mutex
Subsystems (3)
Hi Amit, Rusty
RHBZ: https://bugzilla.redhat.com/show_bug.cgi?id=1127062
steps:
- Read random data by 'dd if=/dev/hwrng of=/dev/null' in guest
- check sysfs files in the same time, 'cat /sys/class/misc/hw_random/rng_*'
Result: cat process will get stuck, it will return if we kill dd process.
We have some static variables (eg, current_rng, data_avail, etc) in hw_random/core.c, they are protected by rng_mutex. I try to workaround this issue by undelay(100) after mutex_unlock() in rng_dev_read(). This gives chance for hwrng_attr_*_show() to get mutex.
This patch also contains some cleanup, moving some code out of mutex protection.
Do you have some suggestion? Thanks.
drivers/char/hw_random/core.c +5 -4
@@ -194,6 +194,7 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf, }mutex_unlock (&rng_mutex); +udelay (100 );if (need_resched ())schedule_timeout_interruptible (1 );
@@ -233,10 +234,10 @@ static ssize_t hwrng_attr_current_store(struct device *dev,int err;struct hwrng *rng; + err = -ENODEV ; err =mutex_lock_interruptible (&rng_mutex);if (err)return -ERESTARTSYS ; - err = -ENODEV ;list_for_each_entry (rng, &rng_list, list) {if (strcmp (rng->name, buf) ==0 ) {if (rng == current_rng) {
@@ -270,8 +271,8 @@ static ssize_t hwrng_attr_current_show(struct device *dev,return -ERESTARTSYS ;if (current_rng) name = current_rng->name; - ret =snprintf (buf,PAGE_SIZE ,"%s\n" , name);mutex_unlock (&rng_mutex); + ret =snprintf (buf,PAGE_SIZE ,"%s\n" , name);return ret; }
@@ -284,19 +285,19 @@ static ssize_t hwrng_attr_available_show(struct device *dev,ssize_t ret =0 ;struct hwrng *rng; + buf[0 ] ='\0' ; err =mutex_lock_interruptible (&rng_mutex);if (err)return -ERESTARTSYS ; - buf[0 ] ='\0' ;list_for_each_entry (rng, &rng_list, list) {strncat (buf, rng->name,PAGE_SIZE - ret -1 ); ret +=strlen (rng->name);strncat (buf," " ,PAGE_SIZE - ret -1 ); ret++; } +mutex_unlock (&rng_mutex);strncat (buf,"\n" ,PAGE_SIZE - ret -1 ); ret++; -mutex_unlock (&rng_mutex);return ret; }
RFC virtio-rng: fail to read sysfs of a busy device
(Resend to fix the subject)
Hi Amit, Rusty
RHBZ: https://bugzilla.redhat.com/show_bug.cgi?id=1127062
steps:
- Read random data by 'dd if=/dev/hwrng of=/dev/null' in guest
- check sysfs files in the same time, 'cat /sys/class/misc/hw_random/rng_*'
Result: cat process will get stuck, it will return if we kill dd process.
We have some static variables (eg, current_rng, data_avail, etc) in hw_random/core.c, they are protected by rng_mutex. I try to workaround this issue by undelay(100) after mutex_unlock() in rng_dev_read(). This gives chance for hwrng_attr_*_show() to get mutex.
This patch also contains some cleanup, moving some code out of mutex protection.
Do you have some suggestion? Thanks.
drivers/char/hw_random/core.c +5 -4
@@ -194,6 +194,7 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf, }mutex_unlock (&rng_mutex); +udelay (100 );if (need_resched ())schedule_timeout_interruptible (1 );
@@ -233,10 +234,10 @@ static ssize_t hwrng_attr_current_store(struct device *dev,int err;struct hwrng *rng; + err = -ENODEV ; err =mutex_lock_interruptible (&rng_mutex);if (err)return -ERESTARTSYS ; - err = -ENODEV ;list_for_each_entry (rng, &rng_list, list) {if (strcmp (rng->name, buf) ==0 ) {if (rng == current_rng) {
@@ -270,8 +271,8 @@ static ssize_t hwrng_attr_current_show(struct device *dev,return -ERESTARTSYS ;if (current_rng) name = current_rng->name; - ret =snprintf (buf,PAGE_SIZE ,"%s\n" , name);mutex_unlock (&rng_mutex); + ret =snprintf (buf,PAGE_SIZE ,"%s\n" , name);return ret; }
@@ -284,19 +285,19 @@ static ssize_t hwrng_attr_available_show(struct device *dev,ssize_t ret =0 ;struct hwrng *rng; + buf[0 ] ='\0' ; err =mutex_lock_interruptible (&rng_mutex);if (err)return -ERESTARTSYS ; - buf[0 ] ='\0' ;list_for_each_entry (rng, &rng_list, list) {strncat (buf, rng->name,PAGE_SIZE - ret -1 ); ret +=strlen (rng->name);strncat (buf," " ,PAGE_SIZE - ret -1 ); ret++; } +mutex_unlock (&rng_mutex);strncat (buf,"\n" ,PAGE_SIZE - ret -1 ); ret++; -mutex_unlock (&rng_mutex);return ret; }
Signature · 1 line
Amos.
Re: RFC virtio-rng: fail to read sysfs of a busy device
Quoted 10 lines · Amos Kong
(Resend to fix the subject)
Hi Amit, Rusty
RHBZ: https://bugzilla.redhat.com/show_bug.cgi?id=1127062
steps:
- Read random data by 'dd if=/dev/hwrng of=/dev/null' in guest
- check sysfs files in the same time, 'cat/sys/class/misc/hw_random/rng_*'Result: cat process will get stuck, it will return if we kill dd process.
How common is it going to be to have a long-running 'dd' process on /dev/hwrng?
Also, with the new khwrng thread, reading from /dev/hwrng isn't required -- just use /dev/random?
(This doesn't mean we shouldn't fix the issue here...)
Quoted 16 lines
We have some static variables (eg,
current_rng,data_avail, etc) inhw_random/core.c, they are protected byrng_mutex. I try to workaround this issue by undelay(100) aftermutex_unlock()inrng_dev_read(). This gives chance for hwrng_attr_*_show() to get mutex.This patch also contains some cleanup, moving some code out of mutex protection.
Do you have some suggestion? Thanks.
drivers/char/hw_random/core.c +0
-0
drivers/char/hw_random/core.c static ssize_t rng_dev_read(struct file *filp, char __user *buf, · line 197
Quoted 4 lines
drivers/char/hw_random/core.c +1
-0@@ -194,6 +194,7 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf, }mutex_unlock (&rng_mutex); +udelay (100 );
We have a need_resched() right below. Why doesn't that work?
drivers/char/hw_random/core.c static ssize_t hwrng_attr_current_store(struct device *dev, · line 235
Quoted 5 lines
drivers/char/hw_random/core.c +0
-0if (need_resched ())schedule_timeout_interruptible (1 );@@ -233,10 +234,10 @@ static ssize_t hwrng_attr_current_store(struct device *dev,int err;struct hwrng *rng;
The following hunk doesn't work:
drivers/char/hw_random/core.c static ssize_t hwrng_attr_current_store(struct device *dev, · line 238
Quoted 2 lines
drivers/char/hw_random/core.c +1
-0+ err = -ENODEV ; err =mutex_lock_interruptible (&rng_mutex);
err is being set to another value in the next line!
drivers/char/hw_random/core.c static ssize_t hwrng_attr_current_store(struct device *dev, · line 239
Quoted 3 lines
drivers/char/hw_random/core.c +0
-1if (err)return -ERESTARTSYS ; - err = -ENODEV ;
And all usage of err below now won't have -ENODEV but some other value.
drivers/char/hw_random/core.c static ssize_t hwrng_attr_current_show(struct device *dev, · line 275
Quoted 10 lines
drivers/char/hw_random/core.c +1
-1list_for_each_entry (rng, &rng_list, list) {if (strcmp (rng->name, buf) ==0 ) {if (rng == current_rng) {@@ -270,8 +271,8 @@ static ssize_t hwrng_attr_current_show(struct device *dev,return -ERESTARTSYS ;if (current_rng) name = current_rng->name; - ret =snprintf (buf,PAGE_SIZE ,"%s\n" , name);mutex_unlock (&rng_mutex); + ret =snprintf (buf,PAGE_SIZE ,"%s\n" , name);
This looks OK...
Quoted 13 lines
drivers/char/hw_random/core.c +1
-1return ret; }@@ -284,19 +285,19 @@ static ssize_t hwrng_attr_available_show(struct device *dev,ssize_t ret =0 ;struct hwrng *rng; + buf[0 ] ='\0' ; err =mutex_lock_interruptible (&rng_mutex);if (err)return -ERESTARTSYS ; - buf[0 ] ='\0' ;
drivers/char/hw_random/core.c static ssize_t hwrng_attr_available_show(struct device *dev, · line 300
Quoted 10 lines
drivers/char/hw_random/core.c +1
-1list_for_each_entry (rng, &rng_list, list) {strncat (buf, rng->name,PAGE_SIZE - ret -1 ); ret +=strlen (rng->name);strncat (buf," " ,PAGE_SIZE - ret -1 ); ret++; } +mutex_unlock (&rng_mutex);strncat (buf,"\n" ,PAGE_SIZE - ret -1 ); ret++; -mutex_unlock (&rng_mutex);
But this isn't resulting in savings; the majority of the time is being spent in the for loop, and that writes to the buffer.
BTW I don't expect strcat'ing to the buf in each of these scenarios is a long operation, so this reworking doesn't strike to me as something we should pursue.
Amit
Re: RFC virtio-rng: fail to read sysfs of a busy device
Quoted 10 lines · Amit Shah
Quoted 9 lines · Amos Kong
(Resend to fix the subject)
Hi Amit, Rusty
RHBZ: https://bugzilla.redhat.com/show_bug.cgi?id=1127062
steps:
- Read random data by 'dd if=/dev/hwrng of=/dev/null' in guest
- check sysfs files in the same time, 'cat/sys/class/misc/hw_random/rng_*'
Quoted 4 lines
Quoted 1 line
Result: cat process will get stuck, it will return if we kill dd process.
How common is it going to be to have a long-running 'dd' process on
/dev/hwrng?
Not a common usage, but we have this strict testing.
Quoted 2 lines
Also, with the new khwrng thread, reading from
/dev/hwrngisn't required -- just use/dev/random?
Yes.
Quoted 1 line
(This doesn't mean we shouldn't fix the issue here...)
Completely agree :-)
Quoted 18 lines
Quoted 18 lines
We have some static variables (eg,
current_rng,data_avail, etc) inhw_random/core.c, they are protected byrng_mutex. I try to workaround this issue by undelay(100) aftermutex_unlock()inrng_dev_read(). This gives chance for hwrng_attr_*_show() to get mutex.This patch also contains some cleanup, moving some code out of mutex protection.
Do you have some suggestion? Thanks.
drivers/char/hw_random/core.c +0
-0@@ -194,6 +194,7 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf, }
Quoted 4 lines
drivers/char/hw_random/core.c static ssize_t rng_dev_read(struct file *filp, char __user *buf, · line 197
Quoted 2 lines
drivers/char/hw_random/core.c +1
-0mutex_unlock (&rng_mutex); +udelay (100 );We have a
need_resched()right below. Why doesn't that work?
need_resched() is giving chance for userspace to
Quoted 1 line
drivers/char/hw_random/core.c static ssize_t rng_dev_read(struct file *filp, char __user *buf, · line 198
Quoted 1 line
drivers/char/hw_random/core.c +0
-0if (need_resched ())
It never success in my debugging.
If we remove this check and always call schedule_timeout_interruptible(1), problem also disappears.
drivers/char/hw_random/core.c +0 -0
@@ -195,8 +195,7 @@ static ssize_t rng_dev_read(struct file *filp,
char __user *buf,
mutex_unlock(&rng_mutex);
- if (need_resched())
- schedule_timeout_interruptible(1);
+ schedule_timeout_interruptible(1);
if (signal_pending(current)) {
err = -ERESTARTSYS;Quoted 12 lines
drivers/char/hw_random/core.c static ssize_t hwrng_attr_current_store(struct device *dev, · line 235
Quoted 4 lines
drivers/char/hw_random/core.c +0
-0schedule_timeout_interruptible (1 );@@ -233,10 +234,10 @@ static ssize_t hwrng_attr_current_store(struct device *dev,int err;struct hwrng *rng;The following hunk doesn't work:
drivers/char/hw_random/core.c static ssize_t hwrng_attr_current_store(struct device *dev, · line 237
Quoted 2 lines
drivers/char/hw_random/core.c +1
-0+ err = -ENODEV ; err =mutex_lock_interruptible (&rng_mutex);err is being set to another value in the next line!
Quoted 5 lines
drivers/char/hw_random/core.c static ssize_t hwrng_attr_current_store(struct device *dev, · line 238
Quoted 3 lines
drivers/char/hw_random/core.c +0
-1if (err)return -ERESTARTSYS ; - err = -ENODEV ;And all usage of err below now won't have
-ENODEVbut some other value.
Oops!
Quoted 25 lines
drivers/char/hw_random/core.c static ssize_t hwrng_attr_current_show(struct device *dev, · line 275
Quoted 10 lines
drivers/char/hw_random/core.c +1
-1list_for_each_entry (rng, &rng_list, list) {if (strcmp (rng->name, buf) ==0 ) {if (rng == current_rng) {@@ -270,8 +271,8 @@ static ssize_t hwrng_attr_current_show(struct device *dev,return -ERESTARTSYS ;if (current_rng) name = current_rng->name; - ret =snprintf (buf,PAGE_SIZE ,"%s\n" , name);mutex_unlock (&rng_mutex); + ret =snprintf (buf,PAGE_SIZE ,"%s\n" , name);This looks OK...
Quoted 12 lines
drivers/char/hw_random/core.c +1
-0return ret; }@@ -284,19 +285,19 @@ static ssize_t hwrng_attr_available_show(struct device *dev,ssize_t ret =0 ;struct hwrng *rng; + buf[0 ] ='\0' ; err =mutex_lock_interruptible (&rng_mutex);if (err)return -ERESTARTSYS ;
Quoted 14 lines
drivers/char/hw_random/core.c static ssize_t hwrng_attr_available_show(struct device *dev, · line 300
Quoted 11 lines
drivers/char/hw_random/core.c +1
-2- buf[0 ] ='\0' ;list_for_each_entry (rng, &rng_list, list) {strncat (buf, rng->name,PAGE_SIZE - ret -1 ); ret +=strlen (rng->name);strncat (buf," " ,PAGE_SIZE - ret -1 ); ret++; } +mutex_unlock (&rng_mutex);strncat (buf,"\n" ,PAGE_SIZE - ret -1 ); ret++; -mutex_unlock (&rng_mutex);But this isn't resulting in savings; the majority of the time is being spent in the for loop, and that writes to the buffer.
Right
Quoted 5 lines
BTW I don't expect strcat'ing to the buf in each of these scenarios is a long operation, so this reworking doesn't strike to me as something we should pursue.
Amit
Signature · 1 line
Amos.
Re: RFC virtio-rng: fail to read sysfs of a busy device
Quoted 11 lines · Amos Kong
Quoted 10 lines · Amit Shah
Quoted 9 lines · Amos Kong
(Resend to fix the subject)
Hi Amit, Rusty
RHBZ: https://bugzilla.redhat.com/show_bug.cgi?id=1127062
steps:
- Read random data by 'dd if=/dev/hwrng of=/dev/null' in guest
- check sysfs files in the same time, 'cat/sys/class/misc/hw_random/rng_*'
Quoted 6 lines
Quoted 4 lines
Quoted 1 line
Result: cat process will get stuck, it will return if we kill dd process.
How common is it going to be to have a long-running 'dd' process on
/dev/hwrng?Not a common usage, but we have this strict testing.
For -smp 1:
It's easy to reproduce with slow backend (/dev/random). cat can return most of time with some delay if we use quick backend (/dev/urandom).
But for -smp 2:
I didn't touch this problem even with slow backend.
Quoted 31 lines
Quoted 2 lines
Also, with the new khwrng thread, reading from
/dev/hwrngisn't required -- just use/dev/random?Yes.
Quoted 1 line
(This doesn't mean we shouldn't fix the issue here...)
Completely agree :-)
Quoted 22 lines
Quoted 16 lines
We have some static variables (eg,
current_rng,data_avail, etc) inhw_random/core.c, they are protected byrng_mutex. I try to workaround this issue by undelay(100) aftermutex_unlock()inrng_dev_read(). This gives chance for hwrng_attr_*_show() to get mutex.This patch also contains some cleanup, moving some code out of mutex protection.
Do you have some suggestion? Thanks.
drivers/char/hw_random/core.c +0
-0drivers/char/hw_random/core.c static ssize_t rng_dev_read(struct file *filp, char __user *buf, · line 197
Quoted 4 lines
drivers/char/hw_random/core.c +1
-0@@ -194,6 +194,7 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf, }mutex_unlock (&rng_mutex); +udelay (100 );We have a
need_resched()right below. Why doesn't that work?
[smp 1]
Why need_resched() always return zero? what's the original purpose of it ?
Quoted 94 lines
Quoted 2 lines
drivers/char/hw_random/core.c static ssize_t rng_dev_read(struct file *filp, char __user *buf, · line 198
Quoted 2 lines
drivers/char/hw_random/core.c +0
-0if (need_resched ())It never success in my debugging.
If we remove this check and always call
schedule_timeout_interruptible(1), problem also disappears.drivers/char/hw_random/core.c +1
-2@@ -195,8 +195,7 @@ static ssize_t rng_dev_read(struct file *filp,char __user *buf, mutex_unlock(&rng_mutex); -if (need_resched ()) -schedule_timeout_interruptible (1 ); +schedule_timeout_interruptible (1 );if (signal_pending (current)) {err = -ERESTARTSYS;Quoted 12 lines
drivers/char/hw_random/core.c static ssize_t hwrng_attr_current_store(struct device *dev, · line 235
Quoted 4 lines
drivers/char/hw_random/core.c +0
-0schedule_timeout_interruptible (1 );@@ -233,10 +234,10 @@ static ssize_t hwrng_attr_current_store(struct device *dev,int err;struct hwrng *rng;The following hunk doesn't work:
drivers/char/hw_random/core.c static ssize_t hwrng_attr_current_store(struct device *dev, · line 237
Quoted 2 lines
drivers/char/hw_random/core.c +1
-0+ err = -ENODEV ; err =mutex_lock_interruptible (&rng_mutex);err is being set to another value in the next line!
Quoted 5 lines
drivers/char/hw_random/core.c static ssize_t hwrng_attr_current_store(struct device *dev, · line 238
Quoted 3 lines
drivers/char/hw_random/core.c +0
-1if (err)return -ERESTARTSYS ; - err = -ENODEV ;And all usage of err below now won't have
-ENODEVbut some other value.Oops!
Quoted 25 lines
drivers/char/hw_random/core.c static ssize_t hwrng_attr_current_show(struct device *dev, · line 275
Quoted 10 lines
drivers/char/hw_random/core.c +1
-1list_for_each_entry (rng, &rng_list, list) {if (strcmp (rng->name, buf) ==0 ) {if (rng == current_rng) {@@ -270,8 +271,8 @@ static ssize_t hwrng_attr_current_show(struct device *dev,return -ERESTARTSYS ;if (current_rng) name = current_rng->name; - ret =snprintf (buf,PAGE_SIZE ,"%s\n" , name);mutex_unlock (&rng_mutex); + ret =snprintf (buf,PAGE_SIZE ,"%s\n" , name);This looks OK...
Quoted 12 lines
drivers/char/hw_random/core.c +1
-0return ret; }@@ -284,19 +285,19 @@ static ssize_t hwrng_attr_available_show(struct device *dev,ssize_t ret =0 ;struct hwrng *rng; + buf[0 ] ='\0' ; err =mutex_lock_interruptible (&rng_mutex);if (err)return -ERESTARTSYS ;Quoted 14 lines
drivers/char/hw_random/core.c static ssize_t hwrng_attr_available_show(struct device *dev, · line 300
Quoted 11 lines
drivers/char/hw_random/core.c +1
-2- buf[0 ] ='\0' ;list_for_each_entry (rng, &rng_list, list) {strncat (buf, rng->name,PAGE_SIZE - ret -1 ); ret +=strlen (rng->name);strncat (buf," " ,PAGE_SIZE - ret -1 ); ret++; } +mutex_unlock (&rng_mutex);strncat (buf,"\n" ,PAGE_SIZE - ret -1 ); ret++; -mutex_unlock (&rng_mutex);But this isn't resulting in savings; the majority of the time is being spent in the for loop, and that writes to the buffer.
Right
Quoted 5 lines
BTW I don't expect strcat'ing to the buf in each of these scenarios is a long operation, so this reworking doesn't strike to me as something we should pursue.
Amit
Signature · 1 line
Amos.
Signature · 1 line
Amos.