2009-05-28 03:56:54 +08:00
|
|
|
/*
|
|
|
|
* MCE grading rules.
|
|
|
|
* Copyright 2008, 2009 Intel Corporation.
|
|
|
|
*
|
|
|
|
* 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; version 2
|
|
|
|
* of the License.
|
|
|
|
*
|
|
|
|
* Author: Andi Kleen
|
|
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
2009-05-28 03:56:57 +08:00
|
|
|
#include <linux/seq_file.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/debugfs.h>
|
2009-05-28 03:56:54 +08:00
|
|
|
#include <asm/mce.h>
|
|
|
|
|
|
|
|
#include "mce-internal.h"
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Grade an mce by severity. In general the most severe ones are processed
|
|
|
|
* first. Since there are quite a lot of combinations test the bits in a
|
|
|
|
* table-driven way. The rules are simply processed in order, first
|
|
|
|
* match wins.
|
2009-05-28 03:56:57 +08:00
|
|
|
*
|
|
|
|
* Note this is only used for machine check exceptions, the corrected
|
|
|
|
* errors use much simpler rules. The exceptions still check for the corrected
|
|
|
|
* errors, but only to leave them alone for the CMCI handler (except for
|
|
|
|
* panic situations)
|
2009-05-28 03:56:54 +08:00
|
|
|
*/
|
|
|
|
|
2009-05-28 03:56:57 +08:00
|
|
|
enum context { IN_KERNEL = 1, IN_USER = 2 };
|
|
|
|
enum ser { SER_REQUIRED = 1, NO_SER = 2 };
|
|
|
|
|
2009-05-28 03:56:54 +08:00
|
|
|
static struct severity {
|
|
|
|
u64 mask;
|
|
|
|
u64 result;
|
|
|
|
unsigned char sev;
|
|
|
|
unsigned char mcgmask;
|
|
|
|
unsigned char mcgres;
|
2009-05-28 03:56:57 +08:00
|
|
|
unsigned char ser;
|
|
|
|
unsigned char context;
|
2009-05-28 03:56:57 +08:00
|
|
|
unsigned char covered;
|
2009-05-28 03:56:54 +08:00
|
|
|
char *msg;
|
|
|
|
} severities[] = {
|
2009-05-28 03:56:57 +08:00
|
|
|
#define KERNEL .context = IN_KERNEL
|
|
|
|
#define USER .context = IN_USER
|
|
|
|
#define SER .ser = SER_REQUIRED
|
|
|
|
#define NOSER .ser = NO_SER
|
2009-05-28 03:56:54 +08:00
|
|
|
#define SEV(s) .sev = MCE_ ## s ## _SEVERITY
|
|
|
|
#define BITCLR(x, s, m, r...) { .mask = x, .result = 0, SEV(s), .msg = m, ## r }
|
|
|
|
#define BITSET(x, s, m, r...) { .mask = x, .result = x, SEV(s), .msg = m, ## r }
|
|
|
|
#define MCGMASK(x, res, s, m, r...) \
|
|
|
|
{ .mcgmask = x, .mcgres = res, SEV(s), .msg = m, ## r }
|
2009-05-28 03:56:57 +08:00
|
|
|
#define MASK(x, y, s, m, r...) \
|
|
|
|
{ .mask = x, .result = y, SEV(s), .msg = m, ## r }
|
|
|
|
#define MCI_UC_S (MCI_STATUS_UC|MCI_STATUS_S)
|
|
|
|
#define MCI_UC_SAR (MCI_STATUS_UC|MCI_STATUS_S|MCI_STATUS_AR)
|
|
|
|
#define MCACOD 0xffff
|
|
|
|
|
2009-05-28 03:56:54 +08:00
|
|
|
BITCLR(MCI_STATUS_VAL, NO, "Invalid"),
|
|
|
|
BITCLR(MCI_STATUS_EN, NO, "Not enabled"),
|
|
|
|
BITSET(MCI_STATUS_PCC, PANIC, "Processor context corrupt"),
|
2009-05-28 03:56:57 +08:00
|
|
|
/* When MCIP is not set something is very confused */
|
|
|
|
MCGMASK(MCG_STATUS_MCIP, 0, PANIC, "MCIP not set in MCA handler"),
|
|
|
|
/* Neither return not error IP -- no chance to recover -> PANIC */
|
|
|
|
MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, 0, PANIC,
|
|
|
|
"Neither restart nor error IP"),
|
|
|
|
MCGMASK(MCG_STATUS_RIPV, 0, PANIC, "In kernel and no restart IP",
|
|
|
|
KERNEL),
|
|
|
|
BITCLR(MCI_STATUS_UC, KEEP, "Corrected error", NOSER),
|
|
|
|
MASK(MCI_STATUS_OVER|MCI_STATUS_UC|MCI_STATUS_EN, MCI_STATUS_UC, SOME,
|
|
|
|
"Spurious not enabled", SER),
|
|
|
|
|
|
|
|
/* ignore OVER for UCNA */
|
|
|
|
MASK(MCI_UC_SAR, MCI_STATUS_UC, KEEP,
|
|
|
|
"Uncorrected no action required", SER),
|
|
|
|
MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_STATUS_UC|MCI_STATUS_AR, PANIC,
|
|
|
|
"Illegal combination (UCNA with AR=1)", SER),
|
|
|
|
MASK(MCI_STATUS_S, 0, KEEP, "Non signalled machine check", SER),
|
|
|
|
|
|
|
|
/* AR add known MCACODs here */
|
|
|
|
MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_STATUS_OVER|MCI_UC_SAR, PANIC,
|
|
|
|
"Action required with lost events", SER),
|
|
|
|
MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD, MCI_UC_SAR, PANIC,
|
|
|
|
"Action required; unknown MCACOD", SER),
|
|
|
|
|
|
|
|
/* known AO MCACODs: */
|
|
|
|
MASK(MCI_UC_SAR|MCI_STATUS_OVER|0xfff0, MCI_UC_S|0xc0, AO,
|
|
|
|
"Action optional: memory scrubbing error", SER),
|
|
|
|
MASK(MCI_UC_SAR|MCI_STATUS_OVER|MCACOD, MCI_UC_S|0x17a, AO,
|
|
|
|
"Action optional: last level cache writeback error", SER),
|
|
|
|
|
|
|
|
MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_S, SOME,
|
|
|
|
"Action optional unknown MCACOD", SER),
|
|
|
|
MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_S|MCI_STATUS_OVER, SOME,
|
|
|
|
"Action optional with lost events", SER),
|
2009-05-28 03:56:54 +08:00
|
|
|
BITSET(MCI_STATUS_UC|MCI_STATUS_OVER, PANIC, "Overflowed uncorrected"),
|
|
|
|
BITSET(MCI_STATUS_UC, UC, "Uncorrected"),
|
|
|
|
BITSET(0, SOME, "No match") /* always matches. keep at end */
|
|
|
|
};
|
|
|
|
|
2009-05-28 03:56:57 +08:00
|
|
|
/*
|
|
|
|
* If the EIPV bit is set, it means the saved IP is the
|
|
|
|
* instruction which caused the MCE.
|
|
|
|
*/
|
|
|
|
static int error_context(struct mce *m)
|
|
|
|
{
|
|
|
|
if (m->mcgstatus & MCG_STATUS_EIPV)
|
|
|
|
return (m->ip && (m->cs & 3) == 3) ? IN_USER : IN_KERNEL;
|
|
|
|
/* Unknown, assume kernel */
|
|
|
|
return IN_KERNEL;
|
|
|
|
}
|
|
|
|
|
2009-05-28 03:56:54 +08:00
|
|
|
int mce_severity(struct mce *a, int tolerant, char **msg)
|
|
|
|
{
|
2009-05-28 03:56:57 +08:00
|
|
|
enum context ctx = error_context(a);
|
2009-05-28 03:56:54 +08:00
|
|
|
struct severity *s;
|
2009-05-28 03:56:57 +08:00
|
|
|
|
2009-05-28 03:56:54 +08:00
|
|
|
for (s = severities;; s++) {
|
|
|
|
if ((a->status & s->mask) != s->result)
|
|
|
|
continue;
|
|
|
|
if ((a->mcgstatus & s->mcgmask) != s->mcgres)
|
|
|
|
continue;
|
2009-05-28 03:56:57 +08:00
|
|
|
if (s->ser == SER_REQUIRED && !mce_ser)
|
|
|
|
continue;
|
|
|
|
if (s->ser == NO_SER && mce_ser)
|
|
|
|
continue;
|
|
|
|
if (s->context && ctx != s->context)
|
|
|
|
continue;
|
2009-05-28 03:56:54 +08:00
|
|
|
if (msg)
|
|
|
|
*msg = s->msg;
|
2009-05-28 03:56:57 +08:00
|
|
|
s->covered = 1;
|
2009-05-28 03:56:57 +08:00
|
|
|
if (s->sev >= MCE_UC_SEVERITY && ctx == IN_KERNEL) {
|
|
|
|
if (panic_on_oops || tolerant < 1)
|
|
|
|
return MCE_PANIC_SEVERITY;
|
|
|
|
}
|
2009-05-28 03:56:54 +08:00
|
|
|
return s->sev;
|
|
|
|
}
|
|
|
|
}
|
2009-05-28 03:56:57 +08:00
|
|
|
|
2009-09-15 02:52:25 +08:00
|
|
|
#ifdef CONFIG_DEBUG_FS
|
2009-05-28 03:56:57 +08:00
|
|
|
static void *s_start(struct seq_file *f, loff_t *pos)
|
|
|
|
{
|
|
|
|
if (*pos >= ARRAY_SIZE(severities))
|
|
|
|
return NULL;
|
|
|
|
return &severities[*pos];
|
|
|
|
}
|
|
|
|
|
|
|
|
static void *s_next(struct seq_file *f, void *data, loff_t *pos)
|
|
|
|
{
|
|
|
|
if (++(*pos) >= ARRAY_SIZE(severities))
|
|
|
|
return NULL;
|
|
|
|
return &severities[*pos];
|
|
|
|
}
|
|
|
|
|
|
|
|
static void s_stop(struct seq_file *f, void *data)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static int s_show(struct seq_file *f, void *data)
|
|
|
|
{
|
|
|
|
struct severity *ser = data;
|
|
|
|
seq_printf(f, "%d\t%s\n", ser->covered, ser->msg);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static const struct seq_operations severities_seq_ops = {
|
|
|
|
.start = s_start,
|
|
|
|
.next = s_next,
|
|
|
|
.stop = s_stop,
|
|
|
|
.show = s_show,
|
|
|
|
};
|
|
|
|
|
|
|
|
static int severities_coverage_open(struct inode *inode, struct file *file)
|
|
|
|
{
|
|
|
|
return seq_open(file, &severities_seq_ops);
|
|
|
|
}
|
|
|
|
|
|
|
|
static ssize_t severities_coverage_write(struct file *file,
|
|
|
|
const char __user *ubuf,
|
|
|
|
size_t count, loff_t *ppos)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
for (i = 0; i < ARRAY_SIZE(severities); i++)
|
|
|
|
severities[i].covered = 0;
|
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
|
|
|
static const struct file_operations severities_coverage_fops = {
|
|
|
|
.open = severities_coverage_open,
|
|
|
|
.release = seq_release,
|
|
|
|
.read = seq_read,
|
|
|
|
.write = severities_coverage_write,
|
llseek: automatically add .llseek fop
All file_operations should get a .llseek operation so we can make
nonseekable_open the default for future file operations without a
.llseek pointer.
The three cases that we can automatically detect are no_llseek, seq_lseek
and default_llseek. For cases where we can we can automatically prove that
the file offset is always ignored, we use noop_llseek, which maintains
the current behavior of not returning an error from a seek.
New drivers should normally not use noop_llseek but instead use no_llseek
and call nonseekable_open at open time. Existing drivers can be converted
to do the same when the maintainer knows for certain that no user code
relies on calling seek on the device file.
The generated code is often incorrectly indented and right now contains
comments that clarify for each added line why a specific variant was
chosen. In the version that gets submitted upstream, the comments will
be gone and I will manually fix the indentation, because there does not
seem to be a way to do that using coccinelle.
Some amount of new code is currently sitting in linux-next that should get
the same modifications, which I will do at the end of the merge window.
Many thanks to Julia Lawall for helping me learn to write a semantic
patch that does all this.
===== begin semantic patch =====
// This adds an llseek= method to all file operations,
// as a preparation for making no_llseek the default.
//
// The rules are
// - use no_llseek explicitly if we do nonseekable_open
// - use seq_lseek for sequential files
// - use default_llseek if we know we access f_pos
// - use noop_llseek if we know we don't access f_pos,
// but we still want to allow users to call lseek
//
@ open1 exists @
identifier nested_open;
@@
nested_open(...)
{
<+...
nonseekable_open(...)
...+>
}
@ open exists@
identifier open_f;
identifier i, f;
identifier open1.nested_open;
@@
int open_f(struct inode *i, struct file *f)
{
<+...
(
nonseekable_open(...)
|
nested_open(...)
)
...+>
}
@ read disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ read_no_fpos disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
... when != off
}
@ write @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ write_no_fpos @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
... when != off
}
@ fops0 @
identifier fops;
@@
struct file_operations fops = {
...
};
@ has_llseek depends on fops0 @
identifier fops0.fops;
identifier llseek_f;
@@
struct file_operations fops = {
...
.llseek = llseek_f,
...
};
@ has_read depends on fops0 @
identifier fops0.fops;
identifier read_f;
@@
struct file_operations fops = {
...
.read = read_f,
...
};
@ has_write depends on fops0 @
identifier fops0.fops;
identifier write_f;
@@
struct file_operations fops = {
...
.write = write_f,
...
};
@ has_open depends on fops0 @
identifier fops0.fops;
identifier open_f;
@@
struct file_operations fops = {
...
.open = open_f,
...
};
// use no_llseek if we call nonseekable_open
////////////////////////////////////////////
@ nonseekable1 depends on !has_llseek && has_open @
identifier fops0.fops;
identifier nso ~= "nonseekable_open";
@@
struct file_operations fops = {
... .open = nso, ...
+.llseek = no_llseek, /* nonseekable */
};
@ nonseekable2 depends on !has_llseek @
identifier fops0.fops;
identifier open.open_f;
@@
struct file_operations fops = {
... .open = open_f, ...
+.llseek = no_llseek, /* open uses nonseekable */
};
// use seq_lseek for sequential files
/////////////////////////////////////
@ seq depends on !has_llseek @
identifier fops0.fops;
identifier sr ~= "seq_read";
@@
struct file_operations fops = {
... .read = sr, ...
+.llseek = seq_lseek, /* we have seq_read */
};
// use default_llseek if there is a readdir
///////////////////////////////////////////
@ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier readdir_e;
@@
// any other fop is used that changes pos
struct file_operations fops = {
... .readdir = readdir_e, ...
+.llseek = default_llseek, /* readdir is present */
};
// use default_llseek if at least one of read/write touches f_pos
/////////////////////////////////////////////////////////////////
@ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read.read_f;
@@
// read fops use offset
struct file_operations fops = {
... .read = read_f, ...
+.llseek = default_llseek, /* read accesses f_pos */
};
@ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write.write_f;
@@
// write fops use offset
struct file_operations fops = {
... .write = write_f, ...
+ .llseek = default_llseek, /* write accesses f_pos */
};
// Use noop_llseek if neither read nor write accesses f_pos
///////////////////////////////////////////////////////////
@ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
identifier write_no_fpos.write_f;
@@
// write fops use offset
struct file_operations fops = {
...
.write = write_f,
.read = read_f,
...
+.llseek = noop_llseek, /* read and write both use no f_pos */
};
@ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write_no_fpos.write_f;
@@
struct file_operations fops = {
... .write = write_f, ...
+.llseek = noop_llseek, /* write uses no f_pos */
};
@ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
@@
struct file_operations fops = {
... .read = read_f, ...
+.llseek = noop_llseek, /* read uses no f_pos */
};
@ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
@@
struct file_operations fops = {
...
+.llseek = noop_llseek, /* no read or write fn */
};
===== End semantic patch =====
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Julia Lawall <julia@diku.dk>
Cc: Christoph Hellwig <hch@infradead.org>
2010-08-16 00:52:59 +08:00
|
|
|
.llseek = seq_lseek,
|
2009-05-28 03:56:57 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
static int __init severities_debugfs_init(void)
|
|
|
|
{
|
|
|
|
struct dentry *dmce = NULL, *fseverities_coverage = NULL;
|
|
|
|
|
2009-07-31 09:41:42 +08:00
|
|
|
dmce = mce_get_debugfs_dir();
|
2009-05-28 03:56:57 +08:00
|
|
|
if (dmce == NULL)
|
|
|
|
goto err_out;
|
|
|
|
fseverities_coverage = debugfs_create_file("severities-coverage",
|
|
|
|
0444, dmce, NULL,
|
|
|
|
&severities_coverage_fops);
|
|
|
|
if (fseverities_coverage == NULL)
|
|
|
|
goto err_out;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
err_out:
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
late_initcall(severities_debugfs_init);
|
2009-09-15 02:52:25 +08:00
|
|
|
#endif
|