s2NDGZ7q1laheXnYHn5c9f1m0NaKN/jyTGgr0X
 TLBiLbX2yRrAuvpctBj6Fna6YN7Vdd9jsf2Bt6ipUI1XgHQoVUGMxQNhWPyjsbSv
 GzRQUNAfVcasLzCP/Mj/47144OkUtDDpn2mjeXDaFljLDGFULD+jp/SsOmLCxkPC
 gI7G2yfBvF96/SOyT0JXrLyMcBd1R2vRoASbc5tPu82mZhx7YJZH5WYtOB9h2gra
 RTYo3xcm0EoN6yeMaH+xOuXxTWWInIrgKPONW4H8s7hxEiMt5oFNVBI7vqPr4LVp
 tpfxiKZDavKOofKXogNV4W7mSMP/Ir5Q9Ha4g5SXHBGp0z/PHmnQ0xDGNq0KDnU4
 eNO0UYCFNCNa+0AOhpNxaVuVm9LjrgvyXRjePgOZQ4akhohwHO6DLrHK1f8Hb1vD
 8Ih6uR+F5zZlKsouWro8HLGYm5w40Wq9tbCI8QbPYH6nkGoDmzpPv9jbAeWgJU5c
 KqP/5TBSLA==
 =Bs4E
 -----END PGP SIGNATURE-----

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

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
Show Stats 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;

2
drivers/md/md.c
View File

@ -6185,7 +6185,7 @@ EXPORT_SYMBOL_GPL(md_stop_writes);
static void mddev_detach(struct mddev *mddev)
{
md_bitmap_wait_behind_writes(mddev);
if (mddev->pers && mddev->pers->quiesce) {
if (mddev->pers && mddev->pers->quiesce && !mddev->suspended) {
mddev->pers->quiesce(mddev, 1);
mddev->pers->quiesce(mddev, 0);
}

2
drivers/nvme/host/Kconfig
View File

@ -32,8 +32,6 @@ config NVME_HWMON
a hardware monitoring device will be created for each NVMe drive
in the system.
If unsure, say N.
config NVME_FABRICS
tristate

255
drivers/nvme/host/core.c
View File

@ -171,7 +171,6 @@ static void nvme_do_delete_ctrl(struct nvme_ctrl *ctrl)
nvme_remove_namespaces(ctrl);
ctrl->ops->delete_ctrl(ctrl);
nvme_uninit_ctrl(ctrl);
nvme_put_ctrl(ctrl);
}
static void nvme_delete_ctrl_work(struct work_struct *work)
@ -192,21 +191,16 @@ int nvme_delete_ctrl(struct nvme_ctrl *ctrl)
}
EXPORT_SYMBOL_GPL(nvme_delete_ctrl);
static int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl)
static void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl)
{
int ret = 0;
/*
* Keep a reference until nvme_do_delete_ctrl() complete,
* since ->delete_ctrl can free the controller.
*/
nvme_get_ctrl(ctrl);
if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING))
ret = -EBUSY;
if (!ret)
if (nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING))
nvme_do_delete_ctrl(ctrl);
nvme_put_ctrl(ctrl);
return ret;
}
static inline bool nvme_ns_has_pi(struct nvme_ns *ns)
@ -291,11 +285,8 @@ void nvme_complete_rq(struct request *req)
nvme_req(req)->ctrl->comp_seen = true;
if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) {
if ((req->cmd_flags & REQ_NVME_MPATH) &&
blk_path_error(status)) {
nvme_failover_req(req);
if ((req->cmd_flags & REQ_NVME_MPATH) && nvme_failover_req(req))
return;
}
if (!blk_queue_dying(req->q)) {
nvme_retry_req(req);
@ -1055,6 +1046,43 @@ static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
return error;
}
static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids,
struct nvme_ns_id_desc *cur)
{
const char *warn_str = "ctrl returned bogus length:";
void *data = cur;
switch (cur->nidt) {
case NVME_NIDT_EUI64:
if (cur->nidl != NVME_NIDT_EUI64_LEN) {
dev_warn(ctrl->device, "%s %d for NVME_NIDT_EUI64\n",
warn_str, cur->nidl);
return -1;
}
memcpy(ids->eui64, data + sizeof(*cur), NVME_NIDT_EUI64_LEN);
return NVME_NIDT_EUI64_LEN;
case NVME_NIDT_NGUID:
if (cur->nidl != NVME_NIDT_NGUID_LEN) {
dev_warn(ctrl->device, "%s %d for NVME_NIDT_NGUID\n",
warn_str, cur->nidl);
return -1;
}
memcpy(ids->nguid, data + sizeof(*cur), NVME_NIDT_NGUID_LEN);
return NVME_NIDT_NGUID_LEN;
case NVME_NIDT_UUID:
if (cur->nidl != NVME_NIDT_UUID_LEN) {
dev_warn(ctrl->device, "%s %d for NVME_NIDT_UUID\n",
warn_str, cur->nidl);
return -1;
}
uuid_copy(&ids->uuid, data + sizeof(*cur));
return NVME_NIDT_UUID_LEN;
default:
/* Skip unknown types */
return cur->nidl;
}
}
static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
struct nvme_ns_ids *ids)
{
@ -1074,8 +1102,17 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
status = nvme_submit_sync_cmd(ctrl->admin_q, &c, data,
NVME_IDENTIFY_DATA_SIZE);
if (status)
if (status) {
dev_warn(ctrl->device,
"Identify Descriptors failed (%d)\n", status);
/*
* Don't treat an error as fatal, as we potentially already
* have a NGUID or EUI-64.
*/
if (status > 0)
status = 0;
goto free_data;
}
for (pos = 0; pos < NVME_IDENTIFY_DATA_SIZE; pos += len) {
struct nvme_ns_id_desc *cur = data + pos;
@ -1083,42 +1120,9 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
if (cur->nidl == 0)
break;
switch (cur->nidt) {
case NVME_NIDT_EUI64:
if (cur->nidl != NVME_NIDT_EUI64_LEN) {
dev_warn(ctrl->device,
"ctrl returned bogus length: %d for NVME_NIDT_EUI64\n",
cur->nidl);
goto free_data;
}
len = NVME_NIDT_EUI64_LEN;
memcpy(ids->eui64, data + pos + sizeof(*cur), len);
break;
case NVME_NIDT_NGUID:
if (cur->nidl != NVME_NIDT_NGUID_LEN) {
dev_warn(ctrl->device,
"ctrl returned bogus length: %d for NVME_NIDT_NGUID\n",
cur->nidl);
goto free_data;
}
len = NVME_NIDT_NGUID_LEN;
memcpy(ids->nguid, data + pos + sizeof(*cur), len);
break;
case NVME_NIDT_UUID:
if (cur->nidl != NVME_NIDT_UUID_LEN) {
dev_warn(ctrl->device,
"ctrl returned bogus length: %d for NVME_NIDT_UUID\n",
cur->nidl);
goto free_data;
}
len = NVME_NIDT_UUID_LEN;
uuid_copy(&ids->uuid, data + pos + sizeof(*cur));
break;
default:
/* Skip unknown types */
len = cur->nidl;
break;
}
len = nvme_process_ns_desc(ctrl, ids, cur);
if (len < 0)
goto free_data;
len += sizeof(*cur);
}
@ -1584,6 +1588,47 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
return ret;
}
#ifdef CONFIG_COMPAT
struct nvme_user_io32 {
__u8 opcode;
__u8 flags;
__u16 control;
__u16 nblocks;
__u16 rsvd;
__u64 metadata;
__u64 addr;
__u64 slba;
__u32 dsmgmt;
__u32 reftag;
__u16 apptag;
__u16 appmask;
} __attribute__((__packed__));
#define NVME_IOCTL_SUBMIT_IO32 _IOW('N', 0x42, struct nvme_user_io32)
static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
/*
* Corresponds to the difference of NVME_IOCTL_SUBMIT_IO
* between 32 bit programs and 64 bit kernel.
* The cause is that the results of sizeof(struct nvme_user_io),
* which is used to define NVME_IOCTL_SUBMIT_IO,
* are not same between 32 bit compiler and 64 bit compiler.
* NVME_IOCTL_SUBMIT_IO32 is for 64 bit kernel handling
* NVME_IOCTL_SUBMIT_IO issued from 32 bit programs.
* Other IOCTL numbers are same between 32 bit and 64 bit.
* So there is nothing to do regarding to other IOCTL numbers.
*/
if (cmd == NVME_IOCTL_SUBMIT_IO32)
return nvme_ioctl(bdev, mode, NVME_IOCTL_SUBMIT_IO, arg);
return nvme_ioctl(bdev, mode, cmd, arg);
}
#else
#define nvme_compat_ioctl NULL
#endif /* CONFIG_COMPAT */
static int nvme_open(struct block_device *bdev, fmode_t mode)
{
struct nvme_ns *ns = bdev->bd_disk->private_data;
@ -1721,26 +1766,15 @@ static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns)
static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid,
struct nvme_id_ns *id, struct nvme_ns_ids *ids)
{
int ret = 0;
memset(ids, 0, sizeof(*ids));
if (ctrl->vs >= NVME_VS(1, 1, 0))
memcpy(ids->eui64, id->eui64, sizeof(id->eui64));
if (ctrl->vs >= NVME_VS(1, 2, 0))
memcpy(ids->nguid, id->nguid, sizeof(id->nguid));
if (ctrl->vs >= NVME_VS(1, 3, 0)) {
/* Don't treat error as fatal we potentially
* already have a NGUID or EUI-64
*/
ret = nvme_identify_ns_descs(ctrl, nsid, ids);
if (ret)
dev_warn(ctrl->device,
"Identify Descriptors failed (%d)\n", ret);
if (ret > 0)
ret = 0;
}
return ret;
if (ctrl->vs >= NVME_VS(1, 3, 0))
return nvme_identify_ns_descs(ctrl, nsid, ids);
return 0;
}
static bool nvme_ns_ids_valid(struct nvme_ns_ids *ids)
@ -2027,7 +2061,7 @@ EXPORT_SYMBOL_GPL(nvme_sec_submit);
static const struct block_device_operations nvme_fops = {
.owner = THIS_MODULE,
.ioctl = nvme_ioctl,
.compat_ioctl = nvme_ioctl,
.compat_ioctl = nvme_compat_ioctl,
.open = nvme_open,
.release = nvme_release,
.getgeo = nvme_getgeo,
@ -2055,7 +2089,7 @@ const struct block_device_operations nvme_ns_head_ops = {
.open = nvme_ns_head_open,
.release = nvme_ns_head_release,
.ioctl = nvme_ioctl,
.compat_ioctl = nvme_ioctl,
.compat_ioctl = nvme_compat_ioctl,
.getgeo = nvme_getgeo,
.pr_ops = &nvme_pr_ops,
};
@ -2074,13 +2108,13 @@ static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled)
if ((csts & NVME_CSTS_RDY) == bit)
break;
msleep(100);
usleep_range(1000, 2000);
if (fatal_signal_pending(current))
return -EINTR;
if (time_after(jiffies, timeout)) {
dev_err(ctrl->device,
"Device not ready; aborting %s\n", enabled ?
"initialisation" : "reset");
"Device not ready; aborting %s, CSTS=0x%x\n",
enabled ? "initialisation" : "reset", csts);
return -ENODEV;
}
}
@ -2591,8 +2625,7 @@ static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
lockdep_assert_held(&nvme_subsystems_lock);
list_for_each_entry(tmp, &subsys->ctrls, subsys_entry) {
if (tmp->state == NVME_CTRL_DELETING ||
tmp->state == NVME_CTRL_DEAD)
if (nvme_state_terminal(tmp))
continue;
if (tmp->cntlid == ctrl->cntlid) {
@ -3193,6 +3226,10 @@ static ssize_t nvme_sysfs_delete(struct device *dev,
{
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
/* Can't delete non-created controllers */
if (!ctrl->created)
return -EBUSY;
if (device_remove_file_self(dev, attr))
nvme_delete_ctrl_sync(ctrl);
return count;
@ -3242,6 +3279,26 @@ static ssize_t nvme_sysfs_show_subsysnqn(struct device *dev,
}
static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, NULL);
static ssize_t nvme_sysfs_show_hostnqn(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->opts->host->nqn);
}
static DEVICE_ATTR(hostnqn, S_IRUGO, nvme_sysfs_show_hostnqn, NULL);
static ssize_t nvme_sysfs_show_hostid(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
return snprintf(buf, PAGE_SIZE, "%pU\n", &ctrl->opts->host->id);
}
static DEVICE_ATTR(hostid, S_IRUGO, nvme_sysfs_show_hostid, NULL);
static ssize_t nvme_sysfs_show_address(struct device *dev,
struct device_attribute *attr,
char *buf)
@ -3267,6 +3324,8 @@ static struct attribute *nvme_dev_attrs[] = {
&dev_attr_numa_node.attr,
&dev_attr_queue_count.attr,
&dev_attr_sqsize.attr,
&dev_attr_hostnqn.attr,
&dev_attr_hostid.attr,
NULL
};
@ -3280,6 +3339,10 @@ static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj,
return 0;
if (a == &dev_attr_address.attr && !ctrl->ops->get_address)
return 0;
if (a == &dev_attr_hostnqn.attr && !ctrl->opts)
return 0;
if (a == &dev_attr_hostid.attr && !ctrl->opts)
return 0;
return a->mode;
}
@ -3294,7 +3357,7 @@ static const struct attribute_group *nvme_dev_attr_groups[] = {
NULL,
};
static struct nvme_ns_head *__nvme_find_ns_head(struct nvme_subsystem *subsys,
static struct nvme_ns_head *nvme_find_ns_head(struct nvme_subsystem *subsys,
unsigned nsid)
{
struct nvme_ns_head *h;
@ -3327,7 +3390,8 @@ static int __nvme_check_ids(struct nvme_subsystem *subsys,
}
static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
unsigned nsid, struct nvme_id_ns *id)
unsigned nsid, struct nvme_id_ns *id,
struct nvme_ns_ids *ids)
{
struct nvme_ns_head *head;
size_t size = sizeof(*head);
@ -3350,12 +3414,9 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
goto out_ida_remove;
head->subsys = ctrl->subsys;
head->ns_id = nsid;
head->ids = *ids;
kref_init(&head->ref);
ret = nvme_report_ns_ids(ctrl, nsid, id, &head->ids);
if (ret)
goto out_cleanup_srcu;
ret = __nvme_check_ids(ctrl->subsys, head);
if (ret) {
dev_err(ctrl->device,
@ -3390,24 +3451,23 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
struct nvme_ctrl *ctrl = ns->ctrl;
bool is_shared = id->nmic & (1 << 0);
struct nvme_ns_head *head = NULL;
struct nvme_ns_ids ids;
int ret = 0;
ret = nvme_report_ns_ids(ctrl, nsid, id, &ids);
if (ret)
goto out;
mutex_lock(&ctrl->subsys->lock);
if (is_shared)
head = __nvme_find_ns_head(ctrl->subsys, nsid);
head = nvme_find_ns_head(ctrl->subsys, nsid);
if (!head) {
head = nvme_alloc_ns_head(ctrl, nsid, id);
head = nvme_alloc_ns_head(ctrl, nsid, id, &ids);
if (IS_ERR(head)) {
ret = PTR_ERR(head);
goto out_unlock;
}
} else {
struct nvme_ns_ids ids;
ret = nvme_report_ns_ids(ctrl, nsid, id, &ids);
if (ret)
goto out_unlock;
if (!nvme_ns_ids_equal(&head->ids, &ids)) {
dev_err(ctrl->device,
"IDs don't match for shared namespace %d\n",
@ -3422,6 +3482,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
out_unlock:
mutex_unlock(&ctrl->subsys->lock);
out:
if (ret > 0)
ret = blk_status_to_errno(nvme_error_status(ret));
return ret;
@ -3480,7 +3541,7 @@ static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns)
return 0;
}
static int nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
{
struct nvme_ns *ns;
struct gendisk *disk;
@ -3490,13 +3551,11 @@ static int nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
if (!ns)
return -ENOMEM;
return;
ns->queue = blk_mq_init_queue(ctrl->tagset);
if (IS_ERR(ns->queue)) {
ret = PTR_ERR(ns->queue);
if (IS_ERR(ns->queue))
goto out_free_ns;
}
if (ctrl->opts && ctrl->opts->data_digest)
ns->queue->backing_dev_info->capabilities
@ -3519,10 +3578,8 @@ static int nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
if (ret)
goto out_free_queue;
if (id->ncap == 0) {
ret = -EINVAL;
if (id->ncap == 0) /* no namespace (legacy quirk) */
goto out_free_id;
}
ret = nvme_init_ns_head(ns, nsid, id);
if (ret)
@ -3531,10 +3588,8 @@ static int nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
nvme_set_disk_name(disk_name, ns, ctrl, &flags);
disk = alloc_disk_node(0, node);
if (!disk) {
ret = -ENOMEM;
if (!disk)
goto out_unlink_ns;
}
disk->fops = &nvme_fops;
disk->private_data = ns;
@ -3565,7 +3620,7 @@ static int nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name);
kfree(id);
return 0;
return;
out_put_disk:
put_disk(ns->disk);
out_unlink_ns:
@ -3579,9 +3634,6 @@ static int nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
blk_cleanup_queue(ns->queue);
out_free_ns:
kfree(ns);
if (ret > 0)
ret = blk_status_to_errno(nvme_error_status(ret));
return ret;
}
static void nvme_ns_remove(struct nvme_ns *ns)
@ -3987,6 +4039,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl)
nvme_queue_scan(ctrl);
nvme_start_queues(ctrl);
}
ctrl->created = true;
}
EXPORT_SYMBOL_GPL(nvme_start_ctrl);
@ -3995,6 +4048,7 @@ void nvme_uninit_ctrl(struct nvme_ctrl *ctrl)
nvme_fault_inject_fini(&ctrl->fault_inject);
dev_pm_qos_hide_latency_tolerance(ctrl->device);
cdev_device_del(&ctrl->cdev, ctrl->device);
nvme_put_ctrl(ctrl);
}
EXPORT_SYMBOL_GPL(nvme_uninit_ctrl);
@ -4077,6 +4131,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
if (ret)
goto out_release_instance;
nvme_get_ctrl(ctrl);
cdev_init(&ctrl->cdev, &nvme_dev_fops);
ctrl->cdev.owner = ops->module;
ret = cdev_device_add(&ctrl->cdev, ctrl->device);
@ -4095,6 +4150,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
return 0;
out_free_name:
nvme_put_ctrl(ctrl);
kfree_const(ctrl->device->kobj.name);
out_release_instance:
ida_simple_remove(&nvme_instance_ida, ctrl->instance);
@ -4299,6 +4355,7 @@ static void __exit nvme_core_exit(void)
destroy_workqueue(nvme_delete_wq);
destroy_workqueue(nvme_reset_wq);
destroy_workqueue(nvme_wq);
ida_destroy(&nvme_instance_ida);
}
MODULE_LICENSE("GPL");

8
drivers/nvme/host/fabrics.c
View File

@ -105,14 +105,14 @@ int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
int len = 0;
if (ctrl->opts->mask & NVMF_OPT_TRADDR)
len += snprintf(buf, size, "traddr=%s", ctrl->opts->traddr);
len += scnprintf(buf, size, "traddr=%s", ctrl->opts->traddr);
if (ctrl->opts->mask & NVMF_OPT_TRSVCID)
len += snprintf(buf + len, size - len, "%strsvcid=%s",
len += scnprintf(buf + len, size - len, "%strsvcid=%s",
(len) ? "," : "", ctrl->opts->trsvcid);
if (ctrl->opts->mask & NVMF_OPT_HOST_TRADDR)
len += snprintf(buf + len, size - len, "%shost_traddr=%s",
len += scnprintf(buf + len, size - len, "%shost_traddr=%s",
(len) ? "," : "", ctrl->opts->host_traddr);
len += snprintf(buf + len, size - len, "\n");
len += scnprintf(buf + len, size - len, "\n");
return len;
}

3
drivers/nvme/host/fc.c
View File

@ -3181,10 +3181,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
goto fail_ctrl;
}
nvme_get_ctrl(&ctrl->ctrl);
if (!queue_delayed_work(nvme_wq, &ctrl->connect_work, 0)) {
nvme_put_ctrl(&ctrl->ctrl);
dev_err(ctrl->ctrl.device,
"NVME-FC{%d}: failed to schedule initial connect\n",
ctrl->cnum);

21
drivers/nvme/host/multipath.c
View File

@ -64,17 +64,12 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
}
}
void nvme_failover_req(struct request *req)
bool nvme_failover_req(struct request *req)
{
struct nvme_ns *ns = req->q->queuedata;
u16 status = nvme_req(req)->status;
unsigned long flags;
spin_lock_irqsave(&ns->head->requeue_lock, flags);
blk_steal_bios(&ns->head->requeue_list, req);
spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
blk_mq_end_request(req, 0);
switch (status & 0x7ff) {
case NVME_SC_ANA_TRANSITION:
case NVME_SC_ANA_INACCESSIBLE:
@ -103,15 +98,17 @@ void nvme_failover_req(struct request *req)
nvme_mpath_clear_current_path(ns);
break;
default:
/*
* Reset the controller for any non-ANA error as we don't know
* what caused the error.
*/
nvme_reset_ctrl(ns->ctrl);
break;
/* This was a non-ANA error so follow the normal error path. */
return false;
}
spin_lock_irqsave(&ns->head->requeue_lock, flags);
blk_steal_bios(&ns->head->requeue_list, req);
spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
blk_mq_end_request(req, 0);
kblockd_schedule_work(&ns->head->requeue_work);
return true;
}
void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)

6
drivers/nvme/host/nvme.h
View File

@ -259,6 +259,7 @@ struct nvme_ctrl {
struct nvme_command ka_cmd;
struct work_struct fw_act_work;
unsigned long events;
bool created;
#ifdef CONFIG_NVME_MULTIPATH
/* asymmetric namespace access: */
@ -550,7 +551,7 @@ void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys);
void nvme_mpath_start_freeze(struct nvme_subsystem *subsys);
void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
struct nvme_ctrl *ctrl, int *flags);
void nvme_failover_req(struct request *req);
bool nvme_failover_req(struct request *req);
void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id);
@ -599,8 +600,9 @@ static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
}
static inline void nvme_failover_req(struct request *req)
static inline bool nvme_failover_req(struct request *req)
{
return false;
}
static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
{

91
drivers/nvme/host/pci.c
View File

@ -971,39 +971,25 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
nvme_end_request(req, cqe->status, cqe->result);
}
static void nvme_complete_cqes(struct nvme_queue *nvmeq, u16 start, u16 end)
{
while (start != end) {
nvme_handle_cqe(nvmeq, start);
if (++start == nvmeq->q_depth)
start = 0;
}
}
static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
{
if (nvmeq->cq_head == nvmeq->q_depth - 1) {
if (++nvmeq->cq_head == nvmeq->q_depth) {
nvmeq->cq_head = 0;
nvmeq->cq_phase = !nvmeq->cq_phase;
} else {
nvmeq->cq_head++;
nvmeq->cq_phase ^= 1;
}
}
static inline int nvme_process_cq(struct nvme_queue *nvmeq, u16 *start,
u16 *end, unsigned int tag)
static inline int nvme_process_cq(struct nvme_queue *nvmeq)
{
int found = 0;
*start = nvmeq->cq_head;
while (nvme_cqe_pending(nvmeq)) {
if (tag == -1U || nvmeq->cqes[nvmeq->cq_head].command_id == tag)
found++;
found++;
nvme_handle_cqe(nvmeq, nvmeq->cq_head);
nvme_update_cq_head(nvmeq);
}
*end = nvmeq->cq_head;
if (*start != *end)
if (found)
nvme_ring_cq_doorbell(nvmeq);
return found;
}
@ -1012,21 +998,16 @@ static irqreturn_t nvme_irq(int irq, void *data)
{
struct nvme_queue *nvmeq = data;
irqreturn_t ret = IRQ_NONE;
u16 start, end;
/*
* The rmb/wmb pair ensures we see all updates from a previous run of
* the irq handler, even if that was on another CPU.
*/
rmb();
nvme_process_cq(nvmeq, &start, &end, -1);
if (nvme_process_cq(nvmeq))
ret = IRQ_HANDLED;
wmb();
if (start != end) {
nvme_complete_cqes(nvmeq, start, end);
return IRQ_HANDLED;
}
return ret;
}
@ -1039,46 +1020,30 @@ static irqreturn_t nvme_irq_check(int irq, void *data)
}
/*
* Poll for completions any queue, including those not dedicated to polling.
* Poll for completions for any interrupt driven queue
* Can be called from any context.
*/
static int nvme_poll_irqdisable(struct nvme_queue *nvmeq, unsigned int tag)
static void nvme_poll_irqdisable(struct nvme_queue *nvmeq)
{
struct pci_dev *pdev = to_pci_dev(nvmeq->dev->dev);
u16 start, end;
int found;
/*
* For a poll queue we need to protect against the polling thread
* using the CQ lock. For normal interrupt driven threads we have
* to disable the interrupt to avoid racing with it.
*/
if (test_bit(NVMEQ_POLLED, &nvmeq->flags)) {
spin_lock(&nvmeq->cq_poll_lock);
found = nvme_process_cq(nvmeq, &start, &end, tag);
spin_unlock(&nvmeq->cq_poll_lock);
} else {
disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
found = nvme_process_cq(nvmeq, &start, &end, tag);
enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
}
WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags));
nvme_complete_cqes(nvmeq, start, end);
return found;
disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
nvme_process_cq(nvmeq);
enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
}
static int nvme_poll(struct blk_mq_hw_ctx *hctx)
{
struct nvme_queue *nvmeq = hctx->driver_data;
u16 start, end;
bool found;
if (!nvme_cqe_pending(nvmeq))
return 0;
spin_lock(&nvmeq->cq_poll_lock);
found = nvme_process_cq(nvmeq, &start, &end, -1);
nvme_complete_cqes(nvmeq, start, end);
found = nvme_process_cq(nvmeq);
spin_unlock(&nvmeq->cq_poll_lock);
return found;
@ -1255,7 +1220,12 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
/*
* Did we miss an interrupt?
*/
if (nvme_poll_irqdisable(nvmeq, req->tag)) {
if (test_bit(NVMEQ_POLLED, &nvmeq->flags))
nvme_poll(req->mq_hctx);
else
nvme_poll_irqdisable(nvmeq);
if (blk_mq_request_completed(req)) {
dev_warn(dev->ctrl.device,
"I/O %d QID %d timeout, completion polled\n",
req->tag, nvmeq->qid);
@ -1398,7 +1368,7 @@ static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown)
else
nvme_disable_ctrl(&dev->ctrl);
nvme_poll_irqdisable(nvmeq, -1);
nvme_poll_irqdisable(nvmeq);
}
/*
@ -1409,13 +1379,10 @@ static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown)
*/
static void nvme_reap_pending_cqes(struct nvme_dev *dev)
{
u16 start, end;
int i;
for (i = dev->ctrl.queue_count - 1; i > 0; i--) {
nvme_process_cq(&dev->queues[i], &start, &end, -1);
nvme_complete_cqes(&dev->queues[i], start, end);
}
for (i = dev->ctrl.queue_count - 1; i > 0; i--)
nvme_process_cq(&dev->queues[i]);
}
static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
@ -2503,13 +2470,13 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
struct nvme_dev *dev = to_nvme_dev(ctrl);
nvme_dbbuf_dma_free(dev);
put_device(dev->dev);
nvme_free_tagset(dev);
if (dev->ctrl.admin_q)
blk_put_queue(dev->ctrl.admin_q);
kfree(dev->queues);
free_opal_dev(dev->ctrl.opal_dev);
mempool_destroy(dev->iod_mempool);
put_device(dev->dev);
kfree(dev->queues);
kfree(dev);
}
@ -2689,7 +2656,7 @@ static int nvme_pci_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
{
struct pci_dev *pdev = to_pci_dev(to_nvme_dev(ctrl)->dev);
return snprintf(buf, size, "%s", dev_name(&pdev->dev));
return snprintf(buf, size, "%s\n", dev_name(&pdev->dev));
}
static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
@ -2835,7 +2802,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
nvme_reset_ctrl(&dev->ctrl);
nvme_get_ctrl(&dev->ctrl);
async_schedule(nvme_async_probe, dev);
return 0;
@ -2907,10 +2873,9 @@ static void nvme_remove(struct pci_dev *pdev)
nvme_free_host_mem(dev);
nvme_dev_remove_admin(dev);
nvme_free_queues(dev, 0);
nvme_uninit_ctrl(&dev->ctrl);
nvme_release_prp_pools(dev);
nvme_dev_unmap(dev);
nvme_put_ctrl(&dev->ctrl);
nvme_uninit_ctrl(&dev->ctrl);
}
#ifdef CONFIG_PM_SLEEP

9
drivers/nvme/host/rdma.c
View File

@ -1024,8 +1024,13 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
if (!changed) {
/* state change failure is ok if we're in DELETING state */
/*
* state change failure is ok if we're in DELETING state,
* unless we're during creation of a new controller to
* avoid races with teardown flow.
*/
WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
WARN_ON_ONCE(new);
ret = -EINVAL;
goto destroy_io;
}
@ -2045,8 +2050,6 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
nvme_get_ctrl(&ctrl->ctrl);
mutex_lock(&nvme_rdma_ctrl_mutex);
list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
mutex_unlock(&nvme_rdma_ctrl_mutex);

120
drivers/nvme/host/tcp.c
View File

@ -20,6 +20,16 @@
struct nvme_tcp_queue;
/* Define the socket priority to use for connections were it is desirable
* that the NIC consider performing optimized packet processing or filtering.
* A non-zero value being sufficient to indicate general consideration of any
* possible optimization. Making it a module param allows for alternative
* values that may be unique for some NIC implementations.
*/
static int so_priority;
module_param(so_priority, int, 0644);
MODULE_PARM_DESC(so_priority, "nvme tcp socket optimize priority");
enum nvme_tcp_send_state {
NVME_TCP_SEND_CMD_PDU = 0,
NVME_TCP_SEND_H2C_PDU,
@ -1017,8 +1027,15 @@ static int nvme_tcp_try_send(struct nvme_tcp_queue *queue)
if (req->state == NVME_TCP_SEND_DDGST)
ret = nvme_tcp_try_send_ddgst(req);
done:
if (ret == -EAGAIN)
if (ret == -EAGAIN) {
ret = 0;
} else if (ret < 0) {
dev_err(queue->ctrl->ctrl.device,
"failed to send request %d\n", ret);
if (ret != -EPIPE && ret != -ECONNRESET)
nvme_tcp_fail_request(queue->request);
nvme_tcp_done_send_req(queue);
}
return ret;
}
@ -1049,25 +1066,16 @@ static void nvme_tcp_io_work(struct work_struct *w)
int result;
result = nvme_tcp_try_send(queue);
if (result > 0) {
if (result > 0)
pending = true;
} else if (unlikely(result < 0)) {
dev_err(queue->ctrl->ctrl.device,
"failed to send request %d\n", result);
/*
* Fail the request unless peer closed the connection,
* in which case error recovery flow will complete all.
*/
if ((result != -EPIPE) && (result != -ECONNRESET))
nvme_tcp_fail_request(queue->request);
nvme_tcp_done_send_req(queue);
return;
}
else if (unlikely(result < 0))
break;
result = nvme_tcp_try_recv(queue);
if (result > 0)
pending = true;
else if (unlikely(result < 0))
break;
if (!pending)
return;
@ -1248,13 +1256,67 @@ free_icreq:
return ret;
}
static bool nvme_tcp_admin_queue(struct nvme_tcp_queue *queue)
{
return nvme_tcp_queue_id(queue) == 0;
}
static bool nvme_tcp_default_queue(struct nvme_tcp_queue *queue)
{
struct nvme_tcp_ctrl *ctrl = queue->ctrl;
int qid = nvme_tcp_queue_id(queue);
return !nvme_tcp_admin_queue(queue) &&
qid < 1 + ctrl->io_queues[HCTX_TYPE_DEFAULT];
}
static bool nvme_tcp_read_queue(struct nvme_tcp_queue *queue)
{
struct nvme_tcp_ctrl *ctrl = queue->ctrl;
int qid = nvme_tcp_queue_id(queue);
return !nvme_tcp_admin_queue(queue) &&
!nvme_tcp_default_queue(queue) &&
qid < 1 + ctrl->io_queues[HCTX_TYPE_DEFAULT] +
ctrl->io_queues[HCTX_TYPE_READ];
}
static bool nvme_tcp_poll_queue(struct nvme_tcp_queue *queue)
{
struct nvme_tcp_ctrl *ctrl = queue->ctrl;
int qid = nvme_tcp_queue_id(queue);
return !nvme_tcp_admin_queue(queue) &&
!nvme_tcp_default_queue(queue) &&
!nvme_tcp_read_queue(queue) &&
qid < 1 + ctrl->io_queues[HCTX_TYPE_DEFAULT] +
ctrl->io_queues[HCTX_TYPE_READ] +
ctrl->io_queues[HCTX_TYPE_POLL];
}
static void nvme_tcp_set_queue_io_cpu(struct nvme_tcp_queue *queue)
{
struct nvme_tcp_ctrl *ctrl = queue->ctrl;
int qid = nvme_tcp_queue_id(queue);
int n = 0;
if (nvme_tcp_default_queue(queue))
n = qid - 1;
else if (nvme_tcp_read_queue(queue))
n = qid - ctrl->io_queues[HCTX_TYPE_DEFAULT] - 1;
else if (nvme_tcp_poll_queue(queue))
n = qid - ctrl->io_queues[HCTX_TYPE_DEFAULT] -
ctrl->io_queues[HCTX_TYPE_READ] - 1;
queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false);
}
static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
int qid, size_t queue_size)
{
struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
struct nvme_tcp_queue *queue = &ctrl->queues[qid];
struct linger sol = { .l_onoff = 1, .l_linger = 0 };
int ret, opt, rcv_pdu_size, n;
int ret, opt, rcv_pdu_size;
queue->ctrl = ctrl;
INIT_LIST_HEAD(&queue->send_list);
@ -1309,6 +1371,17 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
goto err_sock;
}
if (so_priority > 0) {
ret = kernel_setsockopt(queue->sock, SOL_SOCKET, SO_PRIORITY,
(char *)&so_priority, sizeof(so_priority));
if (ret) {
dev_err(ctrl->ctrl.device,
"failed to set SO_PRIORITY sock opt, ret %d\n",
ret);
goto err_sock;
}
}
/* Set socket type of service */
if (nctrl->opts->tos >= 0) {
opt = nctrl->opts->tos;
@ -1322,11 +1395,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
}
queue->sock->sk->sk_allocation = GFP_ATOMIC;
if (!qid)
n = 0;
else
n = (qid - 1) % num_online_cpus();
queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false);
nvme_tcp_set_queue_io_cpu(queue);
queue->request = NULL;
queue->data_remaining = 0;
queue->ddgst_remaining = 0;
@ -1861,8 +1930,13 @@ static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new)
}
if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) {
/* state change failure is ok if we're in DELETING state */
/*
* state change failure is ok if we're in DELETING state,
* unless we're during creation of a new controller to
* avoid races with teardown flow.
*/
WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING);
WARN_ON_ONCE(new);
ret = -EINVAL;
goto destroy_io;
}
@ -2359,8 +2433,6 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n",
ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
nvme_get_ctrl(&ctrl->ctrl);
mutex_lock(&nvme_tcp_ctrl_mutex);
list_add_tail(&ctrl->list, &nvme_tcp_ctrl_list);
mutex_unlock(&nvme_tcp_ctrl_mutex);

34
drivers/nvme/target/admin-cmd.c
View File

@ -323,12 +323,25 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
}
static void nvmet_id_set_model_number(struct nvme_id_ctrl *id,
struct nvmet_subsys *subsys)
{
const char *model = NVMET_DEFAULT_CTRL_MODEL;
struct nvmet_subsys_model *subsys_model;
rcu_read_lock();
subsys_model = rcu_dereference(subsys->model);
if (subsys_model)
model = subsys_model->number;
memcpy_and_pad(id->mn, sizeof(id->mn), model, strlen(model), ' ');
rcu_read_unlock();
}
static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
{
struct nvmet_ctrl *ctrl = req->sq->ctrl;
struct nvme_id_ctrl *id;
u16 status = 0;
const char model[] = "Linux";
id = kzalloc(sizeof(*id), GFP_KERNEL);
if (!id) {
@ -343,7 +356,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
memset(id->sn, ' ', sizeof(id->sn));
bin2hex(id->sn, &ctrl->subsys->serial,
min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2));
memcpy_and_pad(id->mn, sizeof(id->mn), model, sizeof(model) - 1, ' ');
nvmet_id_set_model_number(id, ctrl->subsys);
memcpy_and_pad(id->fr, sizeof(id->fr),
UTS_RELEASE, strlen(UTS_RELEASE), ' ');
@ -357,8 +370,12 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
/* we support multiple ports, multiples hosts and ANA: */
id->cmic = (1 << 0) | (1 << 1) | (1 << 3);
/* no limit on data transfer sizes for now */
id->mdts = 0;
/* Limit MDTS according to transport capability */
if (ctrl->ops->get_mdts)
id->mdts = ctrl->ops->get_mdts(ctrl);
else
id->mdts = 0;
id->cntlid = cpu_to_le16(ctrl->cntlid);
id->ver = cpu_to_le32(ctrl->subsys->ver);
@ -721,13 +738,22 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
{
struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
u32 cdw11 = le32_to_cpu(req->cmd->common.cdw11);
u16 status = 0;
u16 nsqr;
u16 ncqr;
if (!nvmet_check_data_len(req, 0))
return;
switch (cdw10 & 0xff) {
case NVME_FEAT_NUM_QUEUES:
ncqr = (cdw11 >> 16) & 0xffff;
nsqr = cdw11 & 0xffff;
if (ncqr == 0xffff || nsqr == 0xffff) {
status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
break;
}
nvmet_set_result(req,
(subsys->max_qid - 1) | ((subsys->max_qid - 1) << 16));
break;

146
drivers/nvme/target/configfs.c
View File

@ -395,14 +395,12 @@ static ssize_t nvmet_ns_device_uuid_store(struct config_item *item,
struct nvmet_subsys *subsys = ns->subsys;
int ret = 0;
mutex_lock(&subsys->lock);
if (ns->enabled) {
ret = -EBUSY;
goto out_unlock;
}
if (uuid_parse(page, &ns->uuid))
ret = -EINVAL;
@ -815,10 +813,10 @@ static ssize_t nvmet_subsys_attr_version_show(struct config_item *item,
(int)NVME_MAJOR(subsys->ver),
(int)NVME_MINOR(subsys->ver),
(int)NVME_TERTIARY(subsys->ver));
else
return snprintf(page, PAGE_SIZE, "%d.%d\n",
(int)NVME_MAJOR(subsys->ver),
(int)NVME_MINOR(subsys->ver));
return snprintf(page, PAGE_SIZE, "%d.%d\n",
(int)NVME_MAJOR(subsys->ver),
(int)NVME_MINOR(subsys->ver));
}
static ssize_t nvmet_subsys_attr_version_store(struct config_item *item,
@ -828,7 +826,6 @@ static ssize_t nvmet_subsys_attr_version_store(struct config_item *item,
int major, minor, tertiary = 0;
int ret;
ret = sscanf(page, "%d.%d.%d\n", &major, &minor, &tertiary);
if (ret != 2 && ret != 3)
return -EINVAL;
@ -852,20 +849,151 @@ static ssize_t nvmet_subsys_attr_serial_show(struct config_item *item,
static ssize_t nvmet_subsys_attr_serial_store(struct config_item *item,
const char *page, size_t count)
{
struct nvmet_subsys *subsys = to_subsys(item);
u64 serial;
if (sscanf(page, "%llx\n", &serial) != 1)
return -EINVAL;
down_write(&nvmet_config_sem);
sscanf(page, "%llx\n", &subsys->serial);
to_subsys(item)->serial = serial;
up_write(&nvmet_config_sem);
return count;
}
CONFIGFS_ATTR(nvmet_subsys_, attr_serial);
static ssize_t nvmet_subsys_attr_cntlid_min_show(struct config_item *item,
char *page)
{
return snprintf(page, PAGE_SIZE, "%u\n", to_subsys(item)->cntlid_min);
}
static ssize_t nvmet_subsys_attr_cntlid_min_store(struct config_item *item,
const char *page, size_t cnt)
{
u16 cntlid_min;
if (sscanf(page, "%hu\n", &cntlid_min) != 1)
return -EINVAL;
if (cntlid_min == 0)
return -EINVAL;
down_write(&nvmet_config_sem);
if (cntlid_min >= to_subsys(item)->cntlid_max)
goto out_unlock;
to_subsys(item)->cntlid_min = cntlid_min;
up_write(&nvmet_config_sem);
return cnt;
out_unlock:
up_write(&nvmet_config_sem);
return -EINVAL;
}
CONFIGFS_ATTR(nvmet_subsys_, attr_cntlid_min);
static ssize_t nvmet_subsys_attr_cntlid_max_show(struct config_item *item,
char *page)
{
return snprintf(page, PAGE_SIZE, "%u\n", to_subsys(item)->cntlid_max);
}
static ssize_t nvmet_subsys_attr_cntlid_max_store(struct config_item *item,
const char *page, size_t cnt)
{
u16 cntlid_max;
if (sscanf(page, "%hu\n", &cntlid_max) != 1)
return -EINVAL;
if (cntlid_max == 0)
return -EINVAL;
down_write(&nvmet_config_sem);
if (cntlid_max <= to_subsys(item)->cntlid_min)
goto out_unlock;
to_subsys(item)->cntlid_max = cntlid_max;
up_write(&nvmet_config_sem);
return cnt;
out_unlock:
up_write(&nvmet_config_sem);
return -EINVAL;
}
CONFIGFS_ATTR(nvmet_subsys_, attr_cntlid_max);
static ssize_t nvmet_subsys_attr_model_show(struct config_item *item,
char *page)
{
struct nvmet_subsys *subsys = to_subsys(item);
struct nvmet_subsys_model *subsys_model;
char *model = NVMET_DEFAULT_CTRL_MODEL;
int ret;
rcu_read_lock();
subsys_model = rcu_dereference(subsys->model);
if (subsys_model)
model = subsys_model->number;
ret = snprintf(page, PAGE_SIZE, "%s\n", model);
rcu_read_unlock();
return ret;
}
/* See Section 1.5 of NVMe 1.4 */
static bool nvmet_is_ascii(const char c)
{
return c >= 0x20 && c <= 0x7e;
}
static ssize_t nvmet_subsys_attr_model_store(struct config_item *item,
const char *page, size_t count)
{
struct nvmet_subsys *subsys = to_subsys(item);
struct nvmet_subsys_model *new_model;
char *new_model_number;
int pos = 0, len;
len = strcspn(page, "\n");
if (!len)
return -EINVAL;
for (pos = 0; pos < len; pos++) {
if (!nvmet_is_ascii(page[pos]))
return -EINVAL;
}
new_model_number = kstrndup(page, len, GFP_KERNEL);
if (!new_model_number)
return -ENOMEM;
new_model = kzalloc(sizeof(*new_model) + len + 1, GFP_KERNEL);
if (!new_model) {
kfree(new_model_number);
return -ENOMEM;
}
memcpy(new_model->number, new_model_number, len);
down_write(&nvmet_config_sem);
mutex_lock(&subsys->lock);
new_model = rcu_replace_pointer(subsys->model, new_model,
mutex_is_locked(&subsys->lock));
mutex_unlock(&subsys->lock);
up_write(&nvmet_config_sem);
kfree_rcu(new_model, rcuhead);
return count;
}
CONFIGFS_ATTR(nvmet_subsys_, attr_model);
static struct configfs_attribute *nvmet_subsys_attrs[] = {
&nvmet_subsys_attr_attr_allow_any_host,
&nvmet_subsys_attr_attr_version,
&nvmet_subsys_attr_attr_serial,
&nvmet_subsys_attr_attr_cntlid_min,
&nvmet_subsys_attr_attr_cntlid_max,
&nvmet_subsys_attr_attr_model,
NULL,
};

9
drivers/nvme/target/core.c
View File

@ -1289,8 +1289,11 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
if (!ctrl->sqs)
goto out_free_cqs;
if (subsys->cntlid_min > subsys->cntlid_max)
goto out_free_cqs;
ret = ida_simple_get(&cntlid_ida,
NVME_CNTLID_MIN, NVME_CNTLID_MAX,
subsys->cntlid_min, subsys->cntlid_max,
GFP_KERNEL);
if (ret < 0) {
status = NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
@ -1438,7 +1441,8 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
kfree(subsys);
return ERR_PTR(-ENOMEM);
}
subsys->cntlid_min = NVME_CNTLID_MIN;
subsys->cntlid_max = NVME_CNTLID_MAX;
kref_init(&subsys->ref);
mutex_init(&subsys->lock);
@ -1457,6 +1461,7 @@ static void nvmet_subsys_free(struct kref *ref)
WARN_ON_ONCE(!list_empty(&subsys->namespaces));
kfree(subsys->subsysnqn);
kfree_rcu(subsys->model, rcuhead);
kfree(subsys);
}

3
drivers/nvme/target/loop.c
View File

@ -485,7 +485,6 @@ out_destroy_admin:
out_disable:
dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
nvme_uninit_ctrl(&ctrl->ctrl);
nvme_put_ctrl(&ctrl->ctrl);
}
static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
@ -618,8 +617,6 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
dev_info(ctrl->ctrl.device,
"new ctrl: \"%s\"\n", ctrl->ctrl.opts->subsysnqn);
nvme_get_ctrl(&ctrl->ctrl);
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
WARN_ON_ONCE(!changed);

11
drivers/nvme/target/nvmet.h
View File

@ -23,6 +23,7 @@
#define NVMET_ASYNC_EVENTS 4
#define NVMET_ERROR_LOG_SLOTS 128
#define NVMET_NO_ERROR_LOC ((u16)-1)
#define NVMET_DEFAULT_CTRL_MODEL "Linux"
/*
* Supported optional AENs:
@ -202,6 +203,11 @@ struct nvmet_ctrl {
struct nvme_error_slot slots[NVMET_ERROR_LOG_SLOTS];
};
struct nvmet_subsys_model {
struct rcu_head rcuhead;
char number[];
};
struct nvmet_subsys {
enum nvme_subsys_type type;
@ -211,6 +217,8 @@ struct nvmet_subsys {
struct list_head namespaces;
unsigned int nr_namespaces;
unsigned int max_nsid;
u16 cntlid_min;
u16 cntlid_max;
struct list_head ctrls;
@ -227,6 +235,8 @@ struct nvmet_subsys {
struct config_group namespaces_group;
struct config_group allowed_hosts_group;
struct nvmet_subsys_model __rcu *model;
};
static inline struct nvmet_subsys *to_subsys(struct config_item *item)
@ -279,6 +289,7 @@ struct nvmet_fabrics_ops {
struct nvmet_port *port, char *traddr);
u16 (*install_queue)(struct nvmet_sq *nvme_sq);
void (*discovery_chg)(struct nvmet_port *port);
u8 (*get_mdts)(const struct nvmet_ctrl *ctrl);
};
#define NVMET_MAX_INLINE_BIOVEC 8

15
drivers/nvme/target/rdma.c
View File

@ -31,6 +31,9 @@
#define NVMET_RDMA_MAX_INLINE_SGE 4
#define NVMET_RDMA_MAX_INLINE_DATA_SIZE max_t(int, SZ_16K, PAGE_SIZE)
/* Assume mpsmin == device_page_size == 4KB */
#define NVMET_RDMA_MAX_MDTS 8
struct nvmet_rdma_cmd {
struct ib_sge sge[NVMET_RDMA_MAX_INLINE_SGE + 1];
struct ib_cqe cqe;
@ -975,7 +978,7 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
{
struct ib_qp_init_attr qp_attr;
struct nvmet_rdma_device *ndev = queue->dev;
int comp_vector, nr_cqe, ret, i;
int comp_vector, nr_cqe, ret, i, factor;
/*
* Spread the io queues across completion vectors,
@ -1008,7 +1011,9 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
qp_attr.qp_type = IB_QPT_RC;
/* +1 for drain */
qp_attr.cap.max_send_wr = queue->send_queue_size + 1;
qp_attr.cap.max_rdma_ctxs = queue->send_queue_size;
factor = rdma_rw_mr_factor(ndev->device, queue->cm_id->port_num,
1 << NVMET_RDMA_MAX_MDTS);
qp_attr.cap.max_rdma_ctxs = queue->send_queue_size * factor;
qp_attr.cap.max_send_sge = max(ndev->device->attrs.max_sge_rd,
ndev->device->attrs.max_send_sge);
@ -1602,6 +1607,11 @@ static void nvmet_rdma_disc_port_addr(struct nvmet_req *req,
}
}
static u8 nvmet_rdma_get_mdts(const struct nvmet_ctrl *ctrl)
{
return NVMET_RDMA_MAX_MDTS;
}
static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
.owner = THIS_MODULE,
.type = NVMF_TRTYPE_RDMA,
@ -1612,6 +1622,7 @@ static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
.queue_response = nvmet_rdma_queue_response,
.delete_ctrl = nvmet_rdma_delete_ctrl,
.disc_traddr = nvmet_rdma_disc_port_addr,
.get_mdts = nvmet_rdma_get_mdts,
};
static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data)

35
drivers/nvme/target/tcp.c
View File

@ -19,6 +19,16 @@
#define NVMET_TCP_DEF_INLINE_DATA_SIZE (4 * PAGE_SIZE)
/* Define the socket priority to use for connections were it is desirable
* that the NIC consider performing optimized packet processing or filtering.
* A non-zero value being sufficient to indicate general consideration of any
* possible optimization. Making it a module param allows for alternative
* values that may be unique for some NIC implementations.
*/
static int so_priority;
module_param(so_priority, int, 0644);
MODULE_PARM_DESC(so_priority, "nvmet tcp socket optimize priority");
#define NVMET_TCP_RECV_BUDGET 8
#define NVMET_TCP_SEND_BUDGET 8
#define NVMET_TCP_IO_WORK_BUDGET 64
@ -622,7 +632,7 @@ static int nvmet_try_send_r2t(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
return 1;
}
static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd)
static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
{
struct nvmet_tcp_queue *queue = cmd->queue;
struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
@ -632,6 +642,9 @@ static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd)
};
int ret;
if (!last_in_batch && cmd->queue->send_list_len)
msg.msg_flags |= MSG_MORE;
ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len);
if (unlikely(ret <= 0))
return ret;
@ -672,7 +685,7 @@ static int nvmet_tcp_try_send_one(struct nvmet_tcp_queue *queue,
}
if (cmd->state == NVMET_TCP_SEND_DDGST) {
ret = nvmet_try_send_ddgst(cmd);
ret = nvmet_try_send_ddgst(cmd, last_in_batch);
if (ret <= 0)
goto done_send;
}
@ -794,7 +807,7 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue)
icresp->hdr.pdo = 0;
icresp->hdr.plen = cpu_to_le32(icresp->hdr.hlen);
icresp->pfv = cpu_to_le16(NVME_TCP_PFV_1_0);
icresp->maxdata = cpu_to_le32(0xffff); /* FIXME: support r2t */
icresp->maxdata = cpu_to_le32(0x400000); /* 16M arbitrary limit */
icresp->cpda = 0;
if (queue->hdr_digest)
icresp->digest |= NVME_TCP_HDR_DIGEST_ENABLE;
@ -1439,6 +1452,13 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)
if (ret)
return ret;
if (so_priority > 0) {
ret = kernel_setsockopt(sock, SOL_SOCKET, SO_PRIORITY,
(char *)&so_priority, sizeof(so_priority));
if (ret)
return ret;
}
/* Set socket type of service */
if (inet->rcv_tos > 0) {
int tos = inet->rcv_tos;
@ -1628,6 +1648,15 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport)
goto err_sock;
}
if (so_priority > 0) {
ret = kernel_setsockopt(port->sock, SOL_SOCKET, SO_PRIORITY,
(char *)&so_priority, sizeof(so_priority));
if (ret) {
pr_err("failed to set SO_PRIORITY sock opt %d\n", ret);
goto err_sock;
}
}
ret = kernel_bind(port->sock, (struct sockaddr *)&port->addr,
sizeof(port->addr));
if (ret) {

4
include/linux/blkdev.h
View File

@ -952,6 +952,10 @@ static inline unsigned int blk_rq_stats_sectors(const struct request *rq)
}
#ifdef CONFIG_BLK_DEV_ZONED
/* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */
const char *blk_zone_cond_str(enum blk_zone_cond zone_cond);
static inline unsigned int blk_rq_zone_no(struct request *rq)
{
return blk_queue_zone_no(rq->q, blk_rq_pos(rq));

18
include/uapi/linux/fdreg.h
View File

@ -7,26 +7,18 @@
* Handbook", Sanches and Canton.
*/
#ifdef FDPATCHES
#define FD_IOPORT fdc_state[fdc].address
#else
/* It would be a lot saner just to force fdc_state[fdc].address to always
be set ! FIXME */
#define FD_IOPORT 0x3f0
#endif
/* Fd controller regs. S&C, about page 340 */
#define FD_STATUS (4 + FD_IOPORT )
#define FD_DATA (5 + FD_IOPORT )
#define FD_STATUS 4
#define FD_DATA 5
/* Digital Output Register */
#define FD_DOR (2 + FD_IOPORT )
#define FD_DOR 2
/* Digital Input Register (read) */
#define FD_DIR (7 + FD_IOPORT )
#define FD_DIR 7
/* Diskette Control Register (write)*/
#define FD_DCR (7 + FD_IOPORT )
#define FD_DCR 7
/* Bits of main status register */
#define STATUS_BUSYMASK 0x0F /* drive busy mask */