watchdog: dw_wdt: Use a mutex, not a spinlock
PATCH 1/2 watchdog: dw_wdt: Use a mutex, not a spinlock
Right now the dw_wdt uses a spinlock to protect dw_wdt_open(). The problem is that while holding the spinlock we call:
-> dw_wdt_set_top()
-> dw_wdt_top_in_seconds()
-> clk_get_rate()
-> clk_prepare_lock()
-> mutex_lock()Locking a mutex while holding a spinlock is not allowed and leads to warnings like "BUG: spinlock wrong CPU on CPU#1", among other problems.
There's no reason to use a spinlock, so switch to a mutex.
--- drivers/watchdog/dw_wdt.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)
drivers/watchdog/dw_wdt.c +5 -5
@@ -30,12 +30,12 @@#include <linux/miscdevice.h> #include <linux/module.h> #include <linux/moduleparam.h> +#include <linux/mutex.h> #include <linux/notifier.h> #include <linux/of.h> #include <linux/pm.h> #include <linux/platform_device.h> #include <linux/reboot.h> -#include <linux/spinlock.h> #include <linux/timer.h> #include <linux/uaccess.h> #include <linux/watchdog.h>
@@ -61,7 +61,7 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "#define WDT_TIMEOUT (HZ / 2) static struct { - spinlock_t lock; + struct mutex lock; void __iomem *regs; struct clk *clk; unsigned long in_use;
@@ -177,7 +177,7 @@ static int dw_wdt_open(struct inode *inode, struct file *filp)/* Make sure we don't get unloaded. */ __module_get (THIS_MODULE ); -spin_lock (&dw_wdt.lock); +mutex_lock (&dw_wdt.lock);if (!dw_wdt_is_enabled ()) {/* * The watchdog is not currently enabled. Set the timeout to
@@ -190,7 +190,7 @@ static int dw_wdt_open(struct inode *inode, struct file *filp)dw_wdt_set_next_heartbeat (); -spin_unlock (&dw_wdt.lock); +mutex_unlock (&dw_wdt.lock);return nonseekable_open (inode, filp); }
@@ -348,7 +348,7 @@ static int dw_wdt_drv_probe(struct platform_device *pdev)if (ret)return ret; -spin_lock_init (&dw_wdt.lock); +mutex_init (&dw_wdt.lock); ret =misc_register (&dw_wdt_miscdev);if (ret)
Signature · 1 line
2.2.0.rc0.207.ga3a616c
PATCH 2/2 watchdog: dw_wdt: keepalive the watchdog at write time
If you've got code that does this in a tight loop
1. Open watchdog
2. Send 'expect close'
3. Close watchdog
...you'll eventually trigger a watchdog reset. You can reproduce this by using daisydog (1) and running:
while true; do daisydog -c > /dev/null; done
The problem is that each time you write to the watchdog for 'expect close' it moves the timer .5 seconds out. The timer thus never fires and never pats the watchdog for you.
1: http://git.chromium.org/gitweb/?p=chromiumos/third_party/daisydog.git
--- drivers/watchdog/dw_wdt.c | 1 + 1 file changed, 1 insertion(+)
drivers/watchdog/dw_wdt.c +1 -0
@@ -220,6 +220,7 @@ static ssize_t dw_wdt_write(struct file *filp, const char __user *buf, }dw_wdt_set_next_heartbeat (); +dw_wdt_keepalive ();mod_timer (&dw_wdt.timer, jiffies +WDT_TIMEOUT );return len;
Signature · 1 line
2.2.0.rc0.207.ga3a616c
Re: [PATCH 2/2] watchdog: dw_wdt: keepalive the watchdog at write time
Quoted 8 lines · Doug Anderson
If you've got code that does this in a tight loop
1. Open watchdog
2. Send 'expect close'
3. Close watchdog
...you'll eventually trigger a watchdog reset. You can reproduce this by using daisydog (1) and running:
while true; do daisydog -c >/dev/null; done
Quoted 7 lines
The problem is that each time you write to the watchdog for 'expect close' it moves the timer .5 seconds out. The timer thus never fires and never pats the watchdog for you.
1: http://git.chromium.org/gitweb/?p=chromiumos/third_party/daisydog.git
Signed-off-by Doug Anderson <[email protected]>
Re: [PATCH 2/2] watchdog: dw_wdt: keepalive the watchdog at write time
In reply to Doug AndersonQuoted 24 lines · On Thu, 7 May 2015 15:09:24 -0700 Doug Anderson <[email protected]> wrote:
If you've got code that does this in a tight loop
1. Open watchdog
2. Send 'expect close'
3. Close watchdog
...you'll eventually trigger a watchdog reset. You can reproduce this by using daisydog (1) and running:
while true; do daisydog -c >/dev/null; doneThe problem is that each time you write to the watchdog for 'expect close' it moves the timer .5 seconds out. The timer thus never fires and never pats the watchdog for you.
1: http://git.chromium.org/gitweb/?p=chromiumos/third_party/daisydog.git
Signed-off-by Doug Anderson <[email protected]>--- drivers/watchdog/dw_wdt.c | 1 + 1 file changed, 1 insertion(+)drivers/watchdog/dw_wdt.c +0
-0
drivers/watchdog/dw_wdt.c static ssize_t dw_wdt_write(struct file *filp, const char __user *buf, · line 226
Quoted 7 lines
drivers/watchdog/dw_wdt.c +1
-0@@ -220,6 +220,7 @@ static ssize_t dw_wdt_write(struct file *filp, const char __user *buf, }dw_wdt_set_next_heartbeat (); +dw_wdt_keepalive ();mod_timer (&dw_wdt.timer, jiffies +WDT_TIMEOUT );return len;
Quoted 8 lines · Doug Anderson
Right now the
dw_wdtuses a spinlock to protectdw_wdt_open(). The problem is that while holding the spinlock we call:
->dw_wdt_set_top()-> dw_wdt_top_in_seconds() -> clk_get_rate() -> clk_prepare_lock() -> mutex_lock()
Quoted 7 lines
Locking a mutex while holding a spinlock is not allowed and leads to warnings like "BUG: spinlock wrong CPU on CPU#1", among other problems.
There's no reason to use a spinlock, so switch to a mutex.
Signed-off-by Doug Anderson <[email protected]>
Hi,
Quoted 14 lines · Guenter Roeck
Quoted 13 lines · Doug Anderson
Right now the
dw_wdtuses a spinlock to protectdw_wdt_open(). The problem is that while holding the spinlock we call:
->dw_wdt_set_top()-> dw_wdt_top_in_seconds() -> clk_get_rate() -> clk_prepare_lock() -> mutex_lock()Locking a mutex while holding a spinlock is not allowed and leads to warnings like "BUG: spinlock wrong CPU on CPU#1", among other problems.
Quoted 6 lines
Quoted 3 lines
There's no reason to use a spinlock, so switch to a mutex.
Signed-off-by Doug Anderson <[email protected]>Reviewed-by Guenter Roeck <[email protected]>
As Dmitry pointed out in another context, and even better fix is to just remove the spinlock altogether. I'll send up v2...
-Doug
Quoted 65 lines · On Thu, 7 May 2015 15:09:23 -0700 Doug Anderson <[email protected]> wrote:
Right now the
dw_wdtuses a spinlock to protectdw_wdt_open(). The problem is that while holding the spinlock we call:
->dw_wdt_set_top()
->dw_wdt_top_in_seconds()-> clk_get_rate() -> clk_prepare_lock() -> mutex_lock()Locking a mutex while holding a spinlock is not allowed and leads to warnings like "BUG: spinlock wrong CPU on CPU#1", among other problems.
There's no reason to use a spinlock, so switch to a mutex.
Signed-off-by Doug Anderson <[email protected]>--- drivers/watchdog/dw_wdt.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)drivers/watchdog/dw_wdt.c +4
-4@@ -30,12 +30,12 @@#include <linux/miscdevice.h> #include <linux/module.h> #include <linux/moduleparam.h> +#include <linux/mutex.h> #include <linux/notifier.h> #include <linux/of.h> #include <linux/pm.h> #include <linux/platform_device.h> #include <linux/reboot.h> -#include <linux/spinlock.h> #include <linux/timer.h> #include <linux/uaccess.h> #include <linux/watchdog.h> @@ -61,7 +61,7 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "#define WDT_TIMEOUT (HZ / 2) static struct { - spinlock_t lock; + struct mutex lock; void __iomem *regs; struct clk *clk; unsigned long in_use;@@ -177,7 +177,7 @@ static int dw_wdt_open(struct inode *inode, struct file *filp)/* Make sure we don't get unloaded. */ __module_get (THIS_MODULE ); -spin_lock (&dw_wdt.lock); +mutex_lock (&dw_wdt.lock);if (!dw_wdt_is_enabled ()) {/* * The watchdog is not currently enabled. Set the timeout to @@ -190,7 +190,7 @@ static int dw_wdt_open(struct inode *inode, struct file *filp)dw_wdt_set_next_heartbeat (); -spin_unlock (&dw_wdt.lock); +mutex_unlock (&dw_wdt.lock);return nonseekable_open (inode, filp); }
drivers/watchdog/dw_wdt.c static int dw_wdt_drv_probe(struct platform_device *pdev) · line 354
Quoted 8 lines
drivers/watchdog/dw_wdt.c +1
-1@@ -348,7 +348,7 @@ static int dw_wdt_drv_probe(struct platform_device *pdev)if (ret)return ret; -spin_lock_init (&dw_wdt.lock); +mutex_init (&dw_wdt.lock); ret =misc_register (&dw_wdt_miscdev);if (ret)
Tested on marvell BG2Q SoC, no issue found. So