|
|
|
|
/*
|
|
|
|
|
* Machine check injection support.
|
|
|
|
|
* Copyright 2008 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.
|
|
|
|
|
*
|
|
|
|
|
* Authors:
|
|
|
|
|
* Andi Kleen
|
|
|
|
|
* Ying Huang
|
|
|
|
|
*/
|
|
|
|
|
#include <linux/uaccess.h>
|
|
|
|
|
#include <linux/module.h>
|
|
|
|
|
#include <linux/timer.h>
|
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
|
#include <linux/string.h>
|
|
|
|
|
#include <linux/fs.h>
|
|
|
|
|
#include <linux/preempt.h>
|
|
|
|
|
#include <linux/smp.h>
|
|
|
|
|
#include <linux/notifier.h>
|
|
|
|
|
#include <linux/kdebug.h>
|
|
|
|
|
#include <linux/cpu.h>
|
|
|
|
|
#include <linux/sched.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
15 years ago
|
|
|
#include <linux/gfp.h>
|
|
|
|
|
#include <asm/mce.h>
|
|
|
|
|
#include <asm/apic.h>
|
|
|
|
|
#include <asm/nmi.h>
|
|
|
|
|
|
|
|
|
|
/* Update fake mce registers on current CPU. */
|
|
|
|
|
static void inject_mce(struct mce *m)
|
|
|
|
|
{
|
|
|
|
|
struct mce *i = &per_cpu(injectm, m->extcpu);
|
|
|
|
|
|
|
|
|
|
/* Make sure no one reads partially written injectm */
|
|
|
|
|
i->finished = 0;
|
|
|
|
|
mb();
|
|
|
|
|
m->finished = 0;
|
|
|
|
|
/* First set the fields after finished */
|
|
|
|
|
i->extcpu = m->extcpu;
|
|
|
|
|
mb();
|
|
|
|
|
/* Now write record in order, finished last (except above) */
|
|
|
|
|
memcpy(i, m, sizeof(struct mce));
|
|
|
|
|
/* Finally activate it */
|
|
|
|
|
mb();
|
|
|
|
|
i->finished = 1;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void raise_poll(struct mce *m)
|
|
|
|
|
{
|
|
|
|
|
unsigned long flags;
|
|
|
|
|
mce_banks_t b;
|
|
|
|
|
|
|
|
|
|
memset(&b, 0xff, sizeof(mce_banks_t));
|
|
|
|
|
local_irq_save(flags);
|
|
|
|
|
machine_check_poll(0, &b);
|
|
|
|
|
local_irq_restore(flags);
|
|
|
|
|
m->finished = 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void raise_exception(struct mce *m, struct pt_regs *pregs)
|
|
|
|
|
{
|
|
|
|
|
struct pt_regs regs;
|
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
|
|
if (!pregs) {
|
|
|
|
|
memset(®s, 0, sizeof(struct pt_regs));
|
|
|
|
|
regs.ip = m->ip;
|
|
|
|
|
regs.cs = m->cs;
|
|
|
|
|
pregs = ®s;
|
|
|
|
|
}
|
|
|
|
|
/* in mcheck exeception handler, irq will be disabled */
|
|
|
|
|
local_irq_save(flags);
|
|
|
|
|
do_machine_check(pregs, 0);
|
|
|
|
|
local_irq_restore(flags);
|
|
|
|
|
m->finished = 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static cpumask_var_t mce_inject_cpumask;
|
|
|
|
|
static DEFINE_MUTEX(mce_inject_mutex);
|
|
|
|
|
|
|
|
|
|
static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
|
|
|
|
|
{
|
|
|
|
|
int cpu = smp_processor_id();
|
x86: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x). This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less registers
are used when code is generated.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: x86@kernel.org
Acked-by: H. Peter Anvin <hpa@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
11 years ago
|
|
|
struct mce *m = this_cpu_ptr(&injectm);
|
|
|
|
|
if (!cpumask_test_cpu(cpu, mce_inject_cpumask))
|
|
|
|
|
return NMI_DONE;
|
|
|
|
|
cpumask_clear_cpu(cpu, mce_inject_cpumask);
|
|
|
|
|
if (m->inject_flags & MCJ_EXCEPTION)
|
|
|
|
|
raise_exception(m, regs);
|
|
|
|
|
else if (m->status)
|
|
|
|
|
raise_poll(m);
|
|
|
|
|
return NMI_HANDLED;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void mce_irq_ipi(void *info)
|
|
|
|
|
{
|
|
|
|
|
int cpu = smp_processor_id();
|
x86: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x). This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less registers
are used when code is generated.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: x86@kernel.org
Acked-by: H. Peter Anvin <hpa@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
11 years ago
|
|
|
struct mce *m = this_cpu_ptr(&injectm);
|
|
|
|
|
|
|
|
|
|
if (cpumask_test_cpu(cpu, mce_inject_cpumask) &&
|
|
|
|
|
m->inject_flags & MCJ_EXCEPTION) {
|
|
|
|
|
cpumask_clear_cpu(cpu, mce_inject_cpumask);
|
|
|
|
|
raise_exception(m, NULL);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Inject mce on current CPU */
|
|
|
|
|
static int raise_local(void)
|
|
|
|
|
{
|
x86: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x). This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less registers
are used when code is generated.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: x86@kernel.org
Acked-by: H. Peter Anvin <hpa@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
11 years ago
|
|
|
struct mce *m = this_cpu_ptr(&injectm);
|
|
|
|
|
int context = MCJ_CTX(m->inject_flags);
|
|
|
|
|
int ret = 0;
|
|
|
|
|
int cpu = m->extcpu;
|
|
|
|
|
|
|
|
|
|
if (m->inject_flags & MCJ_EXCEPTION) {
|
|
|
|
|
pr_info("Triggering MCE exception on CPU %d\n", cpu);
|
|
|
|
|
switch (context) {
|
|
|
|
|
case MCJ_CTX_IRQ:
|
|
|
|
|
/*
|
|
|
|
|
* Could do more to fake interrupts like
|
|
|
|
|
* calling irq_enter, but the necessary
|
|
|
|
|
* machinery isn't exported currently.
|
|
|
|
|
*/
|
|
|
|
|
/*FALL THROUGH*/
|
|
|
|
|
case MCJ_CTX_PROCESS:
|
|
|
|
|
raise_exception(m, NULL);
|
|
|
|
|
break;
|
|
|
|
|
default:
|
|
|
|
|
pr_info("Invalid MCE context\n");
|
|
|
|
|
ret = -EINVAL;
|
|
|
|
|
}
|
|
|
|
|
pr_info("MCE exception done on CPU %d\n", cpu);
|
|
|
|
|
} else if (m->status) {
|
|
|
|
|
pr_info("Starting machine check poll CPU %d\n", cpu);
|
|
|
|
|
raise_poll(m);
|
|
|
|
|
mce_notify_irq();
|
|
|
|
|
pr_info("Machine check poll done on CPU %d\n", cpu);
|
|
|
|
|
} else
|
|
|
|
|
m->finished = 0;
|
|
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void raise_mce(struct mce *m)
|
|
|
|
|
{
|
|
|
|
|
int context = MCJ_CTX(m->inject_flags);
|
|
|
|
|
|
|
|
|
|
inject_mce(m);
|
|
|
|
|
|
|
|
|
|
if (context == MCJ_CTX_RANDOM)
|
|
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
#ifdef CONFIG_X86_LOCAL_APIC
|
|
|
|
|
if (m->inject_flags & (MCJ_IRQ_BROADCAST | MCJ_NMI_BROADCAST)) {
|
|
|
|
|
unsigned long start;
|
|
|
|
|
int cpu;
|
|
|
|
|
|
|
|
|
|
get_online_cpus();
|
|
|
|
|
cpumask_copy(mce_inject_cpumask, cpu_online_mask);
|
|
|
|
|
cpumask_clear_cpu(get_cpu(), mce_inject_cpumask);
|
|
|
|
|
for_each_online_cpu(cpu) {
|
|
|
|
|
struct mce *mcpu = &per_cpu(injectm, cpu);
|
|
|
|
|
if (!mcpu->finished ||
|
|
|
|
|
MCJ_CTX(mcpu->inject_flags) != MCJ_CTX_RANDOM)
|
|
|
|
|
cpumask_clear_cpu(cpu, mce_inject_cpumask);
|
|
|
|
|
}
|
|
|
|
|
if (!cpumask_empty(mce_inject_cpumask)) {
|
|
|
|
|
if (m->inject_flags & MCJ_IRQ_BROADCAST) {
|
|
|
|
|
/*
|
|
|
|
|
* don't wait because mce_irq_ipi is necessary
|
|
|
|
|
* to be sync with following raise_local
|
|
|
|
|
*/
|
|
|
|
|
preempt_disable();
|
|
|
|
|
smp_call_function_many(mce_inject_cpumask,
|
|
|
|
|
mce_irq_ipi, NULL, 0);
|
|
|
|
|
preempt_enable();
|
|
|
|
|
} else if (m->inject_flags & MCJ_NMI_BROADCAST)
|
|
|
|
|
apic->send_IPI_mask(mce_inject_cpumask,
|
|
|
|
|
NMI_VECTOR);
|
|
|
|
|
}
|
|
|
|
|
start = jiffies;
|
|
|
|
|
while (!cpumask_empty(mce_inject_cpumask)) {
|
|
|
|
|
if (!time_before(jiffies, start + 2*HZ)) {
|
|
|
|
|
pr_err("Timeout waiting for mce inject %lx\n",
|
|
|
|
|
*cpumask_bits(mce_inject_cpumask));
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
cpu_relax();
|
|
|
|
|
}
|
|
|
|
|
raise_local();
|
|
|
|
|
put_cpu();
|
|
|
|
|
put_online_cpus();
|
|
|
|
|
} else
|
|
|
|
|
#endif
|
|
|
|
|
{
|
|
|
|
|
preempt_disable();
|
|
|
|
|
raise_local();
|
|
|
|
|
preempt_enable();
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Error injection interface */
|
|
|
|
|
static ssize_t mce_write(struct file *filp, const char __user *ubuf,
|
|
|
|
|
size_t usize, loff_t *off)
|
|
|
|
|
{
|
|
|
|
|
struct mce m;
|
|
|
|
|
|
|
|
|
|
if (!capable(CAP_SYS_ADMIN))
|
|
|
|
|
return -EPERM;
|
|
|
|
|
/*
|
|
|
|
|
* There are some cases where real MSR reads could slip
|
|
|
|
|
* through.
|
|
|
|
|
*/
|
|
|
|
|
if (!boot_cpu_has(X86_FEATURE_MCE) || !boot_cpu_has(X86_FEATURE_MCA))
|
|
|
|
|
return -EIO;
|
|
|
|
|
|
|
|
|
|
if ((unsigned long)usize > sizeof(struct mce))
|
|
|
|
|
usize = sizeof(struct mce);
|
|
|
|
|
if (copy_from_user(&m, ubuf, usize))
|
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
|
|
if (m.extcpu >= num_possible_cpus() || !cpu_online(m.extcpu))
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Need to give user space some time to set everything up,
|
|
|
|
|
* so do it a jiffie or two later everywhere.
|
|
|
|
|
*/
|
|
|
|
|
schedule_timeout(2);
|
|
|
|
|
|
|
|
|
|
mutex_lock(&mce_inject_mutex);
|
|
|
|
|
raise_mce(&m);
|
|
|
|
|
mutex_unlock(&mce_inject_mutex);
|
|
|
|
|
return usize;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int inject_init(void)
|
|
|
|
|
{
|
|
|
|
|
if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL))
|
|
|
|
|
return -ENOMEM;
|
|
|
|
|
pr_info("Machine check injector initialized\n");
|
|
|
|
|
register_mce_write_callback(mce_write);
|
|
|
|
|
register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0,
|
|
|
|
|
"mce_notify");
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
module_init(inject_init);
|
|
|
|
|
/*
|
|
|
|
|
* Cannot tolerate unloading currently because we cannot
|
|
|
|
|
* guarantee all openers of mce_chrdev will get a reference to us.
|
|
|
|
|
*/
|
|
|
|
|
MODULE_LICENSE("GPL");
|
