linux_dsm_epyc7002/fs/xfs/xfs_sysfs.c
Dave Chinner dae5cd8118 xfs: add mount delay debug option
Similar to log_recovery_delay, this delay occurs between the VFS
superblock being initialised and the xfs_mount being fully
initialised. It also poisons the per-ag radix tree node so that it
can be used for triggering shrinker races during mount
such as the following:

<run memory pressure workload in background>

$ cat dirty-mount.sh
#! /bin/bash

umount -f /dev/pmem0
mkfs.xfs -f /dev/pmem0
mount /dev/pmem0 /mnt/test
rm -f /mnt/test/foo
xfs_io -fxc "pwrite 0 4k" -c fsync -c "shutdown" /mnt/test/foo
umount /dev/pmem0

# let's crash it now!
echo 30 > /sys/fs/xfs/debug/mount_delay
mount /dev/pmem0 /mnt/test
echo 0 > /sys/fs/xfs/debug/mount_delay
umount /dev/pmem0
$ sudo ./dirty-mount.sh
.....
[   60.378118] CPU: 3 PID: 3577 Comm: fs_mark Tainted: G      D W        4.16.0-rc5-dgc #440
[   60.378120] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
[   60.378124] RIP: 0010:radix_tree_next_chunk+0x76/0x320
[   60.378127] RSP: 0018:ffffc9000276f4f8 EFLAGS: 00010282
[   60.383670] RAX: a5a5a5a5a5a5a5a4 RBX: 0000000000000010 RCX: 000000000000001a
[   60.385277] RDX: 0000000000000000 RSI: ffffc9000276f540 RDI: 0000000000000000
[   60.386554] RBP: 0000000000000000 R08: 0000000000000000 R09: a5a5a5a5a5a5a5a5
[   60.388194] R10: 0000000000000006 R11: 0000000000000001 R12: ffffc9000276f598
[   60.389288] R13: 0000000000000040 R14: 0000000000000228 R15: ffff880816cd6458
[   60.390827] FS:  00007f5c124b9740(0000) GS:ffff88083fc00000(0000) knlGS:0000000000000000
[   60.392253] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   60.393423] CR2: 00007f5c11bba0b8 CR3: 000000035580e001 CR4: 00000000000606e0
[   60.394519] Call Trace:
[   60.395252]  radix_tree_gang_lookup_tag+0xc4/0x130
[   60.395948]  xfs_perag_get_tag+0x37/0xf0
[   60.396522]  xfs_reclaim_inodes_count+0x32/0x40
[   60.397178]  xfs_fs_nr_cached_objects+0x11/0x20
[   60.397837]  super_cache_count+0x35/0xc0
[   60.399159]  shrink_slab.part.66+0xb1/0x370
[   60.400194]  shrink_node+0x7e/0x1a0
[   60.401058]  try_to_free_pages+0x199/0x470
[   60.402081]  __alloc_pages_slowpath+0x3a1/0xd20
[   60.403729]  __alloc_pages_nodemask+0x1c3/0x200
[   60.404941]  cache_grow_begin+0x20b/0x2e0
[   60.406164]  fallback_alloc+0x160/0x200
[   60.407088]  kmem_cache_alloc+0x111/0x4e0
[   60.408038]  ? xfs_buf_rele+0x61/0x430
[   60.408925]  kmem_zone_alloc+0x61/0xe0
[   60.409965]  xfs_inode_alloc+0x24/0x1d0
.....


Signed-Off-By: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2018-05-15 17:57:05 -07:00

666 lines
13 KiB
C

/*
* Copyright (c) 2014 Red Hat, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it would be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_sysfs.h"
#include "xfs_log.h"
#include "xfs_log_priv.h"
#include "xfs_stats.h"
#include "xfs_mount.h"
struct xfs_sysfs_attr {
struct attribute attr;
ssize_t (*show)(struct kobject *kobject, char *buf);
ssize_t (*store)(struct kobject *kobject, const char *buf,
size_t count);
};
static inline struct xfs_sysfs_attr *
to_attr(struct attribute *attr)
{
return container_of(attr, struct xfs_sysfs_attr, attr);
}
#define XFS_SYSFS_ATTR_RW(name) \
static struct xfs_sysfs_attr xfs_sysfs_attr_##name = __ATTR_RW(name)
#define XFS_SYSFS_ATTR_RO(name) \
static struct xfs_sysfs_attr xfs_sysfs_attr_##name = __ATTR_RO(name)
#define XFS_SYSFS_ATTR_WO(name) \
static struct xfs_sysfs_attr xfs_sysfs_attr_##name = __ATTR_WO(name)
#define ATTR_LIST(name) &xfs_sysfs_attr_##name.attr
STATIC ssize_t
xfs_sysfs_object_show(
struct kobject *kobject,
struct attribute *attr,
char *buf)
{
struct xfs_sysfs_attr *xfs_attr = to_attr(attr);
return xfs_attr->show ? xfs_attr->show(kobject, buf) : 0;
}
STATIC ssize_t
xfs_sysfs_object_store(
struct kobject *kobject,
struct attribute *attr,
const char *buf,
size_t count)
{
struct xfs_sysfs_attr *xfs_attr = to_attr(attr);
return xfs_attr->store ? xfs_attr->store(kobject, buf, count) : 0;
}
static const struct sysfs_ops xfs_sysfs_ops = {
.show = xfs_sysfs_object_show,
.store = xfs_sysfs_object_store,
};
/*
* xfs_mount kobject. The mp kobject also serves as the per-mount parent object
* that is identified by the fsname under sysfs.
*/
static inline struct xfs_mount *
to_mp(struct kobject *kobject)
{
struct xfs_kobj *kobj = to_kobj(kobject);
return container_of(kobj, struct xfs_mount, m_kobj);
}
static struct attribute *xfs_mp_attrs[] = {
NULL,
};
struct kobj_type xfs_mp_ktype = {
.release = xfs_sysfs_release,
.sysfs_ops = &xfs_sysfs_ops,
.default_attrs = xfs_mp_attrs,
};
#ifdef DEBUG
/* debug */
STATIC ssize_t
bug_on_assert_store(
struct kobject *kobject,
const char *buf,
size_t count)
{
int ret;
int val;
ret = kstrtoint(buf, 0, &val);
if (ret)
return ret;
if (val == 1)
xfs_globals.bug_on_assert = true;
else if (val == 0)
xfs_globals.bug_on_assert = false;
else
return -EINVAL;
return count;
}
STATIC ssize_t
bug_on_assert_show(
struct kobject *kobject,
char *buf)
{
return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.bug_on_assert ? 1 : 0);
}
XFS_SYSFS_ATTR_RW(bug_on_assert);
STATIC ssize_t
log_recovery_delay_store(
struct kobject *kobject,
const char *buf,
size_t count)
{
int ret;
int val;
ret = kstrtoint(buf, 0, &val);
if (ret)
return ret;
if (val < 0 || val > 60)
return -EINVAL;
xfs_globals.log_recovery_delay = val;
return count;
}
STATIC ssize_t
log_recovery_delay_show(
struct kobject *kobject,
char *buf)
{
return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.log_recovery_delay);
}
XFS_SYSFS_ATTR_RW(log_recovery_delay);
STATIC ssize_t
mount_delay_store(
struct kobject *kobject,
const char *buf,
size_t count)
{
int ret;
int val;
ret = kstrtoint(buf, 0, &val);
if (ret)
return ret;
if (val < 0 || val > 60)
return -EINVAL;
xfs_globals.mount_delay = val;
return count;
}
STATIC ssize_t
mount_delay_show(
struct kobject *kobject,
char *buf)
{
return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.mount_delay);
}
XFS_SYSFS_ATTR_RW(mount_delay);
static struct attribute *xfs_dbg_attrs[] = {
ATTR_LIST(bug_on_assert),
ATTR_LIST(log_recovery_delay),
ATTR_LIST(mount_delay),
NULL,
};
struct kobj_type xfs_dbg_ktype = {
.release = xfs_sysfs_release,
.sysfs_ops = &xfs_sysfs_ops,
.default_attrs = xfs_dbg_attrs,
};
#endif /* DEBUG */
/* stats */
static inline struct xstats *
to_xstats(struct kobject *kobject)
{
struct xfs_kobj *kobj = to_kobj(kobject);
return container_of(kobj, struct xstats, xs_kobj);
}
STATIC ssize_t
stats_show(
struct kobject *kobject,
char *buf)
{
struct xstats *stats = to_xstats(kobject);
return xfs_stats_format(stats->xs_stats, buf);
}
XFS_SYSFS_ATTR_RO(stats);
STATIC ssize_t
stats_clear_store(
struct kobject *kobject,
const char *buf,
size_t count)
{
int ret;
int val;
struct xstats *stats = to_xstats(kobject);
ret = kstrtoint(buf, 0, &val);
if (ret)
return ret;
if (val != 1)
return -EINVAL;
xfs_stats_clearall(stats->xs_stats);
return count;
}
XFS_SYSFS_ATTR_WO(stats_clear);
static struct attribute *xfs_stats_attrs[] = {
ATTR_LIST(stats),
ATTR_LIST(stats_clear),
NULL,
};
struct kobj_type xfs_stats_ktype = {
.release = xfs_sysfs_release,
.sysfs_ops = &xfs_sysfs_ops,
.default_attrs = xfs_stats_attrs,
};
/* xlog */
static inline struct xlog *
to_xlog(struct kobject *kobject)
{
struct xfs_kobj *kobj = to_kobj(kobject);
return container_of(kobj, struct xlog, l_kobj);
}
STATIC ssize_t
log_head_lsn_show(
struct kobject *kobject,
char *buf)
{
int cycle;
int block;
struct xlog *log = to_xlog(kobject);
spin_lock(&log->l_icloglock);
cycle = log->l_curr_cycle;
block = log->l_curr_block;
spin_unlock(&log->l_icloglock);
return snprintf(buf, PAGE_SIZE, "%d:%d\n", cycle, block);
}
XFS_SYSFS_ATTR_RO(log_head_lsn);
STATIC ssize_t
log_tail_lsn_show(
struct kobject *kobject,
char *buf)
{
int cycle;
int block;
struct xlog *log = to_xlog(kobject);
xlog_crack_atomic_lsn(&log->l_tail_lsn, &cycle, &block);
return snprintf(buf, PAGE_SIZE, "%d:%d\n", cycle, block);
}
XFS_SYSFS_ATTR_RO(log_tail_lsn);
STATIC ssize_t
reserve_grant_head_show(
struct kobject *kobject,
char *buf)
{
int cycle;
int bytes;
struct xlog *log = to_xlog(kobject);
xlog_crack_grant_head(&log->l_reserve_head.grant, &cycle, &bytes);
return snprintf(buf, PAGE_SIZE, "%d:%d\n", cycle, bytes);
}
XFS_SYSFS_ATTR_RO(reserve_grant_head);
STATIC ssize_t
write_grant_head_show(
struct kobject *kobject,
char *buf)
{
int cycle;
int bytes;
struct xlog *log = to_xlog(kobject);
xlog_crack_grant_head(&log->l_write_head.grant, &cycle, &bytes);
return snprintf(buf, PAGE_SIZE, "%d:%d\n", cycle, bytes);
}
XFS_SYSFS_ATTR_RO(write_grant_head);
static struct attribute *xfs_log_attrs[] = {
ATTR_LIST(log_head_lsn),
ATTR_LIST(log_tail_lsn),
ATTR_LIST(reserve_grant_head),
ATTR_LIST(write_grant_head),
NULL,
};
struct kobj_type xfs_log_ktype = {
.release = xfs_sysfs_release,
.sysfs_ops = &xfs_sysfs_ops,
.default_attrs = xfs_log_attrs,
};
/*
* Metadata IO error configuration
*
* The sysfs structure here is:
* ...xfs/<dev>/error/<class>/<errno>/<error_attrs>
*
* where <class> allows us to discriminate between data IO and metadata IO,
* and any other future type of IO (e.g. special inode or directory error
* handling) we care to support.
*/
static inline struct xfs_error_cfg *
to_error_cfg(struct kobject *kobject)
{
struct xfs_kobj *kobj = to_kobj(kobject);
return container_of(kobj, struct xfs_error_cfg, kobj);
}
static inline struct xfs_mount *
err_to_mp(struct kobject *kobject)
{
struct xfs_kobj *kobj = to_kobj(kobject);
return container_of(kobj, struct xfs_mount, m_error_kobj);
}
static ssize_t
max_retries_show(
struct kobject *kobject,
char *buf)
{
int retries;
struct xfs_error_cfg *cfg = to_error_cfg(kobject);
if (cfg->max_retries == XFS_ERR_RETRY_FOREVER)
retries = -1;
else
retries = cfg->max_retries;
return snprintf(buf, PAGE_SIZE, "%d\n", retries);
}
static ssize_t
max_retries_store(
struct kobject *kobject,
const char *buf,
size_t count)
{
struct xfs_error_cfg *cfg = to_error_cfg(kobject);
int ret;
int val;
ret = kstrtoint(buf, 0, &val);
if (ret)
return ret;
if (val < -1)
return -EINVAL;
if (val == -1)
cfg->max_retries = XFS_ERR_RETRY_FOREVER;
else
cfg->max_retries = val;
return count;
}
XFS_SYSFS_ATTR_RW(max_retries);
static ssize_t
retry_timeout_seconds_show(
struct kobject *kobject,
char *buf)
{
int timeout;
struct xfs_error_cfg *cfg = to_error_cfg(kobject);
if (cfg->retry_timeout == XFS_ERR_RETRY_FOREVER)
timeout = -1;
else
timeout = jiffies_to_msecs(cfg->retry_timeout) / MSEC_PER_SEC;
return snprintf(buf, PAGE_SIZE, "%d\n", timeout);
}
static ssize_t
retry_timeout_seconds_store(
struct kobject *kobject,
const char *buf,
size_t count)
{
struct xfs_error_cfg *cfg = to_error_cfg(kobject);
int ret;
int val;
ret = kstrtoint(buf, 0, &val);
if (ret)
return ret;
/* 1 day timeout maximum, -1 means infinite */
if (val < -1 || val > 86400)
return -EINVAL;
if (val == -1)
cfg->retry_timeout = XFS_ERR_RETRY_FOREVER;
else {
cfg->retry_timeout = msecs_to_jiffies(val * MSEC_PER_SEC);
ASSERT(msecs_to_jiffies(val * MSEC_PER_SEC) < LONG_MAX);
}
return count;
}
XFS_SYSFS_ATTR_RW(retry_timeout_seconds);
static ssize_t
fail_at_unmount_show(
struct kobject *kobject,
char *buf)
{
struct xfs_mount *mp = err_to_mp(kobject);
return snprintf(buf, PAGE_SIZE, "%d\n", mp->m_fail_unmount);
}
static ssize_t
fail_at_unmount_store(
struct kobject *kobject,
const char *buf,
size_t count)
{
struct xfs_mount *mp = err_to_mp(kobject);
int ret;
int val;
ret = kstrtoint(buf, 0, &val);
if (ret)
return ret;
if (val < 0 || val > 1)
return -EINVAL;
mp->m_fail_unmount = val;
return count;
}
XFS_SYSFS_ATTR_RW(fail_at_unmount);
static struct attribute *xfs_error_attrs[] = {
ATTR_LIST(max_retries),
ATTR_LIST(retry_timeout_seconds),
NULL,
};
static struct kobj_type xfs_error_cfg_ktype = {
.release = xfs_sysfs_release,
.sysfs_ops = &xfs_sysfs_ops,
.default_attrs = xfs_error_attrs,
};
static struct kobj_type xfs_error_ktype = {
.release = xfs_sysfs_release,
.sysfs_ops = &xfs_sysfs_ops,
};
/*
* Error initialization tables. These need to be ordered in the same
* order as the enums used to index the array. All class init tables need to
* define a "default" behaviour as the first entry, all other entries can be
* empty.
*/
struct xfs_error_init {
char *name;
int max_retries;
int retry_timeout; /* in seconds */
};
static const struct xfs_error_init xfs_error_meta_init[XFS_ERR_ERRNO_MAX] = {
{ .name = "default",
.max_retries = XFS_ERR_RETRY_FOREVER,
.retry_timeout = XFS_ERR_RETRY_FOREVER,
},
{ .name = "EIO",
.max_retries = XFS_ERR_RETRY_FOREVER,
.retry_timeout = XFS_ERR_RETRY_FOREVER,
},
{ .name = "ENOSPC",
.max_retries = XFS_ERR_RETRY_FOREVER,
.retry_timeout = XFS_ERR_RETRY_FOREVER,
},
{ .name = "ENODEV",
.max_retries = 0, /* We can't recover from devices disappearing */
.retry_timeout = 0,
},
};
static int
xfs_error_sysfs_init_class(
struct xfs_mount *mp,
int class,
const char *parent_name,
struct xfs_kobj *parent_kobj,
const struct xfs_error_init init[])
{
struct xfs_error_cfg *cfg;
int error;
int i;
ASSERT(class < XFS_ERR_CLASS_MAX);
error = xfs_sysfs_init(parent_kobj, &xfs_error_ktype,
&mp->m_error_kobj, parent_name);
if (error)
return error;
for (i = 0; i < XFS_ERR_ERRNO_MAX; i++) {
cfg = &mp->m_error_cfg[class][i];
error = xfs_sysfs_init(&cfg->kobj, &xfs_error_cfg_ktype,
parent_kobj, init[i].name);
if (error)
goto out_error;
cfg->max_retries = init[i].max_retries;
if (init[i].retry_timeout == XFS_ERR_RETRY_FOREVER)
cfg->retry_timeout = XFS_ERR_RETRY_FOREVER;
else
cfg->retry_timeout = msecs_to_jiffies(
init[i].retry_timeout * MSEC_PER_SEC);
}
return 0;
out_error:
/* unwind the entries that succeeded */
for (i--; i >= 0; i--) {
cfg = &mp->m_error_cfg[class][i];
xfs_sysfs_del(&cfg->kobj);
}
xfs_sysfs_del(parent_kobj);
return error;
}
int
xfs_error_sysfs_init(
struct xfs_mount *mp)
{
int error;
/* .../xfs/<dev>/error/ */
error = xfs_sysfs_init(&mp->m_error_kobj, &xfs_error_ktype,
&mp->m_kobj, "error");
if (error)
return error;
error = sysfs_create_file(&mp->m_error_kobj.kobject,
ATTR_LIST(fail_at_unmount));
if (error)
goto out_error;
/* .../xfs/<dev>/error/metadata/ */
error = xfs_error_sysfs_init_class(mp, XFS_ERR_METADATA,
"metadata", &mp->m_error_meta_kobj,
xfs_error_meta_init);
if (error)
goto out_error;
return 0;
out_error:
xfs_sysfs_del(&mp->m_error_kobj);
return error;
}
void
xfs_error_sysfs_del(
struct xfs_mount *mp)
{
struct xfs_error_cfg *cfg;
int i, j;
for (i = 0; i < XFS_ERR_CLASS_MAX; i++) {
for (j = 0; j < XFS_ERR_ERRNO_MAX; j++) {
cfg = &mp->m_error_cfg[i][j];
xfs_sysfs_del(&cfg->kobj);
}
}
xfs_sysfs_del(&mp->m_error_meta_kobj);
xfs_sysfs_del(&mp->m_error_kobj);
}
struct xfs_error_cfg *
xfs_error_get_cfg(
struct xfs_mount *mp,
int error_class,
int error)
{
struct xfs_error_cfg *cfg;
if (error < 0)
error = -error;
switch (error) {
case EIO:
cfg = &mp->m_error_cfg[error_class][XFS_ERR_EIO];
break;
case ENOSPC:
cfg = &mp->m_error_cfg[error_class][XFS_ERR_ENOSPC];
break;
case ENODEV:
cfg = &mp->m_error_cfg[error_class][XFS_ERR_ENODEV];
break;
default:
cfg = &mp->m_error_cfg[error_class][XFS_ERR_DEFAULT];
break;
}
return cfg;
}