linux_dsm_epyc7002/fs/xfs/xfs_error.c
Dave Chinner 73efe4a4dd xfs: prevent NMI timeouts in cmn_err
We currently have a global error message buffer in cmn_err that is
protected by a spin lock that disables interrupts.  Recently there
have been reports of NMI timeouts occurring when the console is
being flooded by SCSI error reports due to cmn_err() getting stuck
trying to print to the console while holding this lock (i.e. with
interrupts disabled). The NMI watchdog is seeing this CPU as
non-responding and so is triggering a panic.  While the trigger for
the reported case is SCSI errors, pretty much anything that spams
the kernel log could cause this to occur.

Realistically the only reason that we have the intemediate message
buffer is to prepend the correct kernel log level prefix to the log
message. The only reason we have the lock is to protect the global
message buffer and the only reason the message buffer is global is
to keep it off the stack. Hence if we can avoid needing a global
message buffer we avoid needing the lock, and we can do this with a
small amount of cleanup and some preprocessor tricks:

	1. clean up xfs_cmn_err() panic mask functionality to avoid
	   needing debug code in xfs_cmn_err()
	2. remove the couple of "!" message prefixes that still exist that
	   the existing cmn_err() code steps over.
	3. redefine CE_* levels directly to KERN_*
	4. redefine cmn_err() and friends to use printk() directly
	   via variable argument length macros.

By doing this, we can completely remove the cmn_err() code and the
lock that is causing the problems, and rely solely on printk()
serialisation to ensure that we don't get garbled messages.

A series of followup patches is really needed to clean up all the
cmn_err() calls and related messages properly, but that results in a
series that is not easily back portable to enterprise kernels. Hence
this initial fix is only to address the direct problem in the lowest
impact way possible.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>
2011-01-12 08:46:41 -06:00

188 lines
4.0 KiB
C

/*
* Copyright (c) 2000-2001,2005 Silicon Graphics, 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_fs.h"
#include "xfs_types.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_utils.h"
#include "xfs_error.h"
#ifdef DEBUG
int xfs_etrap[XFS_ERROR_NTRAP] = {
0,
};
int
xfs_error_trap(int e)
{
int i;
if (!e)
return 0;
for (i = 0; i < XFS_ERROR_NTRAP; i++) {
if (xfs_etrap[i] == 0)
break;
if (e != xfs_etrap[i])
continue;
cmn_err(CE_NOTE, "xfs_error_trap: error %d", e);
BUG();
break;
}
return e;
}
int xfs_etest[XFS_NUM_INJECT_ERROR];
int64_t xfs_etest_fsid[XFS_NUM_INJECT_ERROR];
char * xfs_etest_fsname[XFS_NUM_INJECT_ERROR];
int xfs_error_test_active;
int
xfs_error_test(int error_tag, int *fsidp, char *expression,
int line, char *file, unsigned long randfactor)
{
int i;
int64_t fsid;
if (random32() % randfactor)
return 0;
memcpy(&fsid, fsidp, sizeof(xfs_fsid_t));
for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) {
if (xfs_etest[i] == error_tag && xfs_etest_fsid[i] == fsid) {
cmn_err(CE_WARN,
"Injecting error (%s) at file %s, line %d, on filesystem \"%s\"",
expression, file, line, xfs_etest_fsname[i]);
return 1;
}
}
return 0;
}
int
xfs_errortag_add(int error_tag, xfs_mount_t *mp)
{
int i;
int len;
int64_t fsid;
memcpy(&fsid, mp->m_fixedfsid, sizeof(xfs_fsid_t));
for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) {
if (xfs_etest_fsid[i] == fsid && xfs_etest[i] == error_tag) {
cmn_err(CE_WARN, "XFS error tag #%d on", error_tag);
return 0;
}
}
for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) {
if (xfs_etest[i] == 0) {
cmn_err(CE_WARN, "Turned on XFS error tag #%d",
error_tag);
xfs_etest[i] = error_tag;
xfs_etest_fsid[i] = fsid;
len = strlen(mp->m_fsname);
xfs_etest_fsname[i] = kmem_alloc(len + 1, KM_SLEEP);
strcpy(xfs_etest_fsname[i], mp->m_fsname);
xfs_error_test_active++;
return 0;
}
}
cmn_err(CE_WARN, "error tag overflow, too many turned on");
return 1;
}
int
xfs_errortag_clearall(xfs_mount_t *mp, int loud)
{
int64_t fsid;
int cleared = 0;
int i;
memcpy(&fsid, mp->m_fixedfsid, sizeof(xfs_fsid_t));
for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) {
if ((fsid == 0LL || xfs_etest_fsid[i] == fsid) &&
xfs_etest[i] != 0) {
cleared = 1;
cmn_err(CE_WARN, "Clearing XFS error tag #%d",
xfs_etest[i]);
xfs_etest[i] = 0;
xfs_etest_fsid[i] = 0LL;
kmem_free(xfs_etest_fsname[i]);
xfs_etest_fsname[i] = NULL;
xfs_error_test_active--;
}
}
if (loud || cleared)
cmn_err(CE_WARN,
"Cleared all XFS error tags for filesystem \"%s\"",
mp->m_fsname);
return 0;
}
#endif /* DEBUG */
void
xfs_error_report(
const char *tag,
int level,
struct xfs_mount *mp,
const char *filename,
int linenum,
inst_t *ra)
{
if (level <= xfs_error_level) {
xfs_cmn_err(XFS_PTAG_ERROR_REPORT,
CE_ALERT, mp,
"XFS internal error %s at line %d of file %s. Caller 0x%p\n",
tag, linenum, filename, ra);
xfs_stack_trace();
}
}
void
xfs_corruption_error(
const char *tag,
int level,
struct xfs_mount *mp,
void *p,
const char *filename,
int linenum,
inst_t *ra)
{
if (level <= xfs_error_level)
xfs_hex_dump(p, 16);
xfs_error_report(tag, level, mp, filename, linenum, ra);
}