| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1335546942-28524-1-git-send-email-prarit@redhat.com>
Date: Fri, 27 Apr 2012 13:15:42 -0400
From: Prarit Bhargava <prarit@...hat.com>
To: linux-kernel@...r.kernel.org
Cc: Prarit Bhargava <prarit@...hat.com>,
John Stultz <johnstul@...ibm.com>,
Thomas Gleixner <tglx@...utronix.de>,
gregkh@...uxfoundation.org, lwoodman@...hat.com, jbaron@...hat.com,
dzickus@...hat.com
Subject: [RFC PATCH] tty, add kref to sysrq handlers
On a large system with a large number of tasks, the output of
echo t > /proc/sysrq-trigger
can take a long period of time. If this period is greater than the period
of the current clocksource, the clocksource watchdog will mark the
clocksource as unstable and fail the clocksource over.
The problem with sysrq is that __handle_sysrq() takes a spin_lock with
interrupts disabled and disables interrupts for the duration of the
handler. If this happens during sysrq-t on a large system with a large
number of tasks, the result is a "brown-out" of the system.
The spin_lock in question, sysrq_key_table_lock, is in place to prevent
the removal of a sysrq handler while it is being executed in
__handle_sysrq().
There are two possiblities in dealing with this lock. The first (which is
not implemented, but has been tested) is the complete removal of the lock.
All instances of unregister_sysrq_key() in the kernel occur during module
remove. These module remove functions are executed in the context of a
stop_machine() so AFAICT it is not possible for both the sysrq_handler and the
module remove code to be running in parallel.
If the lock were removed, however, there is one _unlikely_ circumstance in
which the array would be left unprotected. That would be the situation in
which a module was loaded and the sysrq handler was registered during the
execution of the module. Again, the possibility of the scenario is very
small and given the existing usage of unregister_sysrq_key() in the tree
it seems like removing the lock is sufficient.
If that is not acceptable, then I propose to do what is done below -- a
kref is added to each sysrq handler and is incremented and decremented in
__handle_sysrq(). This, while more complicated, leads to minimizing the
time that the sysrq_key_table_lock is acquired and results in a functional
sysrq-t.
I've tested both options and I no longer see the clocksource watchdog
marking the TSC clocksource as unstable.
Of course, I'm more than willing to hear additional suggestions. A rw
lock still requires that it be taken with irqs disabled so IMO it is out
of the question.
P.
Cc: John Stultz <johnstul@...ibm.com>
Cc: Thomas Gleixner <tglx@...utronix.de>
Cc: gregkh@...uxfoundation.org
Cc: lwoodman@...hat.com
Cc: jbaron@...hat.com
Cc: dzickus@...hat.com
---
drivers/tty/sysrq.c | 42 +++++++++++++++++++++++++++++++++++++++---
include/linux/sysrq.h | 2 ++
2 files changed, 41 insertions(+), 3 deletions(-)
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 05728894..38c6ae6 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -458,6 +458,20 @@ static struct sysrq_key_op *sysrq_key_table[36] = {
&sysrq_ftrace_dump_op, /* z */
};
+void sysrq_release(struct kref *kref)
+{
+ struct sysrq_key_op *release_op;
+ int i;
+ unsigned long flags;
+
+ spin_lock_irqsave(&sysrq_key_table_lock, flags);
+ release_op = container_of(kref, struct sysrq_key_op, kref);
+ for (i = 0; i < ARRAY_SIZE(sysrq_key_table); i++)
+ if (sysrq_key_table[i] == release_op)
+ sysrq_key_table[i] = NULL;
+ spin_unlock_irqrestore(&sysrq_key_table_lock, flags);
+}
+
/* key2index calculation, -1 on invalid index */
static int sysrq_key_table_key2index(int key)
{
@@ -502,7 +516,6 @@ void __handle_sysrq(int key, bool check_mask)
int i;
unsigned long flags;
- spin_lock_irqsave(&sysrq_key_table_lock, flags);
/*
* Raise the apparent loglevel to maximum so that the sysrq header
* is shown to provide the user with positive feedback. We do not
@@ -513,7 +526,12 @@ void __handle_sysrq(int key, bool check_mask)
console_loglevel = 7;
printk(KERN_INFO "SysRq : ");
+ spin_lock_irqsave(&sysrq_key_table_lock, flags);
op_p = __sysrq_get_key_op(key);
+ if (op_p)
+ kref_get(&op_p->kref);
+ spin_unlock_irqrestore(&sysrq_key_table_lock, flags);
+
if (op_p) {
/*
* Should we check for enabled operations (/proc/sysrq-trigger
@@ -526,9 +544,14 @@ void __handle_sysrq(int key, bool check_mask)
} else {
printk("This sysrq operation is disabled.\n");
}
+
+ spin_lock_irqsave(&sysrq_key_table_lock, flags);
+ kref_put(&op_p->kref, sysrq_release);
+ spin_unlock_irqrestore(&sysrq_key_table_lock, flags);
} else {
printk("HELP : ");
/* Only print the help msg once per handler */
+ spin_lock_irqsave(&sysrq_key_table_lock, flags);
for (i = 0; i < ARRAY_SIZE(sysrq_key_table); i++) {
if (sysrq_key_table[i]) {
int j;
@@ -541,10 +564,10 @@ void __handle_sysrq(int key, bool check_mask)
printk("%s ", sysrq_key_table[i]->help_msg);
}
}
+ spin_unlock_irqrestore(&sysrq_key_table_lock, flags);
printk("\n");
console_loglevel = orig_log_level;
}
- spin_unlock_irqrestore(&sysrq_key_table_lock, flags);
}
void handle_sysrq(int key)
@@ -837,7 +860,12 @@ static int __sysrq_swap_key_ops(int key, struct sysrq_key_op *insert_op_p,
spin_lock_irqsave(&sysrq_key_table_lock, flags);
if (__sysrq_get_key_op(key) == remove_op_p) {
- __sysrq_put_key_op(key, insert_op_p);
+ if (!remove_op_p) { /* register */
+ __sysrq_put_key_op(key, insert_op_p);
+ kref_init(&insert_op_p->kref);
+ }
+ if (!insert_op_p) /* unregister */
+ kref_put(&remove_op_p->kref, sysrq_release);
retval = 0;
} else {
retval = -1;
@@ -898,6 +926,14 @@ static inline void sysrq_init_procfs(void)
static int __init sysrq_init(void)
{
+ int i;
+
+ spin_lock_irqsave(&sysrq_key_table_lock, flags);
+ for (i = 0; i < ARRAY_SIZE(sysrq_key_table); i++)
+ if (sysrq_key_table[i])
+ kref_init(&sysrq_key_table[i]->kref);
+ spin_unlock_irqrestore(&sysrq_key_table_lock, flags);
+
sysrq_init_procfs();
if (sysrq_on())
diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h
index 7faf933..d458f39 100644
--- a/include/linux/sysrq.h
+++ b/include/linux/sysrq.h
@@ -16,6 +16,7 @@
#include <linux/errno.h>
#include <linux/types.h>
+#include <linux/kref.h>
/* Enable/disable SYSRQ support by default (0==no, 1==yes). */
#define SYSRQ_DEFAULT_ENABLE 1
@@ -36,6 +37,7 @@ struct sysrq_key_op {
char *help_msg;
char *action_msg;
int enable_mask;
+ struct kref kref;
};
#ifdef CONFIG_MAGIC_SYSRQ
--
1.7.7.2
---
drivers/tty/sysrq.c | 42 +++++++++++++++++++++++++++++++++++++++---
include/linux/sysrq.h | 2 ++
2 files changed, 41 insertions(+), 3 deletions(-)
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 0572889..38c6ae6 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -458,6 +458,20 @@ static struct sysrq_key_op *sysrq_key_table[36] = {
&sysrq_ftrace_dump_op, /* z */
};
+void sysrq_release(struct kref *kref)
+{
+ struct sysrq_key_op *release_op;
+ int i;
+ unsigned long flags;
+
+ spin_lock_irqsave(&sysrq_key_table_lock, flags);
+ release_op = container_of(kref, struct sysrq_key_op, kref);
+ for (i = 0; i < ARRAY_SIZE(sysrq_key_table); i++)
+ if (sysrq_key_table[i] == release_op)
+ sysrq_key_table[i] = NULL;
+ spin_unlock_irqrestore(&sysrq_key_table_lock, flags);
+}
+
/* key2index calculation, -1 on invalid index */
static int sysrq_key_table_key2index(int key)
{
@@ -502,7 +516,6 @@ void __handle_sysrq(int key, bool check_mask)
int i;
unsigned long flags;
- spin_lock_irqsave(&sysrq_key_table_lock, flags);
/*
* Raise the apparent loglevel to maximum so that the sysrq header
* is shown to provide the user with positive feedback. We do not
@@ -513,7 +526,12 @@ void __handle_sysrq(int key, bool check_mask)
console_loglevel = 7;
printk(KERN_INFO "SysRq : ");
+ spin_lock_irqsave(&sysrq_key_table_lock, flags);
op_p = __sysrq_get_key_op(key);
+ if (op_p)
+ kref_get(&op_p->kref);
+ spin_unlock_irqrestore(&sysrq_key_table_lock, flags);
+
if (op_p) {
/*
* Should we check for enabled operations (/proc/sysrq-trigger
@@ -526,9 +544,14 @@ void __handle_sysrq(int key, bool check_mask)
} else {
printk("This sysrq operation is disabled.\n");
}
+
+ spin_lock_irqsave(&sysrq_key_table_lock, flags);
+ kref_put(&op_p->kref, sysrq_release);
+ spin_unlock_irqrestore(&sysrq_key_table_lock, flags);
} else {
printk("HELP : ");
/* Only print the help msg once per handler */
+ spin_lock_irqsave(&sysrq_key_table_lock, flags);
for (i = 0; i < ARRAY_SIZE(sysrq_key_table); i++) {
if (sysrq_key_table[i]) {
int j;
@@ -541,10 +564,10 @@ void __handle_sysrq(int key, bool check_mask)
printk("%s ", sysrq_key_table[i]->help_msg);
}
}
+ spin_unlock_irqrestore(&sysrq_key_table_lock, flags);
printk("\n");
console_loglevel = orig_log_level;
}
- spin_unlock_irqrestore(&sysrq_key_table_lock, flags);
}
void handle_sysrq(int key)
@@ -837,7 +860,12 @@ static int __sysrq_swap_key_ops(int key, struct sysrq_key_op *insert_op_p,
spin_lock_irqsave(&sysrq_key_table_lock, flags);
if (__sysrq_get_key_op(key) == remove_op_p) {
- __sysrq_put_key_op(key, insert_op_p);
+ if (!remove_op_p) { /* register */
+ __sysrq_put_key_op(key, insert_op_p);
+ kref_init(&insert_op_p->kref);
+ }
+ if (!insert_op_p) /* unregister */
+ kref_put(&remove_op_p->kref, sysrq_release);
retval = 0;
} else {
retval = -1;
@@ -898,6 +926,14 @@ static inline void sysrq_init_procfs(void)
static int __init sysrq_init(void)
{
+ int i;
+
+ spin_lock_irqsave(&sysrq_key_table_lock, flags);
+ for (i = 0; i < ARRAY_SIZE(sysrq_key_table); i++)
+ if (sysrq_key_table[i])
+ kref_init(&sysrq_key_table[i]->kref);
+ spin_unlock_irqrestore(&sysrq_key_table_lock, flags);
+
sysrq_init_procfs();
if (sysrq_on())
diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h
index 7faf933..d458f39 100644
--- a/include/linux/sysrq.h
+++ b/include/linux/sysrq.h
@@ -16,6 +16,7 @@
#include <linux/errno.h>
#include <linux/types.h>
+#include <linux/kref.h>
/* Enable/disable SYSRQ support by default (0==no, 1==yes). */
#define SYSRQ_DEFAULT_ENABLE 1
@@ -36,6 +37,7 @@ struct sysrq_key_op {
char *help_msg;
char *action_msg;
int enable_mask;
+ struct kref kref;
};
#ifdef CONFIG_MAGIC_SYSRQ
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists